ACS Publications. Most Trusted. Most Cited. Most Read
My Activity
CONTENT TYPES

Learning Matter: Materials Design with Machine Learning and Atomistic Simulations

Cite this: Acc. Mater. Res. 2022, 3, 3, 343–357
Publication Date (Web):February 21, 2022
https://doi.org/10.1021/accountsmr.1c00238
Copyright © 2022 Accounts of Materials Research. Co-published by ShanghaiTech University and American Chemical Society. All rights reserved.

    Article Views

    7048

    Altmetric

    -

    Citations

    LEARN ABOUT THESE METRICS
    Other access options

    Abstract

    Abstract Image
    Conspectus

    Designing new materials is vital for addressing pressing societal challenges in health, energy, and sustainability. The combination of physicochemical laws and empirical trial and error has long guided material design, but this approach is limited by the cost of experiments and the difficulty of deriving complex guiding principles. The space of hypothetical materials to be considered is incredibly large, and only a small fraction of possible compounds can ever be tested experimentally. The computational techniques of atomistic simulation and machine learning (ML) offer an avenue to rapidly invent new materials and navigate this enormous space. Together, they can be used to infer complex design principles and identify high-quality candidates more rapidly than trial-and-error experimentation. In this Account, we review our group’s recent contributions to simulation and ML for materials design. We begin by discussing the numerical representation of materials for use in ML. Representations can be produced through deterministic algorithms, learnable encodings, or physics-based methods and lead to vector, graph, and matrix outputs. We describe how these different approaches offer distinct material- and application-specific advantages. We provide demonstrations from our own work on small-molecule drugs, macromolecules, dyes, electrolytes, and zeolites. In several cases, we show how the appropriate representation led to guiding principles that facilitated experimental materials design. Next, we highlight the development of ML methods for enhancing atomistic simulation. These advances help to improve simulation accuracy and expand the time and length scales that can be explored. They include differentiable atomistic simulations in which ensemble-averaged quantities are differentiated with respect to system parameters, and novel autoregressive methods for enhanced sampling of challenging physical distributions. Other developments include learnable coarse-grained models, which can accelerate molecular dynamics while minimizing the loss of all-atom information, and ML interatomic potentials, which can be trained on maximally informative quantum chemistry data through active learning and adversarial uncertainty attacks. Next, we show how these combined computational advances have enabled high-throughput virtual screening. This has led to the discovery of low-cost organic structure-directing agents for zeolite synthesis, polymer electrolytes, and efficient photoswitches for targeted medicine. We conclude by discussing the limitations of ML and simulation. These include the large data requirements and limited chemical transferability of the former and the speed–accuracy trade-offs of the latter. We predict that advancements in quantum chemistry will further accelerate simulations, while the incorporation of physical principles will improve the reliability of ML.

    Read this article

    To access this article, please review the available access options below.

    Get instant access

    Purchase Access

    Read this article for 48 hours. Check out below using your ACS ID or as a guest.

    Recommended

    Access through Your Institution

    You may have access to this article through your institution.

    Your institution does not have access to this content. You can change your affiliated institution below.

    Cited By

    This article is cited by 16 publications.

    1. Richard J. Sadus. Molecular Simulation Meets Machine Learning. Journal of Chemical & Engineering Data 2024, 69 (1) , 3-11. https://doi.org/10.1021/acs.jced.3c00553
    2. Reisel Millan, Estefanía Bello-Jurado, Manuel Moliner, Mercedes Boronat, Rafael Gomez-Bombarelli. Effect of Framework Composition and NH3 on the Diffusion of Cu+ in Cu-CHA Catalysts Predicted by Machine-Learning Accelerated Molecular Dynamics. ACS Central Science 2023, 9 (11) , 2044-2056. https://doi.org/10.1021/acscentsci.3c00870
    3. Zixin Zhuang, Amanda S. Barnard. Structure-Free Mendeleev Encodings of Material Compounds for Machine Learning. Chemistry of Materials 2023, 35 (21) , 9325-9338. https://doi.org/10.1021/acs.chemmater.3c02134
    4. Simon Axelrod, Eugene Shakhnovich, Rafael Gómez-Bombarelli. Mapping the Space of Photoswitchable Ligands and Photodruggable Proteins with Computational Modeling. Journal of Chemical Information and Modeling 2023, 63 (18) , 5794-5802. https://doi.org/10.1021/acs.jcim.3c00484
    5. Johannes C. B. Dietschreit, Dennis J. Diestler, Rafael Gómez-Bombarelli. Entropy and Energy Profiles of Chemical Reactions. Journal of Chemical Theory and Computation 2023, 19 (16) , 5369-5379. https://doi.org/10.1021/acs.jctc.3c00448
    6. 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
    7. Arash Khajeh, Daniel Schweigert, Steven B. Torrisi, Linda Hung, Brian D. Storey, Ha-Kyung Kwon. Early Prediction of Ion Transport Properties in Solid Polymer Electrolytes Using Machine Learning and System Behavior-Based Descriptors of Molecular Dynamics Simulations. Macromolecules 2023, 56 (13) , 4787-4799. https://doi.org/10.1021/acs.macromol.3c00416
    8. Zhiming Zhang, Hongjian Tang, Mao Wang, Bohui Lyu, Zhongyi Jiang, Jianwen Jiang. Metal–Organic Frameworks for Water Harvesting: Machine Learning-Based Prediction and Rapid Screening. ACS Sustainable Chemistry & Engineering 2023, 11 (21) , 8148-8160. https://doi.org/10.1021/acssuschemeng.3c01233
    9. Pengyun Chen, Yuqiao Zhou, Jin He, Wei Jiang, Junhao Li, Haiyong Ni, Qiuhong Zhang, Litian Lin. On the Crystal Chemistry of RE2Si2O7: Revisited Structures, Group–Subgroup Relationship, and Insights of Ce3+-Activated Radioluminescence. Chemistry of Materials 2023, 35 (6) , 2635-2646. https://doi.org/10.1021/acs.chemmater.3c00245
    10. Eleonora Ricci, Niki Vergadou. Integrating Machine Learning in the Coarse-Grained Molecular Simulation of Polymers. The Journal of Physical Chemistry B 2023, 127 (11) , 2302-2322. https://doi.org/10.1021/acs.jpcb.2c06354
    11. Simon Axelrod, Eugene Shakhnovich, Rafael Gómez-Bombarelli. Thermal Half-Lives of Azobenzene Derivatives: Virtual Screening Based on Intersystem Crossing Using a Machine Learning Potential. ACS Central Science 2023, 9 (2) , 166-176. https://doi.org/10.1021/acscentsci.2c00897
    12. Gavin Winter, Rafael Gómez-Bombarelli. Simulations with machine learning potentials identify the ion conduction mechanism mediating non-Arrhenius behavior in LGPS. Journal of Physics: Energy 2023, 5 (2) , 024004. https://doi.org/10.1088/2515-7655/acbbef
    13. 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, 75 , 2209953. https://doi.org/10.1002/adma.202209953
    14. Kamrun N. Keya, Amara Arshad, Sara A. Tolba, Wenjian Nie, Amirhadi Alesadi, Luis Alberto Ruiz Pestana, Wenjie Xia. Machine learning in materials modeling and design. 2023, 203-236. https://doi.org/10.1016/B978-0-12-823021-3.00010-5
    15. Jiayu Peng, Daniel Schwalbe-Koda, Karthik Akkiraju, Tian Xie, Livia Giordano, Yang Yu, C. John Eom, Jaclyn R. Lunger, Daniel J. Zheng, Reshma R. Rao, Sokseiha Muy, Jeffrey C. Grossman, Karsten Reuter, Rafael Gómez-Bombarelli, Yang Shao-Horn. Human- and machine-centred designs of molecules and materials for sustainability and decarbonization. Nature Reviews Materials 2022, 7 (12) , 991-1009. https://doi.org/10.1038/s41578-022-00466-5
    16. Ping Yang, E. Adrian Henle, Xiaoli Z. Fern, Cory M. Simon. Classifying the toxicity of pesticides to honey bees via support vector machines with random walk graph kernels. The Journal of Chemical Physics 2022, 157 (3) , 034102. https://doi.org/10.1063/5.0090573

    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