Machine learned coarse-grained protein force-fields: Are we there yet?

Aleksander E P Durumeric; Nicholas E Charron; Clark Templeton; Félix Musil; Klara Bonneau; Aldo S Pasos-Trejo; Yaoyi Chen; Atharva Kelkar; Frank Noé; Cecilia Clementi

doi:10.1016/j.sbi.2023.102533

Machine learned coarse-grained protein force-fields: Are we there yet?

Curr Opin Struct Biol. 2023 Apr:79:102533. doi: 10.1016/j.sbi.2023.102533. Epub 2023 Jan 31.

Authors

Affiliations

¹ Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany.
² Department of Physics and Astronomy, Rice University, 6100 Main Street, Houston, 77005, Texas, USA; Department of Physics, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany; Center for Theoretical Biological Physics, Rice University, 6100 Main Street, Houston, 77005, Texas, USA.
³ Department of Physics, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany. Electronic address: https://twitter.com/pbrun03.
⁴ Department of Physics, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany. Electronic address: https://twitter.com/FelixMusil.
⁵ Department of Physics, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany.
⁶ Department of Physics, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany. Electronic address: https://twitter.com/sayeg84.
⁷ Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany. Electronic address: https://twitter.com/hello_yaoyi.
⁸ Microsoft Research AI4Science, Karl-Liebknecht Str. 32, Berlin, 10178, Berlin, Germany; Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany; Department of Physics, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany; Department of Chemistry, Rice University, 6100 Main Street, Houston, 77005, Texas, USA. Electronic address: https://twitter.com/FrankNoeBerlin.
⁹ Department of Physics, Freie Universität Berlin, Arnimallee 12, 14195, Berlin, Germany; Center for Theoretical Biological Physics, Rice University, 6100 Main Street, Houston, 77005, Texas, USA; Department of Chemistry, Rice University, 6100 Main Street, Houston, 77005, Texas, USA; Department of Physics and Astronomy, Rice University, 6100 Main Street, Houston, 77005, Texas, USA. Electronic address: c.clementi@fu-berlin.de.

Abstract

The successful recent application of machine learning methods to scientific problems includes the learning of flexible and accurate atomic-level force-fields for materials and biomolecules from quantum chemical data. In parallel, the machine learning of force-fields at coarser resolutions is rapidly gaining relevance as an efficient way to represent the higher-body interactions needed in coarse-grained force-fields to compensate for the omitted degrees of freedom. Coarse-grained models are important for the study of systems at time and length scales exceeding those of atomistic simulations. However, the development of transferable coarse-grained models via machine learning still presents significant challenges. Here, we discuss recent developments in this field and current efforts to address the remaining challenges.

Publication types

Review
Research Support, Non-U.S. Gov't

MeSH terms

Machine Learning*
Thermodynamics*

Grants and funding

T15 LM007093/LM/NLM NIH HHS/United States