161 lines (159 with data), 6.7 kB

# YAML 1.2
# Metadata for citation of this software according to the CFF format (https://citation-file-format.github.io/)

cff-version: 1.2.0
message: If you use this software, please cite it as below.
title: 'Structure-based protein function prediction using
  graph convolutional networks'
doi: 10.1038/s41467-021-23303-9
authors:
- given-names: Vladimir
  family-names: Gligorijević
  affiliation: Center for Computational Biology, Flatiron
    Institute, New York, NY, USA
  orcid: https://orcid.org/0000-0002-5165-0973
- given-names: P. Douglas
  family-names: Renfrew
  affiliation: Center for Computational Biology, Flatiron Institute,
    New York, NY, USA
- given-names: Tomasz
  family-names: Kosciolek
  affiliation: Malopolska Centre of Biotechnology, Jagiellonian University,
    Krakow, Poland
  orcid: https://orcid.org/0000-0002-5693-3593
- given-names: Julia Koehler
  family-names: Leman
  affiliation: Center for Computational Biology, Flatiron Institute,
    New York, NY, USA
  orcid: https://orcid.org/0000-0002-5693-3593
- given-names: Daniel
  family-names: Berenberg
  affiliation: Center for Computational Biology, Flatiron Institute,
    New York, NY, USA
- given-names: Tommi
  family-names: Vatanen
  affiliation: Broad Institute of MIT and Harvard, Cambridge, MA, USA
  orcid: https://orcid.org/0000-0003-0949-1291
- given-names: Chris
  family-names: Chandler
  affiliation: Center for Computational Biology, Flatiron Institute,
    New York, NY, USA
- given-names: Bryn C.
  family-names: Taylor
  affiliation: Biomedical Sciences Graduate Program,
    University of California San Diego, La Jolla, CA, USA
- given-names: Ian M.
  family-names: Fisk
  affiliation: Scientific Computing Core, Flatiron Institute,
    Simons Foundation, New York, NY, USA
- given-names: Hera
  family-names: Vlamakis
  affiliation: Broad Institute of MIT and Harvard, Cambridge, MA, USA
  orcid: https://orcid.org/0000-0003-1086-9191
- given-names: Ramnik J.
  family-names: Xavier
  affiliation: Broad Institute of MIT and Harvard, Cambridge, MA, USA
  orcid: https://orcid.org/0000-0002-5630-5167
- given-names: Rob
  family-names: Knight
  affiliation: Department of Pediatrics, University of California San Diego,
    La Jolla, CA, USA
  orcid: https://orcid.org/0000-0002-0975-9019
- given-names: Kyunghyun
  family-names: Cho
  affiliation: Center for Data Science, New York University, New York, NY, USA
- given-names: Richard
  family-names: Bonneau
  affiliation: Center for Computational Biology, Flatiron Institute, New York, NY, USA
  orcid: https://orcid.org/0000-0003-4354-7906
version: 1.0.0
date-released: 2021-03-31
repository-code: https://github.com/flatironinstitute/DeepFRI
license: BSD-3-Clause
keywords:
- "Graph Neural Networks"
- "Protein function"
- "Function prediction"
preferred-citation:
  type: article
  authors:
  - given-names: Vladimir
    family-names: Gligorijević
    affiliation: Center for Computational Biology, Flatiron
      Institute, New York, NY, USA
    orcid: https://orcid.org/0000-0002-5165-0973
  - given-names: P. Douglas
    family-names: Renfrew
    affiliation: Center for Computational Biology, Flatiron Institute,
      New York, NY, USA
  - given-names: Tomasz
    family-names: Kosciolek
    affiliation: Malopolska Centre of Biotechnology, Jagiellonian University,
      Krakow, Poland
    orcid: https://orcid.org/0000-0002-5693-3593
  - given-names: Julia Koehler
    family-names: Leman
    affiliation: Center for Computational Biology, Flatiron Institute,
      New York, NY, USA
    orcid: https://orcid.org/0000-0002-5693-3593
  - given-names: Daniel
    family-names: Berenberg
    affiliation: Center for Computational Biology, Flatiron Institute,
      New York, NY, USA
  - given-names: Tommi
    family-names: Vatanen
    affiliation: Broad Institute of MIT and Harvard, Cambridge, MA, USA
    orcid: https://orcid.org/0000-0003-0949-1291
  - given-names: Chris
    family-names: Chandler
    affiliation: Center for Computational Biology, Flatiron Institute,
      New York, NY, USA
  - given-names: Bryn C.
    family-names: Taylor
    affiliation: Biomedical Sciences Graduate Program,
      University of California San Diego, La Jolla, CA, USA
  - given-names: Ian M.
    family-names: Fisk
    affiliation: Scientific Computing Core, Flatiron Institute,
      Simons Foundation, New York, NY, USA
  - given-names: Hera
    family-names: Vlamakis
    affiliation: Broad Institute of MIT and Harvard, Cambridge, MA, USA
    orcid: https://orcid.org/0000-0003-1086-9191
  - given-names: Ramnik J.
    family-names: Xavier
    affiliation: Broad Institute of MIT and Harvard, Cambridge, MA, USA
    orcid: https://orcid.org/0000-0002-5630-5167
  - given-names: Rob
    family-names: Knight
    affiliation: Department of Pediatrics, University of California San Diego,
      La Jolla, CA, USA
    orcid: https://orcid.org/0000-0002-0975-9019
  - given-names: Kyunghyun
    family-names: Cho
    affiliation: Center for Data Science, New York University, New York, NY, USA
  - given-names: Richard
    family-names: Bonneau
    affiliation: Center for Computational Biology, Flatiron Institute, New York, NY, USA
    orcid: https://orcid.org/0000-0003-4354-7906
  doi: "10.1038/s41467-021-23303-9"
  journal: "Nature Communications"
  month: 5
  title: "Structure-based protein function prediction using
    graph convolutional networks"
  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/.'
  year: 2021