Communications Chemistry (Jan 2023)

Transferring chemical and energetic knowledge between molecular systems with machine learning

  • Sajjad Heydari,
  • Stefano Raniolo,
  • Lorenzo Livi,
  • Vittorio Limongelli

DOI
https://doi.org/10.1038/s42004-022-00790-5
Journal volume & issue
Vol. 6, no. 1
pp. 1 – 13

Abstract

Read online

Machine learning algorithms are widely employed for molecular simulations, but there are likely many yet unexplored routes for the prediction of structural and energetic properties of biologically relevant systems. Here, the authors develop a hypergraph representation and message passing method for transferring knowledge obtained from simple molecular systems onto more complex ones, demonstrated by transfer learning from tri-alanine to the deca-alanine system.