Learning from Protein Structure with Geometric Vector Perceptrons

Abstract

Learning on 3D structures of large biomolecules is emerging as a distinct area in machine learning, but there has yet to emerge a unifying network architecture that simultaneously leverages the graph-structured and geometric aspects of the problem domain. To address this gap, we introduce geometric vector perceptrons, which extend standard dense layers to operate on collections of Euclidean vectors. Graph neural networks equipped with such layers are able to perform both geometric and relational reasoning on efficient and natural representations of macromolecular structure. We demonstrate our approach on two important problems in learning from protein structure: model quality assessment and computational protein design. Our approach improves over existing classes of architectures, including state-of-the-art graph-based and voxel-based methods. We release our code at https://github.com/drorlab/gvp.

Presented at ICLR 2021

Cited by in corpus (7)

• A Comprehensive Survey on Deep Graph Representation Learning
• Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast
• Computational protein design with evolutionary-based and physics-inspired modeling: current and future synergies
• Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures
• Geometric and Physical Quantities Improve E(3) Equivariant Message Passing
• Complete Neural Networks for Complete Euclidean Graphs
• Benchmarking deep generative models for diverse antibody sequence design