Variational auto-encoding of protein sequences

TL;DR

This paper introduces a variational auto-encoder model to embed protein sequences, enabling better prediction of mutation effects and understanding of sequence-function relationships, which advances protein analysis and design.

Contribution

The paper presents a novel unsupervised variational auto-encoder approach for protein sequences that outperforms baseline methods and sometimes surpasses state-of-the-art models in predicting mutation impacts.

Findings

Better mutation effect prediction than baseline methods

Outperforms some state-of-the-art inverse-Potts models

Facilitates exploration of protein sequence space

Abstract

Proteins are responsible for the most diverse set of functions in biology. The ability to extract information from protein sequences and to predict the effects of mutations is extremely valuable in many domains of biology and medicine. However the mapping between protein sequence and function is complex and poorly understood. Here we present an embedding of natural protein sequences using a Variational Auto-Encoder and use it to predict how mutations affect protein function. We use this unsupervised approach to cluster natural variants and learn interactions between sets of positions within a protein. This approach generally performs better than baseline methods that consider no interactions within sequences, and in some cases better than the state-of-the-art approaches that use the inverse-Potts model. This generative model can be used to computationally guide exploration of protein sequence space and to better inform rational and automatic protein design.