Structure-based protein function prediction using graph convolutional networks

Vladimir Gligorijević (), P. Douglas Renfrew, Tomasz Kosciolek, Julia Koehler Leman, Daniel Berenberg, Tommi Vatanen, Chris Chandler, Bryn C. Taylor, Ian M. Fisk, Hera Vlamakis, Ramnik J. Xavier, Rob Knight, Kyunghyun Cho and Richard Bonneau ()
Additional contact information
Vladimir Gligorijević: Flatiron Institute
P. Douglas Renfrew: Flatiron Institute
Tomasz Kosciolek: University of California San Diego
Julia Koehler Leman: Flatiron Institute
Daniel Berenberg: Flatiron Institute
Tommi Vatanen: Broad Institute of MIT and Harvard
Chris Chandler: Flatiron Institute
Bryn C. Taylor: University of California San Diego
Ian M. Fisk: Flatiron Institute, Simons Foundation
Hera Vlamakis: Broad Institute of MIT and Harvard
Ramnik J. Xavier: Broad Institute of MIT and Harvard
Rob Knight: University of California San Diego
Kyunghyun Cho: New York University
Richard Bonneau: Flatiron Institute

Nature Communications, 2021, vol. 12, issue 1, 1-14

Abstract: Abstract The rapid increase in the number of proteins in sequence databases and the diversity of their functions challenge computational approaches for automated function prediction. Here, we introduce DeepFRI, a Graph Convolutional Network for predicting protein functions by leveraging sequence features extracted from a protein language model and protein structures. It outperforms current leading methods and sequence-based Convolutional Neural Networks and scales to the size of current sequence repositories. Augmenting the training set of experimental structures with homology models allows us to significantly expand the number of predictable functions. DeepFRI has significant de-noising capability, with only a minor drop in performance when experimental structures are replaced by protein models. Class activation mapping allows function predictions at an unprecedented resolution, allowing site-specific annotations at the residue-level in an automated manner. We show the utility and high performance of our method by annotating structures from the PDB and SWISS-MODEL, making several new confident function predictions. DeepFRI is available as a webserver at https://beta.deepfri.flatironinstitute.org/ .

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (8)

Downloads: (external link)
https://www.nature.com/articles/s41467-021-23303-9 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-23303-9

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-021-23303-9

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().