Atomate2: modular workflows for materials science

High-throughput density functional theory (DFT) calculations have become a vital element of computational materials science, enabling materials screening, property database generation, and training of "universal" machine learning models. While several software frameworks have emerged to support these computational efforts, new developments such as machine learned force fields have increased demands for more flexible and programmable workflow solutions. This manuscript introduces atomate2, a comprehensive evolution of our original atomate framework, designed to address existing limitations in computational materials research infrastructure. Key features include the support for multiple electronic structure packages and interoperability between them, along with generalizable workflows that can be written in an abstract form irrespective of the DFT package or machine learning force field used within them. Our hope is that atomate2's improved usability and extensibility can reduce technical barriers for high-throughput research workflows and facilitate the rapid adoption of emerging methods in computational material science.

Authors

Institutions

Publication Details

Journal
Digital Discovery
Published
2025-01-01
DOI
https://doi.org/10.1039/d5dd00019j
Citations
21
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
10.87

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Atomate2: modular workflows for materials science

Jeffrey B. Neaton, Anubhav Jain, Max C. Gallant, Guido Petretto et al.
21 citations
Digital Discovery
Machine Learning in Materials Science
10.87
article

Atomate2: modular workflows for materials science

Jeffrey B. Neaton, Anubhav Jain, Max C. Gallant, Guido Petretto, Aakash Ashok Naik, Rhys E. A. Goodall, Zhuoying Zhu, D. C. Chrzan, Christina Ertural, Shehan M. Parmar, Mingjian Wen, Bryant Y. Li, Geoffroy Hautier, Thomas A. R. Purcell, Alexander S. Sobolev, Mark Asta, Kristin Aslaug Persson, Rishabh D. Guha, Yuan Chiang, Matthew C. Kuner, Ravishankar Sundararaman, Joana Bustamante, Alexander Bonkowski, Ryan Kingsbury, Hrushikesh Sahasrabuddhe, Jonathan Schmidt, David Waroquiers, Jiongzhi Zheng, Orion A. Cohen, Jimmy‐Xuan Shen, Aaron D. Kaplan, Matthias Scheffler, Matthew J. McDermott, Alex M. Ganose, Derek Vigil‐Fowler, Matthew K. Horton, Francesco Ricci, Janosh Riebesell, Janine George, Gian‐Marco Rignanese, Jacob M. Clary, Andrew Rosen, Joel B. Varley, Benjamin S. Rich, Cooper Tezak, Victor Trinquet, Sophie Gerits, Duo Wang, Xin Chen, Han Yang, Hui Zheng, Tathagata Biswas, Kévin Beck, Théo Jaffrelot Inizan, Rohith Srinivaas Mohanakrishnan, Xavier Linn
article en
21 citations

Abstract

High-throughput density functional theory (DFT) calculations have become a vital element of computational materials science, enabling materials screening, property database generation, and training of "universal" machine learning models. While several software frameworks have emerged to support these computational efforts, new developments such as machine learned force fields have increased demands for more flexible and programmable workflow solutions. This manuscript introduces atomate2, a comprehensive evolution of our original atomate framework, designed to address existing limitations in computational materials research infrastructure. Key features include the support for multiple electronic structure packages and interoperability between them, along with generalizable workflows that can be written in an abstract form irrespective of the DFT package or machine learning force field used within them. Our hope is that atomate2's improved usability and extensibility can reduce technical barriers for high-throughput research workflows and facilitate the rapid adoption of emerging methods in computational material science.

Digital DiscoveryVol. 4(7)
Dartmouth College (US), Lawrence Livermore National Laboratory (US), Microsoft (United States) (US), National Laboratory of the Rockies (US), Georgia Institute of Technology (US), Federal Institute For Materials Research and Testing (DE), University of Arizona (US), Lawrence Berkeley National Laboratory (US), University of Electronic Science and Technology of China (CN), Rensselaer Polytechnic Institute (US), University of Colorado Boulder (US), Princeton University (US), University of Cambridge (GB), Fritz Haber Institute of the Max Planck Society (DE), ETH Zurich (CH), Kavli Energy NanoScience Institute (US), Applied Mathematics (United States) (US), Walloon Excellence in Lifesciences and Biotechnology (BE), Imperial College London (GB), Friedrich Schiller University Jena (DE), RWTH Aachen University (DE), University of California, Berkeley (US), UCLouvain (BE)
National Science Foundation, U.S. Department of Energy, Gordon and Betty Moore Foundation, University of Houston, Adolph C. and Mary Sprague Miller Institute for Basic Research in Science, University of California Berkeley, National Energy Research Scientific Computing Center, European Commission, Fonds De La Recherche Scientifique - FNRS, Fédération Wallonie-Bruxelles, Eidgenössische Technische Hochschule Zürich, Studienstiftung des Deutschen Volkes, Gauss Centre for Supercomputing, Office of Science, Office of Energy Efficiency and Renewable Energy, Engineering and Physical Sciences Research Council, European Research Council, Leibniz-Gemeinschaft, Fonds pour la Formation à la Recherche dans l’Industrie et dans l’Agriculture, Horizon 2020, Leibniz-Rechenzentrum, National Supercomputing Center, Korea Institute of Science and Technology Information, Basic Energy Sciences, Office of Energy Efficiency, National Renewable Energy Laboratory, Lawrence Berkeley National Laboratory
Industry, innovation and infrastructure
Openalex Percentile: Top 1%
Machine Learning in Materials Science
10.87
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.