Keywords: structural biology, graph neural networks, proteins, geometric deep learning
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 geometric and relational 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 representations of macromolecules. 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 on both problems, including state-of-the-art convolutional neural networks and graph neural networks. We release our code at https://github.com/drorlab/gvp.
One-sentence Summary: We introduce a novel graph neural network layer to learn from the structure of macromolecules.
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
Code: [![github](/images/github_icon.svg) drorlab/gvp-pytorch](https://github.com/drorlab/gvp-pytorch) + [![Papers with Code](/images/pwc_icon.svg) 2 community implementations](https://paperswithcode.com/paper/?openreview=1YLJDvSx6J4)