Repository logo
 

ProteInfer, deep neural networks for protein functional inference.

Published version
Peer-reviewed

Change log

Abstract

Predicting the function of a protein from its amino acid sequence is a long-standing challenge in bioinformatics. Traditional approaches use sequence alignment to compare a query sequence either to thousands of models of protein families or to large databases of individual protein sequences. Here we introduce ProteInfer, which instead employs deep convolutional neural networks to directly predict a variety of protein functions - Enzyme Commission (EC) numbers and Gene Ontology (GO) terms - directly from an unaligned amino acid sequence. This approach provides precise predictions which complement alignment-based methods, and the computational efficiency of a single neural network permits novel and lightweight software interfaces, which we demonstrate with an in-browser graphical interface for protein function prediction in which all computation is performed on the user's personal computer with no data uploaded to remote servers. Moreover, these models place full-length amino acid sequences into a generalised functional space, facilitating downstream analysis and interpretation. To read the interactive version of this paper, please visit https://google-research.github.io/proteinfer/.

Description

Peer reviewed: True


Acknowledgements: We thank Babak Alipanahi, Jamie Smith, Eli Bixby, Drew Bryant, Shanqing Cai, Cory McLean, and Abhinay Ramaprasad. The static version of this manuscript uses a template made by Ricardo Henriques. TS receives funding from the Wellcome Trust through a Sir Henry Wellcome Postdoctoral Fellowship (210918/Z/18/Z). LJC receives funding from the Simons Foundation (Award 598399). This work was also supported by the Francis Crick Institute which receives its core funding from Cancer Research UK (FC001043), the UK Medical Research Council (FC001043), and the Wellcome Trust (FC001043). This research was funded in whole, or in part, by the Wellcome Trust (FC001043). For the purpose of Open Access, the authors have applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission.


Funder: Google; FundRef: http://dx.doi.org/10.13039/100006785

Keywords

computational biology, function, learning, neural network, none, prediction, protein, systems biology, Algorithms, Neural Networks, Computer, Proteins, Amino Acid Sequence, Software, Computational Biology

Journal Title

Elife

Conference Name

Journal ISSN

2050-084X
2050-084X

Volume Title

Publisher

eLife Sciences Publications, Ltd
Sponsorship
Cancer Research (FC001043)
UK Medical Research Council (FC001043)
Wellcome Trust (FC001043)
Simons Foundation (598399)