Neural networks to learn protein sequence-function relationships from deep mutational scanning data

74Citations
Citations of this article
230Readers
Mendeley users who have this article in their library.
Get full text

Abstract

The mapping from protein sequence to function is highly complex, making it challenging to predict how sequence changes will affect a protein's behavior and properties. We present a supervised deep learning framework to learn the sequence-function mapping from deep mutational scanning data and make predictions for new, uncharacterized sequence variants. We test multiple neural network architectures, including a graph convolutional network that incorporates protein structure, to explore how a network's internal representation affects its ability to learn the sequence-function mapping. Our supervised learning approach displays superior performance over physics-based and unsupervised prediction methods. We find that networks that capture nonlinear interactions and share parameters across sequence positions are important for learning the relationship between sequence and function. Further analysis of the trained models reveals the networks' ability to learn biologically meaningful information about protein structure and mechanism. Finally, we demonstrate the models' ability to navigate sequence space and design new proteins beyond the training set. We applied the protein G B1 domain (GB1) models to design a sequence that binds to immunoglobulin G with substantially higher affinity than wild-type GB1.

References Powered by Scopus

Get full text

A Comprehensive Survey on Graph Neural Networks

5973Citations
8547Readers
Get full text

Accelerated profile HMM searches

4254Citations
2781Readers

Cited by Powered by Scopus

Get full text
105Citations
194Readers
Get full text
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Gelman, S., Fahlberg, S. A., Heinzelman, P., Romero, P. A., & Gitter, A. (2021). Neural networks to learn protein sequence-function relationships from deep mutational scanning data. Proceedings of the National Academy of Sciences of the United States of America, 118(48). https://doi.org/10.1073/pnas.2104878118

Readers over time

‘20‘21‘22‘23‘24‘250255075100

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 60

56%

Researcher 36

34%

Professor / Associate Prof. 10

9%

Lecturer / Post doc 1

1%

Readers' Discipline

Tooltip

Biochemistry, Genetics and Molecular Bi... 65

63%

Agricultural and Biological Sciences 17

16%

Computer Science 11

11%

Engineering 11

11%

Article Metrics

Tooltip
Mentions
News Mentions: 1
Social Media
Shares, Likes & Comments: 5

Save time finding and organizing research with Mendeley

Sign up for free
0