Nature Communications (May 2021)

Deep learning the structural determinants of protein biochemical properties by comparing structural ensembles with DiffNets

  • Michael D. Ward,
  • Maxwell I. Zimmerman,
  • Artur Meller,
  • Moses Chung,
  • S. J. Swamidass,
  • Gregory R. Bowman

DOI
https://doi.org/10.1038/s41467-021-23246-1
Journal volume & issue
Vol. 12, no. 1
pp. 1 – 12

Abstract

Read online

Comparing and contrasting structural ensembles of different protein variants helps connect specific structural features to a protein’s biochemical properties. Here, the authors propose DiffNets, a self-supervised, deep learning method that streamlines this process.