Cart
Article
General Melting Point Prediction Based on a Diverse Compound Data Set and Artificial Neural Networks
Full Text HTML
Hi-Res PDFPurchase the full-text
- PDF/HTML,
figures/images,
references and tables,
(where available)
Section:Abstract
We report the development of a robust and general model for the prediction of melting points. It is based on a diverse data set of 4173 compounds and employs a large number of 2D and 3D descriptors to capture molecular physicochemical and other graph-based properties. Dimensionality reduction is performed by principal component analysis, while a fully connected feed-forward back-propagation artificial neural network is employed for model generation. The melting point is a fundamental physicochemical property of a molecule that is controlled by both single-molecule properties and intermolecular interactions due to packing in the solid state. Thus, it is difficult to predict, and previously only melting point models for clearly defined and smaller compound sets have been developed. Here we derive the first general model that covers a comparatively large and relevant part of organic chemical space. The final model is based on 2D descriptors, which are found to contain more relevant information than the 3D descriptors calculated. Internal random validation of the model achieves a correlation coefficient of R2 = 0.661 with an average absolute error of 37.6 °C. The model is internally consistent with a correlation coefficient of the test set of Q2 = 0.658 (average absolute error 38.2 °C) and a correlation coefficient of the internal validation set of Q2 = 0.645 (average absolute error 39.8 °C). Additional validation was performed on an external drug data set consisting of 277 compounds. On this external data set a correlation coefficient of Q2 = 0.662 (average absolute error 32.6 °C) was achieved, showing ability of the model to generalize. Compared to an earlier model for the prediction of melting points of druglike compounds our model exhibits slightly improved performance, despite the much larger chemical space covered. The remaining model error is due to molecular properties that are not captured using single-molecule based descriptors, namely both inter- and intramolecular interactions and crystal packing, for which examples of and reasons for outliers are given.
Citing Articles
Citation data is made available by participants in CrossRef's Cited-by Linking service. For a more comprehensive list of citations to this article, users are encouraged to perform a search in SciFinder.
This article has been cited by 12 ACS Journal articles (5 most recent appear below).
Solution-Processable Low-Molecular Weight Extended Arylacetylenes: Versatile p-Type Semiconductors for Field-Effect Transistors and Bulk Heterojunction Solar Cells
Fabio Silvestri, Assunta Marrocchi, Mirko Seri, Choongik Kim, Tobin J. Marks, Antonio Facchetti and Aldo TaticchiJournal of the American Chemical Society2010 132 (17), 6108-6123Solution-Processable Low-Molecular Weight Extended Arylacetylenes: Versatile p-Type Semiconductors for Field-Effect Transistors and Bulk Heterojunction Solar Cells
Fabio Silvestri, Assunta Marrocchi, Mirko Seri, Choongik Kim, Tobin J. Marks, Antonio Facchetti and Aldo TaticchiJournal of the American Chemical Society2010 132 (17), 6108-6123We report the synthesis and characterization of a series of five extended arylacetylenes, 9,10-bis-{[m,p-bis(hexyloxy)phenyl]ethynyl}-anthracene (A-P6t, 1), 9,10-bis-[(p-{[m,p-bis(hexyloxy) phenyl]ethynyl}phenyl)ethynyl]-anthracene (PA-P6t, 2), 4,7-bis-{[...
Escape from Flatland: Increasing Saturation as an Approach to Improving Clinical Success
Frank Lovering, Jack Bikker and Christine HumbletJournal of Medicinal Chemistry2009 52 (21), 6752-6756Escape from Flatland: Increasing Saturation as an Approach to Improving Clinical Success
Frank Lovering, Jack Bikker and Christine HumbletJournal of Medicinal Chemistry2009 52 (21), 6752-6756The medicinal chemistry community has become increasingly aware of the value of tracking calculated physical properties such as molecular weight, topological polar surface area, rotatable bonds, and hydrogen bond donors and acceptors. We hypothesized that ...
Alpha Shapes Applied to Molecular Shape Characterization Exhibit Novel Properties Compared to Established Shape Descriptors
J. Anthony Wilson, Andreas Bender, Taner Kaya and Paul A. ClemonsJournal of Chemical Information and Modeling2009 49 (10), 2231-2241Alpha Shapes Applied to Molecular Shape Characterization Exhibit Novel Properties Compared to Established Shape Descriptors
J. Anthony Wilson, Andreas Bender, Taner Kaya and Paul A. ClemonsJournal of Chemical Information and Modeling2009 49 (10), 2231-2241Despite considerable efforts, description of molecular shape is still largely an unresolved problem. Given the importance of molecular shape in the description of spatial interactions in crystals or ligand-target complexes, this is not a satisfying state. ...
Molecular Characteristics for Solid-State Limited Solubility
Carola M. Wassvik, Anders G. Holmén, Rieke Draheim, Per Artursson and Christel A. S. BergströmJournal of Medicinal Chemistry2008 51 (10), 3035-3039Molecular Characteristics for Solid-State Limited Solubility
Carola M. Wassvik, Anders G. Holmén, Rieke Draheim, Per Artursson and Christel A. S. BergströmJournal of Medicinal Chemistry2008 51 (10), 3035-3039Solubility and solid-state characteristics were determined and multivariate data analysis was used to deduce structural features important for solid-state limited solubility of marketed drugs. Molecules with extended ring structures and large conjugated ...
Scores of Extended Connectivity Fingerprint as Descriptors in QSPR Study of Melting Point and Aqueous Solubility
Diansong Zhou, Yun Alelyunas and Ruifeng LiuJournal of Chemical Information and Modeling2008 48 (5), 981-987Scores of Extended Connectivity Fingerprint as Descriptors in QSPR Study of Melting Point and Aqueous Solubility
Diansong Zhou, Yun Alelyunas and Ruifeng LiuJournal of Chemical Information and Modeling2008 48 (5), 981-987QSPR studies, using scores of SciTegic’s extended connectivity fingerprint as raw descriptors, were extended to the prediction of melting points and aqueous solubility of organic compounds. Robust partial least-squares models were developed that perform ...
Tools
-
Add to Favorites
-
Download Citation
-
Email a Colleague -
Permalink
Order Reprints
Rights & Permissions
Citation Alerts
History
- Published In Issue May 23, 2005
- Received January 12, 2005
ACS
Network
Facebook
Tweet This
CiteULike
Newsvine
Digg This
Delicious
