Iterative SE(3)-transformers

DOI10.1007/978-3-030-80209-7_63MaRDI QIDQ2117906zbMATH OpenOpenAlexFDO

Authors Fabian Fuchs, Edward Wagstaff, Justas Dauparas, I. Posner

Publication date 22 March 2022

Full work available at URL https://arxiv.org/abs/2102.13419

zbMATH Keywords

deep learningproteinsequivariance

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Protein sequences, DNA sequences (92D20)

Abstract: When manipulating three-dimensional data, it is possible to ensure that rotational and translational symmetries are respected by applying so-called SE(3)-equivariant models. Protein structure prediction is a prominent example of a task which displays these symmetries. Recent work in this area has successfully made use of an SE(3)-equivariant model, applying an iterative SE(3)-equivariant attention mechanism. Motivated by this application, we implement an iterative version of the SE(3)-Transformer, an SE(3)-equivariant attention-based model for graph data. We address the additional complications which arise when applying the SE(3)-Transformer in an iterative fashion, compare the iterative and single-pass versions on a toy problem, and consider why an iterative model may be beneficial in some problem settings. We make the code for our implementation available to the community.

Recommendations

• What is... an Equivariant Neural Network?
• \(\mathrm{SU}(1,1)\) equivariant neural networks and application to robust Toeplitz Hermitian positive definite matrix classification
• Using a graph transformer network to predict 3D coordinates of proteins via geometric algebra modelling
• Universal approximations of invariant maps by neural networks
• Probabilistic symmetries and invariant neural networks

Describes a project that uses

Uses Software

• GitHub
• UniProt
• PyTorch

This page was built for publication: Iterative SE(3)-transformers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117906)