Chainsaw: protein domain segmentation with fully convolutional neural networks.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: Protein domains are fundamental units of protein structure and play a pivotal role in understanding folding, function, evolution, and design. The advent of accurate structure prediction techniques has resulted in an influx of new structural data, making the partitioning of these structures into domains essential for inferring evolutionary relationships and functional classification.

Authors

  • Jude Wells
    Centre for Artificial Intelligence, University College London, WC1E 6BT, United Kingdom.
  • Alex Hawkins-Hooker
    Synthetic Biology Group, Microbiology Department, Institut Pasteur, Paris, France.
  • Nicola Bordin
    Institute of Structural and Molecular Biology, University College London, Gower St, WC1E 6BT London, UK.
  • Ian Sillitoe
    Institute of Structural and Molecular Biology, University College London, London, UK.
  • Brooks Paige
    Centre for Artificial Intelligence, University College London, WC1E 6BT, United Kingdom.
  • Christine Orengo
    Institute of Structural and Molecular Biology, University College London, London, UK. c.orengo@ucl.ac.uk.