Audacity of huge: overcoming challenges of data scarcity and data quality for machine learning in computational materials discovery

Nandy, Aditya; Duan, Chenru; Kulik, Heather J.

doi:10.1016/j.coche.2021.100778

Title: Audacity of huge: overcoming challenges of data scarcity and data quality for machine learning in computational materials discovery

Journal Article · Fri Dec 17 00:00:00 EST 2021 · Current Opinion in Chemical Engineering

DOI:https://doi.org/10.1016/j.coche.2021.100778· OSTI ID:1976980

^[1];

^[1]

Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)

Machine learning (ML)-accelerated discovery requires large amounts of high-fidelity data to reveal predictive structure–property relationships. For many properties of interest in materials discovery, the challenging nature and high cost of data generation has resulted in a data landscape that is both scarcely populated and of dubious quality. Data-driven techniques starting to overcome these limitations include the use of consensus across functionals in density functional theory, the development of new functionals or accelerated electronic structure theories, and the detection of where computationally demanding methods are most necessary. When properties cannot be reliably simulated, large experimental data sets can be used to train ML models. In the absence of manual curation, increasingly sophisticated natural language processing and automated image analysis are making it possible to learn structure–property relationships from the literature. Finally, models trained on these data sets will improve as they incorporate community feedback.

View Accepted Manuscript (DOE)

View Accepted Manuscript (Publisher)

Cite

Export

Save

Research Organization:: Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States); Univ. of Minnesota, Minneapolis, MN (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA); Defense Advanced Research Projects Agency (DARPA); National Science Foundation (NSF); US Department of the Navy, Office of Naval Research (ONR)

Grant/Contract Number:: NA0003965; SC0012702; SC0018096; SC0019112; CBET-1704266; CBET-1846426; D18AP00039; N00014-17-1-2956; N00014-18-1-2434; N00014-20-1-2150

OSTI ID:: 1976980

Alternate ID(s):: OSTI ID: 1836609

Journal Information:: Current Opinion in Chemical Engineering, Vol. 36, Issue C; ISSN 2211-3398

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (75)

Understanding the diversity of the metal-organic framework ecosystem Moosavi, Seyed Mohamad; Nandy, Aditya; Jablonka, Kevin Maik Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-17755-8	journal	August 2020
Materials Precursor Score: Modeling Chemists’ Intuition for the Synthetic Accessibility of Porous Organic Cage Precursors Bennett, Steven; Szczypiński, Filip T.; Turcani, Lukas Journal of Chemical Information and Modeling, Vol. 61, Issue 9 https://doi.org/10.1021/acs.jcim.1c00375	journal	August 2021
A data-driven perspective on the colours of metal–organic frameworks Jablonka, Kevin Maik; Moosavi, Seyed Mohamad; Asgari, Mehrdad Chemical Science, Vol. 12, Issue 10 https://doi.org/10.1039/D0SC05337F	journal	January 2021
A Design-to-Device Pipeline for Data-Driven Materials Discovery Cole, Jacqueline M. Accounts of Chemical Research, Vol. 53, Issue 3 https://doi.org/10.1021/acs.accounts.9b00470	journal	February 2020
Efficient Treatment of Large Active Spaces through Multi-GPU Parallel Implementation of Direct Configuration Interaction Fales, B. Scott; Martínez, Todd J. Journal of Chemical Theory and Computation, Vol. 16, Issue 3 https://doi.org/10.1021/acs.jctc.9b01165	journal	January 2020
Semi-supervised Machine Learning Enables the Robust Detection of Multireference Character at Low Cost Duan, Chenru; Liu, Fang; Nandy, Aditya The Journal of Physical Chemistry Letters, Vol. 11, Issue 16 https://doi.org/10.1021/acs.jpclett.0c02018	journal	July 2020
The Cambridge Structural Database Groom, Colin R.; Bruno, Ian J.; Lightfoot, Matthew P. Acta Crystallographica Section B Structural Science, Crystal Engineering and Materials, Vol. 72, Issue 2, p. 171-179 https://doi.org/10.1107/S2052520616003954	journal	April 2016
ImageDataExtractor: A Tool To Extract and Quantify Data from Microscopy Images Mukaddem, Karim T.; Beard, Edward J.; Yildirim, Batuhan Journal of Chemical Information and Modeling, Vol. 60, Issue 5 https://doi.org/10.1021/acs.jcim.9b00734	journal	November 2019
Exploring density functional subspaces with genetic algorithms Gastegger, Michael; González, Leticia; Marquetand, Philipp Monatshefte für Chemie - Chemical Monthly, Vol. 150, Issue 2 https://doi.org/10.1007/s00706-018-2335-3	journal	December 2018
Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning Zahrt, Andrew F.; Henle, Jeremy J.; Rose, Brennan T. Science, Vol. 363, Issue 6424 https://doi.org/10.1126/science.aau5631	journal	January 2019
Opportunities and challenges of text mining in materials research Kononova, Olga; He, Tanjin; Huo, Haoyan iScience, Vol. 24, Issue 3 https://doi.org/10.1016/j.isci.2021.102155	journal	March 2021
Designing in the Face of Uncertainty: Exploiting Electronic Structure and Machine Learning Models for Discovery in Inorganic Chemistry Janet, Jon Paul; Liu, Fang; Nandy, Aditya Inorganic Chemistry, Vol. 58, Issue 16 https://doi.org/10.1021/acs.inorgchem.9b00109	journal	March 2019
Unsupervised word embeddings capture latent knowledge from materials science literature Tshitoyan, Vahe; Dagdelen, John; Weston, Leigh Nature, Vol. 571, Issue 7763 https://doi.org/10.1038/s41586-019-1335-8	journal	July 2019
ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules Smith, Justin S.; Isayev, Olexandr; Roitberg, Adrian E. Scientific Data, Vol. 4, Issue 1 https://doi.org/10.1038/sdata.2017.193	journal	December 2017
Machine learning the quantum-chemical properties of metal–organic frameworks for accelerated materials discovery Rosen, Andrew S.; Iyer, Shaelyn M.; Ray, Debmalya Matter, Vol. 4, Issue 5 https://doi.org/10.1016/j.matt.2021.02.015	journal	May 2021
Autonomous Molecular Design: Then and Now Dimitrov, Tanja; Kreisbeck, Christoph; Becker, Jill S. ACS Applied Materials & Interfaces, Vol. 11, Issue 28 https://doi.org/10.1021/acsami.9b01226	journal	March 2019
Inverse Design of Materials That Exhibit the Magnetocaloric Effect by Text-Mining of the Scientific Literature and Generative Deep Learning Court, Callum J.; Jain, Apoorv; Cole, Jacqueline M. Chemistry of Materials, Vol. 33, Issue 18 https://doi.org/10.1021/acs.chemmater.1c01368	journal	September 2021
Deciphering Cryptic Behavior in Bimetallic Transition-Metal Complexes with Machine Learning Taylor, Michael G.; Nandy, Aditya; Lu, Connie C. The Journal of Physical Chemistry Letters, Vol. 12, Issue 40 https://doi.org/10.1021/acs.jpclett.1c02852	journal	October 2021
Machine-Learning Coupled Cluster Properties through a Density Tensor Representation Peyton, Benjamin G.; Briggs, Connor; D’Cunha, Ruhee The Journal of Physical Chemistry A, Vol. 124, Issue 23 https://doi.org/10.1021/acs.jpca.0c02804	journal	May 2020
Using Machine Learning and Data Mining to Leverage Community Knowledge for the Engineering of Stable Metal–Organic Frameworks Nandy, Aditya; Duan, Chenru; Kulik, Heather J. Journal of the American Chemical Society, Vol. 143, Issue 42 https://doi.org/10.1021/jacs.1c07217	journal	October 2021
Does repeat synthesis in materials chemistry obey a power law? Agrawal, Mayank; Han, Rebecca; Herath, Dinushka Proceedings of the National Academy of Sciences, Vol. 117, Issue 2 https://doi.org/10.1073/pnas.1918484117	journal	December 2019
Machine Learning Approaches toward Orbital-free Density Functional Theory: Simultaneous Training on the Kinetic Energy Density Functional and Its Functional Derivative Meyer, Ralf; Weichselbaum, Manuel; Hauser, Andreas W. Journal of Chemical Theory and Computation, Vol. 16, Issue 9 https://doi.org/10.1021/acs.jctc.0c00580	journal	August 2020
Data-Driven Acceleration of the Coupled-Cluster Singles and Doubles Iterative Solver Townsend, Jacob; Vogiatzis, Konstantinos D. The Journal of Physical Chemistry Letters, Vol. 10, Issue 14 https://doi.org/10.1021/acs.jpclett.9b01442	journal	June 2019
Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis Jia, Xiwen; Lynch, Allyson; Huang, Yuheng Nature, Vol. 573, Issue 7773 https://doi.org/10.1038/s41586-019-1540-5	journal	September 2019
Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning Kim, Edward; Huang, Kevin; Saunders, Adam Chemistry of Materials, Vol. 29, Issue 21 https://doi.org/10.1021/acs.chemmater.7b03500	journal	October 2017
Learning the Exchange-Correlation Functional from Nature with Fully Differentiable Density Functional Theory Kasim, M. F.; Vinko, S. M. Physical Review Letters, Vol. 127, Issue 12 https://doi.org/10.1103/PhysRevLett.127.126403	journal	September 2021
Deep-neural-network solution of the electronic Schrödinger equation Hermann, Jan; Schätzle, Zeno; Noé, Frank Nature Chemistry, Vol. 12, Issue 10 https://doi.org/10.1038/s41557-020-0544-y	journal	September 2020
Computational Ligand Descriptors for Catalyst Design Durand, Derek J.; Fey, Natalie Chemical Reviews, Vol. 119, Issue 11 https://doi.org/10.1021/acs.chemrev.8b00588	journal	October 2018
Rational Density Functional Selection Using Game Theory McAnanama-Brereton, Suzanne; Waller, Mark P. Journal of Chemical Information and Modeling, Vol. 58, Issue 1 https://doi.org/10.1021/acs.jcim.7b00542	journal	December 2017
Identification Schemes for Metal–Organic Frameworks To Enable Rapid Search and Cheminformatics Analysis Bucior, Benjamin J.; Rosen, Andrew S.; Haranczyk, Maciej Crystal Growth & Design, Vol. 19, Issue 11 https://doi.org/10.1021/acs.cgd.9b01050	journal	September 2019
Torsion Angle Effect on the Activation of UiO Metal–Organic Frameworks Ayoub, Ghada; Islamoglu, Timur; Goswami, Subhadip ACS Applied Materials & Interfaces, Vol. 11, Issue 17 https://doi.org/10.1021/acsami.9b02764	journal	April 2019
A Machine Learning Approach to Zeolite Synthesis Enabled by Automatic Literature Data Extraction Jensen, Zach; Kim, Edward; Kwon, Soonhyoung ACS Central Science, Vol. 5, Issue 5 https://doi.org/10.1021/acscentsci.9b00193	journal	April 2019
Thirty years of density functional theory in computational chemistry: an overview and extensive assessment of 200 density functionals Mardirossian, Narbe; Head-Gordon, Martin Molecular Physics, Vol. 115, Issue 19 https://doi.org/10.1080/00268976.2017.1333644	journal	April 2017
ChemDataExtractor: A Toolkit for Automated Extraction of Chemical Information from the Scientific Literature Swain, Matthew C.; Cole, Jacqueline M. Journal of Chemical Information and Modeling, Vol. 56, Issue 10 https://doi.org/10.1021/acs.jcim.6b00207	journal	October 2016
Predictive and mechanistic multivariate linear regression models for reaction development Santiago, Celine B.; Guo, Jing-Yao; Sigman, Matthew S. Chemical Science, Vol. 9, Issue 9 https://doi.org/10.1039/C7SC04679K	journal	January 2018
A critical examination of compound stability predictions from machine-learned formation energies Bartel, Christopher J.; Trewartha, Amalie; Wang, Qi npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-020-00362-y	journal	July 2020
Machine Learning Configuration Interaction Coe, J. P. Journal of Chemical Theory and Computation, Vol. 14, Issue 11 https://doi.org/10.1021/acs.jctc.8b00849	journal	October 2018
Discovering Relationships between OSDAs and Zeolites through Data Mining and Generative Neural Networks Jensen, Zach; Kwon, Soonhyoung; Schwalbe-Koda, Daniel ACS Central Science, Vol. 7, Issue 5 https://doi.org/10.1021/acscentsci.1c00024	journal	April 2021
Machine-Learned Energy Functionals for Multiconfigurational Wave Functions King, Daniel S.; Truhlar, Donald G.; Gagliardi, Laura The Journal of Physical Chemistry Letters, Vol. 12, Issue 32 https://doi.org/10.1021/acs.jpclett.1c02042	journal	August 2021
Data-driven design of metal–organic frameworks for wet flue gas CO2 capture Boyd, Peter G.; Chidambaram, Arunraj; García-Díez, Enrique Nature, Vol. 576, Issue 7786 https://doi.org/10.1038/s41586-019-1798-7	journal	December 2019
Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks Kim, Edward; Jensen, Zach; van Grootel, Alexander Journal of Chemical Information and Modeling, Vol. 60, Issue 3 https://doi.org/10.1021/acs.jcim.9b00995	journal	January 2020
Prediction of water stability of metal–organic frameworks using machine learning Batra, Rohit; Chen, Carmen; Evans, Tania G. Nature Machine Intelligence, Vol. 2, Issue 11 https://doi.org/10.1038/s42256-020-00249-z	journal	November 2020
Named Entity Recognition and Normalization Applied to Large-Scale Information Extraction from the Materials Science Literature Weston, L.; Tshitoyan, V.; Dagdelen, J. Journal of Chemical Information and Modeling, Vol. 59, Issue 9 https://doi.org/10.1021/acs.jcim.9b00470	journal	July 2019
Data-Driven Approaches Can Overcome the Cost–Accuracy Trade-Off in Multireference Diagnostics Duan, Chenru; Liu, Fang; Nandy, Aditya Journal of Chemical Theory and Computation, Vol. 16, Issue 7 https://doi.org/10.1021/acs.jctc.0c00358	journal	June 2020
Bypassing the Kohn-Sham equations with machine learning Brockherde, Felix; Vogt, Leslie; Li, Li Nature Communications, Vol. 8, Issue 1 https://doi.org/10.1038/s41467-017-00839-3	journal	October 2017
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy APL Materials, Vol. 1, Issue 1 https://doi.org/10.1063/1.4812323	journal	July 2013
Advances, Updates, and Analytics for the Computation-Ready, Experimental Metal–Organic Framework Database: CoRE MOF 2019 Chung, Yongchul G.; Haldoupis, Emmanuel; Bucior, Benjamin J. Journal of Chemical & Engineering Data, Vol. 64, Issue 12 https://doi.org/10.1021/acs.jced.9b00835	journal	November 2019
Discovery of complex oxides via automated experiments and data science Yang, Lusann; Haber, Joel A.; Armstrong, Zan Proceedings of the National Academy of Sciences, Vol. 118, Issue 37 https://doi.org/10.1073/pnas.2106042118	journal	September 2021
Seeing Is Believing: Experimental Spin States from Machine Learning Model Structure Predictions Taylor, Michael G.; Yang, Tzuhsiung; Lin, Sean The Journal of Physical Chemistry A, Vol. 124, Issue 16 https://doi.org/10.1021/acs.jpca.0c01458	journal	March 2020
tmQM Dataset—Quantum Geometries and Properties of 86k Transition Metal Complexes Balcells, David; Skjelstad, Bastian Bjerkem Journal of Chemical Information and Modeling, Vol. 60, Issue 12 https://doi.org/10.1021/acs.jcim.0c01041	journal	November 2020
Quantum chemical accuracy from density functional approximations via machine learning Bogojeski, Mihail; Vogt-Maranto, Leslie; Tuckerman, Mark E. Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-19093-1	journal	October 2020
Quantum Deep Field: Data-Driven Wave Function, Electron Density Generation, and Atomization Energy Prediction and Extrapolation with Machine Learning Tsubaki, Masashi; Mizoguchi, Teruyasu Physical Review Letters, Vol. 125, Issue 20 https://doi.org/10.1103/PhysRevLett.125.206401	journal	November 2020
Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions Schütt, K. T.; Gastegger, M.; Tkatchenko, A. Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-12875-2	journal	November 2019
ChemDataExtractor 2.0: Autopopulated Ontologies for Materials Science Mavračić, Juraj; Court, Callum J.; Isazawa, Taketomo Journal of Chemical Information and Modeling, Vol. 61, Issue 9 https://doi.org/10.1021/acs.jcim.1c00446	journal	September 2021
Text Mining Metal–Organic Framework Papers Park, Sanghoon; Kim, Baekjun; Choi, Sihoon Journal of Chemical Information and Modeling, Vol. 58, Issue 2 https://doi.org/10.1021/acs.jcim.7b00608	journal	January 2018
Virtual screening of inorganic materials synthesis parameters with deep learning Kim, Edward; Huang, Kevin; Jegelka, Stefanie npj Computational Materials, Vol. 3, Issue 1 https://doi.org/10.1038/s41524-017-0055-6	journal	December 2017
Materials Informatics with PoreBlazer v4.0 and the CSD MOF Database Sarkisov, Lev; Bueno-Perez, Rocio; Sutharson, Mythili Chemistry of Materials, Vol. 32, Issue 23 https://doi.org/10.1021/acs.chemmater.0c03575	journal	November 2020
Rapid Detection of Strong Correlation with Machine Learning for Transition-Metal Complex High-Throughput Screening Liu, Fang; Duan, Chenru; Kulik, Heather J. The Journal of Physical Chemistry Letters, Vol. 11, Issue 19 https://doi.org/10.1021/acs.jpclett.0c02288	journal	August 2020
Automatic Selection of Active Orbitals from Generalized Valence Bond Orbitals Zou, Jingxiang; Niu, Ke; Ma, Haibo The Journal of Physical Chemistry A, Vol. 124, Issue 40 https://doi.org/10.1021/acs.jpca.0c05216	journal	September 2020
Automation of Active Space Selection for Multireference Methods via Machine Learning on Chemical Bond Dissociation Jeong, WooSeok; Stoneburner, Samuel J.; King, Daniel Journal of Chemical Theory and Computation, Vol. 16, Issue 4 https://doi.org/10.1021/acs.jctc.9b01297	journal	March 2020
Artificial Neural Networks Applied as Molecular Wave Function Solvers Yang, Peng-Jian; Sugiyama, Mahito; Tsuda, Koji Journal of Chemical Theory and Computation, Vol. 16, Issue 6 https://doi.org/10.1021/acs.jctc.9b01132	journal	April 2020
Capturing chemical intuition in synthesis of metal-organic frameworks Moosavi, Seyed Mohamad; Chidambaram, Arunraj; Talirz, Leopold Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-08483-9	journal	February 2019
Big-Data Science in Porous Materials: Materials Genomics and Machine Learning Jablonka, Kevin Maik; Ongari, Daniele; Moosavi, Seyed Mohamad Chemical Reviews, Vol. 120, Issue 16 https://doi.org/10.1021/acs.chemrev.0c00004	journal	June 2020
Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach Gómez-Bombarelli, Rafael; Aguilera-Iparraguirre, Jorge; Hirzel, Timothy D. Nature Materials, Vol. 15, Issue 10 https://doi.org/10.1038/nmat4717	journal	August 2016
Computational Approach to Molecular Catalysis by 3d Transition Metals: Challenges and Opportunities Vogiatzis, Konstantinos D.; Polynski, Mikhail V.; Kirkland, Justin K. Chemical Reviews, Vol. 119, Issue 4 https://doi.org/10.1021/acs.chemrev.8b00361	journal	October 2018
Simple Automatized Tool for Exchange–Correlation Functional Fitting Mitrofanov, Artem; Korolev, Vadim; Andreadi, Nikolai The Journal of Physical Chemistry A, Vol. 124, Issue 13 https://doi.org/10.1021/acs.jpca.9b09093	journal	March 2020
A Ranked-Orbital Approach to Select Active Spaces for High-Throughput Multireference Computation King, Daniel S.; Gagliardi, Laura Journal of Chemical Theory and Computation, Vol. 17, Issue 5 https://doi.org/10.1021/acs.jctc.1c00037	journal	April 2021
Automated Selection of Active Orbital Spaces Stein, Christopher J.; Reiher, Markus Journal of Chemical Theory and Computation, Vol. 12, Issue 4 https://doi.org/10.1021/acs.jctc.6b00156	journal	March 2016
Machine-learning-assisted materials discovery using failed experiments Raccuglia, Paul; Elbert, Katherine C.; Adler, Philip D. F. Nature, Vol. 533, Issue 7601 https://doi.org/10.1038/nature17439	journal	May 2016
Replacing hybrid density functional theory: motivation and recent advances Janesko, Benjamin G. Chemical Society Reviews, Vol. 50, Issue 15 https://doi.org/10.1039/D0CS01074J	journal	January 2021
Using collective knowledge to assign oxidation states of metal cations in metal–organic frameworks Jablonka, Kevin Maik; Ongari, Daniele; Moosavi, Seyed Mohamad Nature Chemistry, Vol. 13, Issue 8 https://doi.org/10.1038/s41557-021-00717-y	journal	July 2021
Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning Nandy, Aditya; Duan, Chenru; Taylor, Michael G. Chemical Reviews, Vol. 121, Issue 16 https://doi.org/10.1021/acs.chemrev.1c00347	journal	July 2021
Random Forests Breiman, Leo Machine Learning, Vol. 45, Issue 1, p. 5-32 https://doi.org/10.1023/A:1010933404324	journal	January 2001
Topologically Guided, Automated Construction of Metal–Organic Frameworks and Their Evaluation for Energy-Related Applications Colón, Yamil J.; Gómez-Gualdrón, Diego A.; Snurr, Randall Q. Crystal Growth & Design, Vol. 17, Issue 11 https://doi.org/10.1021/acs.cgd.7b00848	journal	September 2017
Completing density functional theory by machine learning hidden messages from molecules Nagai, Ryo; Akashi, Ryosuke; Sugino, Osamu npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-020-0310-0	journal	May 2020

Similar Records

Navigating Transition-Metal Chemical Space: Artificial Intelligence for First-Principles Design

Journal Article · Fri Jan 22 00:00:00 EST 2021 · Accounts of Chemical Research · OSTI ID:1976980

Janet, Jon Paul; Duan, Chenru; Nandy, Aditya; +2 more

What's Left for a Computational Chemist To Do in the Age of Machine Learning?

Journal Article · Thu Apr 15 00:00:00 EDT 2021 · Israel Journal of Chemistry · OSTI ID:1976980

Kulik, Heather J.

Representations and strategies for transferable machine learning improve model performance in chemical discovery

Journal Article · Tue Feb 15 00:00:00 EST 2022 · Journal of Chemical Physics · OSTI ID:1976980

Harper, Daniel R.; Nandy, Aditya; Arunachalam, Naveen; +3 more

Related Subjects

97 MATHEMATICS AND COMPUTING
36 MATERIALS SCIENCE
Biotechnology & Applied Microbiology
Engineering
Machine learning
Artificial intelligence
Density functional theory
Computational materials discovery
Natural language processing

Title: Audacity of huge: overcoming challenges of data scarcity and data quality for machine learning in computational materials discovery

Citation Formats

References (75)

Similar Records

Related Subjects