Timezone: »

 
Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations
Xiang Fu · Zhenghao Wu · Wujie Wang · Tian Xie · Sinan Keten · Rafael Gomez-Bombarelli · Tommi Jaakkola

@
in AI for Science: Progress and Promises »
Event URL: https://openreview.net/forum?id=8d2gTDcRMyx »

Molecular dynamics (MD) simulation techniques are widely used for various natural science applications. Increasingly, machine learning (ML) force field (FF) models begin to replace ab-initio simulations by predicting forces directly from atomic structures. Despite significant progress in this area, such techniques are primarily benchmarked by their force/energy prediction errors, even though the practical use case would be to produce realistic MD trajectories. We aim to fill this gap by introducing a novel benchmark suite for ML MD simulation. We curate representative MD systems, including water, organic molecules, peptide, and materials, and design evaluation metrics corresponding to the scientific objectives of respective systems. We benchmark a collection of state-of-the-art (SOTA) ML FF models and illustrate, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics. We demonstrate when and how selected SOTA methods fail, along with offering directions for further improvement. Specifically, we identify stability as a key metric for ML models to improve. Our benchmark suite comes with a comprehensive open source codebase for training and simulation with ML FFs to facilitate further work.

Keywords: Molecular dynamics · simulation-based evaluation · machine learning force field · novel benchmark · AI4Science

Author Information

Xiang Fu (Massachusetts Institute of Technology)
Zhenghao Wu (Technische Universität Darmstadt)
Wujie Wang (Massachusetts Institute of Technology)
Tian Xie (Microsoft Research)
Sinan Keten (Northwestern University)
Rafael Gomez-Bombarelli (Massachusetts Institute of Technology)
Tommi Jaakkola (MIT)

Tommi Jaakkola is a professor of Electrical Engineering and Computer Science at MIT. He received an M.Sc. degree in theoretical physics from Helsinki University of Technology, and Ph.D. from MIT in computational neuroscience. Following a Sloan postdoctoral fellowship in computational molecular biology, he joined the MIT faculty in 1998. His research interests include statistical inference, graphical models, and large scale modern estimation problems with predominantly incomplete data.

More from the Same Authors