Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
Open accessThe DOI matches its Crossref record; 65 of the 65 references it cites were found in a registry or an index.
Abstract
Graph networks are a new machine learning (ML) paradigm that supports both relational reasoning and combinatorial generalization. Here, we develop universal MatErials Graph Network (MEGNet) models for accurate property prediction in both molecules and crystals. We demonstrate that the MEGNet models outperform prior ML models such as the SchNet in 11 out of 13 properties of the QM9 molecule data set. Similarly, we show that MEGNet models trained on ∼60 000 crystals in the Materials Project substantially outperform prior ML models in the prediction of the formation energies, band gaps, and elastic moduli of crystals, achieving better than density functional theory accuracy over a much larger data set. We present two new strategies to address data limitations common in materials science and chemistry. First, we demonstrate a physically intuitive approach to unify four separate molecular MEGNet models for the internal energy at 0 K and room temperature, enthalpy, and Gibbs free energy into a single free energy MEGNet model by incorporating the temperature, pressure, and entropy as global state inputs. Second, we show that the learned element embeddings in MEGNet models encode periodic chemical trends and can be transfer-learned from a property model trained on a larger data set (formation energies) to improve property models with smaller amounts of data (band gaps and elastic moduli).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In this regard, the knowledge shared in interdependent properties of the same material or in the same property of similar concrete types can be transferred to accelerate the training process and improve the accuracy performance of ML models, even with relatively small amounts of available data 143,144 .”
From Machine learning in concrete science: applications, challenges, and best practices (2022) · cites this paper as [143]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This structural model trained on the Materials Project data obtains state-of-the-art results of a mean absolute error of 21 meV atom−1.”
From Scaling deep learning for materials discovery (2023) · cites this paper as [37]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
(2008) · Journal of Machine Learning Research · Cited by 33,051
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
Jain, A., Ong, S. P., Hautier, G., Chen, W., Richards, W. D., Dacek, S., Cholia, S., Gunter, D., Skinner, D., Ceder, G., et al. (2013) · APL Materials · doi:10.1063/1.4812323 · Cited by 13,094
Self-citationTensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,081
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
Behler, J., & Parrinello, M. (2007) · Physical Review Letters · doi:10.1103/physrevlett.98.146401 · Cited by 5,010
Machine learning for molecular and materials science
Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O., & Walsh, A. (2018) · Nature · doi:10.1038/s41586-018-0337-2 · Cited by 4,968
Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis
Ong, S. P., Richards, W. D., Jain, A., Hautier, G., Kocher, M., Cholia, S., Gunter, D., Chevrier, V. L., Persson, K. A., & Ceder, G. (2013) · Computational Materials Science · doi:10.1016/j.commatsci.2012.10.028 · Cited by 4,534
Self-citationNeural Message Passing for Quantum Chemistry
Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., & Dahl, G. E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.01212 · Cited by 3,440
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
Bartók, A. P., Payne, M. C., Kondor, R., & Csányi, G. (2010) · Physical Review Letters · doi:10.1103/physrevlett.104.136403 · Cited by 3,242
Xie, T., & Grossman, J. C. (2018) · Physical Review Letters · doi:10.1103/physrevlett.120.145301 · Cited by 2,828
(2013) · Springer eBooks · Cited by 2,625
Saal, J. E., Kirklin, S., Aykol, M., Meredig, B., & Wolverton, C. (2013) · JOM · doi:10.1007/s11837-013-0755-4 · Cited by 2,584
The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies
Kirklin, S., Saal, J. E., Meredig, B., Thompson, A., Doak, J. W., Aykol, M., Rühl, S., & Wolverton, C. (2015) · npj Computational Materials · doi:10.1038/npjcompumats.2015.10 · Cited by 2,378
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
Rupp, M., Tkatchenko, A., Müller, K.-R., & von Lilienfeld, O. A. (2012) · Physical Review Letters · doi:10.1103/physrevlett.108.058301 · Cited by 2,312 · cited 1×
“se the ˚s to be multi-layer perceptrons with two hidden layers (Equation 7), given their ability to be universal approximators for non-linear functions.40 ˚(x) = W 3((W 2((W 1x+ b 1)) + b 2)) + b 3 (7) where is the modied softplus function10 acting as nonlinear activator, Ws are the kernel weights and bs are the biase…”
BackgroundSchNet – A deep learning architecture for molecules and materials
Schütt, K. T., Sauceda, H. E., Kindermans, P.-J., Tkatchenko, A., & Müller, K.-R. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5019779 · Cited by 2,217
Quantum chemistry structures and properties of 134 kilo molecules
Ramakrishnan, R., Dral, P. O., Rupp, M., & von Lilienfeld, O. A. (2014) · Scientific Data · doi:10.1038/sdata.2014.22 · Cited by 1,966
Machine learning in materials informatics: recent applications and prospects
Ramprasad, R., Batra, R., Pilania, G., Mannodi-Kanakkithodi, A., & Kim, C. (2017) · npj Computational Materials · doi:10.1038/s41524-017-0056-5 · Cited by 1,945
A general-purpose machine learning framework for predicting properties of inorganic materials
Ward, L., Agrawal, A., Choudhary, A., & Wolverton, C. (2016) · npj Computational Materials · doi:10.1038/npjcompumats.2016.28 · Cited by 1,831
Molecular graph convolutions: moving beyond fingerprints
Kearnes, S., McCloskey, K., Berndl, M., Pande, V., & Riley, P. (2016) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-016-9938-8 · Cited by 1,631
AFLOW: An automatic framework for high-throughput materials discovery
Curtarolo, S., Setyawan, W., Hart, G. L. W., Jahnatek, M., Chepulskii, R. V., Taylor, R. H., Wang, S., Xue, J., Yang, K., Levy, O., et al. (2012) · Computational Materials Science · doi:10.1016/j.commatsci.2012.02.005 · Cited by 1,531
Quantum-chemical insights from deep tensor neural networks
Schütt, K. T., Arbabzadah, F., Chmiela, S., Müller, K. R., & Tkatchenko, A. (2017) · Nature Communications · doi:10.1038/ncomms13890 · Cited by 1,445
Thompson, A. P., Swiler, L. P., Trott, C. R., Foiles, S. M., & Tucker, G. J. (2015) · Journal of Computational Physics · doi:10.1016/j.jcp.2014.12.018 · Cited by 1,130
A high-throughput infrastructure for density functional theory calculations
Jain, A., Hautier, G., Moore, C. J., Ping Ong, S., Fischer, C. C., Mueller, T., Persson, K. A., & Ceder, G. (2011) · Computational Materials Science · doi:10.1016/j.commatsci.2011.02.023 · Cited by 1,041
Charting the complete elastic properties of inorganic crystalline compounds
de Jong, M., Chen, W., Angsten, T., Jain, A., Notestine, R., Gamst, A., Sluiter, M., Krishna Ande, C., van der Zwaag, S., Plata, J. J., et al. (2015) · Scientific Data · doi:10.1038/sdata.2015.9 · Cited by 1,005
Accelerating materials property predictions using machine learning
Pilania, G., Wang, C., Jiang, X., Rajasekaran, S., & Ramprasad, R. (2013) · Scientific Reports · doi:10.1038/srep02810 · Cited by 853
Low Data Drug Discovery with One-Shot Learning
Altae-Tran, H., Ramsundar, B., Pappu, A. S., & Pande, V. (2017) · ACS Central Science · doi:10.1021/acscentsci.6b00367 · Cited by 799
Machine learning unifies the modeling of materials and molecules
Bartók, A. P., De, S., Poelking, C., Bernstein, N., Kermode, J. R., Csányi, G., & Ceriotti, M. (2017) · Science Advances · doi:10.1126/sciadv.1701816 · Cited by 764
Universal fragment descriptors for predicting properties of inorganic crystals
Isayev, O., Oses, C., Toher, C., Gossett, E., Curtarolo, S., & Tropsha, A. (2017) · Nature Communications · doi:10.1038/ncomms15679 · Cited by 651
Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error
Faber, F. A., Hutchison, L., Huang, B., Gilmer, J., Schoenholz, S. S., Dahl, G. E., Vinyals, O., Kearnes, S., Riley, P. F., & von Lilienfeld, O. A. (2017) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.7b00577 · Cited by 651
Hautier, G., Fischer, C. C., Jain, A., Mueller, T., & Ceder, G. (2010) · Chemistry of Materials · doi:10.1021/cm100795d · Cited by 580
Ong, S. P., Cholia, S., Jain, A., Brafman, M., Gunter, D., Ceder, G., & Persson, K. A. (2015) · Computational Materials Science · doi:10.1016/j.commatsci.2014.10.037 · Cited by 480
Self-citationConvolutional embedding of attributed molecular graphs for physical property prediction
Coley, C. W., Barzilay, R., Green, W. H., Jaakkola, T. S., & Jensen, K. F. (2017) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6b00601 · Cited by 470 · cited 1×
“30,31 Recently, Faber et al. 32 have benchmarked different features in combination with models extensively on the QM9 data set.”
MethodData Mined Ionic Substitutions for the Discovery of New Compounds
Hautier, G., Fischer, C., Ehrlacher, V., Jain, A., & Ceder, G. (2011) · Inorganic Chemistry · doi:10.1021/ic102031h · Cited by 394
Gated Graph Sequence Neural Networks
Li, Y., Tarlow, D., Brockschmidt, M., & Zemel, R. S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.05493 · Cited by 362
Resolution of the Band Gap Prediction Problem for Materials Design
Crowley, J. M., Tahir-Kheli, J., & Goddard, W. A. (2016) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.5b02870 · Cited by 349
Artrith, N., Urban, A., & Ceder, G. (2017) · Physical Review B · doi:10.1103/physrevb.96.014112 · Cited by 340
Machine Learning Directed Search for Ultraincompressible, Superhard Materials
Mansouri Tehrani, A., Oliynyk, A. O., Parry, M., Rizvi, Z., Couper, S., Lin, F., Miyagi, L., Sparks, T. D., & Brgoch, J. (2018) · Journal of the American Chemical Society · doi:10.1021/jacs.8b02717 · Cited by 317
Machine Learning in Materials Science: Recent Progress and Emerging Applications
Mueller, T., Kusne, A. G., & Ramprasad, R. (2016) · Reviews in Computational Chemistry · doi:10.1002/9781119148739.ch4 · Cited by 295
Deep neural networks for accurate predictions of crystal stability
Ye, W., Chen, C., Wang, Z., Chu, I.-H., & Ong, S. P. (2018) · Nature Communications · doi:10.1038/s41467-018-06322-x · Cited by 263
Self-citationHautier, G., Jain, A., Chen, H., Moore, C., Ong, S. P., & Ceder, G. (2011) · Journal of Materials Chemistry · doi:10.1039/c1jm12216a · Cited by 231
Self-citationChemical graph theory, introduction and fundamentals
M, R. B. (1993) · Journal of Molecular Structure: THEOCHEM · doi:10.1016/0166-1280(93)80032-u · Cited by 219
Data-Driven Learning of Total and Local Energies in Elemental Boron
Deringer, V. L., Pickard, C. J., & Csányi, G. (2018) · Physical Review Letters · doi:10.1103/physrevlett.120.156001 · Cited by 212
Chan, E. M. (2015) · Chemical Society Reviews · doi:10.1039/c4cs00205a · Cited by 201
Learning atoms for materials discovery
Zhou, Q., Tang, P., Liu, S., Pan, J., Yan, Q., & Zhang, S.-C. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1801181115 · Cited by 200
Choudhary, K., DeCost, B., & Tavazza, F. (2018) · Physical Review Materials · doi:10.1103/physrevmaterials.2.083801 · Cited by 177
Accurate force field for molybdenum by machine learning large materials data
Chen, C., Deng, Z., Tran, R., Tang, H., Chu, I.-H., & Ong, S. P. (2017) · Physical Review Materials · doi:10.1103/physrevmaterials.1.043603 · Cited by 164
Self-citationDiscovery of Intermetallic Compounds from Traditional to Machine-Learning Approaches
Oliynyk, A. O., & Mar, A. (2017) · Accounts of Chemical Research · doi:10.1021/acs.accounts.7b00490 · Cited by 143
Semiconductor thermochemistry in density functional calculations
Lany, S. (2008) · Physical Review B · doi:10.1103/physrevb.78.245207 · Cited by 143
Willatt, M. J., Musil, F., & Ceriotti, M. (2018) · Physical Chemistry Chemical Physics · doi:10.1039/c8cp05921g · Cited by 141
Mining Unexplored Chemistries for Phosphors for High-Color-Quality White-Light-Emitting Diodes
Wang, Z., Ha, J., Kim, Y. H., Im, W. B., McKittrick, J. M., & Ong, S. P. (2018) · Joule · doi:10.1016/j.joule.2018.01.015 · Cited by 140
Self-citationChemical Group Theory: Introduction and Fundamentals
Bonchev, D., & Rouvray, D. H. (1994) · Medical Entomology and Zoology · Cited by 137
Structure maps for. Pseudobinary and ternary phases
Pettifor, D. G. (1988) · Materials Science and Technology · doi:10.1179/mst.1988.4.8.675 · Cited by 116
Neural Message Passing with Edge Updates for Predicting Properties of Molecules and MaterialsPreprint
Jørgensen, P. B., Jacobsen, K. W., & Schmidt, M. N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03146 · Cited by 116
Hierarchical visualization of materials space with graph convolutional neural networks
Xie, T., & Grossman, J. C. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5047803 · Cited by 90
Xiang, C., Suram, S. K., Haber, J. A., Guevarra, D., Soedarmadji, E., Jin, J., & Gregoire, J. M. (2013) · ACS Combinatorial Science · doi:10.1021/co400151h · Cited by 84
Outsmarting Quantum Chemistry Through Transfer LearningPreprint
Smith, J. S., Nebgen, B. T., Zubatyuk, R. I., Lubbers, N., Devereux, C., Barros, K. M., Tretiak, S., Isayev, O., & Roitberg, A. E. (2018) · ChemRxiv · doi:10.26434/chemrxiv.6744440.v1 · Cited by 48
Quantum-Accurate Molecular Dynamics Potential for Tungsten
Wood, M. A., & Thompson, A. P. (2017) · doi:10.2172/1365473 · Cited by 27
A Data-Driven Construction of the Periodic Table of the ElementsPreprint
Willatt, M. J., Musil, F., & Ceriotti, M. (2018) · arXiv (Cornell University) · Cited by 6
Quantum-Accurate Molecular Dynamics Potential for TungstenPreprint
Wood, M. A., & Thompson, A. P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07042
Order Matters: Sequence to sequence for sets
Vinyals, O., Bengio, S., & Kudlur, M. (2015) · arXiv · doi:10.48550/arxiv.1511.06391
Research works printed but not linked: 3
- Mueller T., 2016, Recent Progress and Emerging Applications, 29, 186
- Duvenaud D. K., 2015, Adv. Neural Info. Proces. Syst., 2224
- van der Maaten L., 2008, J. Mach. Learn. Res., 9, 2579
Cited by
Recent advances and applications of machine learning in solid-state materials science
Schmidt, J., Marques, M. R. G., Botti, S., & Marques, M. A. L. (2019) · npj Computational Materials · doi:10.1038/s41524-019-0221-0 · Cited by 2,607
Scaling deep learning for materials discovery
Merchant, A., Batzner, S., Schoenholz, S. S., Aykol, M., Cheon, G., & Cubuk, E. D. (2023) · Nature · doi:10.1038/s41586-023-06735-9 · Cited by 1,527
Recent advances and applications of deep learning methods in materials science
Choudhary, K., DeCost, B., Chen, C., Jain, A., Tavazza, F., Cohn, R., Park, C. W., Choudhary, A., Agrawal, A., Billinge, S. J. L., et al. (2022) · npj Computational Materials · doi:10.1038/s41524-022-00734-6 · Cited by 1,172
“com/materialsvirtuallab/megnet [33] DimeNet Mol https://github.”
BackgroundSelf-citationA universal graph deep learning interatomic potential for the periodic table
Chen, C., & Ong, S. P. (2022) · Nature Computational Science · doi:10.1038/s43588-022-00349-3 · Cited by 1,140
Self-citationFour Generations of High-Dimensional Neural Network Potentials
Behler, J. (2021) · Chemical Reviews · doi:10.1021/acs.chemrev.0c00868 · Cited by 873
Metadata
- Authors
- Chen, C., Ye, W., Zuo, Y., Zheng, C., & Ong, S. P.
- Affiliations
- University of California San Diego (US)
- Corresponding author
- Ong, Shyue Ping
- Venue
- Chemistry of Materials
- Publisher
- American Chemical Society (ACS)
- Published
- 2019-04-10
- Volume
- 31
- Issue
- 9
- Pages
- 3564-3572
- ISSN
- 0897-4756 (ISSN-L)
- 1520-5002
- OpenAlex
- W2949095042
- Cited by
- 1,552
- References
- 65
- Citations by year
- 2026: 317 · 2025: 287 · 2024: 293 · 2023: 212 · 2022: 183 · 2021: 149 · 2020: 89 · 2019: 22
- FWCI
- 39.97
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Chemistry of Materials (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Samsung Advanced Institute of Technology
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Keywords
- graph networks, molecular property prediction, crystal property prediction, formation energy, band gap, elastic modulus, free energy prediction, transfer learning, QM9, Materials Project
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.