ACS Publications. Most Trusted. Most Cited. Most Read
Quick View

OR SEARCH CITATIONS

My Activity
Publications
CONTENT TYPES

Figure 1Loading Img
Download Hi-Res ImageDownload to MS-PowerPointCite This:JACS Au 2021, 1, 4, 427-438
RETURN TO ISSUEPREVArticleNEXT

Deep Learning Optical Spectroscopy Based on Experimental Database: Potential Applications to Molecular Design

Cite this: JACS Au 2021, 1, 4, 427–438
Publication Date (Web):March 17, 2021
https://doi.org/10.1021/jacsau.1c00035

Copyright © 2022 The Authors. Published by American Chemical Society. This publication is licensed under

CC-BY-NC-ND 4.0.
  • Open Access

Article Views

13917

Altmetric

-

Citations

43
LEARN ABOUT THESE METRICS
PDF (4 MB)
Get e-Alerts
Supporting Info (1)»
SUBJECTS:

Abstract

High Resolution Image
Download MS PowerPoint Slide

Accurate and reliable prediction of the optical and photophysical properties of organic compounds is important in various research fields. Here, we developed deep learning (DL) optical spectroscopy using a DL model and experimental database to predict seven optical and photophysical properties of organic compounds, namely, the absorption peak position and bandwidth, extinction coefficient, emission peak position and bandwidth, photoluminescence quantum yield (PLQY), and emission lifetime. Our DL model included the chromophore–solvent interaction to account for the effect of local environments on the optical and photophysical properties of organic compounds and was trained using an experimental database of 30 094 chromophore/solvent combinations. Our DL optical spectroscopy made it possible to reliably and quickly predict the aforementioned properties of organic compounds in solution, gas phase, film, and powder with the root mean squared errors of 26.6 and 28.0 nm for absorption and emission peak positions, 603 and 532 cm–1 for absorption and emission bandwidths, and 0.209, 0.371, and 0.262 for the logarithm of the extinction coefficient, PLQY, and emission lifetime, respectively. Finally, we demonstrated how a blue emitter with desired optical and photophysical properties could be efficiently virtually screened and developed by DL optical spectroscopy. DL optical spectroscopy can be efficiently used for developing chromophores and fluorophores in various research areas.

This publication is licensed under

CC-BY-NC-ND 4.0.
  • cc licence
  • by licence
  • nc licence
  • nd licence
KEYWORDS:

Introduction

ARTICLE SECTIONS
Jump To
The optical and photophysical properties of chromophores and fluorophores are important for industrial and academic applications in a variety of research fields such as, organic solar cells, (1) organic light-emitting diodes (OLEDs), (2) bioimaging, (3) organic sensors, (4) and organic dyes. Substantial efforts have been made to design and synthesize new colorful materials based on various chromophores and fluorophores for various purposes. To develop new molecules with desired properties, knowledge of the chemical and physical properties of previously studied molecules is required. In particular, the optical properties of molecules, such as absorption and emission peak positions and bandwidths, extinction coefficients, photoluminescence quantum yield (PLQY), and emission lifetime, are important for the development of chromophores and fluorophores. For given molecules, the aforementioned optical properties are readily measured using various spectroscopic instruments, such as spectrophotometers, spectrofluorometers with integrating spheres, and time-resolved fluorescence (TRF) spectrometers. It is also desirable that the optical properties of newly designed chromophores and fluorophores are accurately estimated in advance to reduce development costs. To estimate the optical properties of molecules, empirical rules or theories, such as the Woodward–Fieser rule, (5) first-principles, (6,7) and time-dependent density functional theory (TD-DFT) calculations (8−10) have been developed. Such methods have limitations resulting from the limited range of molecules to which they can be applied and from the lack of practical theories to calculate specific properties. While these rules and theories have been used to successfully predict many chemical and physical properties, more accurate, facile, and computationally inexpensive methods are still needed.
In this study, we have developed a deep learning (DL) method to reliably and quickly predict the optical and photophysical properties of organic compounds. Our DL method includes chromophore–solvent interactions to account for the effect of environment on the optical and photophysical properties. Our DL model was trained using an experimental database of 30 094 chromophore/solvent combinations consisting of 11 392 unique organic chromophores in 369 solvents or solid states. (11,12) Our DL method is found to readily predict seven optical properties such as the first absorption peak position and bandwidth, extinction coefficient, emission peak position and bandwidth, photoluminescence quantum yield, and emission lifetime. The root mean squared errors of the predicted values were found to be 26.6 and 28.0 nm for absorption and emission peak positions, 603 and 532 cm–1 for absorption and emission bandwidths, and 0.209, 0.371, and 0.262 for the logarithm of the extinction coefficient, PLQY, and emission lifetime, respectively. Using these predicted optical properties of organic compounds, the electronic absorption and emission spectra are shown to be readily reconstructed, and the colors of organic molecules associated with the absorption and emission are estimated in Commission Internationale de l’Eclairage (CIE) color coordinates. Finally, we demonstrate that the DL model can be effectively utilized to prescreen newly designed molecules to find target molecules that exhibit the desired optical and photophysical properties.

Results and Discussion

ARTICLE SECTIONS
Jump To

Experimental Optical Properties of Organic Compounds

The absorption properties of a chromophore in a solvent are characterized by the first absorption peak position (λabs), bandwidth (σabs), and extinction coefficient (ε), whereas the emission properties of a fluorophore are characterized by the emission peak position (λemi), bandwidth (σemi), and photoluminescence quantum yield (PLQY, Φ). In addition, the emission (excited-state) lifetime (τ) is an intrinsic property of fluorophores that is importantly considered in fluorescence lifetime imaging and dynamic quenching. The experimental database of these optical and photophysical properties of organic compounds is prerequisite for our DL method. As shown in Figure 1, the experimental database includes 11 392 unique organic chromophores in 369 solvents or solid states, yielding 30 094 chromophore/solvent combinations. Briefly, the experimental database was built by collecting seven optical and photophysical properties of organic compounds from the literature and has been described in detail elsewhere. (11,12) Not all seven optical and photophysical properties were available for each chromophore/solvent pair in the database. A variety of chromophore structures are included in the database; the frequencies of specific core structures are summarized in Figure S1. For example, more than 1300 BF2-group-containing boron-dipyrromethene (BODIPY) derivatives are found in the database.

Figure 1

Figure 1. Database of the optical properties of organic compounds. Histograms of (a) first absorption peak position (λabs), (b) bandwidth in full width at half-maximum (σabs), (c) extinction coefficient in logarithm (log ε), (d) emission peak position (λemi), (e) bandwidth in full width at half-maximum (σemi), (f) photoluminescence quantum yield (Φ), (g) lifetime (τ), (h) molecular weights of chromophores, and (i) solvents (CH2Cl2 dichloromethane, CH3CN acetonitrile, Tol toluene, CHCl3 chloroform, THF tetrahydrofuran, MeOH methanol, EtOH ethanol, DMSO dimethyl sulfoxide, CH cyclohexane, and DMF N,N-dimethylformamide). The number of data points (N) and the number of chromophores (mol.) are included in each graph. (11,12)

High Resolution Image
Download MS PowerPoint Slide

DL Model for Prediction of Optical and Photophysical Properties

DL based on big data has attracted substantial attention because it can potentially solve problems via direct learning from data without well-defined rules, empirical laws, or theories. (13,14) In chemistry, DL has proven promising for predicting various properties of molecules and materials, (15−29) optimizing reactions and retrosynthesis, (30−32) and designing new molecules including drugs (33,34) and materials. (35−37) Additionally, DL has been effectively used in computational chemistry. (38,39) Nakata and Shimazaki reported a large-scale electronic structure database (PubChemQC) (40) and recently, using the PubChemQC database, Lee and co-workers reported a random forest model to predict the highest oscillator strength and the corresponding excitation energy of molecules. (26) Lin and co-workers used a DL method to predict the bandgap of configurationally hybridized graphene and boron nitride, (21) and Chang and co-workers used a tuplewise material representation to predict the band gap of organic–inorganic perovskite, 2D materials, and binary and ternary inorganic materials. (27) Jiang and co-workers reported DL models that could predict infrared and ultraviolet absorption spectra from the conformations of a molecule using a theoretical database that was generated by molecular dynamics simulations and DFT calculations. (23,28) Rinke and co-workers reported a DL method to predict molecular excitation spectra based on the QM7b and QM9 data sets of small organic molecules containing up to 17 C, N, O, S, and halogen atoms. (24) Li and co-workers reported a machine learning method using the Morgan fingerprint and an experimental database of 4300 molecules to predict three properties such as absorption and emission wavelengths and PLQY. (29)
In this work, we developed a DL model to predict the optical and photophysical properties as described in Figure 2. The molecular structure of a chromophore is represented by a 150 × 150 adjacency matrix (Achm) and a 150 × 43 feature matrix (Xchm) (Figure S2). The adjacency matrix includes the connectivity information on atoms in the chromophore, and the feature matrix (Xchm) includes the identity of the atoms, the number of hydrogen and heavy atoms bonded to them, aromaticity, hybridization, ring structure, and formal charge. The graph convolutional network (GCN) is the simplest version of the message-passing neural network, which is effective for graph structures such as molecular structures. (16,25,41−44) A single graph convolution of the adjacency matrix (Achm) and feature matrix of the lth layer (Hchml) updates the atom’s features, producing a new feature matrix for the l + 1th layer, Hchml+1, which contains all the information related to the nearest-neighboring atoms in the chromophore. The final feature matrix of GCN layers, Hchm(f), is reduced to a row vector, zchm(0), by summing all elements to secure permutation invariance. The row vector, zchm(0), passes through multilayer perceptrons (MLPs) to produce a chemical space vector, zchm(f), for the chromophore. Similarly, a chemical space vector, zsol(f), of the solvent is obtained. The chemical space vectors for the chromophore and solvent, zchm(f) and zsol(f), are concatenated and pass through the MLPs to construct an interaction vector. Finally, the interaction vector passes through the MLPs to obtain the seven optical properties. Note that the interaction vector in the DL model is used to account for the chromophore–solvent interaction.

Figure 2

Figure 2. Our deep learning (DL) model. The interaction vector is used to account for the chromophore–solvent interaction for predicting the optical and photophysical properties of the chromophore.

High Resolution Image
Download MS PowerPoint Slide
It should be highlighted that our DL model includes the chromophore–solvent interaction for accurate estimation of the optical and photophysical properties of organic compounds in various solvents. Details of the DL model and training process are provided in the Supporting Information and Methods. The performance of our DL model is presented in Figure S4. Overall, the DL model is reasonably well trained using the experimental database and the square of the Pearson correlation coefficient (R2) ranges from 0.93 to 0.71 for the test sets (Table S2). It should be noted that σabs, σemi, Φ, and τ for a chromophore cannot be well predicted by currently available theoretical methods because they are highly dependent on many factors, including solute–solvent interactions, density of energy states, and relaxation pathways, which cannot be fully considered in the theoretical methods. However, in our DL model, these properties are shown to be directly learned from the experimental database and reliably predicted, which is a great advantage of the DL method.

Performances of Our DL Model

The DL model trained with the experimental database can be used to achieve DL optical spectroscopy such that seven optical properties for any given molecule are easily predicted. In this section, several interesting examples from the results of our DL model will be discussed.

Structural Diversity of Chromophores

As shown in Table 1a, our DL model predicts the optical properties of widely used core structures of chromophores and fluorophores (45−48) such as Nile red, (49) Prodan, (50) methylene blue, (51) and l-tyrosine. (52) In addition, we compared the λabs and λemi values predicted by our DL model and TD-DFT calculations (53) for 131 combinations involving 53 chromophores (Figure S5 and Table S6). The RMSEs of λabs and λemi predicted by our model are 17.0 and 22.5 nm, respectively, which are 2–3.5 times smaller than those obtained by TD-DFT calculations (46.1 and 81.9 nm, respectively). The biggest advantage of DL method is that the information hidden in the experimental database is directly decoded by the DL model. As a result, the DL model can predict the properties (e.g., σabs, σemi, Φ, and τ) that are traditionally incomputable by theoretical methods. Compared to theory-based TD-DFT calculations, another advantage of the DL method is its low computational cost. The TD-DFT calculations required 236 min per molecule on average to compute the ground- and excited-state geometries, λabs and λemi. Our DL model required only 20 s to simultaneously predict the seven optical properties of 131 chromophore/solvent combinations on the same computer (see Methods for computational details).
Table 1. Prediction of Optical Properties Using Our DL Modela
a

(a) Various optical properties of chromophores with different molecular structures. (b) BODIPY derivatives (in red) with different moieties (in green) at the meso position in dichloromethane. (c) Three protonation states of 7-amino-2-naphthol in water and their experimentally measured and predicted values.

For donor–acceptor (D–A) type molecules, the DL model is found to recognize the core moiety that has a more significant effect on the overall optical properties. Table 1b shows D–A type molecules with BODIPY and other moieties. (54−58) Our DL model confirms that the emission properties (λemi) of the molecules are mainly determined by the BODIPY moiety. For example, for the anthracene (donor)–BODIPY (acceptor) structure, the emission peak position of BODIPY is longer than that of anthracene, and thus, BODIPY determines the emission peak position of the molecule according to Kasha’s rule. (59)
In addition, we further examined whether the DL model could distinguish the optical properties of chromophores with similar structures. Ninety-seven chromophores in dichloromethane were selected from the experimental database (Table S7), and their optical properties were obtained by the DL model and compared with the experimental values (Figure S6). The DL model recognizes the core structure of a given molecule that determines the optical properties and the effect of structural modification of the core structures on the optical properties such as changes in the conjugation length and substituents of the core structures. The diverse changes in the core structures were successfully accounted for in the prediction of the optical properties.
Lastly, a change in protonation state is considered the smallest possible modification to a molecular structure which can dramatically alter its optical properties; this is because protonation/deprotonation changes the chromophore charge distribution and resultantly the chromophore–solvent interactions. Fifty-nine molecules with two or more protonation states were identified in the database (Figure S7). The effects of protonation/deprotonation in acid–base reaction on the optical properties are well predicted by the DL model. For example, the λabs and λemi of the three protonation states of 7-amino-2-naphthol in Table 1c are well distinguished. (60)

Effects of Solvent Polarity

The optical properties are significantly influenced by the solvent polarity known as solvatochromic shifts including bathochromic shift (red shift) and hypsochromic shift (blue shift). In the DL model, chromophore–solvent interactions are included, allowing reliable prediction of solvatochromic shifts. The solvatochromic shifts of Reichardt’s dye (61) (Betaine 30, Figure 3a) in 334 solvent molecules are well predicted by the DL model. The DL model is found to quite accurately predict the λabs of Betaine 30 in solvents with similar dielectric constants (εr): 1,2-dichloroethane (εr = 10.36, λabsexp = 692 nm, λabspred = 692 nm), 1,1-dichloroethane (εr = 10.46, λabsexp = 726 nm, λabspred = 701 nm), and 2,2-dichloropropane (εr = 11.63, λabsexp = 754 nm, λabspred = 715 nm). These results indicate that the chromophore–solvent interactions in the DL model were sufficiently well implemented.

Figure 3

Figure 3. Solvent effects on optical properties predicted by our DL model. (a) Experimental vs predicted λabs values of Reichardt’s dye (Betaine 30) in 334 solvents. The λabs of Reichardt’s dye exhibits a hypsochromic (blue) shift from 1000 to 450 nm with increasing solvent polarity. (b) Experimental vs predicted λemi values of dopants in host matrices (films). (c) Experimental vs predicted Φ values of molecules exhibiting aggregation induced emission in solutions or in solid states.

High Resolution Image
Download MS PowerPoint Slide
Organic fluorophores can also be incorporated as dopants in solid-state host matrices. Such systems are widely used in OLEDs. (62) Our database includes 48 host molecules and 361 fluorophore(dopant)–host systems developed for OLEDs. The matrix effects on the emission properties of the dopants are well predicted (Figures 3b and S8). Estimation of the PLQY of dopants in host matrices is critical for designing dopant molecules, but the PLQYs of molecules in solutions or in films are challenging to estimate theoretically. The DL model could be effectively used to prescreen candidate dopant molecules by accurately estimating their PLQY.
In solid states, nonradiative processes associated with molecular rotations and vibrations are inactive and relatively high fluorescence quantum yields can be achieved. Aggregation-induced emission (AIE) has recently become an active research topic, (63) and we investigated whether our DL model could explain AIE. In our DL model, the effects of local environments are implemented using the adjacency and feature matrices of the solvents (Asol and Xsol), which can be treated as either the molecule itself for one-component solids (i.e., molecular solids) or as the host matrix for solid solutions. Therefore, the optical properties of chromophores in solids are able to be trained and predicted by the DL model. Note that amorphous and crystalline phase solid states are not distinguished in our database. Our database contains 730 examples of chromophores with AIE properties (Figure S9 and Table S3), and their Φ are indeed predicted to be larger in aggregates (molecular solids) than in solutions as shown in Figure 3c. In short, the effects of solvent and local environments on the optical properties of chromophores were successfully implemented to account for both solvatochromic shifts and the AIE effect.

Deep Learning Optical Spectroscopy

For a molecule, absorption and emission properties, which are quantified using spectroscopic measurements, are characterized by their position (λabs/λemi), bandwidth (σabs/σemi), and amplitude (ε/Φ). For any given organic compound, these optical properties are readily predicted by our DL model and can be used to simulate the absorption and emission spectra as described in Methods, making DL optical spectroscopy possible. Furthermore, the daylight and emission colors of a molecule in solution and films under the daylight and UV-lamp can be estimated based on the absorption and emission spectra, respectively.
The absorption and emission spectra of coumarin 153 in ethanol were predicted using the DL model and TD-DFT calculations and are compared in Figure 4a. (64) The daylight and emission colors of coumarin 153 in ethanol are successfully reproduced by the DL model. In contrast, TD-DFT calculations estimated the daylight color well but not the emission color. For a molecule, λabs, λemi, ε, and the radiative rate constant can be estimated by theoretical calculations, but σabs, σemi, and Φ are highly challenging to predict using currently available theoretical methods. The performance of the DL model was further examined using the thermally activated delayed fluorescence (TADF) dye, BPCP-2CPC, in the host molecule, C-2PC. (65) While the optical properties of BPCP-2CPC in toluene are included in our database, those of BPCP-2CPC in C-2PC are not. The emission spectrum and a photograph of BPCP-2CPC in C-2PC are presented in Figure 4b. The emission spectrum of BPCP-2CPC in C-2PC was reasonably well predicted by the DL model, and the emission color is well represented in the CIE 1931 xy chromaticity space (Figure S10). Figures 4c, d and S11 show the photographs of chromophores in various environments along with the emission colors predicted by the DL model. (66,67) The solvent-polarity-dependent colors are well reproduced. Accordingly, our DL optical spectroscopy is successfully implemented to predict the optical properties of chromophores in solutions, films, and powders.

Figure 4

Figure 4. DL optical spectroscopy. Experimentally measured and DL predicted absorption (black) and emission (red) spectra. (a) Coumarin 153 in ethanol. (b) BPCP-2CPC (molecule) in C-2PC (host). The bandwidths in fwhm for the calculated spectra are set to 5370 cm–1 (the default value in GaussView 6). (c) Photograph of (E,E,E)-2-(4-diphenylaminostyryl)-4,6-bis(4-methoxystyryl)pyrimidine in several solvents. The colors below the photograph are those predicted using our DL model [Reproduced with permission from ref (66). Copyright 2018 American Chemical Society]. (d) Photographs of solid state emission. The colors below the photograph are those predicted using our DL model [Reprinted with permission from ref (67). Copyright 2016 Published by Elsevier Ltd.].

High Resolution Image
Download MS PowerPoint Slide

Development of a Target Chromophore by Virtual Screening via DL Optical Spectroscopy

DL optical spectroscopy could be effectively used to select target chromophores with desired optical and photophysical properties from many predesigned candidate molecules as shown in Figure 5a. Many potentially synthesizable molecular structures are predesigned, their seven optical properties are predicted by DL optical spectroscopy, a target molecule with desired properties is selected and synthesized, and finally the optical and photophysical properties of the synthesized target molecule are characterized by many spectroscopic methods and whether the optical and photophysical properties match those desired is evaluated. In this way, new target molecules optimized for a given purpose can be efficiently developed using DL optical spectroscopy.

Figure 5

Figure 5. Development of a target chromophore by virtual screening. (a) Overview for development of a new chromophore by DL optical spectroscopy. (b) Molecular structures of 3 molecules based on a DOBNA core with carbazole (1), phenoxazine (2), and diphenylamine moieties (3), and the optical properties predicted by DL optical spectroscopy. (c) Absorption and emission spectra of compound 1 in toluene. σabs cannot be experimentally measured because the S1 transition is overlapped with higher electronic transitions. (d) Time-resolved fluorescence signal of compound 1 in toluene.

High Resolution Image
Download MS PowerPoint Slide
This section demonstrates how DL optical spectroscopy can be practically used in the development of a new blue fluorophore with a donor (D)–acceptor (A) type. Figure 5b shows three organic molecules with a DOBNA backbone which could be readily predesigned. And then their optical properties in toluene were predicted by DL optical spectroscopy as summarized in Table S4. Depending on the donor unit such as carbazole (1), phenoxazine (2), and diphenylamine moieties (3) as shown in Figure 5b, the predesigned molecules are predicted to exhibit quite different emission colors, very narrow emission bandwidths, and decent PLQYs. Note that DOBNA core structures were shown to exhibit such narrow bandwidths and high PLQYs. (68−70) Among three compounds in Figure 5b, Compound 1 is a fluorophore with a deep blue color (λemi = 428 nm and CIE y < 0.1), narrow emission bandwidth (σemi = 29 nm), and decent PLQY (Φ = ∼0.7). As a desired deep blue emitter, compound 1 was synthesized.
As shown in Figure 5c and d, the optical properties of compound 1 were experimentally measured in toluene, which is a typical solvent for optical measurements of organic compounds, and are summarized in Table S5. The optical properties of compound 1 in toluene are found to agree reasonably well with the values predicted by DL optical spectroscopy within the RMSEs although the experimentally determined values are somewhat slightly smaller than the predicted values. The λabs and λemi in the absorption and emission spectra are ∼30 nm blue-shifted compared to the predicted values. But the emission bandwidth (σemi = 22 nm), PLQY (Φ = 0.543), and lifetime (τ = 5.1 ns) are reasonably well predicted. Furthermore, the CIE coordinates are found to be (0.157, 0.020), which is close to the predicted values (0.153, 0.020).

Conclusions

ARTICLE SECTIONS
Jump To
We have successfully developed a DL method based on an experimental database to predict the optical properties of chromophores or fluorophores in various environments. Our DL model was trained using an experimental database of 30 094 chromophore/solvent combinations consisting of 11 392 unique organic chromophores in 369 solvents or solid states. (11,12) Seven optical properties of each organic molecule can be reliably estimated using the DL model and used to reconstruct the absorption and emission spectra and predict the real-world color of the molecule, achieving DL optical spectroscopy.
DL optical spectroscopy can be effectively used to prescreen whether newly designed chromophores and fluorophores exhibit desired optical properties before they are actually synthesized, which would reduce development costs significantly. We successfully demonstrated a strategy to developing a new deep blue emitter with desired optical properties using virtual screening by DL optical spectroscopy. By utilizing DL optical spectroscopy, the development of organic molecules for electronic and optoelectronic applications will be boosted.
Our DL method represents a framework that could be generally applicable to predict other chemical and physical properties of organic compounds. The experimental database of 30 094 chromophore/solvent combinations is currently in use but can be continuously extended to include a broader range of core structures. Therefore, the prediction accuracy of optical properties and the coverage of molecular structures by our DL optical spectroscopy will be continuously improved in the future. Recently, DL models that generate valid molecular structures based on a variational autoencoder (VAE) and a generative adversarial network (GAN) have been reported, (71−76) and by combining these generative DL models, our DL optical spectroscopy is expected to be used more efficiently in the development of new fluorophores and chromophores. Lastly, using our DL model we developed a web-based interface, “Deep4Chem”, (77) to predict the optical properties of organic compounds as well as the electronic absorption and emission peaks and the corresponding original colors which the materials would have, associated with absorption and emission peaks, in CIE color coordinates.

Methods

ARTICLE SECTIONS
Jump To

Training Our DL Model

Our DL model was trained using an experimental database. In the training process, the loss function was defined by the total mean squared error which was obtained by summing the mean squared errors of seven optical and photophysical properties with the same weight. Note that τ and Φ were taken logarithms before normalization because their values reported in the literature were ranged on many orders of magnitude. In the case of Φ = 0 in the database, 10–5 was added to Φ. The absorption and emission bandwidths (σabs and σemi) in nanometers in the database were converted to those in wavenumbers by using the following equation, σj(cm–1) = 107/[λj – σj(nm)/2] – 107/[λj + σj(nm)/2] where λj is the absorption and emission peak positions in nanometers. In addition, all molecular properties were normalized to follow the standard normal distribution so that the loss of each property was on the same scale. A total of 30 094 chromophore/solvent combinations are randomly divided in a ratio of 0.8:0.1:0.1 for training, validation, and testing. For optimizing the hyper-parameters such as the number and dimension of GCN layers and MLPs, training and validation sets were used. No evidence of overfitting was found during the training over 10 000 epochs, as shown in Figure S3. After optimization, the DL model was trained by using training and validation sets. The training results are displayed in Figure S4 and Tables S1 and S2.

Quantum Chemical Calculations

All quantum chemical calculations were performed using the density functional theory (DFT) and time-dependent DFT (TD-DFT) methods at the B3LYP level with a 6-31G(d) basis set as implemented in the Gaussian 16 package. (53) For all molecules in Table S5, the integral equation formalism for the polarizable continuum model (IEF-PCM) was used for solvation. The absorption and emission spectra of molecules were obtained by optimizing the electronic ground state and excited state, respectively, and subsequently calculating the TD-DFT transition energies. Using a computer with an Intel CPU (i7-6700) and 16 GB of RAM, TD-DFT calculations took an average of 236 min per molecule. On the other hand, our DL model took 20 s for 131 molecule–solvent pairs on the same computer.

Reconstruction of Absorption and Emission Spectra

Absorption and emission spectra, Sj(ω), were calculated as a single peak using the normalized Gaussian function and predicted values by our DL model
(1)
where λj is the absorption or emission peak position in nm and σj is the bandwidth. The vibronic features and asymmetric nature of the spectroscopic peaks were not reflected in eq 1. The absorption intensity is directly related to the extinction coefficient by Beer’s law (A = εbc); thus, the absorption spectrum can be approximated as εSabs(ω). Similarly, the emission intensity is proportional to the absorption intensity and PLQY, and thus, the emission spectrum can be obtained as εΦSemi(ω). The product of PLQY and extinction coefficient (i.e., Φε) is known as the brightness. Using the optical and photophysical properties (λabs, λemi, σabs, σemi, ε, and Φ) predicted by the DL model, the absorption or emission spectra of a molecule were readily calculated. Furthermore, the CIE 1931 color space was computed using the calculated absorption and emission spectra. The CIE Standard Illuminant D65 was used for a daylight color.

Supporting Information

ARTICLE SECTIONS
Jump To

The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/jacsau.1c00035.

  • The details of our deep learning model, prediction by our deep learning model, and synthetic procedure of compound 1 (PDF)

Terms & Conditions

Most electronic Supporting Information files are available without a subscription to ACS Web Editions. Such files may be downloaded by article for research use (if there is a public use license linked to the relevant article, that license may permit other uses). Permission may be obtained from ACS for other uses through requests via the RightsLink permission system: http://pubs.acs.org/page/copyright/permissions.html.

Author Information

ARTICLE SECTIONS
Jump To
  • Corresponding Author
  • Authors
    • Joonyoung F. Joung - Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea;  Orcidhttp://orcid.org/0000-0002-5976-2048
    • Minhi Han - Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea;  Orcidhttp://orcid.org/0000-0002-9873-4904
    • Jinhyo Hwang - Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea
    • Minseok Jeong - Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea
    • Dong Hoon Choi - Department of Chemistry and Research Institute for Natural Science, Korea University, Seoul 02841, Korea;  Orcidhttp://orcid.org/0000-0002-3165-0597
  • Notes
    The authors declare no competing financial interest.

Acknowledgments

ARTICLE SECTIONS
Jump To

This study was supported by grants from the National Research Foundation of Korea (NRF) funded by the Korean government (No. 2019R1A6A1A11044070) and Korea University-Future Research Grant (KU-FRG).

References

ARTICLE SECTIONS
Jump To

This article references 77 other publications.

  1. 1
    Burlingame, Q.; Huang, X.; Liu, X.; Jeong, C.; Coburn, C.; Forrest, S. R. Intrinsically stable organic solar cells under high-intensity illumination. Nature 2019, 573 (7774), 394,  DOI: 10.1038/s41586-019-1544-1
    [Crossref], [PubMed], [CAS], Google Scholar
    1
    Intrinsically stable organic solar cells under high-intensity illumination
    Burlingame, Quinn; Huang, Xiaheng; Liu, Xiao; Jeong, Changyeong; Coburn, Caleb; Forrest, Stephen R.
    Nature (London, United Kingdom) (2019), 573 (7774), 394-397CODEN: NATUAS; ISSN:0028-0836. (Nature Research)
    Org. photovoltaic cells are now approaching com. viable efficiencies, particularly for applications that make use of their unique potential for flexibility and semitransparency. However, their reliability remains a major concern, as even the most stable devices reported so far degrade within only a few years. This has led to the belief that short operational lifetimes are an intrinsic disadvantage of devices that are fabricated using weakly bonded org. materials-an idea that persists despite the rapid growth and acceptance of org. light-emitting devices, which can achieve lifetimes of several million hours. Here we study an extremely stable class of thermally evapd. single-junction org. photovoltaic cells. We accelerated the ageing process by exposing the packaged cells to white-light illumination intensities of up to 37 Suns. The cells maintained more than 87 per cent of their starting efficiency after exposure for more than 68 days. The degrdn. rate increases superlinearly with intensity, leading to an extrapolated intrinsic lifetime, T80, of more than 4.9 × 107 hours, where T80 is the time taken for the power conversion efficiency to decrease to 80 per cent of its initial value. This is equiv. to 27,000 years outdoors. Addnl., we subjected a second group of org. photovoltaic cells to 20 Suns of UV illumination (centered at 365 nm) for 848 h, a dose that would take 1.7 × 104 hours (9.3 years) to accumulate outdoors. No efficiency loss was obsd. over the duration of the test. Overall, we find that org. solar cells packaged in an inert atm. can be extremely stable, which is promising for their future use as a practical energy-generation technol.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhsleltLvF&md5=be093394bc93fbd85271e6bc8731d138
  2. 2
    Uoyama, H.; Goushi, K.; Shizu, K.; Nomura, H.; Adachi, C. Highly efficient organic light-emitting diodes from delayed fluorescence. Nature 2012, 492 (7428), 234,  DOI: 10.1038/nature11687
    [Crossref], [PubMed], [CAS], Google Scholar
    2
    Highly efficient organic light-emitting diodes from delayed fluorescence
    Uoyama, Hiroki; Goushi, Kenichi; Shizu, Katsuyuki; Nomura, Hiroko; Adachi, Chihaya
    Nature (London, United Kingdom) (2012), 492 (7428), 234-238CODEN: NATUAS; ISSN:0028-0836. (Nature Publishing Group)
    The inherent flexibility afforded by mol. design has accelerated the development of a wide variety of org. semiconductors over the past 2 decades. In particular, great advances were made in the development of materials for org. light-emitting diodes (OLEDs), from early devices based on fluorescent mols. to those using phosphorescent mols. In OLEDs, elec. injected charge carriers recombine to form singlet and triplet excitons in a 1:3 ratio; the use of phosphorescent metal-org. complexes exploits the normally nonradiative triplet excitons and so enhances the overall electroluminescence efficiency. Here the authors report a class of metal-free org. electroluminescent mols. in which the energy gap between the singlet and triplet excited states is minimized by design, thereby promoting highly efficient spin up-conversion from nonradiative triplet states to radiative singlet states while maintaining high radiative decay rates, of >106 decays per s. These mols. harness both singlet and triplet excitons for light emission through fluorescence decay channels, leading to an intrinsic fluorescence efficiency >90% and a very high external electroluminescence efficiency, of >19%, which is comparable to that achieved in high-efficiency phosphorescence-based OLEDs.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC38XhvVamurjL&md5=73e6f816abcb9166d7d4e7676a51f5cf
  3. 3
    Li, B.; Zhao, M.; Feng, L.; Dou, C.; Ding, S.; Zhou, G.; Lu, L.; Zhang, H.; Chen, F.; Li, X. Organic NIR-II molecule with long blood half-life for in vivo dynamic vascular imaging. Nat. Commun. 2020, 11 (1), 3102,  DOI: 10.1038/s41467-020-16924-z
    [Crossref], [PubMed], [CAS], Google Scholar
    3
    Organic NIR-II molecule with long blood half-life for in vivo dynamic vascular imaging
    Li, Benhao; Zhao, Mengyao; Feng, Lishuai; Dou, Chaoran; Ding, Suwan; Zhou, Gang; Lu, Lingfei; Zhang, Hongxin; Chen, Feiya; Li, Xiaomin; Li, Guangfeng; Zhao, Shichang; Jiang, Chunyu; Wang, Yan; Zhao, Dongyuan; Cheng, Yingsheng; Zhang, Fan
    Nature Communications (2020), 11 (1), 3102CODEN: NCAOBW; ISSN:2041-1723. (Nature Research)
    Abstr.: Real-time monitoring of vessel dysfunction is of great significance in preclin. research. Optical bioimaging in the second near-IR (NIR-II) window provides advantages including high resoln. and fast feedback. However, the reported mol. dyes are hampered by limited blood circulation time (~ 5-60 min) and short absorption and emission wavelength, which impede the accurate long-term monitoring. Here, we report a NIR-II mol. (LZ-1105) with absorption and emission beyond 1000 nm. Thanks to the long blood circulation time (half-life of 3.2 h), the fluorophore is used for continuous real-time monitoring of dynamic vascular processes, including ischemic reperfusion in hindlimbs, thrombolysis in carotid artery and opening and recovery of the blood brain barrier (BBB). LZ-1105 provides an approach for researchers to assess vessel dysfunction due to the long excitation and emission wavelength and long-term blood circulation properties.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXht1Wmur%252FN&md5=44ddd07f9cd32078d5a0f2fbc8edbef8
  4. 4
    Zhang, Y.; Yang, H.; Ma, H.; Bian, G.; Zang, Q.; Sun, J.; Zhang, C.; An, Z.; Wong, W. Y. Excitation Wavelength Dependent Fluorescence of an ESIPT Triazole Derivative for Amine Sensing and Anti-Counterfeiting Applications. Angew. Chem. 2019, 131 (26), 8865,  DOI: 10.1002/ange.201902890
    [Crossref], Google Scholar
    There is no corresponding record for this reference.
  5. 5
    Woodward, R. B. Structure and the Absorption Spectra of α,β-Unsaturated Ketones. J. Am. Chem. Soc. 1941, 63 (4), 1123,  DOI: 10.1021/ja01849a066
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    5
    Structure and the absorption spectra of α,β-unsaturated ketones
    Woodward, Robert Burns
    Journal of the American Chemical Society (1941), 63 (), 1123-6CODEN: JACSAT; ISSN:0002-7863.
    Tables are given of λmax. for unsatd. ketones contg. an α- or β-substituent, those with α,β- or β,β-disubstituents and those with α,β,β-trisubstituents (6 of the 1st class, 36 of the 2nd and 8 of the 3rd). Compds. of the 1st class are characterized by strong absorption in the region 225 ± 5 mμ, those of the 2nd in the region 239 ± 5 mμ and those of the 3rd in the region 254 ± 5 mμ. The substitution for H of an alkyl group causes a shift toward the red of approx. 15 mμ and the detn. of λmax. reveals unequivocally the extent of the substitution of the C-C double bond in an α,β-unsatd. ketone. The substitution, at least in the α-position, of a Br atom or an AcO group has much the same effect as the substitution of an alkyl group. The 3 classes do not overlap and the av. deviation from the mean position is much less than 5 mμ. The use of the detn. of the position of the wave length of max. absorption for the intense band in the absorption spectra as a method for establishing structure is illustrated with α-cyperone. A few compds. do not conform with the generalizations outlined above and these are being studied.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaH3MXit1Omsg%253D%253D&md5=7341a2edc8cd986f1d3d69f29ac50aee
  6. 6
    Roothaan, C. C. J. New Developments in Molecular Orbital Theory. Rev. Mod. Phys. 1951, 23 (2), 69,  DOI: 10.1103/RevModPhys.23.69
    [Crossref], [CAS], Google Scholar
    6
    New developments in molecular orbital theory
    Roothaan, C. C. J.
    Reviews of Modern Physics (1951), 23 (), 69-89CODEN: RMPHAT; ISSN:0034-6861.
    The mathematics of the "mol. orbital" method are reviewed.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaG38XksVakuw%253D%253D&md5=200a0ce85fea3870e3322cdafd1cd1bc
  7. 7
    McWeeny, R.; Diercksen, G. Self-Consistent Perturbation Theory. II. Extension to Open Shells. J. Chem. Phys. 1968, 49 (11), 4852,  DOI: 10.1063/1.1669970
    [Crossref], [CAS], Google Scholar
    7
    Self-consistent perturbation theory. II. Extension to open shells
    McWeeny, Roy; Diercksen, G.
    Journal of Chemical Physics (1968), 49 (11), 4852-6CODEN: JCPSA6; ISSN:0021-9606.
    The self-consistent perturbation theory developed in earlier papers is extended to the open-shell case. Density matrixes for both shells are calcd. iteratively until first-order self-consistency is achieved. A numerical application indicates the importance of considering both shells sep. when discussing the effects of polarization on the charge d. and the spin d.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaF1MXktVOgsw%253D%253D&md5=1a373d6d76169d17f9a544f5ff72d8bb
  8. 8
    Hohenberg, P.; Kohn, W. Inhomogeneous Electron Gas. Phys. Rev. 1964, 136 (3B), B864,  DOI: 10.1103/PhysRev.136.B864
    [Crossref], Google Scholar
    There is no corresponding record for this reference.
  9. 9
    Bauernschmitt, R.; Ahlrichs, R. Treatment of electronic excitations within the adiabatic approximation of time dependent density functional theory. Chem. Phys. Lett. 1996, 256 (4–5), 454,  DOI: 10.1016/0009-2614(96)00440-X
    [Crossref], [CAS], Google Scholar
    9
    Treatment of electronic excitations within the adiabatic approximation of time dependent density functional theory
    Bauernschmitt, Ruedger; Ahlrichs, Reinhart
    Chemical Physics Letters (1996), 256 (4,5), 454-464CODEN: CHPLBC; ISSN:0009-2614. (Elsevier)
    Time dependent d. functional methods are applied in the adiabatic approxn. to compute low-lying electronic excitations of N2, ethylene, formaldehyde, pyridine and porphin. Out of various local, gradient-cor. and hybrid (including exact exchange) functionals, the best results are obtained for the three-parameter Lee-Yang-Parr (B3LYP) functional proposed by Becke. B3LYP yields excitation energies about 0.4 eV too low but typically gives the correct ordering of states and constitutes a considerable improvement over HF-based approaches requiring comparable numerical work.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaK28XksFWltrs%253D&md5=484b6c8f0fa99d77d9aa02693ee6103a
  10. 10
    Adamo, C.; Jacquemin, D. The calculations of excited-state properties with Time-Dependent Density Functional Theory. Chem. Soc. Rev. 2013, 42 (3), 845,  DOI: 10.1039/C2CS35394F
    [Crossref], [PubMed], [CAS], Google Scholar
    10
    The calculations of excited-state properties with Time-Dependent Density Functional Theory
    Adamo, Carlo; Jacquemin, Denis
    Chemical Society Reviews (2013), 42 (3), 845-856CODEN: CSRVBR; ISSN:0306-0012. (Royal Society of Chemistry)
    In this tutorial review, we show how Time-Dependent D. Functional Theory (TD-DFT) has become a popular tool for computing the signatures of electronically excited states, and more specifically, the properties directly related to the optical (absorption and emission) spectra of mols. We discuss the properties that can be obtained with widely available programs as well as how to account for the environmental effects (solvent and surfaces) and present recent applications in these fields. We next expose the transformation of the TD-DFT results into chem. intuitive parameters (colors as well as charge-transfer distances). Eventually, the non-specialised reader will find a series of advices and warnings necessary to perform her/his first TD-DFT calcns.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC3sXosV2jtA%253D%253D&md5=f34f78385b45bc2f429e1975c10241fc
  11. 11
    Joung, J. F.; Han, M.; Jeong, M.; Park, S. Figshare 2020,  DOI: 10.6084/m9.figshare.12045567.v2
    [Crossref], Google Scholar
    There is no corresponding record for this reference.
  12. 12
    Joung, J. F.; Han, M.; Jeong, M.; Park, S. Experimental database of optical properties of organic compounds. Sci. Data 2020, 7 (1), 295,  DOI: 10.1038/s41597-020-00634-8
    [Crossref], [PubMed], [CAS], Google Scholar
    12
    Experimental database of optical properties of organic compounds
    Joung, Joonyoung F.; Han, Minhi; Jeong, Minseok; Park, Sungnam
    Scientific Data (2020), 7 (1), 295CODEN: SDCABS; ISSN:2052-4463. (Nature Research)
    Exptl. databases on the optical properties of org. chromophores are important for the implementation of data-driven chem. using machine learning. Herein, we present a series of exptl. data including various optical properties such as the first absorption and emission max. wavelengths and their bandwidths (full width at half max.), extinction coeff., photoluminescence quantum yield, and fluorescence lifetime. A database of 20,236 data points was developed by collecting the optical properties of org. compds. already reported in the literature. A dataset of 7,016 unique org. chromophores in 365 solvents or in solid state is available in CSV format.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXhvVWjsLjM&md5=a83b26ef798f04e3934b98b7ba6b0416
  13. 13
    Butler, K. T.; Davies, D. W.; Cartwright, H.; Isayev, O.; Walsh, A. Machine learning for molecular and materials science. Nature 2018, 559 (7715), 547,  DOI: 10.1038/s41586-018-0337-2
    [Crossref], [PubMed], [CAS], Google Scholar
    13
    Machine learning for molecular and materials science
    Butler, Keith T.; Davies, Daniel W.; Cartwright, Hugh; Isayev, Olexandr; Walsh, Aron
    Nature (London, United Kingdom) (2018), 559 (7715), 547-555CODEN: NATUAS; ISSN:0028-0836. (Nature Research)
    Here we summarize recent progress in machine learning for the chem. sciences. We outline machine-learning techniques that are suitable for addressing research questions in this domain, as well as future directions for the field. We envisage a future in which the design, synthesis, characterization and application of mols. and materials is accelerated by artificial intelligence.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXhtl2jt7vL&md5=13d36f27db8d59f558fe28e946b4b009
  14. 14
    Mater, A. C.; Coote, M. L. Deep Learning in Chemistry. J. Chem. Inf. Model. 2019, 59 (6), 2545,  DOI: 10.1021/acs.jcim.9b00266
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    14
    Deep Learning in Chemistry
    Mater, Adam C.; Coote, Michelle L.
    Journal of Chemical Information and Modeling (2019), 59 (6), 2545-2559CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
    A review. Machine learning enables computers to address problems by learning from data. Deep learning is a type of machine learning that uses a hierarchical recombination of features to ext. pertinent information and then learn the patterns represented in the data. Over the last eight years, its abilities have increasingly been applied to a wide variety of chem. challenges, from improving computational chem. to drug and materials design and even synthesis planning. This review aims to explain the concepts of deep learning to chemists from any background and follows this with an overview of the diverse applications demonstrated in the literature. We hope that this will empower the broader chem. community to engage with this burgeoning field and foster the growing movement of deep learning accelerated chem.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtFGhtrvK&md5=67bcc93a2f733c51afd9fe3ed23cea39
  15. 15
    Montavon, G.; Rupp, M.; Gobre, V.; Vazquez-Mayagoitia, A.; Hansen, K.; Tkatchenko, A.; Müller, K.-R.; Anatole von Lilienfeld, O. Machine learning of molecular electronic properties in chemical compound space. New J. Phys. 2013, 15 (9), 095003,  DOI: 10.1088/1367-2630/15/9/095003
    [Crossref], [CAS], Google Scholar
    15
    Machine learning of molecular electronic properties in chemical compound space
    Montavon, Gregoire; Rupp, Matthias; Gobre, Vivekanand; Vazquez-Mayagoitia, Alvaro; Hansen, Katja; Tkatchenko, Alexandre; Mueller, Klaus-Robert; von Lilienfeld, O. Anatole
    New Journal of Physics (2013), 15 (Sept.), 095003CODEN: NJOPFM; ISSN:1367-2630. (IOP Publishing Ltd.)
    The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amt. of data amenable to intelligent data anal. for the identification of meaningful, novel and predictive structure-property relationships. Such relationships enable high-throughput screening for relevant properties in an exponentially growing pool of virtual compds. that are synthetically accessible. Here, we present a machine learning model, trained on a database of ab initio calcn. results for thousands of org. mols., that simultaneously predicts multiple electronic ground- and excited-state properties. The properties include atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity and excitation energies. The machine learning model is based on a deep multi-task artificial neural network, exploiting the underlying correlations between various mol. properties. The input is identical to ab initio methods, i.e. nuclear charges and Cartesian coordinates of all atoms. For small org. mols., the accuracy of such a 'quantum machine' is similar, and sometimes superior, to modern quantum-chem. methods-at negligible computational cost.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2cXltlKgs74%253D&md5=b38a7678efd055385e4eb6ee9b7aadae
  16. 16
    Coley, C. W.; Barzilay, R.; Green, W. H.; Jaakkola, T. S.; Jensen, K. F. Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction. J. Chem. Inf. Model. 2017, 57 (8), 1757,  DOI: 10.1021/acs.jcim.6b00601
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    16
    Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction
    Coley, Connor W.; Barzilay, Regina; Green, William H.; Jaakkola, Tommi S.; Jensen, Klavs F.
    Journal of Chemical Information and Modeling (2017), 57 (8), 1757-1772CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
    The task of learning an expressive mol. representation is central to developing quant. structure-activity and property relationships. Traditional approaches rely on group additivity rules, empirical measurements or parameters, or generation of thousands of descriptors. In this paper, we employ a convolutional neural network for this embedding task by treating mols. as undirected graphs with attributed nodes and edges. Simple atom and bond attributes are used to construct atom-specific feature vectors that take into account the local chem. environment using different neighborhood radii. By working directly with the full mol. graph, there is a greater opportunity for models to identify important features relevant to a prediction task. Unlike other graph-based approaches, our atom featurization preserves mol.-level spatial information that significantly enhances model performance. Our models learn to identify important features of atom clusters for the prediction of aq. soly., octanol soly., m.p., and toxicity. Extensions and limitations of this strategy are discussed.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2sXhtFCmtbzF&md5=85e942e40e2b7a827788113bdf5f6240
  17. 17
    Musil, F.; De, S.; Yang, J.; Campbell, J. E.; Day, G. M.; Ceriotti, M. Machine learning for the structure-energy-property landscapes of molecular crystals. Chem. Sci. 2018, 9 (5), 1289,  DOI: 10.1039/C7SC04665K
    [Crossref], [PubMed], [CAS], Google Scholar
    17
    Machine learning for the structure-energy-property landscapes of molecular crystals
    Musil, Felix; De, Sandip; Yang, Jack; Campbell, Joshua E.; Day, Graeme M.; Ceriotti, Michele
    Chemical Science (2018), 9 (5), 1289-1300CODEN: CSHCCN; ISSN:2041-6520. (Royal Society of Chemistry)
    Mol. crystals play an important role in several fields of science and technol. They frequently crystallize in different polymorphs with substantially different phys. properties. To help guide the synthesis of candidate materials, at.-scale modeling can be used to enumerate the stable polymorphs and to predict their properties, as well as to propose heuristic rules to rationalize the correlations between crystal structure and materials properties. Here we show how a recently-developed machine-learning (ML) framework can be used to achieve inexpensive and accurate predictions of the stability and properties of polymorphs, and a data-driven classification that is less biased and more flexible than typical heuristic rules. We discuss, as examples, the lattice energy and property landscapes of pentacene and two azapentacene isomers that are of interest as org. semiconductor materials. We show that we can est. force field or DFT lattice energies with sub-kJ mol-1 accuracy, using only a few hundred ref. configurations, and reduce by a factor of ten the computational effort needed to predict charge mobility in the crystal structures. The automatic structural classification of the polymorphs reveals a more detailed picture of mol. packing than that provided by conventional heuristics, and helps disentangle the role of hydrogen bonded and π-stacking interactions in detg. mol. self-assembly. This observation demonstrates that ML is not just a black-box scheme to interpolate between ref. calcns., but can also be used as a tool to gain intuitive insights into structure-property relations in mol. crystal engineering.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2sXhvFGnsbfE&md5=48b184722478d1a988a2090f765135e2
  18. 18
    Jinich, A.; Sanchez-Lengeling, B.; Ren, H.; Harman, R.; Aspuru-Guzik, A. A Mixed Quantum Chemistry/Machine Learning Approach for the Fast and Accurate Prediction of Biochemical Redox Potentials and Its Large-Scale Application to 315000 Redox Reactions. ACS Cent. Sci. 2019, 5 (7), 1199,  DOI: 10.1021/acscentsci.9b00297
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    18
    A Mixed Quantum Chemistry/Machine Learning Approach for the Fast and Accurate Prediction of Biochemical Redox Potentials and Its Large-Scale Application to 315 000 Redox Reactions
    Jinich, Adrian; Sanchez-Lengeling, Benjamin; Ren, Haniu; Harman, Rebecca; Aspuru-Guzik, Alan
    ACS Central Science (2019), 5 (7), 1199-1210CODEN: ACSCII; ISSN:2374-7951. (American Chemical Society)
    A quant. understanding of the thermodn. of biochem. reactions is essential for accurately modeling metab. The group contribution method (GCM) is one of the most widely used approaches to est. std. Gibbs energies and redox potentials of reactions for which no exptl. measurements exist. Previous work has shown that quantum chem. predictions of biochem. thermodn. are a promising approach to overcome the limitations of GCM. However, the quantum chem. approach is significantly more expensive. Here, the authors use a combination of quantum chem. and machine learning to obtain a fast and accurate method for predicting the thermodn. of biochem. redox reactions. The authors focus on predicting the redox potentials of carbonyl functional group redns. to alcs. and amines, two of the most ubiquitous carbon redox transformations in biol. The method relies on semiempirical quantum chem. calcns. calibrated with Gaussian process (GP) regression against available exptl. data and results in higher predictive power than the GCM at low computational cost. Direct calibration of GCM and fingerprint-based predictions (without quantum chem.) with GP regression also results in significant improvements in prediction accuracy, demonstrating the versatility of the approach. The authors design and implement a network expansion algorithm that iteratively reduces and oxidizes a set of natural seed metabolites and demonstrate the high-throughput applicability of the method by predicting the std. potentials of more than 315 000 redox reactions involving approx. 70 000 compds. Addnl., the authors developed a novel fingerprint-based framework for detecting mol. environment motifs that are enriched or depleted across different regions of the redox potential landscape. The authors provide open access to all source code and data generated.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtFWisb%252FN&md5=cc4e50e301cbd9a2736befbbb67a09db
  19. 19
    Yamada, H.; Liu, C.; Wu, S.; Koyama, Y.; Ju, S.; Shiomi, J.; Morikawa, J.; Yoshida, R. Predicting Materials Properties with Little Data Using Shotgun Transfer Learning. ACS Cent. Sci. 2019, 5 (10), 1717,  DOI: 10.1021/acscentsci.9b00804
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    19
    Predicting Materials Properties with Little Data Using Shotgun Transfer Learning
    Yamada, Hironao; Liu, Chang; Wu, Stephen; Koyama, Yukinori; Ju, Shenghong; Shiomi, Junichiro; Morikawa, Junko; Yoshida, Ryo
    ACS Central Science (2019), 5 (10), 1717-1730CODEN: ACSCII; ISSN:2374-7951. (American Chemical Society)
    There is a growing demand for the use of machine learning (ML) to derive fast-to-evaluate surrogate models of materials properties. In recent years, a broad array of materials property databases have emerged as part of a digital transformation of materials science. However, recent technol. advances in ML are not fully exploited because of the insufficient vol. and diversity of materials data. An ML framework called "transfer learning" has considerable potential to overcome the problem of limited amts. of materials data. Transfer learning relies on the concept that various property types, such as phys., chem., electronic, thermodn., and mech. properties, are phys. interrelated. For a given target property to be predicted from a limited supply of training data, models of related proxy properties are pretrained using sufficient data; these models capture common features relevant to the target task. Repurposing of such machine-acquired features on the target task yields outstanding prediction performance even with exceedingly small data sets, as if highly experienced human experts can make rational inferences even for considerably less experienced tasks. In this study, to facilitate widespread use of transfer learning, we develop a pretrained model library called XenonPy.MDL. In this first release, the library comprises more than 140 000 pretrained models for various properties of small mols., polymers, and inorg. cryst. materials. Along with these pretrained models, we describe some outstanding successes of transfer learning in different scenarios such as building models with only dozens of materials data, increasing the ability of extrapolative prediction through a strategic model transfer, and so on. Remarkably, transfer learning has autonomously identified rather nontrivial transferability across different properties transcending the different disciplines of materials science; for example, our anal. has revealed underlying bridges between small mols. and polymers and between org. and inorg. chem. Along with the XenonPy.MDL model library, we describe the great potential of transfer learning to break the barrier of limited amts. of data in materials property prediction using machine learning.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhvVGms77L&md5=04e4b7016b754aecfc235812e511bb84
  20. 20
    Afzal, M. A. F.; Sonpal, A.; Haghighatlari, M.; Schultz, A. J.; Hachmann, J. A deep neural network model for packing density predictions and its application in the study of 1.5 million organic molecules. Chem. Sci. 2019, 10 (36), 8374,  DOI: 10.1039/C9SC02677K
    [Crossref], [PubMed], [CAS], Google Scholar
    20
    A deep neural network model for packing density predictions and its application in the study of 1.5 million organic molecules
    Afzal, Mohammad Atif Faiz; Sonpal, Aditya; Haghighatlari, Mojtaba; Schultz, Andrew J.; Hachmann, Johannes
    Chemical Science (2019), 10 (36), 8374-8383CODEN: CSHCCN; ISSN:2041-6520. (Royal Society of Chemistry)
    The process of developing new compds. and materials is increasingly driven by computational modeling and simulation, which allow us to characterize candidates before pursuing them in the lab. One of the non-trivial properties of interest for org. materials is their packing in the bulk, which is highly dependent on their mol. structure. By controlling the latter, we can realize materials with a desired d. (as well as other target properties). Mol. dynamics simulations are a popular and reasonably accurate way to compute the bulk d. of mols., however, since these calcns. are computationally intensive, they are not a practically viable option for high-throughput screening studies that assess material candidates on a massive scale. In this work, we employ machine learning to develop a data-derived prediction model that is an alternative to physics-based simulations, and we utilize it for the hyperscreening of 1.5 million small org. mols. as well as to gain insights into the relationship between structural makeup and packing d. We also use this study to analyze the learning curve of the employed neural network approach and gain empirical data on the dependence of model performance and training data size, which will inform future investigations.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtleisLjP&md5=8457f2edf3e0a2df77a473d1252db825
  21. 21
    Dong, Y.; Wu, C.; Zhang, C.; Liu, Y.; Cheng, J.; Lin, J. Bandgap prediction by deep learning in configurationally hybridized graphene and boron nitride. npj Comput. Mater. 2019, 5 (1), 26,  DOI: 10.1038/s41524-019-0165-4
    [Crossref], Google Scholar
    There is no corresponding record for this reference.
  22. 22
    So, S.; Mun, J.; Rho, J. Simultaneous Inverse Design of Materials and Structures via Deep Learning: Demonstration of Dipole Resonance Engineering Using Core-Shell Nanoparticles. ACS Appl. Mater. Interfaces 2019, 11 (27), 24264,  DOI: 10.1021/acsami.9b05857
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    22
    Simultaneous Inverse Design of Materials and Structures via Deep Learning: Demonstration of Dipole Resonance Engineering Using Core-Shell Nanoparticles
    So, Sunae; Mun, Jungho; Rho, Junsuk
    ACS Applied Materials & Interfaces (2019), 11 (27), 24264-24268CODEN: AAMICK; ISSN:1944-8244. (American Chemical Society)
    Recent introduction of data-driven approaches based on deep-learning technol. has revolutionized the field of nanophotonics by allowing efficient inverse design methods. A simultaneous inverse design of materials and structure parameters of core-shell nanoparticles is achieved using deep learning of a neural network. A neural network to learn the correlation between the extinction spectra of elec. and magnetic dipoles and core-shell nanoparticle designs, which include material information and shell thicknesses, is developed and trained. Deep-learning-assisted inverse design of core-shell nanoparticles is demonstrated for (1) spectral tuning elec. dipole resonances, (2) finding spectrally isolated pure magnetic dipole resonances, and (3) finding spectrally overlapped elec. dipole and magnetic dipole resonances. The finding paves the way for the rapid development of nanophotonics by allowing a practical use of deep-learning technol. for nanophotonic inverse design.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtFyjs7rE&md5=bcbafdb550972b24c9fa738a976d4850
  23. 23
    Ye, S.; Hu, W.; Li, X.; Zhang, J.; Zhong, K.; Zhang, G.; Luo, Y.; Mukamel, S.; Jiang, J. A neural network protocol for electronic excitations of N-methylacetamide. Proc. Natl. Acad. Sci. U. S. A. 2019, 116 (24), 11612,  DOI: 10.1073/pnas.1821044116
    [Crossref], [PubMed], [CAS], Google Scholar
    23
    A neural network protocol for electronic excitations of N-methylacetamide
    Ye, Sheng; Hu, Wei; Li, Xin; Zhang, Jinxiao; Zhong, Kai; Zhang, Guozhen; Luo, Yi; Mukamel, Shaul; Jiang, Jun
    Proceedings of the National Academy of Sciences of the United States of America (2019), 116 (24), 11612-11617CODEN: PNASA6; ISSN:0027-8424. (National Academy of Sciences)
    UV absorption is widely used for characterizing proteins structures. The mapping of UV spectra to at. structure of proteins relies on expensive theor. simulations, circumventing the heavy computational cost which involves repeated quantum-mech. simulations of excited-state properties of many fluctuating protein geometries, which has been a long-time challenge. Here we show that a neural network machine-learning technique can predict electronic absorption spectra of N-methylacetamide (NMA), which is a widely used model system for the peptide bond. Using ground-state geometric parameters and charge information as descriptors, we employed a neural network to predict transition energies, ground-state, and transition dipole moments of many mol.-dynamics conformations at different temps., in agreement with time-dependent d.-functional theory calcns. The neural network simulations are nearly 3,000x faster than comparable quantum calcns. Machine learning should provide a cost-effective tool for simulating optical properties of proteins.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtFeqsLvM&md5=c59a23eb43db53bf7f3975a25efca882
  24. 24
    Ghosh, K.; Stuke, A.; Todorovic, M.; Jorgensen, P. B.; Schmidt, M. N.; Vehtari, A.; Rinke, P. Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra. Adv. Sci. 2019, 6 (9), 1801367,  DOI: 10.1002/advs.201801367
    [Crossref], [CAS], Google Scholar
    24
    Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra
    Ghosh Kunal; Vehtari Aki; Ghosh Kunal; Stuke Annika; Todorovic Milica; Rinke Patrick; Jorgensen Peter Bjorn; Schmidt Mikkel N; Rinke Patrick
    Advanced science (Weinheim, Baden-Wurttemberg, Germany) (2019), 6 (9), 1801367 ISSN:2198-3844.
    Deep learning methods for the prediction of molecular excitation spectra are presented. For the example of the electronic density of states of 132k organic molecules, three different neural network architectures: multilayer perceptron (MLP), convolutional neural network (CNN), and deep tensor neural network (DTNN) are trained and assessed. The inputs for the neural networks are the coordinates and charges of the constituent atoms of each molecule. Already, the MLP is able to learn spectra, but the root mean square error (RMSE) is still as high as 0.3 eV. The learning quality improves significantly for the CNN (RMSE = 0.23 eV) and reaches its best performance for the DTNN (RMSE = 0.19 eV). Both CNN and DTNN capture even small nuances in the spectral shape. In a showcase application of this method, the structures of 10k previously unseen organic molecules are scanned and instant spectra predictions are obtained to identify molecules for potential applications.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A280%3ADC%252BB3M7jsVGrsg%253D%253D&md5=cf103cea58059fa56008375f3ecb8698
  25. 25
    Back, S.; Yoon, J.; Tian, N.; Zhong, W.; Tran, K.; Ulissi, Z. W. Convolutional Neural Network of Atomic Surface Structures To Predict Binding Energies for High-Throughput Screening of Catalysts. J. Phys. Chem. Lett. 2019, 10 (15), 4401,  DOI: 10.1021/acs.jpclett.9b01428
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    25
    Convolutional Neural Network of Atomic Surface Structures To Predict Binding Energies for High-Throughput Screening of Catalysts
    Back, Seoin; Yoon, Junwoong; Tian, Nianhan; Zhong, Wen; Tran, Kevin; Ulissi, Zachary W.
    Journal of Physical Chemistry Letters (2019), 10 (15), 4401-4408CODEN: JPCLCD; ISSN:1948-7185. (American Chemical Society)
    High-throughput screening of catalysts can be performed using d. functional theory calcns. to predict catalytic properties, often correlated with adsorbate binding energies. More complete studies would require an order of 2 more calcns. compared to the current approach, making the computational cost a bottleneck. Recently developed machine-learning methods predict these properties from hand-crafted features but have struggled to scale to large compn. spaces or complex active sites. An application of a deep-learning convolutional neural network of at. surface structures using at. and Voronoi polyhedra-based neighbor information is presented. The model effectively learns the most important surface features to predict binding energies. The method predicts CO and H binding energies after training with 12,000 data for each adsorbate with a mean abs. error of 0.15 eV for a diverse chem. space. The method is capable of creating saliency maps that det. at. contributions to binding energies.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtlyju7jM&md5=cc068cadd2973b1bb2f17cec64ad61b3
  26. 26
    Kang, B.; Seok, C.; Lee, J. Prediction of Molecular Electronic Transitions Using Random Forests. J. Chem. Inf. Model. 2020, 60 (12), 5984,  DOI: 10.1021/acs.jcim.0c00698
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    26
    Prediction of Molecular Electronic Transitions Using Random Forests
    Kang, Beomchang; Seok, Chaok; Lee, Juyong
    Journal of Chemical Information and Modeling (2020), 60 (12), 5984-5994CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
    Fluorescent mols., fluorophores or dyes, play essential roles in bioimaging. Effective bioimaging requires fluorophores with diverse colors and high quantum yields for better resoln. An essential computational component to design novel dye mols. is an accurate model that predicts the electronic properties of mols. Here, we present statistical machines that predict the excitation energies and assocd. oscillator strengths of a given mol. using the random forest algorithm. The excitation energies and oscillator strengths of a mol. are closely related to the emission spectrum and the quantum yields of fluorophores, resp. In this study, we identified specific mol. substructures that induce high oscillator strengths of mols. The results of our study are expected to serve as new design principles for designing novel fluorophores.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXitFagtb%252FJ&md5=352c2b1634e6985d526dce4b69c57e7a
  27. 27
    Na, G. S.; Jang, S.; Lee, Y. L.; Chang, H. Tuplewise Material Representation Based Machine Learning for Accurate Band Gap Prediction. J. Phys. Chem. A 2020, 124 (50), 10616,  DOI: 10.1021/acs.jpca.0c07802
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    27
    Tuplewise Material Representation Based Machine Learning for Accurate Band Gap Prediction
    Na, Gyoung S.; Jang, Seunghun; Lee, Yea-Lee; Chang, Hyunju
    Journal of Physical Chemistry A (2020), 124 (50), 10616-10623CODEN: JPCAFH; ISSN:1089-5639. (American Chemical Society)
    The open-access material databases allowed us to approach scientific questions from a completely new perspective with machine learning methods. Here, on the basis of open-access databases, we focus on the classical band gap problem for predicting accurately the band gap of a cryst. compd. using a machine learning approach with newly developed tuplewise graph neural networks (TGNN), which is devised to automatically generate input representation of crystal structures in tuple types and to exploit crystal-level properties as one of the input features. Our method brings about a highly accurate prediction of the band gaps at hybrid functionals and GW approxn. levels for multiple material data sets without heavy computational cost. Furthermore, to demonstrate the applicability of our prediction model, we provide a data set of GW band gaps for 45835 materials predicted by TGNN posing higher accuracy than std. d. functional theory calcns.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXisVyiu7bL&md5=1ba7446df9022996a21f735a4ce88f0b
  28. 28
    Ye, S.; Zhong, K.; Zhang, J.; Hu, W.; Hirst, J. D.; Zhang, G.; Mukamel, S.; Jiang, J. A Machine Learning Protocol for Predicting Protein Infrared Spectra. J. Am. Chem. Soc. 2020, 142 (45), 19071,  DOI: 10.1021/jacs.0c06530
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    28
    A Machine Learning Protocol for Predicting Protein Infrared Spectra
    Ye, Sheng; Zhong, Kai; Zhang, Jinxiao; Hu, Wei; Hirst, Jonathan D.; Zhang, Guozhen; Mukamel, Shaul; Jiang, Jun
    Journal of the American Chemical Society (2020), 142 (45), 19071-19077CODEN: JACSAT; ISSN:0002-7863. (American Chemical Society)
    IR (IR) absorption provides important chem. fingerprints of biomols. Protein secondary structure detn. from IR spectra is tedious since its theor. interpretation requires repeated expensive quantum-mech. calcns. in a fluctuating environment. Herein we present a novel machine learning protocol that uses a few key structural descriptors to rapidly predict amide I IR spectra of various proteins and agrees well with expt. Its transferability enabled us to distinguish protein secondary structures, probe at. structure variations with temp., and monitor protein folding. This approach offers a cost-effective tool to model the relationship between protein spectra and their biol./chem. properties.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXitF2iu7jK&md5=7a3324e31a6e01900f5eb6f9ebd18d27
  29. 29
    Li, B.; Liu, R.; Bai, H.; Ju, C.-W. Can Machine Learning Be More Accurate Than TD-DFT? Prediction of Emission Wavelengths and Quantum Yields of Organic Fluorescent Materials. ChemRxiv 2020,  DOI: 10.26434/chemrxiv.12111060.v1
    [Crossref], [PubMed], Google Scholar
    There is no corresponding record for this reference.
  30. 30
    Gao, H.; Struble, T. J.; Coley, C. W.; Wang, Y.; Green, W. H.; Jensen, K. F. Using Machine Learning To Predict Suitable Conditions for Organic Reactions. ACS Cent. Sci. 2018, 4 (11), 1465,  DOI: 10.1021/acscentsci.8b00357
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    30
    Using Machine Learning To Predict Suitable Conditions for Organic Reactions
    Gao, Hanyu; Struble, Thomas J.; Coley, Connor W.; Wang, Yuran; Green, William H.; Jensen, Klavs F.
    ACS Central Science (2018), 4 (11), 1465-1476CODEN: ACSCII; ISSN:2374-7951. (American Chemical Society)
    Reaction condition recommendation is an essential element for the realization of computer-assisted synthetic planning. Accurate suggestions of reaction conditions are required for exptl. validation and can have a significant effect on the success or failure of an attempted transformation. However, de novo condition recommendation remains a challenging and under-explored problem and relies heavily on chemists' knowledge and experience. In this work, we develop a neural-network model to predict the chem. context (catalyst(s), solvent(s), reagent(s)), as well as the temp. most suitable for any particular org. reaction. Trained on ∼10 million examples from Reaxys, the model is able to propose conditions where a close match to the recorded catalyst, solvent, and reagent is found within the top-10 predictions 69.6% of the time, with top-10 accuracies for individual species reaching 80-90%. Temp. is accurately predicted within ±20 °C from the recorded temp. in 60-70% of test cases, with higher accuracy for cases with correct chem. context predictions. The utility of the model is illustrated through several examples spanning a range of common reaction classes. We also demonstrate that the model implicitly learns a continuous numerical embedding of solvent and reagent species that captures their functional similarity.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXit1aru77J&md5=fef56b949b8b8febb5d1403327238f4b
  31. 31
    Segler, M. H. S.; Preuss, M.; Waller, M. P. Planning chemical syntheses with deep neural networks and symbolic AI. Nature 2018, 555 (7698), 604,  DOI: 10.1038/nature25978
    [Crossref], [PubMed], [CAS], Google Scholar
    31
    Planning chemical syntheses with deep neural networks and symbolic AI
    Segler, Marwin H. S.; Preuss, Mike; Waller, Mark P.
    Nature (London, United Kingdom) (2018), 555 (7698), 604-610CODEN: NATUAS; ISSN:0028-0836. (Nature Research)
    To plan the syntheses of small org. mols., chemists use retrosynthesis, a problem-solving technique in which target mols. are recursively transformed into increasingly simpler precursors. Computer-aided retrosynthesis would be a valuable tool but at present it is slow and provides results of unsatisfactory quality. Here, we use Monte Carlo tree search and symbolic artificial intelligence (AI) to discover retrosynthetic routes. We combined Monte Carlo tree search with an expansion policy network that guides the search, and a filter network to pre-select the most promising retrosynthetic steps. These deep neural networks were trained on essentially all reactions ever published in org. chem. Our system solves for almost twice as many mols., thirty times faster than the traditional computer-aided search method, which is based on extd. rules and hand-designed heuristics. In a double-blind AB test, chemists on av. considered our computer-generated routes to be equiv. to reported literature routes.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXmsVGqt7c%253D&md5=400e9945ff83ffe2d12278aa4c562893
  32. 32
    Voznyy, O.; Levina, L.; Fan, J. Z.; Askerka, M.; Jain, A.; Choi, M. J.; Ouellette, O.; Todorovic, P.; Sagar, L. K.; Sargent, E. H. Machine Learning Accelerates Discovery of Optimal Colloidal Quantum Dot Synthesis. ACS Nano 2019, 13 (10), 11122,  DOI: 10.1021/acsnano.9b03864
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    32
    Machine Learning Accelerates Discovery of Optimal Colloidal Quantum Dot Synthesis
    Voznyy, Oleksandr; Levina, Larissa; Fan, James Z.; Askerka, Mikhail; Jain, Ankit; Choi, Min-Jae; Ouellette, Olivier; Todorovic, Petar; Sagar, Laxmi K.; Sargent, Edward H.
    ACS Nano (2019), 13 (10), 11122-11128CODEN: ANCAC3; ISSN:1936-0851. (American Chemical Society)
    Colloidal quantum dots (CQDs) allow broad tuning of the bandgap across the visible and near-IR spectral regions. Recent advances in applying CQDs in light sensing, photovoltaics, and light emission have heightened interest in achieving further synthetic improvements. In particular, improving monodispersity remains a key priority in order to improve solar cells' open-circuit voltage, decrease lasing thresholds, and improve photodetectors' noise-equiv. power. Here we utilize machine-learning-in-the-loop to learn from available exptl. data, propose exptl. parameters to try, and, ultimately, point to regions of synthetic parameter space that will enable record-monodispersity PbS quantum dots. The resultant studies reveal that adding a growth-slowing precursor (oleylamine) allows nucleation to prevail over growth, a strategy that enables record-large-bandgap (611 nm exciton) PbS nanoparticles with a well-defined excitonic absorption peak (half-width at half-max. (HWHM) of 145 meV). At longer wavelengths, we also achieve improved monodispersity, with an hwhm of 55 meV at 950 nm and 24 meV at 1500 nm, compared to the best published to date values of 75 and 26 meV, resp.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhvVWksrnN&md5=c80559d7cd097b78be5480435484af37
  33. 33
    Torng, W.; Altman, R. B. Graph Convolutional Neural Networks for Predicting Drug-Target Interactions. J. Chem. Inf. Model. 2019, 59 (10), 4131,  DOI: 10.1021/acs.jcim.9b00628
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    33
    Graph Convolutional Neural Networks for Predicting Drug-Target Interactions
    Torng, Wen; Altman, Russ B.
    Journal of Chemical Information and Modeling (2019), 59 (10), 4131-4149CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
    Accurate detn. of target-ligand interactions is crucial in the drug discovery process. In this paper, we propose a graph-convolutional (Graph-CNN) framework for predicting protein-ligand interactions. First, we built an unsupervised graph-autoencoder to learn fixed-size representations of protein pockets from a set of representative druggable protein binding sites. Second, we trained two Graph-CNNs to automatically ext. features from pocket graphs and 2D ligand graphs, resp., driven by binding classification labels. We demonstrate that graph-autoencoders can learn fixed-size representations for protein pockets of varying sizes and the Graph-CNN framework can effectively capture protein-ligand binding interactions without relying on target-ligand complexes. Across several metrics, Graph-CNNs achieved better or comparable performance to 3DCNN ligand-scoring, AutoDock Vina, RF-Score, and NNScore on common virtual screening benchmark data sets. Visualization of key pocket residues and ligand atoms contributing to the classification decisions confirms that our networks are able to detect important interface residues and ligand atoms within the pockets and ligands, resp.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhvFSisrzI&md5=c9a71957bcde3dba1df2f969bb70168c
  34. 34
    Lim, J.; Hwang, S.-Y.; Moon, S.; Kim, S.; Kim, W. Y. Scaffold-based molecular design with a graph generative model. Chem. Sci. 2020, 11 (4), 1153,  DOI: 10.1039/C9SC04503A
    [Crossref], [CAS], Google Scholar
    34
    Scaffold-based molecular design with a graph generative model
    Lim, Jaechang; Hwang, Sang-Yeon; Moon, Seokhyun; Kim, Seungsu; Kim, Woo Youn
    Chemical Science (2020), 11 (4), 1153-1164CODEN: CSHCCN; ISSN:2041-6520. (Royal Society of Chemistry)
    Searching for new mols. in areas like drug discovery often starts from the core structures of known mols. Such a method has called for a strategy of designing deriv. compds. retaining a particular scaffold as a substructure. On this account, our present work proposes a graph generative model that targets its use in scaffold-based mol. design. Our model accepts a mol. scaffold as input and extends it by sequentially adding atoms and bonds. The generated mols. are then guaranteed to contain the scaffold with certainty, and their properties can be controlled by conditioning the generation process on desired properties. The learned rule of extending mols. can well generalize to arbitrary kinds of scaffolds, including those unseen during learning. In the conditional generation of mols., our model can simultaneously control multiple chem. properties despite the search space constrained by fixing the substructure. As a demonstration, we applied our model to designing inhibitors of the epidermal growth factor receptor and show that our model can employ a simple semi-supervised extension to broaden its applicability to situations where only a small amt. of data is available.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXit1Ortr%252FO&md5=be36a65abcce15f18b4c1e529bffd905
  35. 35
    Jha, D.; Ward, L.; Paul, A.; Liao, W. K.; Choudhary, A.; Wolverton, C.; Agrawal, A. ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition. Sci. Rep. 2018, 8 (1), 17593,  DOI: 10.1038/s41598-018-35934-y
    [Crossref], [PubMed], [CAS], Google Scholar
    35
    ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition
    Jha Dipendra; Paul Arindam; Liao Wei-Keng; Choudhary Alok; Agrawal Ankit; Ward Logan; Wolverton Chris
    Scientific reports (2018), 8 (1), 17593 ISSN:.
    Conventional machine learning approaches for predicting material properties from elemental compositions have emphasized the importance of leveraging domain knowledge when designing model inputs. Here, we demonstrate that by using a deep learning approach, we can bypass such manual feature engineering requiring domain knowledge and achieve much better results, even with only a few thousand training samples. We present the design and implementation of a deep neural network model referred to as ElemNet; it automatically captures the physical and chemical interactions and similarities between different elements using artificial intelligence which allows it to predict the materials properties with better accuracy and speed. The speed and best-in-class accuracy of ElemNet enable us to perform a fast and robust screening for new material candidates in a huge combinatorial space; where we predict hundreds of thousands of chemical systems that could contain yet-undiscovered compounds.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A280%3ADC%252BB3cros1aqtw%253D%253D&md5=de8a35358c9fe7fc2bab30c8e1dd0637
  36. 36
    Sahu, H.; Yang, F.; Ye, X.; Ma, J.; Fang, W.; Ma, H. Designing promising molecules for organic solar cells via machine learning assisted virtual screening. J. Mater. Chem. A 2019, 7 (29), 17480,  DOI: 10.1039/C9TA04097H
    [Crossref], [CAS], Google Scholar
    36
    Designing promising molecules for organic solar cells via machine learning assisted virtual screening
    Sahu, Harikrishna; Yang, Feng; Ye, Xiaobo; Ma, Jing; Fang, Weihai; Ma, Haibo
    Journal of Materials Chemistry A: Materials for Energy and Sustainability (2019), 7 (29), 17480-17488CODEN: JMCAET; ISSN:2050-7496. (Royal Society of Chemistry)
    Navigating chem. space for org. photovoltaics (OPVs) is in high demand for further increasing the device efficiency, which can be accelerated through virtual screening of a large no. of possible candidate mols. using a computationally cheap and efficient model. However, predicting the efficiency of an OPV is quite challenging due to the complex correlations between factors influencing the energy conversion process. In this work, we performed high-throughput virtual screening of 10 170 candidate mols., constructed from 32 unique building blocks, with several newly built, computationally affordable and high-performing (Pearson's correlation coeff. = 0.7-0.8) machine learning (ML) models using relevant descriptors. Important building blocks are identified, and new design rules are introduced to construct efficient mols. The crit. mol. properties required for high efficiency are unraveled. Also, 126 candidates with theor. predicted efficiency >8% are proposed for synthesis and device fabrication. Similar ML-assisted virtual screening studies may reveal hidden guidelines to design promising mols. and could be a breakthrough in the search for lead candidates for OPVs.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXht1yksr7L&md5=433fcf452600d70af3093b0a811b5ff8
  37. 37
    Kim, B.; Lee, S.; Kim, J. Inverse design of porous materials using artificial neural networks. Sci. Adv. 2020, 6 (1), eaax9324,  DOI: 10.1126/sciadv.aax9324
    [Crossref], [PubMed], Google Scholar
    There is no corresponding record for this reference.
  38. 38
    Hansen, K.; Biegler, F.; Ramakrishnan, R.; Pronobis, W.; von Lilienfeld, O. A.; Muller, K. R.; Tkatchenko, A. Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space. J. Phys. Chem. Lett. 2015, 6 (12), 2326,  DOI: 10.1021/acs.jpclett.5b00831
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    38
    Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space
    Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan; Pronobis, Wiktor; von Lilienfeld, O. Anatole; Mueller, Klaus-Robert; Tkatchenko, Alexandre
    Journal of Physical Chemistry Letters (2015), 6 (12), 2326-2331CODEN: JPCLCD; ISSN:1948-7185. (American Chemical Society)
    Simultaneously accurate and efficient prediction of mol. properties throughout chem. compd. space is a crit. ingredient toward rational compd. design in chem. and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to est. atomization and total energies of mols. These methods range from a simple sum over atoms, to addn. of bond energies, to pairwise interat. force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equil. mol. geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calcd. using d. functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the "holy grail" of chem. accuracy of 1 kcal/mol for both equil. and out-of-equil. geometries. This remarkable accuracy is achieved by a vectorized representation of mols. (so-called Bag of Bonds model) that exhibits strong nonlocality in chem. space. In addn., the same representation allows us to predict accurate electronic properties of mols., such as their polarizability and mol. frontier orbital energies.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2MXpsFOmsrg%253D&md5=402cfd080b9ab0aae17932dffda375cf
  39. 39
    Hermann, J.; Schätzle, Z.; Noé, F. Deep-neural-network solution of the electronic Schrödinger equation. Nat. Chem. 2020, 12 (10), 891,  DOI: 10.1038/s41557-020-0544-y
    [Crossref], [PubMed], [CAS], Google Scholar
    39
    Deep-neural-network solution of the electronic Schrodinger equation
    Hermann, Jan; Schaetzle, Zeno; Noe, Frank
    Nature Chemistry (2020), 12 (10), 891-897CODEN: NCAHBB; ISSN:1755-4330. (Nature Research)
    The electronic Schrodinger equation can only be solved anal. for the hydrogen atom, and the numerically exact full configuration-interaction method is exponentially expensive in the no. of electrons. Quantum Monte Carlo methods are a possible way out: they scale well for large mols., they can be parallelized and their accuracy has, as yet, been only limited by the flexibility of the wavefunction ansatz used. Here we propose PauliNet, a deep-learning wavefunction ansatz that achieves nearly exact solns. of the electronic Schrodinger equation for mols. with up to 30 electrons. PauliNet has a multireference Hartree-Fock soln. built in as a baseline, incorporates the physics of valid wavefunctions and is trained using variational quantum Monte Carlo. PauliNet outperforms previous state-of-the-art variational ansatzes for atoms, diat. mols. and a strongly correlated linear H10, and matches the accuracy of highly specialized quantum chem. methods on the transition-state energy of cyclobutadiene, while being computationally efficient.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXhvFCht77L&md5=274495cfa9d66ff2a7055c50de26c313
  40. 40
    Nakata, M.; Shimazaki, T. PubChemQC Project: A Large-Scale First-Principles Electronic Structure Database for Data-Driven Chemistry. J. Chem. Inf. Model. 2017, 57 (6), 1300,  DOI: 10.1021/acs.jcim.7b00083
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    40
    PubChemQC Project: A Large-Scale First-Principles Electronic Structure Database for Data-Driven Chemistry
    Nakata, Maho; Shimazaki, Tomomi
    Journal of Chemical Information and Modeling (2017), 57 (6), 1300-1308CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
    Large-scale mol. databases play an essential role in the investigation of various subjects such as the development of org. materials, in-silico drug designs, and data-driven studies with machine learning, among others. We developed a large-scale quantum chem. database based on the first-principles method without performing any expt. Our database currently contains three million mol. electronic structures based on the d. functional theory method at the B3LYP/6-31G* level, and we successively calcd. 10 low-lying excited states of over two million mols. by the time-dependent DFT method with the 6-31+G* basis set. To select the mols. calcd. in our project, we mainly referred to the PubChem project, and it was used as a source of the mol. structures in short strings using the InChI and the SMILES representations. Accordingly, we named our quantum chem. database project as "PubChemQC" (http://pubchemqc.riken.jp/) and placed it in the public domain. In this paper, we showed the fundamental features of the PubChemQC database and dis- cussed the techniques used to construct the dataset for large-scale quantum chem. calcns. We also presented a machine-learning approach to predict the electronic structure of mols. as an example to demonstrate the suitability of the large-scale quantum chem. database.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2sXntFKnt7g%253D&md5=be48dc3c13a5f05cdd7700c427949ec3
  41. 41
    Gilmer, J.; Schoenholz, S. S.; Riley, P. F.; Vinyals, O.; Dahl, G. E. Neural Message Passing for Quantum Chemistry. arXiv.org 2017, 1704.01212v2
    Google Scholar
    There is no corresponding record for this reference.
  42. 42
    Ryu, S.; Lim, J.; Hong, S. H.; Kim, W. Y. Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network. arXiv.org 2018, 1805.10988
    Google Scholar
    There is no corresponding record for this reference.
  43. 43
    Wang, X.; Li, Z.; Jiang, M.; Wang, S.; Zhang, S.; Wei, Z. Molecule Property Prediction Based on Spatial Graph Embedding. J. Chem. Inf. Model. 2019, 59 (9), 3817,  DOI: 10.1021/acs.jcim.9b00410
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    43
    Molecule Property Prediction Based on Spatial Graph Embedding
    Wang, Xiaofeng; Li, Zhen; Jiang, Mingjian; Wang, Shuang; Zhang, Shugang; Wei, Zhiqiang
    Journal of Chemical Information and Modeling (2019), 59 (9), 3817-3828CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
    Accurate prediction of mol. properties is important for new compd. design, which is a crucial step in drug discovery. In this paper, mol. graph data is utilized for property prediction based on graph convolution neural networks. In addn., a convolution spatial graph embedding layer (C-SGEL) is introduced to retain the spatial connection information on mols. And, multiple C-SGELs are stacked to construct a convolution spatial graph embedding network (C-SGEN) for end-to-end representation learning. In order to enhance the robustness of the network, mol. fingerprints are also combined with C-SGEN to build a composite model for predicting mol. properties. Our comparative expts. have shown that our method is accurate and achieves the best results on some open benchmark datasets.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhs1egur7I&md5=a28bda9eeef821f2e6627e934d90844f
  44. 44
    Li, X.; Yan, X.; Gu, Q.; Zhou, H.; Wu, D.; Xu, J. DeepChemStable: Chemical Stability Prediction with an Attention-Based Graph Convolution Network. J. Chem. Inf. Model. 2019, 59 (3), 1044,  DOI: 10.1021/acs.jcim.8b00672
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    44
    DeepChemStable: Chemical Stability Prediction with an Attention-Based Graph Convolution Network
    Li, Xiuming; Yan, Xin; Gu, Qiong; Zhou, Huihao; Wu, Di; Xu, Jun
    Journal of Chemical Information and Modeling (2019), 59 (3), 1044-1049CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
    In the drug discovery process, unstable compds. in storage can lead to false pos. or false neg. bioassay conclusions. Prediction of the chem. stability of a compd. by de novo methods is complex. Chem. instability prediction is commonly based on a model derived from empirical data. The COMDECOM (Compd. Decompn.) project provides the empirical data for prediction of chem. stability. Models such as the extended-connectivity fingerprint and atom center fragments were built from the COMDECOM data and used for estn. of chem. stability, but deficits in the existing models remain. In this paper, we report DeepChemStable, a model employing an attention-based graph convolution network based on the COMDECOM data. The main advantage of this method is that DeepChemStable is an end-to-end model, which does not predefine structural fingerprint features, but instead, dynamically learns structural features and assocs. the features through the learning process of an attention-based graph convolution network. The previous ChemStable program relied on a rule-based method to reduce the false negatives. DeepChemStable, on the other hand, reduces the risk of false negatives without using a rule-based method. Because minimizing the rate of false negatives is a greater concern for instability prediction, this feature is a major improvement. This model achieves an AUC value of 84.7%, recall rate of 79.8%, and 10-fold stratified cross-validation accuracy of 79.1%.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXjtVSgsbo%253D&md5=39ca436fe4c15d480c0a404df6576143
  45. 45
    Joung, J. F.; Kim, S.; Park, S. Cationic Effect on the Equilibria and Kinetics of the Excited-State Proton Transfer Reaction of a Photoacid in Aqueous Solutions. J. Phys. Chem. B 2018, 122 (19), 5087,  DOI: 10.1021/acs.jpcb.8b00588
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    45
    Cationic Effect on the Equilibria and Kinetics of the Excited-State Proton Transfer Reaction of a Photoacid in Aqueous Solutions
    Joung, Joonyoung F.; Kim, Sangin; Park, Sungnam
    Journal of Physical Chemistry B (2018), 122 (19), 5087-5093CODEN: JPCBFK; ISSN:1520-5207. (American Chemical Society)
    Dissolved ions have a significant effect on the chem. equil. and kinetics in aq. solns. by changing the phys. properties and hydrogen bond network of water. In this work, the ionic effects on the excited-state proton transfer (ESPT) reactions of Coumarin 183 (C183) in aq. ionic solns. are comprehensively studied in terms of pKa, pK*a, activation energies, and kinetic isotope effect (KIE). The acid dissocn. consts. (pKa and pK*a) of C183 on the ground and excited states are detd. by UV-visible absorption and steady-state fluorescence spectroscopy. The activation energies (Ea) and KIE for the ESPT reaction of C183 are directly obtained by time-resolved fluorescence spectroscopy. The changes in pKa, pK*a, Ea, and KIE values of C183 are found to be dependent on the charge d. of cations. The secondary KIE is more substantially influenced by the dissolved ions than the primary KIE. Furthermore, the ionic effects on the equil. (pKa and pK*a) and kinetic (Ea and KIE) parameters of C183 are found to be well-explained by the free-energy reactivity relation. Our current results are very important in understanding the ionic effects on the equil. and ESPT kinetics of photoacids in aq. ionic solns.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXot1CitLo%253D&md5=2fa29ddba8db6137048122e0e038c615
  46. 46
    Niko, Y.; Hiroshige, Y.; Kawauchi, S.; Konishi, G.-i. Fundamental photoluminescence properties of pyrene carbonyl compounds through absolute fluorescence quantum yield measurement and density functional theory. Tetrahedron 2012, 68 (31), 6177,  DOI: 10.1016/j.tet.2012.05.072
    [Crossref], [CAS], Google Scholar
    46
    Fundamental photoluminescence properties of pyrene carbonyl compounds through absolute fluorescence quantum yield measurement and density functional theory
    Niko, Yosuke; Hiroshige, Yuki; Kawauchi, Susumu; Konishi, Gen-ichi
    Tetrahedron (2012), 68 (31), 6177-6185CODEN: TETRAB; ISSN:0040-4020. (Elsevier Ltd.)
    We reviewed the photophys. properties of carbonyl-functionalized pyrene derivs. [i.e., pyrene with aldehyde (PA: 1-formylpyrene), ketone (PK: 1-acetylpyrene), carboxylic acid (PCA: 1-pyrenecarboxylic acid), and ester groups (PE: 1-methoxycarbonylpyrene)] using a measurement of abs. fluorescence quantum yield in various solvents and time-dependent d. functional theory (TD-DFT) calcns. Here, we obtained new important data that fill in the gaps in existing datasets on these properties and help identify photoluminescence mechanisms. The results of the TD-DFT calcns. were in agreement with the exptl. results, and indicated that the low fluorescence of PA and PK is derived not only from intersystem crossing but also from internal conversion due to the proximity effect; this inference was also supported by the measurements of the photoluminescence spectra at low temps. In addn., factors leading efficiently to non-radiative processes were shown to be absent in PCA and PE. Thus, we successfully revised and systematized the photophys. properties of pyrene modified by carbonyl substitutes, including carboxamide groups, which were previously reported by us. Moreover, we showed that the photoluminescence properties of such compds. might be predictable by using TD-DFT calcns.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC38XoslSks7c%253D&md5=0920c356c851ff8ffbd5b87f96235435
  47. 47
    Ciubini, B.; Visentin, S.; Serpe, L.; Canaparo, R.; Fin, A.; Barbero, N. Design and synthesis of symmetrical pentamethine cyanine dyes as NIR photosensitizers for PDT. Dyes Pigm. 2019, 160, 806,  DOI: 10.1016/j.dyepig.2018.09.009
    [Crossref], [CAS], Google Scholar
    47
    Design and synthesis of symmetrical pentamethine cyanine dyes as NIR photosensitizers for PDT
    Ciubini, Betty; Visentin, Sonja; Serpe, Loredana; Canaparo, Roberto; Fin, Andrea; Barbero, Nadia
    Dyes and Pigments (2019), 160 (), 806-813CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
    Herein, we report the synthesis and spectroscopic characterization of novel Near Infra-Red (NIR) pentamethine cyanine dyes, as potential photosensitizers for Photodynamic Therapy (PDT) characterized by a strong absorption in the tissue transparency window (600-800 nm). The heteroarom. benzoindolenine ring of various sym. cyanine dyes has been differently functionalized and quaternarized as a result of a structure-activity study and to det. the substituent effect on the cellular uptake, ROS prodn. and photodynamic activity. These probes present low cytotoxicity in dark, but promote phototoxic effect, upon irradn., in human fibrosarcoma cell line (HT-1080) with interesting and unexpected structure to property activity.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXhslejt73M&md5=a205d2a835f3831d8ae6c878603bf4c3
  48. 48
    Khopkar, S.; Jachak, M.; Shankarling, G. Novel A(2)-D-A(1)-D-A(2) type NIR absorbing symmetrical squaraines based on 2, 3, 3, 8-tetramethyl-3H-pyrrolo [3, 2-h] quinoline: Synthesis, photophysical, electrochemical, thermal properties and photostability study. Spectrochim. Acta, Part A 2019, 211, 114,  DOI: 10.1016/j.saa.2018.11.061
    [Crossref], [PubMed], [CAS], Google Scholar
    48
    Novel A2-D-A1-D-A2 type NIR absorbing symmetrical squaraines based on 2, 3, 3, 8-tetramethyl-3H-pyrrolo [3, 2-h] quinoline: Synthesis, photophysical, electrochemical, thermal properties and photostability study
    Khopkar, Sushil; Jachak, Mahesh; Shankarling, Ganapati
    Spectrochimica Acta, Part A: Molecular and Biomolecular Spectroscopy (2019), 211 (), 114-124CODEN: SAMCAS; ISSN:1386-1425. (Elsevier B.V.)
    Two novel acceptor-donor-acceptor-donor-acceptor (A2-D-A1-D-A2) type pi-conjugated sym. squaraine dyes, denoted by PQSQ 1 and PQSQ 2 based on 2, 3, 3, 8-tetra-Me -3H-pyrrolo [3,2-h] quinoline were successfully synthesized for the first time to arrive absorption and emission at NIR region. These dyes comprise indolenines as electron donor units, squaryl ring as a central electron acceptor and pyridines as terminal electron acceptor units. The relationship between mol. structures and photophys. properties of these dyes was studied in comparison with their parent compds. (ISQ and N-Et ISQ). These novel squaraine dyes displayed an intense absorption within the range 671 to 692 nm in polar to non- polar solvents resp. with good molar extinction coeffs. ( > 105 Lmol-1 cm-1). Compared to their parent squaraines, both dyes showed red-shifted absorption (33-44 nm) as well as emission (38-59 nm) due to the electron-accepting ability of the ancillary pyridine acceptors and extended pi-conjugation. These dyes exhibited neg. solvatochromism and Reichardt's ET (30) scale was applied to propose a quant. relationship of the relative stability of ground and excited-state of these squaraines with solvent polarity. The electrochem. and computational properties of these sym. squaraines were investigated with the help of cyclic voltammetry and d. functional theory (DFT). Moreover, PQSQ 1-2 exhibited high thermal and photo-stability. These A2-D-A1-D-A2 type dyes showed improved photostabilities compared to their parent D-A-D type dyes.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXisVOiurfJ&md5=d4a4428ba229bdef743d2a8b88771e3e
  49. 49
    Cser, A.; Nagy, K.; Biczók, L. Fluorescence lifetime of Nile Red as a probe for the hydrogen bonding strength with its microenvironment. Chem. Phys. Lett. 2002, 360 (5–6), 473,  DOI: 10.1016/S0009-2614(02)00784-4
    [Crossref], [CAS], Google Scholar
    49
    Fluorescence lifetime of Nile red as a probe for the hydrogen bonding strength with its microenvironment
    Cser, Adrienn; Nagy, Krisztina; Biczok, Laszlo
    Chemical Physics Letters (2002), 360 (5,6), 473-478CODEN: CHPLBC; ISSN:0009-2614. (Elsevier Science B.V.)
    The fluorescence lifetime of Nile Red (NR) is not sensitive to dielec. solvent-solute interactions but markedly decreases with increasing hydrogen bond donating ability in alcs. because vibrations assocd. with hydrogen bonding are involved in the deactivation process. The negligible viscosity effect indicates that twisting of the diethylamino moiety of NR does not play a significant role in the dissipation of the excitation energy.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BD38XlsFOgsb4%253D&md5=d987832ac02308077476d1a9bc558bc2
  50. 50
    Niko, Y.; Kawauchi, S.; Konishi, G. Solvatochromic pyrene analogues of Prodan exhibiting extremely high fluorescence quantum yields in apolar and polar solvents. Chem. - Eur. J. 2013, 19 (30), 9760,  DOI: 10.1002/chem.201301020
    [Crossref], [PubMed], [CAS], Google Scholar
    50
    Solvatochromic Pyrene Analogues of Prodan Exhibiting Extremely High Fluorescence Quantum Yields in Apolar and Polar Solvents
    Niko, Yosuke; Kawauchi, Susumu; Konishi, Gen-ichi
    Chemistry - A European Journal (2013), 19 (30), 9760-9765CODEN: CEUJED; ISSN:0947-6539. (Wiley-VCH Verlag GmbH & Co. KGaA)
    The authors report the synthesis and photophys. properties of the pyrene derivs. PA [3,8-dibutyl-6-(piperidin-1-yl)pyrene-1-carbaldehyde] and PK [1-(3,8-dibutyl-6-(piperidin-1-yl)pyren-1- yl)butan-1-one], and demonstrate their outstanding photoluminescence properties, which include their extremely high QYs in both apolar (hexane) and polar (methanol) media as well as their strong solvatochromism.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC3sXptVCksbg%253D&md5=b4c74c9b3aaadd595a83d0f153fb4872
  51. 51
    Santin, L. R. R.; dos Santos, S. C.; Novo, D. L. R.; Bianchini, D.; Gerola, A. P.; Braga, G.; Caetano, W.; Moreira, L. M.; Bastos, E. L.; Romani, A. P. Study between solvatochromism and steady-state and time-resolved fluorescence measurements of the Methylene blue in binary mixtures. Dyes Pigm. 2015, 119, 12,  DOI: 10.1016/j.dyepig.2015.03.004
    [Crossref], [CAS], Google Scholar
    51
    Study between solvatochromism and steady-state and time-resolved fluorescence measurements of the Methylene blue in binary mixtures
    Santin, Luiza R. R.; dos Santos, Sandra C.; Novo, Diogo La Rosa; Bianchini, Daniela; Gerola, Adriana P.; Braga, Gustavo; Caetano, Wilker; Moreira, Leonardo M.; Bastos, Erick Leite; Romani, Ana Paula; de Oliveira, Hueder P. M.
    Dyes and Pigments (2015), 119 (), 12-21CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
    In this work, the study on the influence of binary mixts. of solvents (water-acetonitrile, water-ethanol and water-glycerol) upon the spectroscopic properties of methylene blue (MB) was done. In addn., the photophys. characterization of the MB in different concns. in the solvent mixts. was done. In the mixts., the increase in the quantity of water has decreased the fluorescence quantum yield together with other photophys. alterations. The studies of time-resolved fluorescence have demonstrated a first-order decay, with lifetimes between 328 and 550 ps. These values increase as the org. solvent proportion is increased. The results have shown a direct relationship between the viscosity and the rotational lifetime, correlating with the interference in the processes of deactivation of the excited state, which are slower in media with higher viscosity. The conformation of the clusters in the binary mixts. was also identified as a key factor to det. the results obtained in this work.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2MXks1yks7g%253D&md5=e7a4ae4d3235eb8079fd92f1b7846e92
  52. 52
    Wünsch, U. J.; Murphy, K. R.; Stedmon, C. A. Fluorescence Quantum Yields of Natural Organic Matter and Organic Compounds: Implications for the Fluorescence-based Interpretation of Organic Matter Composition. Front. Mar. Sci. 2015,  DOI: 10.3389/fmars.2015.00098
    [Crossref], Google Scholar
    There is no corresponding record for this reference.
  53. 53
    Frisch, M. J.; Trucks, G. W.; Schlegel, H. B.; Scuseria, G. E.; Robb, M. A.; Cheeseman, J. R.; Scalmani, G.; Barone, V.; Petersson, G. A.; Nakatsuji, H.; Li, X.; Caricato, M.; Marenich, A. V.; Bloino, J.; Janesko, B. G.; Gomperts, R.; Mennucci, B.; Hratchian, H. P.; Ortiz, J. V.; Izmaylov, A. F.; Sonnenberg, J. L.; Williams-Young, D.; Ding, F.; Lipparini, F.; Egidi, F.; Goings, J.; Peng, B.; Petrone, A.; Henderson, T.; Ranasinghe, D.; Zakrzewski, V. G.; Gao, J.; Rega, N.; Zheng, G.; Liang, W.; Hada, M.; Ehara, M.; Toyota, K.; Fukuda, R.; Hasegawa, J.; Ishida, M.; Nakajima, T.; Honda, Y.; Kitao, O.; Nakai, H.; Vreven, T.; Throssell, K.; Montgomery, J. A., Jr.; Peralta, J. E.; Ogliaro, F.; Bearpark, M. J.; Heyd, J. J.; Brothers, E. N.; Kudin, K. N.; Staroverov, V. N.; Keith, T. A.; Kobayashi, R.; Normand, J.; Raghavachari, K.; Rendell, A. P.; Burant, J. C.; Iyengar, S. S.; Tomasi, J.; Cossi, M.; Millam, J. M.; Klene, M.; Adamo, C.; Cammi, R.; Ochterski, J. W.; Martin, R. L.; Morokuma, K.; Farkas, O.; Foresman, J. B.; Fox, D. J. Gaussian 16; Gaussian, Inc.: Wallingford, CT, 2016.
    Google Scholar
    There is no corresponding record for this reference.
  54. 54
    Sun, H.; Dong, X.; Liu, S.; Zhao, Q.; Mou, X.; Yang, H. Y.; Huang, W. Excellent BODIPY Dye Containing Dimesitylboryl Groups as PeT-Based Fluorescent Probes for Fluoride. J. Phys. Chem. C 2011, 115 (40), 19947,  DOI: 10.1021/jp206396v
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    54
    Excellent BODIPY Dye Containing Dimesitylboryl Groups as PeT-Based Fluorescent Probes for Fluoride
    Sun, Hui-Bin; Dong, Xiao-Chen; Liu, Shu-Juan; Zhao, Qiang; Mou, Xin; Yang, Hui-Ying; Huang, Wei
    Journal of Physical Chemistry C (2011), 115 (40), 19947-19954CODEN: JPCCCK; ISSN:1932-7447. (American Chemical Society)
    A highly selective fluorescent probe BBDPB for F- was realized on the basis of the boron-dipyrromethene (BODIPY) dye contg. two dimesitylboryl (Mes2B) moieties. The fluorophore displays highly efficient orange-red fluorescence with an emission peak of 602 nm and quantum efficiency (Φ) of 0.65 in dichloromethane soln. Signaling changes were obsd. through UV/vis absorption and photoluminescence spectra. Obvious spectral changes in absorption and fluorescent emission bands were detected after adding F- in company with an obvious soln. color change from pink to deep blue. The effects of F- on the electronic structure of BBDPB were studied in detail by performing theor. calcns. using the Gaussian 03 package. According to the theor. calcn. and contrast expts., the binding of Mes2B moieties with F- would give rise to nonradiative photoinduced-electron-transfer (PeT) deactivation from Mes2B moieties to BODIPY core and then quench the fluorescence. To implement this approach, an excellent solid-film sensing device was designed by doping BBDPB in polymethylmethacrylate (PMMA).
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC3MXht1SltLzL&md5=63e18d490d1ada0a328b36fe31b15764
  55. 55
    Li, Z.; Lv, X.; Chen, Y.; Fu, W.-F. Synthesis, structures and photophysical properties of boron–fluorine derivatives based on pyridine/1,8-naphthyridine. Dyes Pigm. 2014, 105, 157,  DOI: 10.1016/j.dyepig.2014.01.022
    [Crossref], [CAS], Google Scholar
    55
    Synthesis, structures and photophysical properties of boron-fluorine derivatives based on pyridine/1,8-naphthyridine
    Li, Zhensheng; Lv, Xiaojun; Chen, Yong; Fu, Wen-Fu
    Dyes and Pigments (2014), 105 (), 157-162CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
    Three boron-fluorine complexes B1-B3 contg. pyridine/1,8-naphthyridine were synthesized and structurally characterized. Compds. B1 and B2 exhibited strong fluorescence in soln. and solid state. The solvent-dependent luminous properties and large Stokes shift in soln. could be explained by intramol. charge transfer, which is confirmed by time-dependent d. functional theory calcn. The abs. quantum yield of B1 in powder form reached 0.48 because of inhibiting planar π···π stacking. Single-crystal x-ray diffraction analyses of B1 and B2 revealed that weak intermol. C-H···F and H···π interactions hinder further stacking of π···π dimers, consequently preventing aggregation-induced quenching. Complex B3, composed of boron-dipyrromethene and 1,8-naphthyridine fluorophore, had potential applications as a pH ratiometric fluorescent sensor.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2cXltFKqs7w%253D&md5=47e3e7ca47274444b744777d5d6accc4
  56. 56
    Zhang, S.; Liu, X.; Yuan, W.; Zheng, W.; Li, H.; Li, C.; Sun, Y.; Wang, Y.; Yang, Y.; Li, Y. New aryl substituted pyridylimidazo[1,2-a]pyridine-BODIPY conjugates: Emission color tuning from green to NIR. Dyes Pigm. 2018, 159, 406,  DOI: 10.1016/j.dyepig.2018.04.070
    [Crossref], [CAS], Google Scholar
    56
    New aryl substituted pyridylimidazo[1,2-a]pyridine-BODIPY conjugates: Emission color tuning from green to NIR
    Zhang, Shasha; Liu, Xiaojuan; Yuan, Wei; Zheng, Wei; Li, Hongkun; Li, Chenghui; Sun, Yufang; Wang, Yong; Yang, Yonggang; Li, Yahong; Liu, Wei
    Dyes and Pigments (2018), 159 (), 406-418CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
    Based on pyridylimidazo[1,2-a]pyridine-BODIPY compd. 1, we have prepd. three halogenated derivs. 2-4, and eight mono-/dual-arylated pyridylimidazo[1,2-a]pyridine-BODIPY conjugates 5-12. Single crystal X-ray diffraction analyses of 2, 4 and 6 revealed C-H···F interactions between mols. in the solid-state. Large effects of different electron-donating substituents (phenyl-, 4-(methoxy)phenyl-, 4-(diphenylamino)phenyl-, and 4-(dimethylamino)phenyl-) on absorption and fluorescence were detected, and the emission colors were successfully tuned from green to NIR. Upon addn. of H+, special colorimetric and spectroscopic variations for 4-dimethylaminophenyl- analogs 9 and 10 have been obsd. DFT and TDDFT calcns. for all new compds. have been carried out for deep understanding of their electronic transitions at ground states. The living cell imaging results of compd. 7 suggest its promising utility in biol. area.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXht1yisbnP&md5=6e7d46791bb60cbe22f24f210b677884
  57. 57
    Filatov, M. A.; Karuthedath, S.; Polestshuk, P. M.; Callaghan, S.; Flanagan, K. J.; Telitchko, M.; Wiesner, T.; Laquai, F.; Senge, M. O. Control of triplet state generation in heavy atom-free BODIPY-anthracene dyads by media polarity and structural factors. Phys. Chem. Chem. Phys. 2018, 20 (12), 8016,  DOI: 10.1039/C7CP08472B
    [Crossref], [PubMed], [CAS], Google Scholar
    57
    Control of triplet state generation in heavy atom-free BODIPY-anthracene dyads by media polarity and structural factors
    Filatov, Mikhail A.; Karuthedath, Safakath; Polestshuk, Pavel M.; Callaghan, Susan; Flanagan, Keith J.; Telitchko, Maxime; Wiesner, Thomas; Laquai, Frederic; Senge, Mathias O.
    Physical Chemistry Chemical Physics (2018), 20 (12), 8016-8031CODEN: PPCPFQ; ISSN:1463-9076. (Royal Society of Chemistry)
    A family of heavy atom-free BODIPY-anthracene dyads (BADs) exhibiting triplet excited state formation from charge-transfer states is reported. Four types of BODIPY scaffolds, different in the alkyl substitution pattern, and 4 anthracene derivs. were used to access BADs. Fluorescence and intersystem crossing (ISC) in these dyads depend on donor-acceptor couplings and can be accurately controlled by substitution or media polarity. Under conditions that do not allow charge transfer (CT), the dyads exhibit fluorescence with high quantum yields. Formation of charge-transfer states triggers ISC and the formation of long-lived triplet excited states in the dyads. The excited state properties were studied by steady-state techniques and ultrafast pump-probe spectroscopy to det. the parameters of the obsd. processes. Structural information for various BADs was derived from single crystal x-ray structure detns. alongside DFT mol. geometry optimization, revealing the effects of mutual orientation of subunits on the photophys. properties. The calcns. showed that alkyl substituents on the BODIPY destabilize CT states in the dyads, thus controlling the charge transfer between the subunits. The effect of the dyad structure on the ISC efficiency was considered at the M06-2X level of theory, and a correlation between mutual orientation of the subunits and the energy gap between singlet and triplet CT states was studied using a multiref. CASSCF method.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXisFOjuro%253D&md5=22c9b5c6affb1e7719aebbdc8f17480e
  58. 58
    Zhang, X. F.; Zhang, G. Q.; Zhu, J. Methylated Unsymmetric BODIPY Compounds: Synthesis, High Fluorescence Quantum Yield and Long Fluorescence Time. J. Fluoresc. 2019, 29 (2), 407,  DOI: 10.1007/s10895-019-02349-5
    [Crossref], [PubMed], [CAS], Google Scholar
    58
    Methylated Unsymmetric BODIPY Compounds: Synthesis, High Fluorescence Quantum Yield and Long Fluorescence Time
    Zhang, Xian-Fu; Zhang, George Q.; Zhu, Jiale
    Journal of Fluorescence (2019), 29 (2), 407-416CODEN: JOFLEN; ISSN:1053-0509. (Springer)
    We show that unsym. BODIPY compds. with one, two, and three Me groups can be synthesized easily and efficiently by the unsym. reaction method. Their steady state and time-resolved fluorescence properties are examd. in solvents of different polarity. These compds. show high fluorescence quantum yields (0.87 to 1.0), long fluorescence lifetimes (5.89 to 7.40 ns), and small Stokes shift (199 to 443 cm-1). The Me substitution exhibits influence on the UV-Vis absorption and fluorescence properties, such as the blue shift in emission and absorption spectra. It is the no. rather than the position of methyls that play major roles. Except for 3 M-BDP, the increase in the no. of methyls on BODIPY core leads to the increase in both fluorescence quantum yield and radiative rate const., but causes the decrease in fluorescence lifetime. H-bonding solvents increase both the fluorescence lifetime and quantum yields. The methylated BODIPYs show the ability to generate singlet oxygen (1Δg) which is evidenced by near-IR luminescence and DPBF chem. trapping techniques. The formation quantum yield of singlet oxygen (1Δg) for the compds. is up to 0.15 ± 0.05.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXns1Cls7s%253D&md5=96ac1d4f31df608c4c49edb99604bfe8
  59. 59
    Kasha, M. Characterization of electronic transitions in complex molecules. Discuss. Faraday Soc. 1950, 9, 14,  DOI: 10.1039/df9500900014
    [Crossref], Google Scholar
    There is no corresponding record for this reference.
  60. 60
    Cotter, L. F.; Brown, P. J.; Nelson, R. C.; Takematsu, K. Divergent Hammett Plots of the Ground- and Excited-State Proton Transfer Reactions of 7-Substituted-2-Naphthol Compounds. J. Phys. Chem. B 2019, 123 (19), 4301,  DOI: 10.1021/acs.jpcb.9b01295
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    60
    Divergent Hammett Plots of the Ground- and Excited-State Proton Transfer Reactions of 7-Substituted-2-Naphthol Compounds
    Cotter, Laura F.; Brown, Paige J.; Nelson, Ryan C.; Takematsu, Kana
    Journal of Physical Chemistry B (2019), 123 (19), 4301-4310CODEN: JPCBFK; ISSN:1520-5207. (American Chemical Society)
    The rational design of photoacids requires accessible predictive models of the electronic effect of functional groups on chem. templates of interest. Here, the effect of substituents on the photoacidity and excited-state proton transfer (PT) pathways of prototype 2-naphthol (2OH) at the sym. C7 position was investigated through photochem. and computational studies of 7-amino-2-naphthol (7N2OH) and 7-methoxy-2-naphthol (7OMe2OH). Time-resolved emission expts. of 7N2OH revealed that the presence of an electron-withdrawing vs. electron-donating group (EWG vs EDG, NH3+ vs NH2) led to a drastic decline in photoacidity: pKa* = 1.1 ± 0.2 vs 9.6 ± 0.2. Time-dependent d. functional theory calcns. with explicit water mols. confirmed that the excited neutral state (x = NH2) is greatly stabilized by water, with equation-of-motion coupled cluster singles and doubles calcns. supporting potential mixing between the La and Lb states. Similar suppression of photoacidity, however, was not obsd. for 7OMe2OH with EDG OCH3, pKa* = 2.7 ± 0.1. Hammett plots of the ground- and excited-state PT reactions of substituted 7-x-2OH compds. (x = CN, NH3+, H, CH3, OCH3, OH, and NH2) vs Hammett parameters σp showed breaks in the linearity between the EDG and EWG regions: ρ ∼ 0 vs 1.14 and ρ* ∼ 0 vs 3.86. The divergent acidic behavior most likely arises from different mixing mechanisms of the lowest Lb state with the La and possible Bb states upon substitution of naphthalene in water.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXot1Oqu70%253D&md5=a14ce3564a7406a1f4d507790b77c84c
  61. 61
    Reichardt, C. Solvatochromic Dyes as Solvent Polarity Indicators. Chem. Rev. 1994, 94 (8), 2319,  DOI: 10.1021/cr00032a005
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    61
    Solvatochromic Dyes as Solvent Polarity Indicators
    Reichardt, Christian
    Chemical Reviews (Washington, DC, United States) (1994), 94 (8), 2319-58CODEN: CHREAY; ISSN:0009-2665.
    This review with 345 refs. compiles pos. and neg. solvatochromic compds. which have been used to establish empirical scales of solvent polarity by means of UV/visible/near-IR spectroscopic measurements in soln. with particular emphasis on the ET(30) scale derived from neg. solvatochromic pyridinium N-phenolate betaine dyes. A discussion is presented on the concept of solvent polarity and how empirical parameters of solvent polarity can be derived and understood in the framework of linear free-energy relationships.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaK2cXntV2gtrY%253D&md5=8fd8a3f562211929e30191207fe97e33
  62. 62
    Nakanotani, H.; Higuchi, T.; Furukawa, T.; Masui, K.; Morimoto, K.; Numata, M.; Tanaka, H.; Sagara, Y.; Yasuda, T.; Adachi, C. High-efficiency organic light-emitting diodes with fluorescent emitters. Nat. Commun. 2014, 5, 4016,  DOI: 10.1038/ncomms5016
    [Crossref], [PubMed], [CAS], Google Scholar
    62
    High-efficiency organic light-emitting diodes with fluorescent emitters
    Nakanotani, Hajime; Higuchi, Takahiro; Furukawa, Taro; Masui, Kensuke; Morimoto, Kei; Numata, Masaki; Tanaka, Hiroyuki; Sagara, Yuta; Yasuda, Takuma; Adachi, Chihaya
    Nature Communications (2014), 5 (), 4016CODEN: NCAOBW; ISSN:2041-1723. (Nature Publishing Group)
    Fluorescence-based org. light-emitting diodes have continued to attract interest because of their long operational lifetimes, high color purity of electroluminescence and potential to be manufd. at low cost in next-generation full-color display and lighting applications. In fluorescent mols., however, the exciton prodn. efficiency is limited to 25% due to the deactivation of triplet excitons. Here we report fluorescence-based org. light-emitting diodes that realize external quantum efficiencies as high as 13.4-18% for blue, green, yellow and red emission, indicating that the exciton prodn. efficiency reached nearly 100%. The high performance is enabled by utilization of thermally activated delayed fluorescence mols. as assistant dopants that permit efficient transfer of all elec. generated singlet and triplet excitons from the assistant dopants to the fluorescent emitters. Org. light-emitting diodes employing this exciton harvesting process provide freedom for the selection of emitters from a wide variety of conventional fluorescent mols.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2cXhvF2murjK&md5=d88fbd541737c290739d25c324529ba6
  63. 63
    Hong, Y.; Lam, J. W.; Tang, B. Z. Aggregation-induced emission. Chem. Soc. Rev. 2011, 40 (11), 5361,  DOI: 10.1039/c1cs15113d
    [Crossref], [PubMed], [CAS], Google Scholar
    63
    Aggregation-induced emission
    Hong, Yuning; Lam, Jacky W. Y.; Tang, Ben Zhong
    Chemical Society Reviews (2011), 40 (11), 5361-5388CODEN: CSRVBR; ISSN:0306-0012. (Royal Society of Chemistry)
    A review. Luminogenic materials with aggregation-induced emission (AIE) attributes have attracted much interest since the debut of the AIE concept in 2001. In this crit. review, recent progress in the area of AIE research is summarized. Typical examples of AIE systems are discussed, from which their structure-property relationships are derived. Through mechanistic decipherment of the photophys. processes, structural design strategies for generating new AIE luminogens are developed. Technol., esp. optoelectronic and biol., applications of the AIE systems are exemplified to illustrate how the novel AIE effect can be utilized for high-tech innovations (183 refs.).
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC3MXhtlaiu7bE&md5=c2c6daf422ea27baec6dce8288e547ed
  64. 64
    Jones, G.; Jackson, W. R.; Choi, C. Y.; Bergmark, W. R. Solvent effects on emission yield and lifetime for coumarin laser dyes. Requirements for a rotatory decay mechanism. J. Phys. Chem. 1985, 89 (2), 294,  DOI: 10.1021/j100248a024
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    64
    Solvent effects on emission yield and lifetime for coumarin laser dyes. Requirements for a rotatory decay mechanism
    Jones, Guilford, II; Jackson, William R.; Choi, Chol Yoo; Bergmark, William R.
    Journal of Physical Chemistry (1985), 89 (2), 294-300CODEN: JPCHAX; ISSN:0022-3654.
    Photophys. parameters were detd. for coumarin laser dyes in a variety or org. solvents and in water and mixed media. The response of fluorescence emission yields and lifetimes to changes in solvent polarity was a sensitive function of coumarin substitution pattern. Most important were substituent influences which resulted in larger excited-state dipole moments (for the fluorescent state), in restrictions of rotatory motion for the amine group at the 7-position, and the delocalization of excitation energy away from the coumarin moiety. For dyes displaying sharp redns. in emission yield and lifetime with increased solvent polarity, protic media and particularly water were most effective in inhibiting fluorescence although D isotope effects (H2O/D2O) on photophys. parameters were minimal. The temp. dependence of emission yield and lifetime was measured for 2 solvent-sensitive dyes in MeCN and in a highly viscous solvent, glycerol. The quenching of coumarin fluorescence by O for dyes with lifetimes >2 ns was also obsd. The dominant photophys. features for coumarin dyes are discussed in terms of emission from an intramol. charge-transfer (ICT) excited state and an important nonradiative decay path involving rotation of the amine functionality (7-position) leading to a twisted intramol. CT state (TICT). This previously proposed nonradiative decay path is a subtle function of coumarin structure, solvent polarity and viscosity, and temp. and is most sensitive to substituent patterns whose localize excitation at the 7-amino group and which stabilize charge in the twisted zwitterionic (TICT) intermediate. The role of excited-state bond orders involving the rotating group in detg. the importance of interconversions of the type ICT → TICT is discussed.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaL2MXltlaqsw%253D%253D&md5=e6cba44606a2942d0ab52ed4a15f777a
  65. 65
    Kim, H. J.; Kim, S. K.; Godumala, M.; Yoon, J.; Kim, C. Y.; Jeong, J. E.; Woo, H. Y.; Kwon, J. H.; Cho, M. J.; Choi, D. H. Novel molecular triad exhibiting aggregation-induced emission and thermally activated fluorescence for efficient non-doped organic light-emitting diodes. Chem. Commun. 2019, 55 (64), 9475,  DOI: 10.1039/C9CC05391C
    [Crossref], [PubMed], [CAS], Google Scholar
    65
    Novel molecular triad exhibiting aggregation-induced emission and thermally activated fluorescence for efficient non-doped organic light-emitting diodes
    Kim, Hyung Jong; Kim, Seong Keun; Godumala, Mallesham; Yoon, Jiwon; Kim, Chae Yeong; Jeong, Ji-Eun; Woo, Han Young; Kwon, Jang Hyuk; Cho, Min Ju; Choi, Dong Hoon
    Chemical Communications (Cambridge, United Kingdom) (2019), 55 (64), 9475-9478CODEN: CHCOFS; ISSN:1359-7345. (Royal Society of Chemistry)
    A light-emitting mol. triad (BPCP-2CPC) with dual functionality was successfully synthesized and applied to soln.-processed non-doped org. light-emitting diodes. The BPCP-2CPC triad contains 9-phenyl-9H-carbazole units as a host moiety tethered to a green-emitting core (BPCP) through a cyclohexane unit and exhibits thermally activated delayed fluorescence (TADF) and aggregation-induced emission (AIE) characteristics simultaneously. The BPCP-2CPC-based non-doped TADF-OLED devices showed a high external quantum efficiency (EQE) of 13.4%.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtl2nsrvO&md5=3d984ee37faab64eb021cb9730e8fc13
  66. 66
    Feckova, M.; le Poul, P.; Guen, F. R.; Roisnel, T.; Pytela, O.; Klikar, M.; Bures, F.; Achelle, S. 2,4-Distyryl- and 2,4,6-Tristyrylpyrimidines: Synthesis and Photophysical Properties. J. Org. Chem. 2018, 83 (19), 11712,  DOI: 10.1021/acs.joc.8b01653
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    66
    2,4-Distyryl- and 2,4,6-Tristyrylpyrimidines: Synthesis and Photophysical Properties
    Feckova, Michaela; le Poul, Pascal; Guen, Francoise Robin-le; Roisnel, Thierry; Pytela, Oldrich; Klikar, Milan; Bures, Filip; Achelle, Sylvain
    Journal of Organic Chemistry (2018), 83 (19), 11712-11726CODEN: JOCEAH; ISSN:0022-3263. (American Chemical Society)
    The synthesis of a series of 20 new 2,4,6-tristyrylpyrimidines and three new 2,4-distyrylpyrimidines by means of combination of Knoevenagel condensation and Suzuki-Miyaura cross-coupling reaction is reported. This methodol. enables us to obtain chromophores with identical or different substituent on each arm. The photophys. properties of the compds. are described. Optical properties and time-dependent d. functional theory calcns. indicate that photophys. properties of target compds. are mainly affected by the nature of the electron-donating group in C4/C6 positions, except when the C2 substituent is a significantly stronger electron-donating group. However, the C2 substituent has a strong influence on emission quantum yield: addn. of a strong electron-donating group tends to decrease the fluorescence quantum yield, whereas a moderate electron-withdrawing group results in a significant increase of fluorescence quantum yield.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXhs1Chtr7J&md5=7ac142b9ae6e358f08ed53acf7a108bc
  67. 67
    Wen, W.; Shi, Z.-F.; Cao, X.-P.; Xu, N.-S. Triphenylethylene-based fluorophores: Facile preparation and full-color emission in both solution and solid states. Dyes Pigm. 2016, 132, 282,  DOI: 10.1016/j.dyepig.2016.04.014
    [Crossref], [CAS], Google Scholar
    67
    Triphenylethylene-based fluorophores: Facile preparation and full-color emission in both solution and solid states
    Wen, Wei; Shi, Zi-Fa; Cao, Xiao-Ping; Xu, Nian-Sheng
    Dyes and Pigments (2016), 132 (), 282-290CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
    Triphenylethylene-based luminophoric mols. were efficiently synthesized. The substituent effect of the fluorophores on their photophys. properties was then studied. Consequently, longer conjugated system and larger mol. dipole of the donor-π-acceptor fluorophores could result in bathochromic shifts of UV-visible absorption and emission bands, so do the Stokes shifts. Esp., full-color fluorescent emissions in both soln. and solid states could be achieved by changing conjugation length and substituents with different electron-donating or accepting abilities in the triphenylethylene skeleton. The d. functional theory calcns. further demonstrated that with the increase of the electron-donating or accepting abilities of the substituents, the energy gaps of the fluorophores gradually decreased, which elucidated the substituent effect of the org. fluorophores on their photophys. properties.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC28XpslWls74%253D&md5=32842b1c74871b42addd8fbd0b54977e
  68. 68
    Hirai, H.; Nakajima, K.; Nakatsuka, S.; Shiren, K.; Ni, J.; Nomura, S.; Ikuta, T.; Hatakeyama, T. One-Step Borylation of 1,3-Diaryloxybenzenes Towards Efficient Materials for Organic Light-Emitting Diodes. Angew. Chem., Int. Ed. 2015, 54 (46), 13581,  DOI: 10.1002/anie.201506335
    [Crossref], [CAS], Google Scholar
    68
    One-Step Borylation of 1,3-Diaryloxybenzenes Towards Efficient Materials for Organic Light-Emitting Diodes
    Hirai, Hiroki; Nakajima, Kiichi; Nakatsuka, Soichiro; Shiren, Kazushi; Ni, Jingping; Nomura, Shintaro; Ikuta, Toshiaki; Hatakeyama, Takuji
    Angewandte Chemie, International Edition (2015), 54 (46), 13581-13585CODEN: ACIEF5; ISSN:1433-7851. (Wiley-VCH Verlag GmbH & Co. KGaA)
    The development of a 1-step borylation of 1,3-diaryloxybenzenes, yielding novel B-contg. polycyclic arom. compds., is reported. The resulting B-contg. compds. possess high singlet-triplet excitation energies of localized frontier MOs induced by B and O. Using these compds. as a host material, phosphorescent org. LEDs exhibiting high efficiency and adequate lifetimes were prepd. Using the present 1-step borylation, the synthesis of an efficient, thermally-activated delayed fluorescence emitter and B-fused benzo[6]helicene was accomplished. Crystallog. data are given.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2MXhsFWrtrbI&md5=ab150773f2fa5e6d4273d8018e8d52fc
  69. 69
    Kondo, Y.; Yoshiura, K.; Kitera, S.; Nishi, H.; Oda, S.; Gotoh, H.; Sasada, Y.; Yanai, M.; Hatakeyama, T. Narrowband deep-blue organic light-emitting diode featuring an organoboron-based emitter. Nat. Photonics 2019, 13 (10), 678,  DOI: 10.1038/s41566-019-0476-5
    [Crossref], [CAS], Google Scholar
    69
    Narrowband deep-blue organic light-emitting diode featuring an organoboron-based emitter
    Kondo, Yasuhiro; Yoshiura, Kazuki; Kitera, Sayuri; Nishi, Hiroki; Oda, Susumu; Gotoh, Hajime; Sasada, Yasuyuki; Yanai, Motoki; Hatakeyama, Takuji
    Nature Photonics (2019), 13 (10), 678-682CODEN: NPAHBY; ISSN:1749-4885. (Nature Research)
    Luminescent materials that exhibit narrowband emission are vital for full-color displays. Here, we report a thermally activated delayed-fluorescence material that exhibits ultrapure blue emission with full-width at half-max. of just 14 nm. The emitter consists of five benzene rings connected by two boron and four nitrogen atoms and two diphenylamino substituents. The multiple resonance effect of the boron and nitrogen atoms induces significant localization of the highest occupied and lowest unoccupied MOs on different atoms to minimize not only the vibronic coupling between the ground state (S0) and the singlet excited state (S1) but also the energy gap between the S1 state and triplet excited state (T1). Org. light-emitting diode devices employing the emitter emit light at 469 nm with full-width at half-max. of 18 nm with an external quantum efficiency of 34.4% at the max. and 26.0% at 1,000 cd m-2.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtlOlsLjK&md5=7ccab1765bbb7ae0e3c9e7430ba2b5a8
  70. 70
    Madayanad Suresh, S.; Hall, D.; Beljonne, D.; Olivier, Y.; Zysman-Colman, E. Multiresonant Thermally Activated Delayed Fluorescence Emitters Based on Heteroatom-Doped Nanographenes: Recent Advances and Prospects for Organic Light-Emitting Diodes. Adv. Funct. Mater. 2020, 30 (33), 1908677,  DOI: 10.1002/adfm.201908677
    [Crossref], [CAS], Google Scholar
    70
    Multiresonant Thermally Activated Delayed Fluorescence Emitters Based on Heteroatom-Doped Nanographenes: Recent Advances and Prospects for Organic Light-Emitting Diodes
    Madayanad Suresh, Subeesh; Hall, David; Beljonne, David; Olivier, Yoann; Zysman-Colman, Eli
    Advanced Functional Materials (2020), 30 (33), 1908677CODEN: AFMDC6; ISSN:1616-301X. (Wiley-VCH Verlag GmbH & Co. KGaA)
    A review. Since the 1st report in 2015, multiresonant thermally activated delayed fluorescent (MR-TADF) compds., a subclass of TADF emitters based on a heteroatom-doped nanographene material, have come to the fore as attractive hosts as well as emitters for org. light-emitting diodes (OLEDs). MR-TADF compds. typically show very narrow-band emission, high luminescence quantum yields, and small ΔEST values, typically around 200 meV, coupled with high chem. and thermal stabilities. These materials properties have translated into some of the best reported deep-blue TADF OLEDs. Here, a detailed review of MR-TADF compds. and their derivs. reported so far is presented. This review comprehensively documents all MR-TADF compds., with a focus on the synthesis, optoelectronic behavior, and OLED performance. Computational approaches are surveyed to accurately model the excited state properties of these compds.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXhtVahtbjL&md5=ece5abf3f27c37c1ce143450c633a767
  71. 71
    Sanchez-Lengeling, B.; Aspuru-Guzik, A. Inverse molecular design using machine learning: Generative models for matter engineering. Science 2018, 361 (6400), 360,  DOI: 10.1126/science.aat2663
    [Crossref], [PubMed], [CAS], Google Scholar
    71
    Inverse molecular design using machine learning: Generative models for matter engineering
    Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alan
    Science (Washington, DC, United States) (2018), 361 (6400), 360-365CODEN: SCIEAS; ISSN:0036-8075. (American Association for the Advancement of Science)
    The discovery of new materials can bring enormous societal and technol. progress. In this context, exploring completely the large space of potential materials is computationally intractable. Here, we review methods for achieving inverse design, which aims to discover tailored materials from the starting point of a particular desired functionality. Recent advances from the rapidly growing field of artificial intelligence, mostly from the subfield of machine learning, have resulted in a fertile exchange of ideas, where approaches to inverse mol. design are being proposed and employed at a rapid pace. Among these, deep generative models have been applied to numerous classes of materials: rational design of prospective drugs, synthetic routes to org. compds., and optimization of photovoltaics and redox flow batteries, as well as a variety of other solid-state materials.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXhtlyitr3L&md5=779c4a42ba1e84d99d13ad1b32b9529a
  72. 72
    Popova, M.; Isayev, O.; Tropsha, A. Deep reinforcement learning for de novo drug design. Sci. Adv. 2018, 4 (7), eaap7885,  DOI: 10.1126/sciadv.aap7885
    [Crossref], [PubMed], Google Scholar
    There is no corresponding record for this reference.
  73. 73
    Lim, J.; Ryu, S.; Kim, J. W.; Kim, W. Y. Molecular generative model based on conditional variational autoencoder for de novo molecular design. J. Cheminf. 2018, 10 (1), 31,  DOI: 10.1186/s13321-018-0286-7
    [Crossref], [CAS], Google Scholar
    73
    Molecular generative model based on conditional variational autoencoder for de novo molecular design
    Lim, Jaechang; Ryu, Seongok; Kim, Jin Woo; Kim, Woo Youn
    Journal of Cheminformatics (2018), 10 (), 31/1-31/9CODEN: JCOHB3; ISSN:1758-2946. (Chemistry Central Ltd.)
    We propose a mol. generative model based on the conditional variational autoencoder for de novo mol. design. It is specialized to control multiple mol. properties simultaneously by imposing them on a latent space. As a proof of concept, we demonstrate that it can be used to generate drug-like mols. with five target properties. We were also able to adjust a single property without changing the others and to manipulate it beyond the range of the dataset.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXmtFWhtrw%253D&md5=8a1262077f9d6ffa5ec0385ed1a69f6f
  74. 74
    Elton, D. C.; Boukouvalas, Z.; Fuge, M. D.; Chung, P. W. Deep learning for molecular design—a review of the state of the art. Mol. Syst. Des. Eng. 2019, 4 (4), 828,  DOI: 10.1039/C9ME00039A
    [Crossref], [CAS], Google Scholar
    74
    Deep learning for molecular design-a review of the state of the art
    Elton, Daniel C.; Boukouvalas, Zois; Fuge, Mark D.; Chung, Peter W.
    Molecular Systems Design & Engineering (2019), 4 (4), 828-849CODEN: MSDEBG; ISSN:2058-9689. (Royal Society of Chemistry)
    In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of mols.-in our review we found 45 papers on the subject published in the past two years. These works point to a future where such systems will be used to generate lead mols., greatly reducing resources spent downstream synthesizing and characterizing bad leads in the lab. In this review we survey the increasingly complex landscape of models and representation schemes that have been proposed. The four classes of techniques we describe are recursive neural networks, autoencoders, generative adversarial networks, and reinforcement learning. After first discussing some of the math. fundamentals of each technique, we draw high level connections and comparisons with other techniques and expose the pros and cons of each. Several important high level themes emerge as a result of this work, including the shift away from the SMILES string representation of mols. towards more sophisticated representations such as graph grammars and 3D representations, the importance of reward function design, the need for better stds. for benchmarking and testing, and the benefits of adversarial training and reinforcement learning over max. likelihood based training.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtVWktLjN&md5=a0925fdace3a12af31b2f6fc1edef89b
  75. 75
    Hong, S. H.; Ryu, S.; Lim, J.; Kim, W. Y. Molecular Generative Model Based on an Adversarially Regularized Autoencoder. J. Chem. Inf. Model. 2020, 60 (1), 29,  DOI: 10.1021/acs.jcim.9b00694
    [ACS Full Text ACS Full Text], [CAS], Google Scholar
    75
    Molecular Generative Model Based on an Adversarially Regularized Autoencoder
    Hong, Seung Hwan; Ryu, Seongok; Lim, Jaechang; Kim, Woo Youn
    Journal of Chemical Information and Modeling (2020), 60 (1), 29-36CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
    Deep generative models are attracting great attention as a new promising approach for mol. design. A variety of models reported so far are based on either a variational autoencoder (VAE) or a generative adversarial network (GAN), but they have limitations such as low validity and uniqueness. Here, we propose a new type of model based on an adversarially regularized autoencoder (ARAE). It basically uses latent variables like VAE, but the distribution of the latent variables is estd. by adversarial training like in GAN. The latter is intended to avoid both the insufficiently flexible approxn. of posterior distribution in VAE and the difficulty in handling discrete variables in GAN. Our benchmark study showed that ARAE indeed outperformed conventional models in terms of validity, uniqueness, and novelty per generated mol. We also demonstrated a successful conditional generation of drug-like mols. with ARAE for the control of both cases of single and multiple properties. As a potential real-world application, we could generate epidermal growth factor receptor inhibitors sharing the scaffolds of known active mols. while satisfying drug-like conditions simultaneously.
    >> More from SciFinder ®
    https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXitleru7rF&md5=5bbeae953836253deb3e004e7b779976
  76. 76
    Krenn, M.; Häse, F.; Nigam, A.; Friederich, P.; Aspuru-Guzik, A. Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation. Mach. Learn.: Sci. Technol. 2020, 1 (4), 045024,  DOI: 10.1088/2632-2153/aba947
    [Crossref], Google Scholar
    There is no corresponding record for this reference.
  77. 77
    Joung, J. F.; Han, M.; Park, S. Deep4Chem, 2020; http://deep4chem.korea.ac.kr/.
    Google Scholar
    There is no corresponding record for this reference.

Cited By

This article is cited by 43 publications.

  1. Manon H. E. Bousquet, Thomas V. Papineau, Koen Veys, Daniel Escudero, Denis Jacquemin. Extensive Analysis of the Parameters Influencing Radiative Rates Obtained through Vibronic Calculations. Journal of Chemical Theory and Computation 2023, 19 (16) , 5525-5547. https://doi.org/10.1021/acs.jctc.3c00191
  2. Marcel Ruth, Dennis Gerbig, Peter R. Schreiner. Machine Learning for Bridging the Gap between Density Functional Theory and Coupled Cluster Energies. Journal of Chemical Theory and Computation 2023, 19 (15) , 4912-4920. https://doi.org/10.1021/acs.jctc.3c00274
  3. Sheng-Hsuan Hung, Zong-Rong Ye, Chi-Feng Cheng, Berlin Chen, Ming-Kang Tsai. Enhanced Predictions for the Experimental Photophysical Data Using the Featurized Schnet-Bondstep Approach. Journal of Chemical Theory and Computation 2023, 19 (14) , 4559-4567. https://doi.org/10.1021/acs.jctc.3c00054
  4. Elizaveta F. Petrusevich, Manon H. E. Bousquet, Borys Ośmiałowski, Denis Jacquemin, Josep M. Luis, Robert Zaleśny. Cost-Effective Simulations of Vibrationally-Resolved Absorption Spectra of Fluorophores with Machine-Learning-Based Inhomogeneous Broadening. Journal of Chemical Theory and Computation 2023, 19 (8) , 2304-2315. https://doi.org/10.1021/acs.jctc.2c01285
  5. Andrew D. McNaughton, Rajendra P. Joshi, Carter R. Knutson, Anubhav Fnu, Kevin J. Luebke, Jeremiah P. Malerich, Peter B. Madrid, Neeraj Kumar. Machine Learning Models for Predicting Molecular UV–Vis Spectra with Quantum Mechanical Properties. Journal of Chemical Information and Modeling 2023, 63 (5) , 1462-1471. https://doi.org/10.1021/acs.jcim.2c01662
  6. Jiali Guo, Ming Sun, Xueyan Zhao, Chaojie Shi, Haoming Su, Yanzhi Guo, Xuemei Pu. General Graph Neural Network-Based Model To Accurately Predict Cocrystal Density and Insight from Data Quality and Feature Representation. Journal of Chemical Information and Modeling 2023, 63 (4) , 1143-1156. https://doi.org/10.1021/acs.jcim.2c01538
  7. Zong-Rong Ye, Sheng-Hsuan Hung, Berlin Chen, Ming-Kang Tsai. Assessment of Predicting Frontier Orbital Energies for Small Organic Molecules Using Knowledge-Based and Structural Information. ACS Engineering Au 2022, 2 (4) , 360-368. https://doi.org/10.1021/acsengineeringau.2c00011
  8. Joonyoung F. Joung, Minhi Han, Minseok Jeong, Sungnam Park. Beyond Woodward–Fieser Rules: Design Principles of Property-Oriented Chromophores Based on Explainable Deep Learning Optical Spectroscopy. Journal of Chemical Information and Modeling 2022, 62 (12) , 2933-2942. https://doi.org/10.1021/acs.jcim.2c00173
  9. Simon Axelrod, Daniel Schwalbe-Koda, Somesh Mohapatra, James Damewood, Kevin P. Greenman, Rafael Gómez-Bombarelli. Learning Matter: Materials Design with Machine Learning and Atomistic Simulations. Accounts of Materials Research 2022, 3 (3) , 343-357. https://doi.org/10.1021/accountsmr.1c00238
  10. Yihuan Zhao, Kuan Chen, Lei Zhu, Qiang Huang. Data-driven machine learning models for quick prediction of the Stokes shift of organic fluorescent materials. Dyes and Pigments 2023, 220 , 111670. https://doi.org/10.1016/j.dyepig.2023.111670
  11. Darinel Valencia-Marquez, Antonio Flores-Tlacuahuac, Alan Aguirre-Soto. Computer aided molecular design coupled to deep learning techniques as a less-expensive approach to design organic photoredox catalysts. Computers & Chemical Engineering 2023, 178 , 108392. https://doi.org/10.1016/j.compchemeng.2023.108392
  12. Zheng Cheng, Jiapeng Liu, Tong Jiang, Mohan Chen, Fuzhi Dai, Zhifeng Gao, Guolin Ke, Zifeng Zhao, Qi Ou. Automatic Screen‐out of Ir(III) Complex Emitters by Combined Machine Learning and Computational Analysis. Advanced Optical Materials 2023, 11 (18) https://doi.org/10.1002/adom.202301093
  13. Rami Shafei, Ai Hamano, Christophe Gourlaouen, Dimitrios Maganas, Keiko Takano, Chantal Daniel, Frank Neese. Theoretical spectroscopy for unraveling the intensity mechanism of the optical and photoluminescent spectra of chiral Re(I) transition metal complexes. The Journal of Chemical Physics 2023, 159 (8) https://doi.org/10.1063/5.0153742
  14. Szabolcs Góger, Leonardo Medrano Sandonas, Carolin Müller, Alexandre Tkatchenko. Data-driven tailoring of molecular dipole polarizability and frontier orbital energies in chemical compound space. Physical Chemistry Chemical Physics 2023, 25 (33) , 22211-22222. https://doi.org/10.1039/D3CP02256K
  15. Gabriel Glotz, Sabrina Püschmann, Michael Haas, Georg Gescheidt. Direct detection of photo-induced reactions by IR: from Brook rearrangement to photo-catalysis. Photochemical & Photobiological Sciences 2023, 22 (7) , 1683-1693. https://doi.org/10.1007/s43630-023-00406-4
  16. Ke R. Yang, Gregory W. Kyro, Victor S. Batista. The landscape of computational approaches for artificial photosynthesis. Nature Computational Science 2023, 3 (6) , 504-513. https://doi.org/10.1038/s43588-023-00450-1
  17. Jiale He, Jingwen Chen, Jieqiong Wang, Linke Ge, Feifei Cui, Xi Chen. 环境水体中化学品光化学持久性的预测模型. Chinese Science Bulletin 2023, https://doi.org/10.1360/TB-2023-0362
  18. Mahnaz Jabbarzadeh Sani. Theoretical survey on the electronic, linear and nonlinear optical properties of substituted benzenes and polycondensed π-systems. A density functional theory study. Computational and Theoretical Chemistry 2023, 1223 , 114100. https://doi.org/10.1016/j.comptc.2023.114100
  19. Jae‐Min Kim, Kyung Hyung Lee, Jun Yeob Lee. Extracting Polaron Recombination from Electroluminescence in Organic Light‐Emitting Diodes by Artificial Intelligence. Advanced Materials 2023, 35 (14) https://doi.org/10.1002/adma.202209953
  20. Jiaojiao Qin, Hao Wang, Yu Xu, Fangfang Shi, Shijie Yang, Hui Huang, Jun Liu, Callum Stewart, Linxian Li, Fei Li, Jinsong Han, Wenwen Wu. A simple array integrating machine learning for identification of flavonoids in red wines. RSC Advances 2023, 13 (13) , 8882-8889. https://doi.org/10.1039/D2RA08049D
  21. Andrés I. Bertoni, Cristián G. Sánchez. Data-driven approach for benchmarking DFTB-approximate excited state methods. Physical Chemistry Chemical Physics 2023, 25 (5) , 3789-3798. https://doi.org/10.1039/D2CP04979A
  22. Gyoung S. Na. Numerical Representations of Chemical Data for Structure‐Based Machine Learning. 2023, 173-200. https://doi.org/10.1002/9781119819783.ch7
  23. Felix Y. Telegin, Viktoria S. Karpova, Anna O. Makshanova, Roman G. Astrakhantsev, Yuriy S. Marfin. Solvatochromic Sensitivity of BODIPY Probes: A New Tool for Selecting Fluorophores and Polarity Mapping. International Journal of Molecular Sciences 2023, 24 (2) , 1217. https://doi.org/10.3390/ijms24021217
  24. Minori Furukori, Yasushi Nagamune, Yasuo Nakayama, Takuya Hosokai. High-throughput transient photoluminescence spectrometer for deep learning of thermally activated delayed fluorescence materials. Journal of Materials Chemistry C 2023, 492 https://doi.org/10.1039/D3TC00482A
  25. Praveen Kumar Bommineni, Manohar Kakunuri, Sarat Babu Anne. Prediction of product distribution using machine learning techniques. 2023, 673-678. https://doi.org/10.1016/B978-0-443-15274-0.50107-4
  26. Gyoung S. Na. Conditional Graph Regression for Complex Chemical Systems with Heterogeneous Substructures. 2022, 1651-1660. https://doi.org/10.1109/BigData55660.2022.10020289
  27. Minseok Jeong, Joonyoung F. Joung, Jinhyo Hwang, Minhi Han, Chang Woo Koh, Dong Hoon Choi, Sungnam Park. Deep learning for development of organic optoelectronic devices: efficient prescreening of hosts and emitters in deep-blue fluorescent OLEDs. npj Computational Materials 2022, 8 (1) https://doi.org/10.1038/s41524-022-00834-3
  28. Chang Woo Myung, Amir Hajibabaei, Ji‐Hyun Cha, Miran Ha, Junu Kim, Kwang S. Kim. Challenges, Opportunities, and Prospects in Metal Halide Perovskites from Theoretical and Machine Learning Perspectives. Advanced Energy Materials 2022, 12 (45) , 2202279. https://doi.org/10.1002/aenm.202202279
  29. Patryk Rybczyński, Manon H. E. Bousquet, Anna Kaczmarek-Kędziera, Beata Jędrzejewska, Denis Jacquemin, Borys Ośmiałowski. Controlling the fluorescence quantum yields of benzothiazole-difluoroborates by optimal substitution. Chemical Science 2022, 13 (45) , 13347-13360. https://doi.org/10.1039/D2SC05044G
  30. Anna Pakuła, Wojciech Żołnowski, Sławomir Paśko, Olimpia Kursa, Paweł Marć, Leszek R. Jaroszewicz. Multispectral Portable Fibre-Optic Reflectometer for the Classification of the Origin of Chicken Eggshells in the Case of Mycoplasma synoviae Infections. Sensors 2022, 22 (22) , 8690. https://doi.org/10.3390/s22228690
  31. Jae-Min Kim, Junseop Lim, Jun Yeob Lee. Understanding the charge dynamics in organic light-emitting diodes using convolutional neural network. Materials Horizons 2022, 9 (10) , 2551-2563. https://doi.org/10.1039/D2MH00373B
  32. Alexander A. Ksenofontov, Michail M. Lukanov, Pavel S. Bocharov. Can machine learning methods accurately predict the molar absorption coefficient of different classes of dyes?. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 2022, 279 , 121442. https://doi.org/10.1016/j.saa.2022.121442
  33. Jiaqi Mai, Tian Lu, Pengcheng Xu, Zhengheng Lian, Minjie Li, Wencong Lu. Predicting the maximum absorption wavelength of azo dyes using an interpretable machine learning strategy. Dyes and Pigments 2022, 206 , 110647. https://doi.org/10.1016/j.dyepig.2022.110647
  34. Mohsen Tamtaji, Mohammad Kazemeini. Enhanced singlet oxygen production under nanoconfinement using silica nanocomposites towards improving the photooxygenation’s conversion. Journal of Nanoparticle Research 2022, 24 (9) https://doi.org/10.1007/s11051-022-05553-w
  35. Jun Yan, Xabier Rodríguez-Martínez, Drew Pearce, Hana Douglas, Danai Bili, Mohammed Azzouzi, Flurin Eisner, Alise Virbule, Elham Rezasoltani, Valentina Belova, Bernhard Dörling, Sheridan Few, Anna A. Szumska, Xueyan Hou, Guichuan Zhang, Hin-Lap Yip, Mariano Campoy-Quiles, Jenny Nelson. Identifying structure–absorption relationships and predicting absorption strength of non-fullerene acceptors for organic photovoltaics. Energy & Environmental Science 2022, 15 (7) , 2958-2973. https://doi.org/10.1039/D2EE00887D
  36. Austin Biaggne, Lawrence Spear, German Barcenas, Maia Ketteridge, Young C. Kim, Joseph S. Melinger, William B. Knowlton, Bernard Yurke, Lan Li. Data-Driven and Multiscale Modeling of DNA-Templated Dye Aggregates. Molecules 2022, 27 (11) , 3456. https://doi.org/10.3390/molecules27113456
  37. Scott N. Genin, Ilya G. Ryabinkin, Nathan R. Paisley, Sarah O. Whelan, Michael G. Helander, Zachary M. Hudson. Estimating Phosphorescent Emission Energies in Ir III Complexes Using Large‐Scale Quantum Computing Simulations**. Angewandte Chemie International Edition 2022, 61 (19) https://doi.org/10.1002/anie.202116175
  38. Scott N. Genin, Ilya G. Ryabinkin, Nathan R. Paisley, Sarah O. Whelan, Michael G. Helander, Zachary M. Hudson. Estimating Phosphorescent Emission Energies in Ir III Complexes Using Large‐Scale Quantum Computing Simulations**. Angewandte Chemie 2022, 134 (19) https://doi.org/10.1002/ange.202116175
  39. Beomchang Kang, Chaok Seok, Juyong Lee. A benchmark study of machine learning methods for molecular electronic transition: Tree‐based ensemble learning versus graph neural network. Bulletin of the Korean Chemical Society 2022, 43 (3) , 328-335. https://doi.org/10.1002/bkcs.12468
  40. Aleksey I. Rusanov, Olga A. Dmitrieva, Nugzar Zh. Mamardashvili, Igor V. Tetko. More Is Not Always Better: Local Models Provide Accurate Predictions of Spectral Properties of Porphyrins. International Journal of Molecular Sciences 2022, 23 (3) , 1201. https://doi.org/10.3390/ijms23031201
  41. Alexander A. Ksenofontov, Michail M. Lukanov, Pavel S. Bocharov, Michail B. Berezin, Igor V. Tetko. Deep neural network model for highly accurate prediction of BODIPYs absorption. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 2022, 267 , 120577. https://doi.org/10.1016/j.saa.2021.120577
  42. Zhisen Meng, Xiaosi Zhu, Péter Kovács, Enwei Liang, Zhao Wang. Machine-learning Interpretation of the Correlation between Infrared Emission Features of Interstellar Polycyclic Aromatic Hydrocarbons. The Astrophysical Journal 2021, 922 (2) , 101. https://doi.org/10.3847/1538-4357/ac2c78
  43. Rafael Mamede, Florbela Pereira, João Aires-de-Sousa. Machine learning prediction of UV–Vis spectra features of organic compounds related to photoreactive potential. Scientific Reports 2021, 11 (1) https://doi.org/10.1038/s41598-021-03070-9
Download PDF

  • Abstract

    High Resolution Image
    Download MS PowerPoint Slide

    Figure 1

    Figure 1. Database of the optical properties of organic compounds. Histograms of (a) first absorption peak position (λabs), (b) bandwidth in full width at half-maximum (σabs), (c) extinction coefficient in logarithm (log ε), (d) emission peak position (λemi), (e) bandwidth in full width at half-maximum (σemi), (f) photoluminescence quantum yield (Φ), (g) lifetime (τ), (h) molecular weights of chromophores, and (i) solvents (CH2Cl2 dichloromethane, CH3CN acetonitrile, Tol toluene, CHCl3 chloroform, THF tetrahydrofuran, MeOH methanol, EtOH ethanol, DMSO dimethyl sulfoxide, CH cyclohexane, and DMF N,N-dimethylformamide). The number of data points (N) and the number of chromophores (mol.) are included in each graph. (11,12)

    High Resolution Image
    Download MS PowerPoint Slide

    Figure 2

    Figure 2. Our deep learning (DL) model. The interaction vector is used to account for the chromophore–solvent interaction for predicting the optical and photophysical properties of the chromophore.

    High Resolution Image
    Download MS PowerPoint Slide

    Figure 3

    Figure 3. Solvent effects on optical properties predicted by our DL model. (a) Experimental vs predicted λabs values of Reichardt’s dye (Betaine 30) in 334 solvents. The λabs of Reichardt’s dye exhibits a hypsochromic (blue) shift from 1000 to 450 nm with increasing solvent polarity. (b) Experimental vs predicted λemi values of dopants in host matrices (films). (c) Experimental vs predicted Φ values of molecules exhibiting aggregation induced emission in solutions or in solid states.

    High Resolution Image
    Download MS PowerPoint Slide

    Figure 4

    Figure 4. DL optical spectroscopy. Experimentally measured and DL predicted absorption (black) and emission (red) spectra. (a) Coumarin 153 in ethanol. (b) BPCP-2CPC (molecule) in C-2PC (host). The bandwidths in fwhm for the calculated spectra are set to 5370 cm–1 (the default value in GaussView 6). (c) Photograph of (E,E,E)-2-(4-diphenylaminostyryl)-4,6-bis(4-methoxystyryl)pyrimidine in several solvents. The colors below the photograph are those predicted using our DL model [Reproduced with permission from ref (66). Copyright 2018 American Chemical Society]. (d) Photographs of solid state emission. The colors below the photograph are those predicted using our DL model [Reprinted with permission from ref (67). Copyright 2016 Published by Elsevier Ltd.].

    High Resolution Image
    Download MS PowerPoint Slide

    Figure 5

    Figure 5. Development of a target chromophore by virtual screening. (a) Overview for development of a new chromophore by DL optical spectroscopy. (b) Molecular structures of 3 molecules based on a DOBNA core with carbazole (1), phenoxazine (2), and diphenylamine moieties (3), and the optical properties predicted by DL optical spectroscopy. (c) Absorption and emission spectra of compound 1 in toluene. σabs cannot be experimentally measured because the S1 transition is overlapped with higher electronic transitions. (d) Time-resolved fluorescence signal of compound 1 in toluene.

    High Resolution Image
    Download MS PowerPoint Slide

  • References

    ARTICLE SECTIONS
    Jump To

    This article references 77 other publications.

    1. 1
      Burlingame, Q.; Huang, X.; Liu, X.; Jeong, C.; Coburn, C.; Forrest, S. R. Intrinsically stable organic solar cells under high-intensity illumination. Nature 2019, 573 (7774), 394,  DOI: 10.1038/s41586-019-1544-1
      [Crossref], [PubMed], [CAS], Google Scholar
      1
      Intrinsically stable organic solar cells under high-intensity illumination
      Burlingame, Quinn; Huang, Xiaheng; Liu, Xiao; Jeong, Changyeong; Coburn, Caleb; Forrest, Stephen R.
      Nature (London, United Kingdom) (2019), 573 (7774), 394-397CODEN: NATUAS; ISSN:0028-0836. (Nature Research)
      Org. photovoltaic cells are now approaching com. viable efficiencies, particularly for applications that make use of their unique potential for flexibility and semitransparency. However, their reliability remains a major concern, as even the most stable devices reported so far degrade within only a few years. This has led to the belief that short operational lifetimes are an intrinsic disadvantage of devices that are fabricated using weakly bonded org. materials-an idea that persists despite the rapid growth and acceptance of org. light-emitting devices, which can achieve lifetimes of several million hours. Here we study an extremely stable class of thermally evapd. single-junction org. photovoltaic cells. We accelerated the ageing process by exposing the packaged cells to white-light illumination intensities of up to 37 Suns. The cells maintained more than 87 per cent of their starting efficiency after exposure for more than 68 days. The degrdn. rate increases superlinearly with intensity, leading to an extrapolated intrinsic lifetime, T80, of more than 4.9 × 107 hours, where T80 is the time taken for the power conversion efficiency to decrease to 80 per cent of its initial value. This is equiv. to 27,000 years outdoors. Addnl., we subjected a second group of org. photovoltaic cells to 20 Suns of UV illumination (centered at 365 nm) for 848 h, a dose that would take 1.7 × 104 hours (9.3 years) to accumulate outdoors. No efficiency loss was obsd. over the duration of the test. Overall, we find that org. solar cells packaged in an inert atm. can be extremely stable, which is promising for their future use as a practical energy-generation technol.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhsleltLvF&md5=be093394bc93fbd85271e6bc8731d138
    2. 2
      Uoyama, H.; Goushi, K.; Shizu, K.; Nomura, H.; Adachi, C. Highly efficient organic light-emitting diodes from delayed fluorescence. Nature 2012, 492 (7428), 234,  DOI: 10.1038/nature11687
      [Crossref], [PubMed], [CAS], Google Scholar
      2
      Highly efficient organic light-emitting diodes from delayed fluorescence
      Uoyama, Hiroki; Goushi, Kenichi; Shizu, Katsuyuki; Nomura, Hiroko; Adachi, Chihaya
      Nature (London, United Kingdom) (2012), 492 (7428), 234-238CODEN: NATUAS; ISSN:0028-0836. (Nature Publishing Group)
      The inherent flexibility afforded by mol. design has accelerated the development of a wide variety of org. semiconductors over the past 2 decades. In particular, great advances were made in the development of materials for org. light-emitting diodes (OLEDs), from early devices based on fluorescent mols. to those using phosphorescent mols. In OLEDs, elec. injected charge carriers recombine to form singlet and triplet excitons in a 1:3 ratio; the use of phosphorescent metal-org. complexes exploits the normally nonradiative triplet excitons and so enhances the overall electroluminescence efficiency. Here the authors report a class of metal-free org. electroluminescent mols. in which the energy gap between the singlet and triplet excited states is minimized by design, thereby promoting highly efficient spin up-conversion from nonradiative triplet states to radiative singlet states while maintaining high radiative decay rates, of >106 decays per s. These mols. harness both singlet and triplet excitons for light emission through fluorescence decay channels, leading to an intrinsic fluorescence efficiency >90% and a very high external electroluminescence efficiency, of >19%, which is comparable to that achieved in high-efficiency phosphorescence-based OLEDs.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC38XhvVamurjL&md5=73e6f816abcb9166d7d4e7676a51f5cf
    3. 3
      Li, B.; Zhao, M.; Feng, L.; Dou, C.; Ding, S.; Zhou, G.; Lu, L.; Zhang, H.; Chen, F.; Li, X. Organic NIR-II molecule with long blood half-life for in vivo dynamic vascular imaging. Nat. Commun. 2020, 11 (1), 3102,  DOI: 10.1038/s41467-020-16924-z
      [Crossref], [PubMed], [CAS], Google Scholar
      3
      Organic NIR-II molecule with long blood half-life for in vivo dynamic vascular imaging
      Li, Benhao; Zhao, Mengyao; Feng, Lishuai; Dou, Chaoran; Ding, Suwan; Zhou, Gang; Lu, Lingfei; Zhang, Hongxin; Chen, Feiya; Li, Xiaomin; Li, Guangfeng; Zhao, Shichang; Jiang, Chunyu; Wang, Yan; Zhao, Dongyuan; Cheng, Yingsheng; Zhang, Fan
      Nature Communications (2020), 11 (1), 3102CODEN: NCAOBW; ISSN:2041-1723. (Nature Research)
      Abstr.: Real-time monitoring of vessel dysfunction is of great significance in preclin. research. Optical bioimaging in the second near-IR (NIR-II) window provides advantages including high resoln. and fast feedback. However, the reported mol. dyes are hampered by limited blood circulation time (~ 5-60 min) and short absorption and emission wavelength, which impede the accurate long-term monitoring. Here, we report a NIR-II mol. (LZ-1105) with absorption and emission beyond 1000 nm. Thanks to the long blood circulation time (half-life of 3.2 h), the fluorophore is used for continuous real-time monitoring of dynamic vascular processes, including ischemic reperfusion in hindlimbs, thrombolysis in carotid artery and opening and recovery of the blood brain barrier (BBB). LZ-1105 provides an approach for researchers to assess vessel dysfunction due to the long excitation and emission wavelength and long-term blood circulation properties.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXht1Wmur%252FN&md5=44ddd07f9cd32078d5a0f2fbc8edbef8
    4. 4
      Zhang, Y.; Yang, H.; Ma, H.; Bian, G.; Zang, Q.; Sun, J.; Zhang, C.; An, Z.; Wong, W. Y. Excitation Wavelength Dependent Fluorescence of an ESIPT Triazole Derivative for Amine Sensing and Anti-Counterfeiting Applications. Angew. Chem. 2019, 131 (26), 8865,  DOI: 10.1002/ange.201902890
      [Crossref], Google Scholar
      There is no corresponding record for this reference.
    5. 5
      Woodward, R. B. Structure and the Absorption Spectra of α,β-Unsaturated Ketones. J. Am. Chem. Soc. 1941, 63 (4), 1123,  DOI: 10.1021/ja01849a066
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      5
      Structure and the absorption spectra of α,β-unsaturated ketones
      Woodward, Robert Burns
      Journal of the American Chemical Society (1941), 63 (), 1123-6CODEN: JACSAT; ISSN:0002-7863.
      Tables are given of λmax. for unsatd. ketones contg. an α- or β-substituent, those with α,β- or β,β-disubstituents and those with α,β,β-trisubstituents (6 of the 1st class, 36 of the 2nd and 8 of the 3rd). Compds. of the 1st class are characterized by strong absorption in the region 225 ± 5 mμ, those of the 2nd in the region 239 ± 5 mμ and those of the 3rd in the region 254 ± 5 mμ. The substitution for H of an alkyl group causes a shift toward the red of approx. 15 mμ and the detn. of λmax. reveals unequivocally the extent of the substitution of the C-C double bond in an α,β-unsatd. ketone. The substitution, at least in the α-position, of a Br atom or an AcO group has much the same effect as the substitution of an alkyl group. The 3 classes do not overlap and the av. deviation from the mean position is much less than 5 mμ. The use of the detn. of the position of the wave length of max. absorption for the intense band in the absorption spectra as a method for establishing structure is illustrated with α-cyperone. A few compds. do not conform with the generalizations outlined above and these are being studied.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaH3MXit1Omsg%253D%253D&md5=7341a2edc8cd986f1d3d69f29ac50aee
    6. 6
      Roothaan, C. C. J. New Developments in Molecular Orbital Theory. Rev. Mod. Phys. 1951, 23 (2), 69,  DOI: 10.1103/RevModPhys.23.69
      [Crossref], [CAS], Google Scholar
      6
      New developments in molecular orbital theory
      Roothaan, C. C. J.
      Reviews of Modern Physics (1951), 23 (), 69-89CODEN: RMPHAT; ISSN:0034-6861.
      The mathematics of the "mol. orbital" method are reviewed.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaG38XksVakuw%253D%253D&md5=200a0ce85fea3870e3322cdafd1cd1bc
    7. 7
      McWeeny, R.; Diercksen, G. Self-Consistent Perturbation Theory. II. Extension to Open Shells. J. Chem. Phys. 1968, 49 (11), 4852,  DOI: 10.1063/1.1669970
      [Crossref], [CAS], Google Scholar
      7
      Self-consistent perturbation theory. II. Extension to open shells
      McWeeny, Roy; Diercksen, G.
      Journal of Chemical Physics (1968), 49 (11), 4852-6CODEN: JCPSA6; ISSN:0021-9606.
      The self-consistent perturbation theory developed in earlier papers is extended to the open-shell case. Density matrixes for both shells are calcd. iteratively until first-order self-consistency is achieved. A numerical application indicates the importance of considering both shells sep. when discussing the effects of polarization on the charge d. and the spin d.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaF1MXktVOgsw%253D%253D&md5=1a373d6d76169d17f9a544f5ff72d8bb
    8. 8
      Hohenberg, P.; Kohn, W. Inhomogeneous Electron Gas. Phys. Rev. 1964, 136 (3B), B864,  DOI: 10.1103/PhysRev.136.B864
      [Crossref], Google Scholar
      There is no corresponding record for this reference.
    9. 9
      Bauernschmitt, R.; Ahlrichs, R. Treatment of electronic excitations within the adiabatic approximation of time dependent density functional theory. Chem. Phys. Lett. 1996, 256 (4–5), 454,  DOI: 10.1016/0009-2614(96)00440-X
      [Crossref], [CAS], Google Scholar
      9
      Treatment of electronic excitations within the adiabatic approximation of time dependent density functional theory
      Bauernschmitt, Ruedger; Ahlrichs, Reinhart
      Chemical Physics Letters (1996), 256 (4,5), 454-464CODEN: CHPLBC; ISSN:0009-2614. (Elsevier)
      Time dependent d. functional methods are applied in the adiabatic approxn. to compute low-lying electronic excitations of N2, ethylene, formaldehyde, pyridine and porphin. Out of various local, gradient-cor. and hybrid (including exact exchange) functionals, the best results are obtained for the three-parameter Lee-Yang-Parr (B3LYP) functional proposed by Becke. B3LYP yields excitation energies about 0.4 eV too low but typically gives the correct ordering of states and constitutes a considerable improvement over HF-based approaches requiring comparable numerical work.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaK28XksFWltrs%253D&md5=484b6c8f0fa99d77d9aa02693ee6103a
    10. 10
      Adamo, C.; Jacquemin, D. The calculations of excited-state properties with Time-Dependent Density Functional Theory. Chem. Soc. Rev. 2013, 42 (3), 845,  DOI: 10.1039/C2CS35394F
      [Crossref], [PubMed], [CAS], Google Scholar
      10
      The calculations of excited-state properties with Time-Dependent Density Functional Theory
      Adamo, Carlo; Jacquemin, Denis
      Chemical Society Reviews (2013), 42 (3), 845-856CODEN: CSRVBR; ISSN:0306-0012. (Royal Society of Chemistry)
      In this tutorial review, we show how Time-Dependent D. Functional Theory (TD-DFT) has become a popular tool for computing the signatures of electronically excited states, and more specifically, the properties directly related to the optical (absorption and emission) spectra of mols. We discuss the properties that can be obtained with widely available programs as well as how to account for the environmental effects (solvent and surfaces) and present recent applications in these fields. We next expose the transformation of the TD-DFT results into chem. intuitive parameters (colors as well as charge-transfer distances). Eventually, the non-specialised reader will find a series of advices and warnings necessary to perform her/his first TD-DFT calcns.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC3sXosV2jtA%253D%253D&md5=f34f78385b45bc2f429e1975c10241fc
    11. 11
      Joung, J. F.; Han, M.; Jeong, M.; Park, S. Figshare 2020,  DOI: 10.6084/m9.figshare.12045567.v2
      [Crossref], Google Scholar
      There is no corresponding record for this reference.
    12. 12
      Joung, J. F.; Han, M.; Jeong, M.; Park, S. Experimental database of optical properties of organic compounds. Sci. Data 2020, 7 (1), 295,  DOI: 10.1038/s41597-020-00634-8
      [Crossref], [PubMed], [CAS], Google Scholar
      12
      Experimental database of optical properties of organic compounds
      Joung, Joonyoung F.; Han, Minhi; Jeong, Minseok; Park, Sungnam
      Scientific Data (2020), 7 (1), 295CODEN: SDCABS; ISSN:2052-4463. (Nature Research)
      Exptl. databases on the optical properties of org. chromophores are important for the implementation of data-driven chem. using machine learning. Herein, we present a series of exptl. data including various optical properties such as the first absorption and emission max. wavelengths and their bandwidths (full width at half max.), extinction coeff., photoluminescence quantum yield, and fluorescence lifetime. A database of 20,236 data points was developed by collecting the optical properties of org. compds. already reported in the literature. A dataset of 7,016 unique org. chromophores in 365 solvents or in solid state is available in CSV format.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXhvVWjsLjM&md5=a83b26ef798f04e3934b98b7ba6b0416
    13. 13
      Butler, K. T.; Davies, D. W.; Cartwright, H.; Isayev, O.; Walsh, A. Machine learning for molecular and materials science. Nature 2018, 559 (7715), 547,  DOI: 10.1038/s41586-018-0337-2
      [Crossref], [PubMed], [CAS], Google Scholar
      13
      Machine learning for molecular and materials science
      Butler, Keith T.; Davies, Daniel W.; Cartwright, Hugh; Isayev, Olexandr; Walsh, Aron
      Nature (London, United Kingdom) (2018), 559 (7715), 547-555CODEN: NATUAS; ISSN:0028-0836. (Nature Research)
      Here we summarize recent progress in machine learning for the chem. sciences. We outline machine-learning techniques that are suitable for addressing research questions in this domain, as well as future directions for the field. We envisage a future in which the design, synthesis, characterization and application of mols. and materials is accelerated by artificial intelligence.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXhtl2jt7vL&md5=13d36f27db8d59f558fe28e946b4b009
    14. 14
      Mater, A. C.; Coote, M. L. Deep Learning in Chemistry. J. Chem. Inf. Model. 2019, 59 (6), 2545,  DOI: 10.1021/acs.jcim.9b00266
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      14
      Deep Learning in Chemistry
      Mater, Adam C.; Coote, Michelle L.
      Journal of Chemical Information and Modeling (2019), 59 (6), 2545-2559CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
      A review. Machine learning enables computers to address problems by learning from data. Deep learning is a type of machine learning that uses a hierarchical recombination of features to ext. pertinent information and then learn the patterns represented in the data. Over the last eight years, its abilities have increasingly been applied to a wide variety of chem. challenges, from improving computational chem. to drug and materials design and even synthesis planning. This review aims to explain the concepts of deep learning to chemists from any background and follows this with an overview of the diverse applications demonstrated in the literature. We hope that this will empower the broader chem. community to engage with this burgeoning field and foster the growing movement of deep learning accelerated chem.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtFGhtrvK&md5=67bcc93a2f733c51afd9fe3ed23cea39
    15. 15
      Montavon, G.; Rupp, M.; Gobre, V.; Vazquez-Mayagoitia, A.; Hansen, K.; Tkatchenko, A.; Müller, K.-R.; Anatole von Lilienfeld, O. Machine learning of molecular electronic properties in chemical compound space. New J. Phys. 2013, 15 (9), 095003,  DOI: 10.1088/1367-2630/15/9/095003
      [Crossref], [CAS], Google Scholar
      15
      Machine learning of molecular electronic properties in chemical compound space
      Montavon, Gregoire; Rupp, Matthias; Gobre, Vivekanand; Vazquez-Mayagoitia, Alvaro; Hansen, Katja; Tkatchenko, Alexandre; Mueller, Klaus-Robert; von Lilienfeld, O. Anatole
      New Journal of Physics (2013), 15 (Sept.), 095003CODEN: NJOPFM; ISSN:1367-2630. (IOP Publishing Ltd.)
      The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amt. of data amenable to intelligent data anal. for the identification of meaningful, novel and predictive structure-property relationships. Such relationships enable high-throughput screening for relevant properties in an exponentially growing pool of virtual compds. that are synthetically accessible. Here, we present a machine learning model, trained on a database of ab initio calcn. results for thousands of org. mols., that simultaneously predicts multiple electronic ground- and excited-state properties. The properties include atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity and excitation energies. The machine learning model is based on a deep multi-task artificial neural network, exploiting the underlying correlations between various mol. properties. The input is identical to ab initio methods, i.e. nuclear charges and Cartesian coordinates of all atoms. For small org. mols., the accuracy of such a 'quantum machine' is similar, and sometimes superior, to modern quantum-chem. methods-at negligible computational cost.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2cXltlKgs74%253D&md5=b38a7678efd055385e4eb6ee9b7aadae
    16. 16
      Coley, C. W.; Barzilay, R.; Green, W. H.; Jaakkola, T. S.; Jensen, K. F. Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction. J. Chem. Inf. Model. 2017, 57 (8), 1757,  DOI: 10.1021/acs.jcim.6b00601
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      16
      Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction
      Coley, Connor W.; Barzilay, Regina; Green, William H.; Jaakkola, Tommi S.; Jensen, Klavs F.
      Journal of Chemical Information and Modeling (2017), 57 (8), 1757-1772CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
      The task of learning an expressive mol. representation is central to developing quant. structure-activity and property relationships. Traditional approaches rely on group additivity rules, empirical measurements or parameters, or generation of thousands of descriptors. In this paper, we employ a convolutional neural network for this embedding task by treating mols. as undirected graphs with attributed nodes and edges. Simple atom and bond attributes are used to construct atom-specific feature vectors that take into account the local chem. environment using different neighborhood radii. By working directly with the full mol. graph, there is a greater opportunity for models to identify important features relevant to a prediction task. Unlike other graph-based approaches, our atom featurization preserves mol.-level spatial information that significantly enhances model performance. Our models learn to identify important features of atom clusters for the prediction of aq. soly., octanol soly., m.p., and toxicity. Extensions and limitations of this strategy are discussed.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2sXhtFCmtbzF&md5=85e942e40e2b7a827788113bdf5f6240
    17. 17
      Musil, F.; De, S.; Yang, J.; Campbell, J. E.; Day, G. M.; Ceriotti, M. Machine learning for the structure-energy-property landscapes of molecular crystals. Chem. Sci. 2018, 9 (5), 1289,  DOI: 10.1039/C7SC04665K
      [Crossref], [PubMed], [CAS], Google Scholar
      17
      Machine learning for the structure-energy-property landscapes of molecular crystals
      Musil, Felix; De, Sandip; Yang, Jack; Campbell, Joshua E.; Day, Graeme M.; Ceriotti, Michele
      Chemical Science (2018), 9 (5), 1289-1300CODEN: CSHCCN; ISSN:2041-6520. (Royal Society of Chemistry)
      Mol. crystals play an important role in several fields of science and technol. They frequently crystallize in different polymorphs with substantially different phys. properties. To help guide the synthesis of candidate materials, at.-scale modeling can be used to enumerate the stable polymorphs and to predict their properties, as well as to propose heuristic rules to rationalize the correlations between crystal structure and materials properties. Here we show how a recently-developed machine-learning (ML) framework can be used to achieve inexpensive and accurate predictions of the stability and properties of polymorphs, and a data-driven classification that is less biased and more flexible than typical heuristic rules. We discuss, as examples, the lattice energy and property landscapes of pentacene and two azapentacene isomers that are of interest as org. semiconductor materials. We show that we can est. force field or DFT lattice energies with sub-kJ mol-1 accuracy, using only a few hundred ref. configurations, and reduce by a factor of ten the computational effort needed to predict charge mobility in the crystal structures. The automatic structural classification of the polymorphs reveals a more detailed picture of mol. packing than that provided by conventional heuristics, and helps disentangle the role of hydrogen bonded and π-stacking interactions in detg. mol. self-assembly. This observation demonstrates that ML is not just a black-box scheme to interpolate between ref. calcns., but can also be used as a tool to gain intuitive insights into structure-property relations in mol. crystal engineering.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2sXhvFGnsbfE&md5=48b184722478d1a988a2090f765135e2
    18. 18
      Jinich, A.; Sanchez-Lengeling, B.; Ren, H.; Harman, R.; Aspuru-Guzik, A. A Mixed Quantum Chemistry/Machine Learning Approach for the Fast and Accurate Prediction of Biochemical Redox Potentials and Its Large-Scale Application to 315000 Redox Reactions. ACS Cent. Sci. 2019, 5 (7), 1199,  DOI: 10.1021/acscentsci.9b00297
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      18
      A Mixed Quantum Chemistry/Machine Learning Approach for the Fast and Accurate Prediction of Biochemical Redox Potentials and Its Large-Scale Application to 315 000 Redox Reactions
      Jinich, Adrian; Sanchez-Lengeling, Benjamin; Ren, Haniu; Harman, Rebecca; Aspuru-Guzik, Alan
      ACS Central Science (2019), 5 (7), 1199-1210CODEN: ACSCII; ISSN:2374-7951. (American Chemical Society)
      A quant. understanding of the thermodn. of biochem. reactions is essential for accurately modeling metab. The group contribution method (GCM) is one of the most widely used approaches to est. std. Gibbs energies and redox potentials of reactions for which no exptl. measurements exist. Previous work has shown that quantum chem. predictions of biochem. thermodn. are a promising approach to overcome the limitations of GCM. However, the quantum chem. approach is significantly more expensive. Here, the authors use a combination of quantum chem. and machine learning to obtain a fast and accurate method for predicting the thermodn. of biochem. redox reactions. The authors focus on predicting the redox potentials of carbonyl functional group redns. to alcs. and amines, two of the most ubiquitous carbon redox transformations in biol. The method relies on semiempirical quantum chem. calcns. calibrated with Gaussian process (GP) regression against available exptl. data and results in higher predictive power than the GCM at low computational cost. Direct calibration of GCM and fingerprint-based predictions (without quantum chem.) with GP regression also results in significant improvements in prediction accuracy, demonstrating the versatility of the approach. The authors design and implement a network expansion algorithm that iteratively reduces and oxidizes a set of natural seed metabolites and demonstrate the high-throughput applicability of the method by predicting the std. potentials of more than 315 000 redox reactions involving approx. 70 000 compds. Addnl., the authors developed a novel fingerprint-based framework for detecting mol. environment motifs that are enriched or depleted across different regions of the redox potential landscape. The authors provide open access to all source code and data generated.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtFWisb%252FN&md5=cc4e50e301cbd9a2736befbbb67a09db
    19. 19
      Yamada, H.; Liu, C.; Wu, S.; Koyama, Y.; Ju, S.; Shiomi, J.; Morikawa, J.; Yoshida, R. Predicting Materials Properties with Little Data Using Shotgun Transfer Learning. ACS Cent. Sci. 2019, 5 (10), 1717,  DOI: 10.1021/acscentsci.9b00804
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      19
      Predicting Materials Properties with Little Data Using Shotgun Transfer Learning
      Yamada, Hironao; Liu, Chang; Wu, Stephen; Koyama, Yukinori; Ju, Shenghong; Shiomi, Junichiro; Morikawa, Junko; Yoshida, Ryo
      ACS Central Science (2019), 5 (10), 1717-1730CODEN: ACSCII; ISSN:2374-7951. (American Chemical Society)
      There is a growing demand for the use of machine learning (ML) to derive fast-to-evaluate surrogate models of materials properties. In recent years, a broad array of materials property databases have emerged as part of a digital transformation of materials science. However, recent technol. advances in ML are not fully exploited because of the insufficient vol. and diversity of materials data. An ML framework called "transfer learning" has considerable potential to overcome the problem of limited amts. of materials data. Transfer learning relies on the concept that various property types, such as phys., chem., electronic, thermodn., and mech. properties, are phys. interrelated. For a given target property to be predicted from a limited supply of training data, models of related proxy properties are pretrained using sufficient data; these models capture common features relevant to the target task. Repurposing of such machine-acquired features on the target task yields outstanding prediction performance even with exceedingly small data sets, as if highly experienced human experts can make rational inferences even for considerably less experienced tasks. In this study, to facilitate widespread use of transfer learning, we develop a pretrained model library called XenonPy.MDL. In this first release, the library comprises more than 140 000 pretrained models for various properties of small mols., polymers, and inorg. cryst. materials. Along with these pretrained models, we describe some outstanding successes of transfer learning in different scenarios such as building models with only dozens of materials data, increasing the ability of extrapolative prediction through a strategic model transfer, and so on. Remarkably, transfer learning has autonomously identified rather nontrivial transferability across different properties transcending the different disciplines of materials science; for example, our anal. has revealed underlying bridges between small mols. and polymers and between org. and inorg. chem. Along with the XenonPy.MDL model library, we describe the great potential of transfer learning to break the barrier of limited amts. of data in materials property prediction using machine learning.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhvVGms77L&md5=04e4b7016b754aecfc235812e511bb84
    20. 20
      Afzal, M. A. F.; Sonpal, A.; Haghighatlari, M.; Schultz, A. J.; Hachmann, J. A deep neural network model for packing density predictions and its application in the study of 1.5 million organic molecules. Chem. Sci. 2019, 10 (36), 8374,  DOI: 10.1039/C9SC02677K
      [Crossref], [PubMed], [CAS], Google Scholar
      20
      A deep neural network model for packing density predictions and its application in the study of 1.5 million organic molecules
      Afzal, Mohammad Atif Faiz; Sonpal, Aditya; Haghighatlari, Mojtaba; Schultz, Andrew J.; Hachmann, Johannes
      Chemical Science (2019), 10 (36), 8374-8383CODEN: CSHCCN; ISSN:2041-6520. (Royal Society of Chemistry)
      The process of developing new compds. and materials is increasingly driven by computational modeling and simulation, which allow us to characterize candidates before pursuing them in the lab. One of the non-trivial properties of interest for org. materials is their packing in the bulk, which is highly dependent on their mol. structure. By controlling the latter, we can realize materials with a desired d. (as well as other target properties). Mol. dynamics simulations are a popular and reasonably accurate way to compute the bulk d. of mols., however, since these calcns. are computationally intensive, they are not a practically viable option for high-throughput screening studies that assess material candidates on a massive scale. In this work, we employ machine learning to develop a data-derived prediction model that is an alternative to physics-based simulations, and we utilize it for the hyperscreening of 1.5 million small org. mols. as well as to gain insights into the relationship between structural makeup and packing d. We also use this study to analyze the learning curve of the employed neural network approach and gain empirical data on the dependence of model performance and training data size, which will inform future investigations.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtleisLjP&md5=8457f2edf3e0a2df77a473d1252db825
    21. 21
      Dong, Y.; Wu, C.; Zhang, C.; Liu, Y.; Cheng, J.; Lin, J. Bandgap prediction by deep learning in configurationally hybridized graphene and boron nitride. npj Comput. Mater. 2019, 5 (1), 26,  DOI: 10.1038/s41524-019-0165-4
      [Crossref], Google Scholar
      There is no corresponding record for this reference.
    22. 22
      So, S.; Mun, J.; Rho, J. Simultaneous Inverse Design of Materials and Structures via Deep Learning: Demonstration of Dipole Resonance Engineering Using Core-Shell Nanoparticles. ACS Appl. Mater. Interfaces 2019, 11 (27), 24264,  DOI: 10.1021/acsami.9b05857
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      22
      Simultaneous Inverse Design of Materials and Structures via Deep Learning: Demonstration of Dipole Resonance Engineering Using Core-Shell Nanoparticles
      So, Sunae; Mun, Jungho; Rho, Junsuk
      ACS Applied Materials & Interfaces (2019), 11 (27), 24264-24268CODEN: AAMICK; ISSN:1944-8244. (American Chemical Society)
      Recent introduction of data-driven approaches based on deep-learning technol. has revolutionized the field of nanophotonics by allowing efficient inverse design methods. A simultaneous inverse design of materials and structure parameters of core-shell nanoparticles is achieved using deep learning of a neural network. A neural network to learn the correlation between the extinction spectra of elec. and magnetic dipoles and core-shell nanoparticle designs, which include material information and shell thicknesses, is developed and trained. Deep-learning-assisted inverse design of core-shell nanoparticles is demonstrated for (1) spectral tuning elec. dipole resonances, (2) finding spectrally isolated pure magnetic dipole resonances, and (3) finding spectrally overlapped elec. dipole and magnetic dipole resonances. The finding paves the way for the rapid development of nanophotonics by allowing a practical use of deep-learning technol. for nanophotonic inverse design.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtFyjs7rE&md5=bcbafdb550972b24c9fa738a976d4850
    23. 23
      Ye, S.; Hu, W.; Li, X.; Zhang, J.; Zhong, K.; Zhang, G.; Luo, Y.; Mukamel, S.; Jiang, J. A neural network protocol for electronic excitations of N-methylacetamide. Proc. Natl. Acad. Sci. U. S. A. 2019, 116 (24), 11612,  DOI: 10.1073/pnas.1821044116
      [Crossref], [PubMed], [CAS], Google Scholar
      23
      A neural network protocol for electronic excitations of N-methylacetamide
      Ye, Sheng; Hu, Wei; Li, Xin; Zhang, Jinxiao; Zhong, Kai; Zhang, Guozhen; Luo, Yi; Mukamel, Shaul; Jiang, Jun
      Proceedings of the National Academy of Sciences of the United States of America (2019), 116 (24), 11612-11617CODEN: PNASA6; ISSN:0027-8424. (National Academy of Sciences)
      UV absorption is widely used for characterizing proteins structures. The mapping of UV spectra to at. structure of proteins relies on expensive theor. simulations, circumventing the heavy computational cost which involves repeated quantum-mech. simulations of excited-state properties of many fluctuating protein geometries, which has been a long-time challenge. Here we show that a neural network machine-learning technique can predict electronic absorption spectra of N-methylacetamide (NMA), which is a widely used model system for the peptide bond. Using ground-state geometric parameters and charge information as descriptors, we employed a neural network to predict transition energies, ground-state, and transition dipole moments of many mol.-dynamics conformations at different temps., in agreement with time-dependent d.-functional theory calcns. The neural network simulations are nearly 3,000x faster than comparable quantum calcns. Machine learning should provide a cost-effective tool for simulating optical properties of proteins.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtFeqsLvM&md5=c59a23eb43db53bf7f3975a25efca882
    24. 24
      Ghosh, K.; Stuke, A.; Todorovic, M.; Jorgensen, P. B.; Schmidt, M. N.; Vehtari, A.; Rinke, P. Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra. Adv. Sci. 2019, 6 (9), 1801367,  DOI: 10.1002/advs.201801367
      [Crossref], [CAS], Google Scholar
      24
      Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra
      Ghosh Kunal; Vehtari Aki; Ghosh Kunal; Stuke Annika; Todorovic Milica; Rinke Patrick; Jorgensen Peter Bjorn; Schmidt Mikkel N; Rinke Patrick
      Advanced science (Weinheim, Baden-Wurttemberg, Germany) (2019), 6 (9), 1801367 ISSN:2198-3844.
      Deep learning methods for the prediction of molecular excitation spectra are presented. For the example of the electronic density of states of 132k organic molecules, three different neural network architectures: multilayer perceptron (MLP), convolutional neural network (CNN), and deep tensor neural network (DTNN) are trained and assessed. The inputs for the neural networks are the coordinates and charges of the constituent atoms of each molecule. Already, the MLP is able to learn spectra, but the root mean square error (RMSE) is still as high as 0.3 eV. The learning quality improves significantly for the CNN (RMSE = 0.23 eV) and reaches its best performance for the DTNN (RMSE = 0.19 eV). Both CNN and DTNN capture even small nuances in the spectral shape. In a showcase application of this method, the structures of 10k previously unseen organic molecules are scanned and instant spectra predictions are obtained to identify molecules for potential applications.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A280%3ADC%252BB3M7jsVGrsg%253D%253D&md5=cf103cea58059fa56008375f3ecb8698
    25. 25
      Back, S.; Yoon, J.; Tian, N.; Zhong, W.; Tran, K.; Ulissi, Z. W. Convolutional Neural Network of Atomic Surface Structures To Predict Binding Energies for High-Throughput Screening of Catalysts. J. Phys. Chem. Lett. 2019, 10 (15), 4401,  DOI: 10.1021/acs.jpclett.9b01428
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      25
      Convolutional Neural Network of Atomic Surface Structures To Predict Binding Energies for High-Throughput Screening of Catalysts
      Back, Seoin; Yoon, Junwoong; Tian, Nianhan; Zhong, Wen; Tran, Kevin; Ulissi, Zachary W.
      Journal of Physical Chemistry Letters (2019), 10 (15), 4401-4408CODEN: JPCLCD; ISSN:1948-7185. (American Chemical Society)
      High-throughput screening of catalysts can be performed using d. functional theory calcns. to predict catalytic properties, often correlated with adsorbate binding energies. More complete studies would require an order of 2 more calcns. compared to the current approach, making the computational cost a bottleneck. Recently developed machine-learning methods predict these properties from hand-crafted features but have struggled to scale to large compn. spaces or complex active sites. An application of a deep-learning convolutional neural network of at. surface structures using at. and Voronoi polyhedra-based neighbor information is presented. The model effectively learns the most important surface features to predict binding energies. The method predicts CO and H binding energies after training with 12,000 data for each adsorbate with a mean abs. error of 0.15 eV for a diverse chem. space. The method is capable of creating saliency maps that det. at. contributions to binding energies.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtlyju7jM&md5=cc068cadd2973b1bb2f17cec64ad61b3
    26. 26
      Kang, B.; Seok, C.; Lee, J. Prediction of Molecular Electronic Transitions Using Random Forests. J. Chem. Inf. Model. 2020, 60 (12), 5984,  DOI: 10.1021/acs.jcim.0c00698
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      26
      Prediction of Molecular Electronic Transitions Using Random Forests
      Kang, Beomchang; Seok, Chaok; Lee, Juyong
      Journal of Chemical Information and Modeling (2020), 60 (12), 5984-5994CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
      Fluorescent mols., fluorophores or dyes, play essential roles in bioimaging. Effective bioimaging requires fluorophores with diverse colors and high quantum yields for better resoln. An essential computational component to design novel dye mols. is an accurate model that predicts the electronic properties of mols. Here, we present statistical machines that predict the excitation energies and assocd. oscillator strengths of a given mol. using the random forest algorithm. The excitation energies and oscillator strengths of a mol. are closely related to the emission spectrum and the quantum yields of fluorophores, resp. In this study, we identified specific mol. substructures that induce high oscillator strengths of mols. The results of our study are expected to serve as new design principles for designing novel fluorophores.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXitFagtb%252FJ&md5=352c2b1634e6985d526dce4b69c57e7a
    27. 27
      Na, G. S.; Jang, S.; Lee, Y. L.; Chang, H. Tuplewise Material Representation Based Machine Learning for Accurate Band Gap Prediction. J. Phys. Chem. A 2020, 124 (50), 10616,  DOI: 10.1021/acs.jpca.0c07802
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      27
      Tuplewise Material Representation Based Machine Learning for Accurate Band Gap Prediction
      Na, Gyoung S.; Jang, Seunghun; Lee, Yea-Lee; Chang, Hyunju
      Journal of Physical Chemistry A (2020), 124 (50), 10616-10623CODEN: JPCAFH; ISSN:1089-5639. (American Chemical Society)
      The open-access material databases allowed us to approach scientific questions from a completely new perspective with machine learning methods. Here, on the basis of open-access databases, we focus on the classical band gap problem for predicting accurately the band gap of a cryst. compd. using a machine learning approach with newly developed tuplewise graph neural networks (TGNN), which is devised to automatically generate input representation of crystal structures in tuple types and to exploit crystal-level properties as one of the input features. Our method brings about a highly accurate prediction of the band gaps at hybrid functionals and GW approxn. levels for multiple material data sets without heavy computational cost. Furthermore, to demonstrate the applicability of our prediction model, we provide a data set of GW band gaps for 45835 materials predicted by TGNN posing higher accuracy than std. d. functional theory calcns.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXisVyiu7bL&md5=1ba7446df9022996a21f735a4ce88f0b
    28. 28
      Ye, S.; Zhong, K.; Zhang, J.; Hu, W.; Hirst, J. D.; Zhang, G.; Mukamel, S.; Jiang, J. A Machine Learning Protocol for Predicting Protein Infrared Spectra. J. Am. Chem. Soc. 2020, 142 (45), 19071,  DOI: 10.1021/jacs.0c06530
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      28
      A Machine Learning Protocol for Predicting Protein Infrared Spectra
      Ye, Sheng; Zhong, Kai; Zhang, Jinxiao; Hu, Wei; Hirst, Jonathan D.; Zhang, Guozhen; Mukamel, Shaul; Jiang, Jun
      Journal of the American Chemical Society (2020), 142 (45), 19071-19077CODEN: JACSAT; ISSN:0002-7863. (American Chemical Society)
      IR (IR) absorption provides important chem. fingerprints of biomols. Protein secondary structure detn. from IR spectra is tedious since its theor. interpretation requires repeated expensive quantum-mech. calcns. in a fluctuating environment. Herein we present a novel machine learning protocol that uses a few key structural descriptors to rapidly predict amide I IR spectra of various proteins and agrees well with expt. Its transferability enabled us to distinguish protein secondary structures, probe at. structure variations with temp., and monitor protein folding. This approach offers a cost-effective tool to model the relationship between protein spectra and their biol./chem. properties.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXitF2iu7jK&md5=7a3324e31a6e01900f5eb6f9ebd18d27
    29. 29
      Li, B.; Liu, R.; Bai, H.; Ju, C.-W. Can Machine Learning Be More Accurate Than TD-DFT? Prediction of Emission Wavelengths and Quantum Yields of Organic Fluorescent Materials. ChemRxiv 2020,  DOI: 10.26434/chemrxiv.12111060.v1
      [Crossref], [PubMed], Google Scholar
      There is no corresponding record for this reference.
    30. 30
      Gao, H.; Struble, T. J.; Coley, C. W.; Wang, Y.; Green, W. H.; Jensen, K. F. Using Machine Learning To Predict Suitable Conditions for Organic Reactions. ACS Cent. Sci. 2018, 4 (11), 1465,  DOI: 10.1021/acscentsci.8b00357
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      30
      Using Machine Learning To Predict Suitable Conditions for Organic Reactions
      Gao, Hanyu; Struble, Thomas J.; Coley, Connor W.; Wang, Yuran; Green, William H.; Jensen, Klavs F.
      ACS Central Science (2018), 4 (11), 1465-1476CODEN: ACSCII; ISSN:2374-7951. (American Chemical Society)
      Reaction condition recommendation is an essential element for the realization of computer-assisted synthetic planning. Accurate suggestions of reaction conditions are required for exptl. validation and can have a significant effect on the success or failure of an attempted transformation. However, de novo condition recommendation remains a challenging and under-explored problem and relies heavily on chemists' knowledge and experience. In this work, we develop a neural-network model to predict the chem. context (catalyst(s), solvent(s), reagent(s)), as well as the temp. most suitable for any particular org. reaction. Trained on ∼10 million examples from Reaxys, the model is able to propose conditions where a close match to the recorded catalyst, solvent, and reagent is found within the top-10 predictions 69.6% of the time, with top-10 accuracies for individual species reaching 80-90%. Temp. is accurately predicted within ±20 °C from the recorded temp. in 60-70% of test cases, with higher accuracy for cases with correct chem. context predictions. The utility of the model is illustrated through several examples spanning a range of common reaction classes. We also demonstrate that the model implicitly learns a continuous numerical embedding of solvent and reagent species that captures their functional similarity.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXit1aru77J&md5=fef56b949b8b8febb5d1403327238f4b
    31. 31
      Segler, M. H. S.; Preuss, M.; Waller, M. P. Planning chemical syntheses with deep neural networks and symbolic AI. Nature 2018, 555 (7698), 604,  DOI: 10.1038/nature25978
      [Crossref], [PubMed], [CAS], Google Scholar
      31
      Planning chemical syntheses with deep neural networks and symbolic AI
      Segler, Marwin H. S.; Preuss, Mike; Waller, Mark P.
      Nature (London, United Kingdom) (2018), 555 (7698), 604-610CODEN: NATUAS; ISSN:0028-0836. (Nature Research)
      To plan the syntheses of small org. mols., chemists use retrosynthesis, a problem-solving technique in which target mols. are recursively transformed into increasingly simpler precursors. Computer-aided retrosynthesis would be a valuable tool but at present it is slow and provides results of unsatisfactory quality. Here, we use Monte Carlo tree search and symbolic artificial intelligence (AI) to discover retrosynthetic routes. We combined Monte Carlo tree search with an expansion policy network that guides the search, and a filter network to pre-select the most promising retrosynthetic steps. These deep neural networks were trained on essentially all reactions ever published in org. chem. Our system solves for almost twice as many mols., thirty times faster than the traditional computer-aided search method, which is based on extd. rules and hand-designed heuristics. In a double-blind AB test, chemists on av. considered our computer-generated routes to be equiv. to reported literature routes.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXmsVGqt7c%253D&md5=400e9945ff83ffe2d12278aa4c562893
    32. 32
      Voznyy, O.; Levina, L.; Fan, J. Z.; Askerka, M.; Jain, A.; Choi, M. J.; Ouellette, O.; Todorovic, P.; Sagar, L. K.; Sargent, E. H. Machine Learning Accelerates Discovery of Optimal Colloidal Quantum Dot Synthesis. ACS Nano 2019, 13 (10), 11122,  DOI: 10.1021/acsnano.9b03864
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      32
      Machine Learning Accelerates Discovery of Optimal Colloidal Quantum Dot Synthesis
      Voznyy, Oleksandr; Levina, Larissa; Fan, James Z.; Askerka, Mikhail; Jain, Ankit; Choi, Min-Jae; Ouellette, Olivier; Todorovic, Petar; Sagar, Laxmi K.; Sargent, Edward H.
      ACS Nano (2019), 13 (10), 11122-11128CODEN: ANCAC3; ISSN:1936-0851. (American Chemical Society)
      Colloidal quantum dots (CQDs) allow broad tuning of the bandgap across the visible and near-IR spectral regions. Recent advances in applying CQDs in light sensing, photovoltaics, and light emission have heightened interest in achieving further synthetic improvements. In particular, improving monodispersity remains a key priority in order to improve solar cells' open-circuit voltage, decrease lasing thresholds, and improve photodetectors' noise-equiv. power. Here we utilize machine-learning-in-the-loop to learn from available exptl. data, propose exptl. parameters to try, and, ultimately, point to regions of synthetic parameter space that will enable record-monodispersity PbS quantum dots. The resultant studies reveal that adding a growth-slowing precursor (oleylamine) allows nucleation to prevail over growth, a strategy that enables record-large-bandgap (611 nm exciton) PbS nanoparticles with a well-defined excitonic absorption peak (half-width at half-max. (HWHM) of 145 meV). At longer wavelengths, we also achieve improved monodispersity, with an hwhm of 55 meV at 950 nm and 24 meV at 1500 nm, compared to the best published to date values of 75 and 26 meV, resp.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhvVWksrnN&md5=c80559d7cd097b78be5480435484af37
    33. 33
      Torng, W.; Altman, R. B. Graph Convolutional Neural Networks for Predicting Drug-Target Interactions. J. Chem. Inf. Model. 2019, 59 (10), 4131,  DOI: 10.1021/acs.jcim.9b00628
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      33
      Graph Convolutional Neural Networks for Predicting Drug-Target Interactions
      Torng, Wen; Altman, Russ B.
      Journal of Chemical Information and Modeling (2019), 59 (10), 4131-4149CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
      Accurate detn. of target-ligand interactions is crucial in the drug discovery process. In this paper, we propose a graph-convolutional (Graph-CNN) framework for predicting protein-ligand interactions. First, we built an unsupervised graph-autoencoder to learn fixed-size representations of protein pockets from a set of representative druggable protein binding sites. Second, we trained two Graph-CNNs to automatically ext. features from pocket graphs and 2D ligand graphs, resp., driven by binding classification labels. We demonstrate that graph-autoencoders can learn fixed-size representations for protein pockets of varying sizes and the Graph-CNN framework can effectively capture protein-ligand binding interactions without relying on target-ligand complexes. Across several metrics, Graph-CNNs achieved better or comparable performance to 3DCNN ligand-scoring, AutoDock Vina, RF-Score, and NNScore on common virtual screening benchmark data sets. Visualization of key pocket residues and ligand atoms contributing to the classification decisions confirms that our networks are able to detect important interface residues and ligand atoms within the pockets and ligands, resp.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhvFSisrzI&md5=c9a71957bcde3dba1df2f969bb70168c
    34. 34
      Lim, J.; Hwang, S.-Y.; Moon, S.; Kim, S.; Kim, W. Y. Scaffold-based molecular design with a graph generative model. Chem. Sci. 2020, 11 (4), 1153,  DOI: 10.1039/C9SC04503A
      [Crossref], [CAS], Google Scholar
      34
      Scaffold-based molecular design with a graph generative model
      Lim, Jaechang; Hwang, Sang-Yeon; Moon, Seokhyun; Kim, Seungsu; Kim, Woo Youn
      Chemical Science (2020), 11 (4), 1153-1164CODEN: CSHCCN; ISSN:2041-6520. (Royal Society of Chemistry)
      Searching for new mols. in areas like drug discovery often starts from the core structures of known mols. Such a method has called for a strategy of designing deriv. compds. retaining a particular scaffold as a substructure. On this account, our present work proposes a graph generative model that targets its use in scaffold-based mol. design. Our model accepts a mol. scaffold as input and extends it by sequentially adding atoms and bonds. The generated mols. are then guaranteed to contain the scaffold with certainty, and their properties can be controlled by conditioning the generation process on desired properties. The learned rule of extending mols. can well generalize to arbitrary kinds of scaffolds, including those unseen during learning. In the conditional generation of mols., our model can simultaneously control multiple chem. properties despite the search space constrained by fixing the substructure. As a demonstration, we applied our model to designing inhibitors of the epidermal growth factor receptor and show that our model can employ a simple semi-supervised extension to broaden its applicability to situations where only a small amt. of data is available.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXit1Ortr%252FO&md5=be36a65abcce15f18b4c1e529bffd905
    35. 35
      Jha, D.; Ward, L.; Paul, A.; Liao, W. K.; Choudhary, A.; Wolverton, C.; Agrawal, A. ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition. Sci. Rep. 2018, 8 (1), 17593,  DOI: 10.1038/s41598-018-35934-y
      [Crossref], [PubMed], [CAS], Google Scholar
      35
      ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition
      Jha Dipendra; Paul Arindam; Liao Wei-Keng; Choudhary Alok; Agrawal Ankit; Ward Logan; Wolverton Chris
      Scientific reports (2018), 8 (1), 17593 ISSN:.
      Conventional machine learning approaches for predicting material properties from elemental compositions have emphasized the importance of leveraging domain knowledge when designing model inputs. Here, we demonstrate that by using a deep learning approach, we can bypass such manual feature engineering requiring domain knowledge and achieve much better results, even with only a few thousand training samples. We present the design and implementation of a deep neural network model referred to as ElemNet; it automatically captures the physical and chemical interactions and similarities between different elements using artificial intelligence which allows it to predict the materials properties with better accuracy and speed. The speed and best-in-class accuracy of ElemNet enable us to perform a fast and robust screening for new material candidates in a huge combinatorial space; where we predict hundreds of thousands of chemical systems that could contain yet-undiscovered compounds.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A280%3ADC%252BB3cros1aqtw%253D%253D&md5=de8a35358c9fe7fc2bab30c8e1dd0637
    36. 36
      Sahu, H.; Yang, F.; Ye, X.; Ma, J.; Fang, W.; Ma, H. Designing promising molecules for organic solar cells via machine learning assisted virtual screening. J. Mater. Chem. A 2019, 7 (29), 17480,  DOI: 10.1039/C9TA04097H
      [Crossref], [CAS], Google Scholar
      36
      Designing promising molecules for organic solar cells via machine learning assisted virtual screening
      Sahu, Harikrishna; Yang, Feng; Ye, Xiaobo; Ma, Jing; Fang, Weihai; Ma, Haibo
      Journal of Materials Chemistry A: Materials for Energy and Sustainability (2019), 7 (29), 17480-17488CODEN: JMCAET; ISSN:2050-7496. (Royal Society of Chemistry)
      Navigating chem. space for org. photovoltaics (OPVs) is in high demand for further increasing the device efficiency, which can be accelerated through virtual screening of a large no. of possible candidate mols. using a computationally cheap and efficient model. However, predicting the efficiency of an OPV is quite challenging due to the complex correlations between factors influencing the energy conversion process. In this work, we performed high-throughput virtual screening of 10 170 candidate mols., constructed from 32 unique building blocks, with several newly built, computationally affordable and high-performing (Pearson's correlation coeff. = 0.7-0.8) machine learning (ML) models using relevant descriptors. Important building blocks are identified, and new design rules are introduced to construct efficient mols. The crit. mol. properties required for high efficiency are unraveled. Also, 126 candidates with theor. predicted efficiency >8% are proposed for synthesis and device fabrication. Similar ML-assisted virtual screening studies may reveal hidden guidelines to design promising mols. and could be a breakthrough in the search for lead candidates for OPVs.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXht1yksr7L&md5=433fcf452600d70af3093b0a811b5ff8
    37. 37
      Kim, B.; Lee, S.; Kim, J. Inverse design of porous materials using artificial neural networks. Sci. Adv. 2020, 6 (1), eaax9324,  DOI: 10.1126/sciadv.aax9324
      [Crossref], [PubMed], Google Scholar
      There is no corresponding record for this reference.
    38. 38
      Hansen, K.; Biegler, F.; Ramakrishnan, R.; Pronobis, W.; von Lilienfeld, O. A.; Muller, K. R.; Tkatchenko, A. Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space. J. Phys. Chem. Lett. 2015, 6 (12), 2326,  DOI: 10.1021/acs.jpclett.5b00831
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      38
      Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space
      Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan; Pronobis, Wiktor; von Lilienfeld, O. Anatole; Mueller, Klaus-Robert; Tkatchenko, Alexandre
      Journal of Physical Chemistry Letters (2015), 6 (12), 2326-2331CODEN: JPCLCD; ISSN:1948-7185. (American Chemical Society)
      Simultaneously accurate and efficient prediction of mol. properties throughout chem. compd. space is a crit. ingredient toward rational compd. design in chem. and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to est. atomization and total energies of mols. These methods range from a simple sum over atoms, to addn. of bond energies, to pairwise interat. force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equil. mol. geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calcd. using d. functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the "holy grail" of chem. accuracy of 1 kcal/mol for both equil. and out-of-equil. geometries. This remarkable accuracy is achieved by a vectorized representation of mols. (so-called Bag of Bonds model) that exhibits strong nonlocality in chem. space. In addn., the same representation allows us to predict accurate electronic properties of mols., such as their polarizability and mol. frontier orbital energies.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2MXpsFOmsrg%253D&md5=402cfd080b9ab0aae17932dffda375cf
    39. 39
      Hermann, J.; Schätzle, Z.; Noé, F. Deep-neural-network solution of the electronic Schrödinger equation. Nat. Chem. 2020, 12 (10), 891,  DOI: 10.1038/s41557-020-0544-y
      [Crossref], [PubMed], [CAS], Google Scholar
      39
      Deep-neural-network solution of the electronic Schrodinger equation
      Hermann, Jan; Schaetzle, Zeno; Noe, Frank
      Nature Chemistry (2020), 12 (10), 891-897CODEN: NCAHBB; ISSN:1755-4330. (Nature Research)
      The electronic Schrodinger equation can only be solved anal. for the hydrogen atom, and the numerically exact full configuration-interaction method is exponentially expensive in the no. of electrons. Quantum Monte Carlo methods are a possible way out: they scale well for large mols., they can be parallelized and their accuracy has, as yet, been only limited by the flexibility of the wavefunction ansatz used. Here we propose PauliNet, a deep-learning wavefunction ansatz that achieves nearly exact solns. of the electronic Schrodinger equation for mols. with up to 30 electrons. PauliNet has a multireference Hartree-Fock soln. built in as a baseline, incorporates the physics of valid wavefunctions and is trained using variational quantum Monte Carlo. PauliNet outperforms previous state-of-the-art variational ansatzes for atoms, diat. mols. and a strongly correlated linear H10, and matches the accuracy of highly specialized quantum chem. methods on the transition-state energy of cyclobutadiene, while being computationally efficient.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXhvFCht77L&md5=274495cfa9d66ff2a7055c50de26c313
    40. 40
      Nakata, M.; Shimazaki, T. PubChemQC Project: A Large-Scale First-Principles Electronic Structure Database for Data-Driven Chemistry. J. Chem. Inf. Model. 2017, 57 (6), 1300,  DOI: 10.1021/acs.jcim.7b00083
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      40
      PubChemQC Project: A Large-Scale First-Principles Electronic Structure Database for Data-Driven Chemistry
      Nakata, Maho; Shimazaki, Tomomi
      Journal of Chemical Information and Modeling (2017), 57 (6), 1300-1308CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
      Large-scale mol. databases play an essential role in the investigation of various subjects such as the development of org. materials, in-silico drug designs, and data-driven studies with machine learning, among others. We developed a large-scale quantum chem. database based on the first-principles method without performing any expt. Our database currently contains three million mol. electronic structures based on the d. functional theory method at the B3LYP/6-31G* level, and we successively calcd. 10 low-lying excited states of over two million mols. by the time-dependent DFT method with the 6-31+G* basis set. To select the mols. calcd. in our project, we mainly referred to the PubChem project, and it was used as a source of the mol. structures in short strings using the InChI and the SMILES representations. Accordingly, we named our quantum chem. database project as "PubChemQC" (http://pubchemqc.riken.jp/) and placed it in the public domain. In this paper, we showed the fundamental features of the PubChemQC database and dis- cussed the techniques used to construct the dataset for large-scale quantum chem. calcns. We also presented a machine-learning approach to predict the electronic structure of mols. as an example to demonstrate the suitability of the large-scale quantum chem. database.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2sXntFKnt7g%253D&md5=be48dc3c13a5f05cdd7700c427949ec3
    41. 41
      Gilmer, J.; Schoenholz, S. S.; Riley, P. F.; Vinyals, O.; Dahl, G. E. Neural Message Passing for Quantum Chemistry. arXiv.org 2017, 1704.01212v2
      Google Scholar
      There is no corresponding record for this reference.
    42. 42
      Ryu, S.; Lim, J.; Hong, S. H.; Kim, W. Y. Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network. arXiv.org 2018, 1805.10988
      Google Scholar
      There is no corresponding record for this reference.
    43. 43
      Wang, X.; Li, Z.; Jiang, M.; Wang, S.; Zhang, S.; Wei, Z. Molecule Property Prediction Based on Spatial Graph Embedding. J. Chem. Inf. Model. 2019, 59 (9), 3817,  DOI: 10.1021/acs.jcim.9b00410
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      43
      Molecule Property Prediction Based on Spatial Graph Embedding
      Wang, Xiaofeng; Li, Zhen; Jiang, Mingjian; Wang, Shuang; Zhang, Shugang; Wei, Zhiqiang
      Journal of Chemical Information and Modeling (2019), 59 (9), 3817-3828CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
      Accurate prediction of mol. properties is important for new compd. design, which is a crucial step in drug discovery. In this paper, mol. graph data is utilized for property prediction based on graph convolution neural networks. In addn., a convolution spatial graph embedding layer (C-SGEL) is introduced to retain the spatial connection information on mols. And, multiple C-SGELs are stacked to construct a convolution spatial graph embedding network (C-SGEN) for end-to-end representation learning. In order to enhance the robustness of the network, mol. fingerprints are also combined with C-SGEN to build a composite model for predicting mol. properties. Our comparative expts. have shown that our method is accurate and achieves the best results on some open benchmark datasets.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhs1egur7I&md5=a28bda9eeef821f2e6627e934d90844f
    44. 44
      Li, X.; Yan, X.; Gu, Q.; Zhou, H.; Wu, D.; Xu, J. DeepChemStable: Chemical Stability Prediction with an Attention-Based Graph Convolution Network. J. Chem. Inf. Model. 2019, 59 (3), 1044,  DOI: 10.1021/acs.jcim.8b00672
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      44
      DeepChemStable: Chemical Stability Prediction with an Attention-Based Graph Convolution Network
      Li, Xiuming; Yan, Xin; Gu, Qiong; Zhou, Huihao; Wu, Di; Xu, Jun
      Journal of Chemical Information and Modeling (2019), 59 (3), 1044-1049CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
      In the drug discovery process, unstable compds. in storage can lead to false pos. or false neg. bioassay conclusions. Prediction of the chem. stability of a compd. by de novo methods is complex. Chem. instability prediction is commonly based on a model derived from empirical data. The COMDECOM (Compd. Decompn.) project provides the empirical data for prediction of chem. stability. Models such as the extended-connectivity fingerprint and atom center fragments were built from the COMDECOM data and used for estn. of chem. stability, but deficits in the existing models remain. In this paper, we report DeepChemStable, a model employing an attention-based graph convolution network based on the COMDECOM data. The main advantage of this method is that DeepChemStable is an end-to-end model, which does not predefine structural fingerprint features, but instead, dynamically learns structural features and assocs. the features through the learning process of an attention-based graph convolution network. The previous ChemStable program relied on a rule-based method to reduce the false negatives. DeepChemStable, on the other hand, reduces the risk of false negatives without using a rule-based method. Because minimizing the rate of false negatives is a greater concern for instability prediction, this feature is a major improvement. This model achieves an AUC value of 84.7%, recall rate of 79.8%, and 10-fold stratified cross-validation accuracy of 79.1%.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXjtVSgsbo%253D&md5=39ca436fe4c15d480c0a404df6576143
    45. 45
      Joung, J. F.; Kim, S.; Park, S. Cationic Effect on the Equilibria and Kinetics of the Excited-State Proton Transfer Reaction of a Photoacid in Aqueous Solutions. J. Phys. Chem. B 2018, 122 (19), 5087,  DOI: 10.1021/acs.jpcb.8b00588
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      45
      Cationic Effect on the Equilibria and Kinetics of the Excited-State Proton Transfer Reaction of a Photoacid in Aqueous Solutions
      Joung, Joonyoung F.; Kim, Sangin; Park, Sungnam
      Journal of Physical Chemistry B (2018), 122 (19), 5087-5093CODEN: JPCBFK; ISSN:1520-5207. (American Chemical Society)
      Dissolved ions have a significant effect on the chem. equil. and kinetics in aq. solns. by changing the phys. properties and hydrogen bond network of water. In this work, the ionic effects on the excited-state proton transfer (ESPT) reactions of Coumarin 183 (C183) in aq. ionic solns. are comprehensively studied in terms of pKa, pK*a, activation energies, and kinetic isotope effect (KIE). The acid dissocn. consts. (pKa and pK*a) of C183 on the ground and excited states are detd. by UV-visible absorption and steady-state fluorescence spectroscopy. The activation energies (Ea) and KIE for the ESPT reaction of C183 are directly obtained by time-resolved fluorescence spectroscopy. The changes in pKa, pK*a, Ea, and KIE values of C183 are found to be dependent on the charge d. of cations. The secondary KIE is more substantially influenced by the dissolved ions than the primary KIE. Furthermore, the ionic effects on the equil. (pKa and pK*a) and kinetic (Ea and KIE) parameters of C183 are found to be well-explained by the free-energy reactivity relation. Our current results are very important in understanding the ionic effects on the equil. and ESPT kinetics of photoacids in aq. ionic solns.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXot1CitLo%253D&md5=2fa29ddba8db6137048122e0e038c615
    46. 46
      Niko, Y.; Hiroshige, Y.; Kawauchi, S.; Konishi, G.-i. Fundamental photoluminescence properties of pyrene carbonyl compounds through absolute fluorescence quantum yield measurement and density functional theory. Tetrahedron 2012, 68 (31), 6177,  DOI: 10.1016/j.tet.2012.05.072
      [Crossref], [CAS], Google Scholar
      46
      Fundamental photoluminescence properties of pyrene carbonyl compounds through absolute fluorescence quantum yield measurement and density functional theory
      Niko, Yosuke; Hiroshige, Yuki; Kawauchi, Susumu; Konishi, Gen-ichi
      Tetrahedron (2012), 68 (31), 6177-6185CODEN: TETRAB; ISSN:0040-4020. (Elsevier Ltd.)
      We reviewed the photophys. properties of carbonyl-functionalized pyrene derivs. [i.e., pyrene with aldehyde (PA: 1-formylpyrene), ketone (PK: 1-acetylpyrene), carboxylic acid (PCA: 1-pyrenecarboxylic acid), and ester groups (PE: 1-methoxycarbonylpyrene)] using a measurement of abs. fluorescence quantum yield in various solvents and time-dependent d. functional theory (TD-DFT) calcns. Here, we obtained new important data that fill in the gaps in existing datasets on these properties and help identify photoluminescence mechanisms. The results of the TD-DFT calcns. were in agreement with the exptl. results, and indicated that the low fluorescence of PA and PK is derived not only from intersystem crossing but also from internal conversion due to the proximity effect; this inference was also supported by the measurements of the photoluminescence spectra at low temps. In addn., factors leading efficiently to non-radiative processes were shown to be absent in PCA and PE. Thus, we successfully revised and systematized the photophys. properties of pyrene modified by carbonyl substitutes, including carboxamide groups, which were previously reported by us. Moreover, we showed that the photoluminescence properties of such compds. might be predictable by using TD-DFT calcns.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC38XoslSks7c%253D&md5=0920c356c851ff8ffbd5b87f96235435
    47. 47
      Ciubini, B.; Visentin, S.; Serpe, L.; Canaparo, R.; Fin, A.; Barbero, N. Design and synthesis of symmetrical pentamethine cyanine dyes as NIR photosensitizers for PDT. Dyes Pigm. 2019, 160, 806,  DOI: 10.1016/j.dyepig.2018.09.009
      [Crossref], [CAS], Google Scholar
      47
      Design and synthesis of symmetrical pentamethine cyanine dyes as NIR photosensitizers for PDT
      Ciubini, Betty; Visentin, Sonja; Serpe, Loredana; Canaparo, Roberto; Fin, Andrea; Barbero, Nadia
      Dyes and Pigments (2019), 160 (), 806-813CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
      Herein, we report the synthesis and spectroscopic characterization of novel Near Infra-Red (NIR) pentamethine cyanine dyes, as potential photosensitizers for Photodynamic Therapy (PDT) characterized by a strong absorption in the tissue transparency window (600-800 nm). The heteroarom. benzoindolenine ring of various sym. cyanine dyes has been differently functionalized and quaternarized as a result of a structure-activity study and to det. the substituent effect on the cellular uptake, ROS prodn. and photodynamic activity. These probes present low cytotoxicity in dark, but promote phototoxic effect, upon irradn., in human fibrosarcoma cell line (HT-1080) with interesting and unexpected structure to property activity.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXhslejt73M&md5=a205d2a835f3831d8ae6c878603bf4c3
    48. 48
      Khopkar, S.; Jachak, M.; Shankarling, G. Novel A(2)-D-A(1)-D-A(2) type NIR absorbing symmetrical squaraines based on 2, 3, 3, 8-tetramethyl-3H-pyrrolo [3, 2-h] quinoline: Synthesis, photophysical, electrochemical, thermal properties and photostability study. Spectrochim. Acta, Part A 2019, 211, 114,  DOI: 10.1016/j.saa.2018.11.061
      [Crossref], [PubMed], [CAS], Google Scholar
      48
      Novel A2-D-A1-D-A2 type NIR absorbing symmetrical squaraines based on 2, 3, 3, 8-tetramethyl-3H-pyrrolo [3, 2-h] quinoline: Synthesis, photophysical, electrochemical, thermal properties and photostability study
      Khopkar, Sushil; Jachak, Mahesh; Shankarling, Ganapati
      Spectrochimica Acta, Part A: Molecular and Biomolecular Spectroscopy (2019), 211 (), 114-124CODEN: SAMCAS; ISSN:1386-1425. (Elsevier B.V.)
      Two novel acceptor-donor-acceptor-donor-acceptor (A2-D-A1-D-A2) type pi-conjugated sym. squaraine dyes, denoted by PQSQ 1 and PQSQ 2 based on 2, 3, 3, 8-tetra-Me -3H-pyrrolo [3,2-h] quinoline were successfully synthesized for the first time to arrive absorption and emission at NIR region. These dyes comprise indolenines as electron donor units, squaryl ring as a central electron acceptor and pyridines as terminal electron acceptor units. The relationship between mol. structures and photophys. properties of these dyes was studied in comparison with their parent compds. (ISQ and N-Et ISQ). These novel squaraine dyes displayed an intense absorption within the range 671 to 692 nm in polar to non- polar solvents resp. with good molar extinction coeffs. ( > 105 Lmol-1 cm-1). Compared to their parent squaraines, both dyes showed red-shifted absorption (33-44 nm) as well as emission (38-59 nm) due to the electron-accepting ability of the ancillary pyridine acceptors and extended pi-conjugation. These dyes exhibited neg. solvatochromism and Reichardt's ET (30) scale was applied to propose a quant. relationship of the relative stability of ground and excited-state of these squaraines with solvent polarity. The electrochem. and computational properties of these sym. squaraines were investigated with the help of cyclic voltammetry and d. functional theory (DFT). Moreover, PQSQ 1-2 exhibited high thermal and photo-stability. These A2-D-A1-D-A2 type dyes showed improved photostabilities compared to their parent D-A-D type dyes.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXisVOiurfJ&md5=d4a4428ba229bdef743d2a8b88771e3e
    49. 49
      Cser, A.; Nagy, K.; Biczók, L. Fluorescence lifetime of Nile Red as a probe for the hydrogen bonding strength with its microenvironment. Chem. Phys. Lett. 2002, 360 (5–6), 473,  DOI: 10.1016/S0009-2614(02)00784-4
      [Crossref], [CAS], Google Scholar
      49
      Fluorescence lifetime of Nile red as a probe for the hydrogen bonding strength with its microenvironment
      Cser, Adrienn; Nagy, Krisztina; Biczok, Laszlo
      Chemical Physics Letters (2002), 360 (5,6), 473-478CODEN: CHPLBC; ISSN:0009-2614. (Elsevier Science B.V.)
      The fluorescence lifetime of Nile Red (NR) is not sensitive to dielec. solvent-solute interactions but markedly decreases with increasing hydrogen bond donating ability in alcs. because vibrations assocd. with hydrogen bonding are involved in the deactivation process. The negligible viscosity effect indicates that twisting of the diethylamino moiety of NR does not play a significant role in the dissipation of the excitation energy.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BD38XlsFOgsb4%253D&md5=d987832ac02308077476d1a9bc558bc2
    50. 50
      Niko, Y.; Kawauchi, S.; Konishi, G. Solvatochromic pyrene analogues of Prodan exhibiting extremely high fluorescence quantum yields in apolar and polar solvents. Chem. - Eur. J. 2013, 19 (30), 9760,  DOI: 10.1002/chem.201301020
      [Crossref], [PubMed], [CAS], Google Scholar
      50
      Solvatochromic Pyrene Analogues of Prodan Exhibiting Extremely High Fluorescence Quantum Yields in Apolar and Polar Solvents
      Niko, Yosuke; Kawauchi, Susumu; Konishi, Gen-ichi
      Chemistry - A European Journal (2013), 19 (30), 9760-9765CODEN: CEUJED; ISSN:0947-6539. (Wiley-VCH Verlag GmbH & Co. KGaA)
      The authors report the synthesis and photophys. properties of the pyrene derivs. PA [3,8-dibutyl-6-(piperidin-1-yl)pyrene-1-carbaldehyde] and PK [1-(3,8-dibutyl-6-(piperidin-1-yl)pyren-1- yl)butan-1-one], and demonstrate their outstanding photoluminescence properties, which include their extremely high QYs in both apolar (hexane) and polar (methanol) media as well as their strong solvatochromism.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC3sXptVCksbg%253D&md5=b4c74c9b3aaadd595a83d0f153fb4872
    51. 51
      Santin, L. R. R.; dos Santos, S. C.; Novo, D. L. R.; Bianchini, D.; Gerola, A. P.; Braga, G.; Caetano, W.; Moreira, L. M.; Bastos, E. L.; Romani, A. P. Study between solvatochromism and steady-state and time-resolved fluorescence measurements of the Methylene blue in binary mixtures. Dyes Pigm. 2015, 119, 12,  DOI: 10.1016/j.dyepig.2015.03.004
      [Crossref], [CAS], Google Scholar
      51
      Study between solvatochromism and steady-state and time-resolved fluorescence measurements of the Methylene blue in binary mixtures
      Santin, Luiza R. R.; dos Santos, Sandra C.; Novo, Diogo La Rosa; Bianchini, Daniela; Gerola, Adriana P.; Braga, Gustavo; Caetano, Wilker; Moreira, Leonardo M.; Bastos, Erick Leite; Romani, Ana Paula; de Oliveira, Hueder P. M.
      Dyes and Pigments (2015), 119 (), 12-21CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
      In this work, the study on the influence of binary mixts. of solvents (water-acetonitrile, water-ethanol and water-glycerol) upon the spectroscopic properties of methylene blue (MB) was done. In addn., the photophys. characterization of the MB in different concns. in the solvent mixts. was done. In the mixts., the increase in the quantity of water has decreased the fluorescence quantum yield together with other photophys. alterations. The studies of time-resolved fluorescence have demonstrated a first-order decay, with lifetimes between 328 and 550 ps. These values increase as the org. solvent proportion is increased. The results have shown a direct relationship between the viscosity and the rotational lifetime, correlating with the interference in the processes of deactivation of the excited state, which are slower in media with higher viscosity. The conformation of the clusters in the binary mixts. was also identified as a key factor to det. the results obtained in this work.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2MXks1yks7g%253D&md5=e7a4ae4d3235eb8079fd92f1b7846e92
    52. 52
      Wünsch, U. J.; Murphy, K. R.; Stedmon, C. A. Fluorescence Quantum Yields of Natural Organic Matter and Organic Compounds: Implications for the Fluorescence-based Interpretation of Organic Matter Composition. Front. Mar. Sci. 2015,  DOI: 10.3389/fmars.2015.00098
      [Crossref], Google Scholar
      There is no corresponding record for this reference.
    53. 53
      Frisch, M. J.; Trucks, G. W.; Schlegel, H. B.; Scuseria, G. E.; Robb, M. A.; Cheeseman, J. R.; Scalmani, G.; Barone, V.; Petersson, G. A.; Nakatsuji, H.; Li, X.; Caricato, M.; Marenich, A. V.; Bloino, J.; Janesko, B. G.; Gomperts, R.; Mennucci, B.; Hratchian, H. P.; Ortiz, J. V.; Izmaylov, A. F.; Sonnenberg, J. L.; Williams-Young, D.; Ding, F.; Lipparini, F.; Egidi, F.; Goings, J.; Peng, B.; Petrone, A.; Henderson, T.; Ranasinghe, D.; Zakrzewski, V. G.; Gao, J.; Rega, N.; Zheng, G.; Liang, W.; Hada, M.; Ehara, M.; Toyota, K.; Fukuda, R.; Hasegawa, J.; Ishida, M.; Nakajima, T.; Honda, Y.; Kitao, O.; Nakai, H.; Vreven, T.; Throssell, K.; Montgomery, J. A., Jr.; Peralta, J. E.; Ogliaro, F.; Bearpark, M. J.; Heyd, J. J.; Brothers, E. N.; Kudin, K. N.; Staroverov, V. N.; Keith, T. A.; Kobayashi, R.; Normand, J.; Raghavachari, K.; Rendell, A. P.; Burant, J. C.; Iyengar, S. S.; Tomasi, J.; Cossi, M.; Millam, J. M.; Klene, M.; Adamo, C.; Cammi, R.; Ochterski, J. W.; Martin, R. L.; Morokuma, K.; Farkas, O.; Foresman, J. B.; Fox, D. J. Gaussian 16; Gaussian, Inc.: Wallingford, CT, 2016.
      Google Scholar
      There is no corresponding record for this reference.
    54. 54
      Sun, H.; Dong, X.; Liu, S.; Zhao, Q.; Mou, X.; Yang, H. Y.; Huang, W. Excellent BODIPY Dye Containing Dimesitylboryl Groups as PeT-Based Fluorescent Probes for Fluoride. J. Phys. Chem. C 2011, 115 (40), 19947,  DOI: 10.1021/jp206396v
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      54
      Excellent BODIPY Dye Containing Dimesitylboryl Groups as PeT-Based Fluorescent Probes for Fluoride
      Sun, Hui-Bin; Dong, Xiao-Chen; Liu, Shu-Juan; Zhao, Qiang; Mou, Xin; Yang, Hui-Ying; Huang, Wei
      Journal of Physical Chemistry C (2011), 115 (40), 19947-19954CODEN: JPCCCK; ISSN:1932-7447. (American Chemical Society)
      A highly selective fluorescent probe BBDPB for F- was realized on the basis of the boron-dipyrromethene (BODIPY) dye contg. two dimesitylboryl (Mes2B) moieties. The fluorophore displays highly efficient orange-red fluorescence with an emission peak of 602 nm and quantum efficiency (Φ) of 0.65 in dichloromethane soln. Signaling changes were obsd. through UV/vis absorption and photoluminescence spectra. Obvious spectral changes in absorption and fluorescent emission bands were detected after adding F- in company with an obvious soln. color change from pink to deep blue. The effects of F- on the electronic structure of BBDPB were studied in detail by performing theor. calcns. using the Gaussian 03 package. According to the theor. calcn. and contrast expts., the binding of Mes2B moieties with F- would give rise to nonradiative photoinduced-electron-transfer (PeT) deactivation from Mes2B moieties to BODIPY core and then quench the fluorescence. To implement this approach, an excellent solid-film sensing device was designed by doping BBDPB in polymethylmethacrylate (PMMA).
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC3MXht1SltLzL&md5=63e18d490d1ada0a328b36fe31b15764
    55. 55
      Li, Z.; Lv, X.; Chen, Y.; Fu, W.-F. Synthesis, structures and photophysical properties of boron–fluorine derivatives based on pyridine/1,8-naphthyridine. Dyes Pigm. 2014, 105, 157,  DOI: 10.1016/j.dyepig.2014.01.022
      [Crossref], [CAS], Google Scholar
      55
      Synthesis, structures and photophysical properties of boron-fluorine derivatives based on pyridine/1,8-naphthyridine
      Li, Zhensheng; Lv, Xiaojun; Chen, Yong; Fu, Wen-Fu
      Dyes and Pigments (2014), 105 (), 157-162CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
      Three boron-fluorine complexes B1-B3 contg. pyridine/1,8-naphthyridine were synthesized and structurally characterized. Compds. B1 and B2 exhibited strong fluorescence in soln. and solid state. The solvent-dependent luminous properties and large Stokes shift in soln. could be explained by intramol. charge transfer, which is confirmed by time-dependent d. functional theory calcn. The abs. quantum yield of B1 in powder form reached 0.48 because of inhibiting planar π···π stacking. Single-crystal x-ray diffraction analyses of B1 and B2 revealed that weak intermol. C-H···F and H···π interactions hinder further stacking of π···π dimers, consequently preventing aggregation-induced quenching. Complex B3, composed of boron-dipyrromethene and 1,8-naphthyridine fluorophore, had potential applications as a pH ratiometric fluorescent sensor.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2cXltFKqs7w%253D&md5=47e3e7ca47274444b744777d5d6accc4
    56. 56
      Zhang, S.; Liu, X.; Yuan, W.; Zheng, W.; Li, H.; Li, C.; Sun, Y.; Wang, Y.; Yang, Y.; Li, Y. New aryl substituted pyridylimidazo[1,2-a]pyridine-BODIPY conjugates: Emission color tuning from green to NIR. Dyes Pigm. 2018, 159, 406,  DOI: 10.1016/j.dyepig.2018.04.070
      [Crossref], [CAS], Google Scholar
      56
      New aryl substituted pyridylimidazo[1,2-a]pyridine-BODIPY conjugates: Emission color tuning from green to NIR
      Zhang, Shasha; Liu, Xiaojuan; Yuan, Wei; Zheng, Wei; Li, Hongkun; Li, Chenghui; Sun, Yufang; Wang, Yong; Yang, Yonggang; Li, Yahong; Liu, Wei
      Dyes and Pigments (2018), 159 (), 406-418CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
      Based on pyridylimidazo[1,2-a]pyridine-BODIPY compd. 1, we have prepd. three halogenated derivs. 2-4, and eight mono-/dual-arylated pyridylimidazo[1,2-a]pyridine-BODIPY conjugates 5-12. Single crystal X-ray diffraction analyses of 2, 4 and 6 revealed C-H···F interactions between mols. in the solid-state. Large effects of different electron-donating substituents (phenyl-, 4-(methoxy)phenyl-, 4-(diphenylamino)phenyl-, and 4-(dimethylamino)phenyl-) on absorption and fluorescence were detected, and the emission colors were successfully tuned from green to NIR. Upon addn. of H+, special colorimetric and spectroscopic variations for 4-dimethylaminophenyl- analogs 9 and 10 have been obsd. DFT and TDDFT calcns. for all new compds. have been carried out for deep understanding of their electronic transitions at ground states. The living cell imaging results of compd. 7 suggest its promising utility in biol. area.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXht1yisbnP&md5=6e7d46791bb60cbe22f24f210b677884
    57. 57
      Filatov, M. A.; Karuthedath, S.; Polestshuk, P. M.; Callaghan, S.; Flanagan, K. J.; Telitchko, M.; Wiesner, T.; Laquai, F.; Senge, M. O. Control of triplet state generation in heavy atom-free BODIPY-anthracene dyads by media polarity and structural factors. Phys. Chem. Chem. Phys. 2018, 20 (12), 8016,  DOI: 10.1039/C7CP08472B
      [Crossref], [PubMed], [CAS], Google Scholar
      57
      Control of triplet state generation in heavy atom-free BODIPY-anthracene dyads by media polarity and structural factors
      Filatov, Mikhail A.; Karuthedath, Safakath; Polestshuk, Pavel M.; Callaghan, Susan; Flanagan, Keith J.; Telitchko, Maxime; Wiesner, Thomas; Laquai, Frederic; Senge, Mathias O.
      Physical Chemistry Chemical Physics (2018), 20 (12), 8016-8031CODEN: PPCPFQ; ISSN:1463-9076. (Royal Society of Chemistry)
      A family of heavy atom-free BODIPY-anthracene dyads (BADs) exhibiting triplet excited state formation from charge-transfer states is reported. Four types of BODIPY scaffolds, different in the alkyl substitution pattern, and 4 anthracene derivs. were used to access BADs. Fluorescence and intersystem crossing (ISC) in these dyads depend on donor-acceptor couplings and can be accurately controlled by substitution or media polarity. Under conditions that do not allow charge transfer (CT), the dyads exhibit fluorescence with high quantum yields. Formation of charge-transfer states triggers ISC and the formation of long-lived triplet excited states in the dyads. The excited state properties were studied by steady-state techniques and ultrafast pump-probe spectroscopy to det. the parameters of the obsd. processes. Structural information for various BADs was derived from single crystal x-ray structure detns. alongside DFT mol. geometry optimization, revealing the effects of mutual orientation of subunits on the photophys. properties. The calcns. showed that alkyl substituents on the BODIPY destabilize CT states in the dyads, thus controlling the charge transfer between the subunits. The effect of the dyad structure on the ISC efficiency was considered at the M06-2X level of theory, and a correlation between mutual orientation of the subunits and the energy gap between singlet and triplet CT states was studied using a multiref. CASSCF method.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXisFOjuro%253D&md5=22c9b5c6affb1e7719aebbdc8f17480e
    58. 58
      Zhang, X. F.; Zhang, G. Q.; Zhu, J. Methylated Unsymmetric BODIPY Compounds: Synthesis, High Fluorescence Quantum Yield and Long Fluorescence Time. J. Fluoresc. 2019, 29 (2), 407,  DOI: 10.1007/s10895-019-02349-5
      [Crossref], [PubMed], [CAS], Google Scholar
      58
      Methylated Unsymmetric BODIPY Compounds: Synthesis, High Fluorescence Quantum Yield and Long Fluorescence Time
      Zhang, Xian-Fu; Zhang, George Q.; Zhu, Jiale
      Journal of Fluorescence (2019), 29 (2), 407-416CODEN: JOFLEN; ISSN:1053-0509. (Springer)
      We show that unsym. BODIPY compds. with one, two, and three Me groups can be synthesized easily and efficiently by the unsym. reaction method. Their steady state and time-resolved fluorescence properties are examd. in solvents of different polarity. These compds. show high fluorescence quantum yields (0.87 to 1.0), long fluorescence lifetimes (5.89 to 7.40 ns), and small Stokes shift (199 to 443 cm-1). The Me substitution exhibits influence on the UV-Vis absorption and fluorescence properties, such as the blue shift in emission and absorption spectra. It is the no. rather than the position of methyls that play major roles. Except for 3 M-BDP, the increase in the no. of methyls on BODIPY core leads to the increase in both fluorescence quantum yield and radiative rate const., but causes the decrease in fluorescence lifetime. H-bonding solvents increase both the fluorescence lifetime and quantum yields. The methylated BODIPYs show the ability to generate singlet oxygen (1Δg) which is evidenced by near-IR luminescence and DPBF chem. trapping techniques. The formation quantum yield of singlet oxygen (1Δg) for the compds. is up to 0.15 ± 0.05.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXns1Cls7s%253D&md5=96ac1d4f31df608c4c49edb99604bfe8
    59. 59
      Kasha, M. Characterization of electronic transitions in complex molecules. Discuss. Faraday Soc. 1950, 9, 14,  DOI: 10.1039/df9500900014
      [Crossref], Google Scholar
      There is no corresponding record for this reference.
    60. 60
      Cotter, L. F.; Brown, P. J.; Nelson, R. C.; Takematsu, K. Divergent Hammett Plots of the Ground- and Excited-State Proton Transfer Reactions of 7-Substituted-2-Naphthol Compounds. J. Phys. Chem. B 2019, 123 (19), 4301,  DOI: 10.1021/acs.jpcb.9b01295
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      60
      Divergent Hammett Plots of the Ground- and Excited-State Proton Transfer Reactions of 7-Substituted-2-Naphthol Compounds
      Cotter, Laura F.; Brown, Paige J.; Nelson, Ryan C.; Takematsu, Kana
      Journal of Physical Chemistry B (2019), 123 (19), 4301-4310CODEN: JPCBFK; ISSN:1520-5207. (American Chemical Society)
      The rational design of photoacids requires accessible predictive models of the electronic effect of functional groups on chem. templates of interest. Here, the effect of substituents on the photoacidity and excited-state proton transfer (PT) pathways of prototype 2-naphthol (2OH) at the sym. C7 position was investigated through photochem. and computational studies of 7-amino-2-naphthol (7N2OH) and 7-methoxy-2-naphthol (7OMe2OH). Time-resolved emission expts. of 7N2OH revealed that the presence of an electron-withdrawing vs. electron-donating group (EWG vs EDG, NH3+ vs NH2) led to a drastic decline in photoacidity: pKa* = 1.1 ± 0.2 vs 9.6 ± 0.2. Time-dependent d. functional theory calcns. with explicit water mols. confirmed that the excited neutral state (x = NH2) is greatly stabilized by water, with equation-of-motion coupled cluster singles and doubles calcns. supporting potential mixing between the La and Lb states. Similar suppression of photoacidity, however, was not obsd. for 7OMe2OH with EDG OCH3, pKa* = 2.7 ± 0.1. Hammett plots of the ground- and excited-state PT reactions of substituted 7-x-2OH compds. (x = CN, NH3+, H, CH3, OCH3, OH, and NH2) vs Hammett parameters σp showed breaks in the linearity between the EDG and EWG regions: ρ ∼ 0 vs 1.14 and ρ* ∼ 0 vs 3.86. The divergent acidic behavior most likely arises from different mixing mechanisms of the lowest Lb state with the La and possible Bb states upon substitution of naphthalene in water.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXot1Oqu70%253D&md5=a14ce3564a7406a1f4d507790b77c84c
    61. 61
      Reichardt, C. Solvatochromic Dyes as Solvent Polarity Indicators. Chem. Rev. 1994, 94 (8), 2319,  DOI: 10.1021/cr00032a005
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      61
      Solvatochromic Dyes as Solvent Polarity Indicators
      Reichardt, Christian
      Chemical Reviews (Washington, DC, United States) (1994), 94 (8), 2319-58CODEN: CHREAY; ISSN:0009-2665.
      This review with 345 refs. compiles pos. and neg. solvatochromic compds. which have been used to establish empirical scales of solvent polarity by means of UV/visible/near-IR spectroscopic measurements in soln. with particular emphasis on the ET(30) scale derived from neg. solvatochromic pyridinium N-phenolate betaine dyes. A discussion is presented on the concept of solvent polarity and how empirical parameters of solvent polarity can be derived and understood in the framework of linear free-energy relationships.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaK2cXntV2gtrY%253D&md5=8fd8a3f562211929e30191207fe97e33
    62. 62
      Nakanotani, H.; Higuchi, T.; Furukawa, T.; Masui, K.; Morimoto, K.; Numata, M.; Tanaka, H.; Sagara, Y.; Yasuda, T.; Adachi, C. High-efficiency organic light-emitting diodes with fluorescent emitters. Nat. Commun. 2014, 5, 4016,  DOI: 10.1038/ncomms5016
      [Crossref], [PubMed], [CAS], Google Scholar
      62
      High-efficiency organic light-emitting diodes with fluorescent emitters
      Nakanotani, Hajime; Higuchi, Takahiro; Furukawa, Taro; Masui, Kensuke; Morimoto, Kei; Numata, Masaki; Tanaka, Hiroyuki; Sagara, Yuta; Yasuda, Takuma; Adachi, Chihaya
      Nature Communications (2014), 5 (), 4016CODEN: NCAOBW; ISSN:2041-1723. (Nature Publishing Group)
      Fluorescence-based org. light-emitting diodes have continued to attract interest because of their long operational lifetimes, high color purity of electroluminescence and potential to be manufd. at low cost in next-generation full-color display and lighting applications. In fluorescent mols., however, the exciton prodn. efficiency is limited to 25% due to the deactivation of triplet excitons. Here we report fluorescence-based org. light-emitting diodes that realize external quantum efficiencies as high as 13.4-18% for blue, green, yellow and red emission, indicating that the exciton prodn. efficiency reached nearly 100%. The high performance is enabled by utilization of thermally activated delayed fluorescence mols. as assistant dopants that permit efficient transfer of all elec. generated singlet and triplet excitons from the assistant dopants to the fluorescent emitters. Org. light-emitting diodes employing this exciton harvesting process provide freedom for the selection of emitters from a wide variety of conventional fluorescent mols.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2cXhvF2murjK&md5=d88fbd541737c290739d25c324529ba6
    63. 63
      Hong, Y.; Lam, J. W.; Tang, B. Z. Aggregation-induced emission. Chem. Soc. Rev. 2011, 40 (11), 5361,  DOI: 10.1039/c1cs15113d
      [Crossref], [PubMed], [CAS], Google Scholar
      63
      Aggregation-induced emission
      Hong, Yuning; Lam, Jacky W. Y.; Tang, Ben Zhong
      Chemical Society Reviews (2011), 40 (11), 5361-5388CODEN: CSRVBR; ISSN:0306-0012. (Royal Society of Chemistry)
      A review. Luminogenic materials with aggregation-induced emission (AIE) attributes have attracted much interest since the debut of the AIE concept in 2001. In this crit. review, recent progress in the area of AIE research is summarized. Typical examples of AIE systems are discussed, from which their structure-property relationships are derived. Through mechanistic decipherment of the photophys. processes, structural design strategies for generating new AIE luminogens are developed. Technol., esp. optoelectronic and biol., applications of the AIE systems are exemplified to illustrate how the novel AIE effect can be utilized for high-tech innovations (183 refs.).
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC3MXhtlaiu7bE&md5=c2c6daf422ea27baec6dce8288e547ed
    64. 64
      Jones, G.; Jackson, W. R.; Choi, C. Y.; Bergmark, W. R. Solvent effects on emission yield and lifetime for coumarin laser dyes. Requirements for a rotatory decay mechanism. J. Phys. Chem. 1985, 89 (2), 294,  DOI: 10.1021/j100248a024
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      64
      Solvent effects on emission yield and lifetime for coumarin laser dyes. Requirements for a rotatory decay mechanism
      Jones, Guilford, II; Jackson, William R.; Choi, Chol Yoo; Bergmark, William R.
      Journal of Physical Chemistry (1985), 89 (2), 294-300CODEN: JPCHAX; ISSN:0022-3654.
      Photophys. parameters were detd. for coumarin laser dyes in a variety or org. solvents and in water and mixed media. The response of fluorescence emission yields and lifetimes to changes in solvent polarity was a sensitive function of coumarin substitution pattern. Most important were substituent influences which resulted in larger excited-state dipole moments (for the fluorescent state), in restrictions of rotatory motion for the amine group at the 7-position, and the delocalization of excitation energy away from the coumarin moiety. For dyes displaying sharp redns. in emission yield and lifetime with increased solvent polarity, protic media and particularly water were most effective in inhibiting fluorescence although D isotope effects (H2O/D2O) on photophys. parameters were minimal. The temp. dependence of emission yield and lifetime was measured for 2 solvent-sensitive dyes in MeCN and in a highly viscous solvent, glycerol. The quenching of coumarin fluorescence by O for dyes with lifetimes >2 ns was also obsd. The dominant photophys. features for coumarin dyes are discussed in terms of emission from an intramol. charge-transfer (ICT) excited state and an important nonradiative decay path involving rotation of the amine functionality (7-position) leading to a twisted intramol. CT state (TICT). This previously proposed nonradiative decay path is a subtle function of coumarin structure, solvent polarity and viscosity, and temp. and is most sensitive to substituent patterns whose localize excitation at the 7-amino group and which stabilize charge in the twisted zwitterionic (TICT) intermediate. The role of excited-state bond orders involving the rotating group in detg. the importance of interconversions of the type ICT → TICT is discussed.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADyaL2MXltlaqsw%253D%253D&md5=e6cba44606a2942d0ab52ed4a15f777a
    65. 65
      Kim, H. J.; Kim, S. K.; Godumala, M.; Yoon, J.; Kim, C. Y.; Jeong, J. E.; Woo, H. Y.; Kwon, J. H.; Cho, M. J.; Choi, D. H. Novel molecular triad exhibiting aggregation-induced emission and thermally activated fluorescence for efficient non-doped organic light-emitting diodes. Chem. Commun. 2019, 55 (64), 9475,  DOI: 10.1039/C9CC05391C
      [Crossref], [PubMed], [CAS], Google Scholar
      65
      Novel molecular triad exhibiting aggregation-induced emission and thermally activated fluorescence for efficient non-doped organic light-emitting diodes
      Kim, Hyung Jong; Kim, Seong Keun; Godumala, Mallesham; Yoon, Jiwon; Kim, Chae Yeong; Jeong, Ji-Eun; Woo, Han Young; Kwon, Jang Hyuk; Cho, Min Ju; Choi, Dong Hoon
      Chemical Communications (Cambridge, United Kingdom) (2019), 55 (64), 9475-9478CODEN: CHCOFS; ISSN:1359-7345. (Royal Society of Chemistry)
      A light-emitting mol. triad (BPCP-2CPC) with dual functionality was successfully synthesized and applied to soln.-processed non-doped org. light-emitting diodes. The BPCP-2CPC triad contains 9-phenyl-9H-carbazole units as a host moiety tethered to a green-emitting core (BPCP) through a cyclohexane unit and exhibits thermally activated delayed fluorescence (TADF) and aggregation-induced emission (AIE) characteristics simultaneously. The BPCP-2CPC-based non-doped TADF-OLED devices showed a high external quantum efficiency (EQE) of 13.4%.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtl2nsrvO&md5=3d984ee37faab64eb021cb9730e8fc13
    66. 66
      Feckova, M.; le Poul, P.; Guen, F. R.; Roisnel, T.; Pytela, O.; Klikar, M.; Bures, F.; Achelle, S. 2,4-Distyryl- and 2,4,6-Tristyrylpyrimidines: Synthesis and Photophysical Properties. J. Org. Chem. 2018, 83 (19), 11712,  DOI: 10.1021/acs.joc.8b01653
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      66
      2,4-Distyryl- and 2,4,6-Tristyrylpyrimidines: Synthesis and Photophysical Properties
      Feckova, Michaela; le Poul, Pascal; Guen, Francoise Robin-le; Roisnel, Thierry; Pytela, Oldrich; Klikar, Milan; Bures, Filip; Achelle, Sylvain
      Journal of Organic Chemistry (2018), 83 (19), 11712-11726CODEN: JOCEAH; ISSN:0022-3263. (American Chemical Society)
      The synthesis of a series of 20 new 2,4,6-tristyrylpyrimidines and three new 2,4-distyrylpyrimidines by means of combination of Knoevenagel condensation and Suzuki-Miyaura cross-coupling reaction is reported. This methodol. enables us to obtain chromophores with identical or different substituent on each arm. The photophys. properties of the compds. are described. Optical properties and time-dependent d. functional theory calcns. indicate that photophys. properties of target compds. are mainly affected by the nature of the electron-donating group in C4/C6 positions, except when the C2 substituent is a significantly stronger electron-donating group. However, the C2 substituent has a strong influence on emission quantum yield: addn. of a strong electron-donating group tends to decrease the fluorescence quantum yield, whereas a moderate electron-withdrawing group results in a significant increase of fluorescence quantum yield.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXhs1Chtr7J&md5=7ac142b9ae6e358f08ed53acf7a108bc
    67. 67
      Wen, W.; Shi, Z.-F.; Cao, X.-P.; Xu, N.-S. Triphenylethylene-based fluorophores: Facile preparation and full-color emission in both solution and solid states. Dyes Pigm. 2016, 132, 282,  DOI: 10.1016/j.dyepig.2016.04.014
      [Crossref], [CAS], Google Scholar
      67
      Triphenylethylene-based fluorophores: Facile preparation and full-color emission in both solution and solid states
      Wen, Wei; Shi, Zi-Fa; Cao, Xiao-Ping; Xu, Nian-Sheng
      Dyes and Pigments (2016), 132 (), 282-290CODEN: DYPIDX; ISSN:0143-7208. (Elsevier Ltd.)
      Triphenylethylene-based luminophoric mols. were efficiently synthesized. The substituent effect of the fluorophores on their photophys. properties was then studied. Consequently, longer conjugated system and larger mol. dipole of the donor-π-acceptor fluorophores could result in bathochromic shifts of UV-visible absorption and emission bands, so do the Stokes shifts. Esp., full-color fluorescent emissions in both soln. and solid states could be achieved by changing conjugation length and substituents with different electron-donating or accepting abilities in the triphenylethylene skeleton. The d. functional theory calcns. further demonstrated that with the increase of the electron-donating or accepting abilities of the substituents, the energy gaps of the fluorophores gradually decreased, which elucidated the substituent effect of the org. fluorophores on their photophys. properties.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC28XpslWls74%253D&md5=32842b1c74871b42addd8fbd0b54977e
    68. 68
      Hirai, H.; Nakajima, K.; Nakatsuka, S.; Shiren, K.; Ni, J.; Nomura, S.; Ikuta, T.; Hatakeyama, T. One-Step Borylation of 1,3-Diaryloxybenzenes Towards Efficient Materials for Organic Light-Emitting Diodes. Angew. Chem., Int. Ed. 2015, 54 (46), 13581,  DOI: 10.1002/anie.201506335
      [Crossref], [CAS], Google Scholar
      68
      One-Step Borylation of 1,3-Diaryloxybenzenes Towards Efficient Materials for Organic Light-Emitting Diodes
      Hirai, Hiroki; Nakajima, Kiichi; Nakatsuka, Soichiro; Shiren, Kazushi; Ni, Jingping; Nomura, Shintaro; Ikuta, Toshiaki; Hatakeyama, Takuji
      Angewandte Chemie, International Edition (2015), 54 (46), 13581-13585CODEN: ACIEF5; ISSN:1433-7851. (Wiley-VCH Verlag GmbH & Co. KGaA)
      The development of a 1-step borylation of 1,3-diaryloxybenzenes, yielding novel B-contg. polycyclic arom. compds., is reported. The resulting B-contg. compds. possess high singlet-triplet excitation energies of localized frontier MOs induced by B and O. Using these compds. as a host material, phosphorescent org. LEDs exhibiting high efficiency and adequate lifetimes were prepd. Using the present 1-step borylation, the synthesis of an efficient, thermally-activated delayed fluorescence emitter and B-fused benzo[6]helicene was accomplished. Crystallog. data are given.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC2MXhsFWrtrbI&md5=ab150773f2fa5e6d4273d8018e8d52fc
    69. 69
      Kondo, Y.; Yoshiura, K.; Kitera, S.; Nishi, H.; Oda, S.; Gotoh, H.; Sasada, Y.; Yanai, M.; Hatakeyama, T. Narrowband deep-blue organic light-emitting diode featuring an organoboron-based emitter. Nat. Photonics 2019, 13 (10), 678,  DOI: 10.1038/s41566-019-0476-5
      [Crossref], [CAS], Google Scholar
      69
      Narrowband deep-blue organic light-emitting diode featuring an organoboron-based emitter
      Kondo, Yasuhiro; Yoshiura, Kazuki; Kitera, Sayuri; Nishi, Hiroki; Oda, Susumu; Gotoh, Hajime; Sasada, Yasuyuki; Yanai, Motoki; Hatakeyama, Takuji
      Nature Photonics (2019), 13 (10), 678-682CODEN: NPAHBY; ISSN:1749-4885. (Nature Research)
      Luminescent materials that exhibit narrowband emission are vital for full-color displays. Here, we report a thermally activated delayed-fluorescence material that exhibits ultrapure blue emission with full-width at half-max. of just 14 nm. The emitter consists of five benzene rings connected by two boron and four nitrogen atoms and two diphenylamino substituents. The multiple resonance effect of the boron and nitrogen atoms induces significant localization of the highest occupied and lowest unoccupied MOs on different atoms to minimize not only the vibronic coupling between the ground state (S0) and the singlet excited state (S1) but also the energy gap between the S1 state and triplet excited state (T1). Org. light-emitting diode devices employing the emitter emit light at 469 nm with full-width at half-max. of 18 nm with an external quantum efficiency of 34.4% at the max. and 26.0% at 1,000 cd m-2.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtlOlsLjK&md5=7ccab1765bbb7ae0e3c9e7430ba2b5a8
    70. 70
      Madayanad Suresh, S.; Hall, D.; Beljonne, D.; Olivier, Y.; Zysman-Colman, E. Multiresonant Thermally Activated Delayed Fluorescence Emitters Based on Heteroatom-Doped Nanographenes: Recent Advances and Prospects for Organic Light-Emitting Diodes. Adv. Funct. Mater. 2020, 30 (33), 1908677,  DOI: 10.1002/adfm.201908677
      [Crossref], [CAS], Google Scholar
      70
      Multiresonant Thermally Activated Delayed Fluorescence Emitters Based on Heteroatom-Doped Nanographenes: Recent Advances and Prospects for Organic Light-Emitting Diodes
      Madayanad Suresh, Subeesh; Hall, David; Beljonne, David; Olivier, Yoann; Zysman-Colman, Eli
      Advanced Functional Materials (2020), 30 (33), 1908677CODEN: AFMDC6; ISSN:1616-301X. (Wiley-VCH Verlag GmbH & Co. KGaA)
      A review. Since the 1st report in 2015, multiresonant thermally activated delayed fluorescent (MR-TADF) compds., a subclass of TADF emitters based on a heteroatom-doped nanographene material, have come to the fore as attractive hosts as well as emitters for org. light-emitting diodes (OLEDs). MR-TADF compds. typically show very narrow-band emission, high luminescence quantum yields, and small ΔEST values, typically around 200 meV, coupled with high chem. and thermal stabilities. These materials properties have translated into some of the best reported deep-blue TADF OLEDs. Here, a detailed review of MR-TADF compds. and their derivs. reported so far is presented. This review comprehensively documents all MR-TADF compds., with a focus on the synthesis, optoelectronic behavior, and OLED performance. Computational approaches are surveyed to accurately model the excited state properties of these compds.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BB3cXhtVahtbjL&md5=ece5abf3f27c37c1ce143450c633a767
    71. 71
      Sanchez-Lengeling, B.; Aspuru-Guzik, A. Inverse molecular design using machine learning: Generative models for matter engineering. Science 2018, 361 (6400), 360,  DOI: 10.1126/science.aat2663
      [Crossref], [PubMed], [CAS], Google Scholar
      71
      Inverse molecular design using machine learning: Generative models for matter engineering
      Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alan
      Science (Washington, DC, United States) (2018), 361 (6400), 360-365CODEN: SCIEAS; ISSN:0036-8075. (American Association for the Advancement of Science)
      The discovery of new materials can bring enormous societal and technol. progress. In this context, exploring completely the large space of potential materials is computationally intractable. Here, we review methods for achieving inverse design, which aims to discover tailored materials from the starting point of a particular desired functionality. Recent advances from the rapidly growing field of artificial intelligence, mostly from the subfield of machine learning, have resulted in a fertile exchange of ideas, where approaches to inverse mol. design are being proposed and employed at a rapid pace. Among these, deep generative models have been applied to numerous classes of materials: rational design of prospective drugs, synthetic routes to org. compds., and optimization of photovoltaics and redox flow batteries, as well as a variety of other solid-state materials.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1cXhtlyitr3L&md5=779c4a42ba1e84d99d13ad1b32b9529a
    72. 72
      Popova, M.; Isayev, O.; Tropsha, A. Deep reinforcement learning for de novo drug design. Sci. Adv. 2018, 4 (7), eaap7885,  DOI: 10.1126/sciadv.aap7885
      [Crossref], [PubMed], Google Scholar
      There is no corresponding record for this reference.
    73. 73
      Lim, J.; Ryu, S.; Kim, J. W.; Kim, W. Y. Molecular generative model based on conditional variational autoencoder for de novo molecular design. J. Cheminf. 2018, 10 (1), 31,  DOI: 10.1186/s13321-018-0286-7
      [Crossref], [CAS], Google Scholar
      73
      Molecular generative model based on conditional variational autoencoder for de novo molecular design
      Lim, Jaechang; Ryu, Seongok; Kim, Jin Woo; Kim, Woo Youn
      Journal of Cheminformatics (2018), 10 (), 31/1-31/9CODEN: JCOHB3; ISSN:1758-2946. (Chemistry Central Ltd.)
      We propose a mol. generative model based on the conditional variational autoencoder for de novo mol. design. It is specialized to control multiple mol. properties simultaneously by imposing them on a latent space. As a proof of concept, we demonstrate that it can be used to generate drug-like mols. with five target properties. We were also able to adjust a single property without changing the others and to manipulate it beyond the range of the dataset.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXmtFWhtrw%253D&md5=8a1262077f9d6ffa5ec0385ed1a69f6f
    74. 74
      Elton, D. C.; Boukouvalas, Z.; Fuge, M. D.; Chung, P. W. Deep learning for molecular design—a review of the state of the art. Mol. Syst. Des. Eng. 2019, 4 (4), 828,  DOI: 10.1039/C9ME00039A
      [Crossref], [CAS], Google Scholar
      74
      Deep learning for molecular design-a review of the state of the art
      Elton, Daniel C.; Boukouvalas, Zois; Fuge, Mark D.; Chung, Peter W.
      Molecular Systems Design & Engineering (2019), 4 (4), 828-849CODEN: MSDEBG; ISSN:2058-9689. (Royal Society of Chemistry)
      In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of mols.-in our review we found 45 papers on the subject published in the past two years. These works point to a future where such systems will be used to generate lead mols., greatly reducing resources spent downstream synthesizing and characterizing bad leads in the lab. In this review we survey the increasingly complex landscape of models and representation schemes that have been proposed. The four classes of techniques we describe are recursive neural networks, autoencoders, generative adversarial networks, and reinforcement learning. After first discussing some of the math. fundamentals of each technique, we draw high level connections and comparisons with other techniques and expose the pros and cons of each. Several important high level themes emerge as a result of this work, including the shift away from the SMILES string representation of mols. towards more sophisticated representations such as graph grammars and 3D representations, the importance of reward function design, the need for better stds. for benchmarking and testing, and the benefits of adversarial training and reinforcement learning over max. likelihood based training.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXhtVWktLjN&md5=a0925fdace3a12af31b2f6fc1edef89b
    75. 75
      Hong, S. H.; Ryu, S.; Lim, J.; Kim, W. Y. Molecular Generative Model Based on an Adversarially Regularized Autoencoder. J. Chem. Inf. Model. 2020, 60 (1), 29,  DOI: 10.1021/acs.jcim.9b00694
      [ACS Full Text ACS Full Text], [CAS], Google Scholar
      75
      Molecular Generative Model Based on an Adversarially Regularized Autoencoder
      Hong, Seung Hwan; Ryu, Seongok; Lim, Jaechang; Kim, Woo Youn
      Journal of Chemical Information and Modeling (2020), 60 (1), 29-36CODEN: JCISD8; ISSN:1549-9596. (American Chemical Society)
      Deep generative models are attracting great attention as a new promising approach for mol. design. A variety of models reported so far are based on either a variational autoencoder (VAE) or a generative adversarial network (GAN), but they have limitations such as low validity and uniqueness. Here, we propose a new type of model based on an adversarially regularized autoencoder (ARAE). It basically uses latent variables like VAE, but the distribution of the latent variables is estd. by adversarial training like in GAN. The latter is intended to avoid both the insufficiently flexible approxn. of posterior distribution in VAE and the difficulty in handling discrete variables in GAN. Our benchmark study showed that ARAE indeed outperformed conventional models in terms of validity, uniqueness, and novelty per generated mol. We also demonstrated a successful conditional generation of drug-like mols. with ARAE for the control of both cases of single and multiple properties. As a potential real-world application, we could generate epidermal growth factor receptor inhibitors sharing the scaffolds of known active mols. while satisfying drug-like conditions simultaneously.
      >> More from SciFinder ®
      https://chemport.cas.org/services/resolver?origin=ACS&resolution=options&coi=1%3ACAS%3A528%3ADC%252BC1MXitleru7rF&md5=5bbeae953836253deb3e004e7b779976
    76. 76
      Krenn, M.; Häse, F.; Nigam, A.; Friederich, P.; Aspuru-Guzik, A. Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation. Mach. Learn.: Sci. Technol. 2020, 1 (4), 045024,  DOI: 10.1088/2632-2153/aba947
      [Crossref], Google Scholar
      There is no corresponding record for this reference.
    77. 77
      Joung, J. F.; Han, M.; Park, S. Deep4Chem, 2020; http://deep4chem.korea.ac.kr/.
      Google Scholar
      There is no corresponding record for this reference.

  • Supporting Information

    Supporting Information

    ARTICLE SECTIONS
    Jump To

    The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/jacsau.1c00035.

    • The details of our deep learning model, prediction by our deep learning model, and synthetic procedure of compound 1 (PDF)


    Terms & Conditions

    Most electronic Supporting Information files are available without a subscription to ACS Web Editions. Such files may be downloaded by article for research use (if there is a public use license linked to the relevant article, that license may permit other uses). Permission may be obtained from ACS for other uses through requests via the RightsLink permission system: http://pubs.acs.org/page/copyright/permissions.html.

PDF [ 4MB]

Pair your accounts.

Export articles to Mendeley

Get article recommendations from ACS based on references in your Mendeley library.

Pair your accounts.

Export articles to Mendeley

Get article recommendations from ACS based on references in your Mendeley library.

You’ve supercharged your research process with ACS and Mendeley!

STEP 1:
Click to create an ACS ID

Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

MENDELEY PAIRING EXPIRED
Your Mendeley pairing has expired. Please reconnect