SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials

no code implementations • 21 Sep 2022 • Peter Eastman, Pavan Kumar Behara, David L. Dotson, Raimondas Galvelis, John E. Herr, Josh T. Horton, Yuezhi Mao, John D. Chodera, Benjamin P. Pritchard, Yuanqing Wang, Gianni de Fabritiis, Thomas E. Markland

Machine learning potentials are an important tool for molecular simulation, but their development is held back by a shortage of high quality datasets to train them on.

End-to-End Differentiable Molecular Mechanics Force Field Construction

3 code implementations • 2 Oct 2020 • Yuanqing Wang, Josh Fass, Benjamin Kaminow, John E. Herr, Dominic Rufa, Ivy Zhang, Iván Pulido, Mike Henry, John D. Chodera

Trained with arbitrary loss functions, it can construct entirely new force fields self-consistently applicable to both biopolymers and small molecules directly from quantum chemical calculations, with superior fidelity than traditional atom or parameter typing schemes.

Drug Discovery

Compressing physical properties of atomic species for improving predictive chemistry

2 code implementations • 31 Oct 2018 • John E. Herr, Kevin Koh, Kun Yao, John Parkhill

The answers to many unsolved problems lie in the intractable chemical space of molecules and materials.

BIG-bench Machine Learning

Metadynamics for Training Neural Network Model Chemistries: a Competitive Assessment

1 code implementation • 19 Dec 2017 • John E. Herr, Kun Yao, Ryker McIntyre, David Toth, John Parkhill

At short range, however, these models are data driven and data limited.

The Many-Body Expansion Combined with Neural Networks

no code implementations • 22 Sep 2016 • Kun Yao, John E. Herr, John Parkhill

Although they are fast, NNs suffer from their own curse of dimensionality; they must be trained on a representative sample of chemical space.