ATOM3D: Tasks On Molecules in Three Dimensions

Raphael John Lamarre Townshend, Martin Vogele, Patricia Suriana, Alex Derry, Alex Powers, Yianni Laloudakis, Sidhika Balachandar, Brandon M Anderson, Stephan Eismann, Risi Kondor, Russ Altman, Ron O. Dror

Keywords: machine learning, structural biology, biomolecules

Abstract: While a variety of methods have been developed for predicting molecular properties, deep learning networks that operate directly on three-dimensional molecular structure have recently demonstrated particular promise. In this work we present ATOM3D, a collection of both novel and existing datasets spanning several key classes of biomolecules, to systematically assess such learning methods. We develop three-dimensional molecular learning networks for each of these tasks, finding that they consistently improve performance relative to one- and two-dimensional methods. The specific choice of architecture proves to be critical for performance, with three-dimensional convolutional networks excelling at tasks involving complex geometries, while graph networks perform well on systems requiring detailed positional information. Furthermore, equivariant networks show significant promise but are currently unable to scale. Our results indicate many molecular problems stand to gain from three-dimensional molecular learning. All code and datasets are available at github.com/xxxxxxx/xxxxxx.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: ATOM3D is a collection of benchmark datasets for learning algorithms that work with 3D biomolecular structure.

Community Implementations: [ 7 code implementations](https://www.catalyzex.com/paper/arxiv:2012.04035/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=W5PPqLAWs5