Machine learning for evolutionary-based and physics-inspired protein design: Current and future synergies

Cyril Malbranke*, David Bikard, Simona Cocco, Rémi Monasson, Jérôme Tubiana*

*Corresponding author for this work

Research output: Contribution to journalReview articlepeer-review

8 Scopus citations

Abstract

Computational protein design facilitates the discovery of novel proteins with prescribed structure and functionality. Exciting designs were recently reported using novel data-driven methodologies that can be roughly divided into two categories: evolutionary-based and physics-inspired approaches. The former infer characteristic sequence features shared by sets of evolutionary-related proteins, such as conserved or coevolving positions, and recombine them to generate candidates with similar structure and function. The latter approaches estimate key biochemical properties, such as structure free energy, conformational entropy, or binding affinities using machine learning surrogates, and optimize them to yield improved designs. Here, we review recent progress along both tracks, discuss their strengths and weaknesses, and highlight opportunities for synergistic approaches.

Original languageEnglish
Article number102571
JournalCurrent Opinion in Structural Biology
Volume80
DOIs
StatePublished - Jun 2023

Funding

FundersFunder number
Ecole Doctorale Frontières de l'Innovation
Ecole Doctorale Frontières de l’Innovation
Edmond J. Safra Center for Bioinformatics
Learning Planet Institute
Human Frontier Science Program
Tel Aviv University
Fondation de l'École Polytechnique

    Fingerprint

    Dive into the research topics of 'Machine learning for evolutionary-based and physics-inspired protein design: Current and future synergies'. Together they form a unique fingerprint.

    Cite this