Disentanglement of Evolutionary Constraints in Statistical Models of Proteins
PRX Life · 18.04.2024 · 2 (2)
DOI: 10.1103/prxlife.2.023005 ↗Kurz gefasst
Fachartikel in der Zeitschrift PRX Life, online erschienen am 18.04.2024. Verfasst von Haobo Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH Office of the Director, Japan Science and Technology Corporation, Precursory Research for Embryonic Science and Technology.
Abstract (Originalsprache)
The exponential growth of protein sequences in the post-genomic era has revolutionized the application of generative sequence models for pivotal tasks such as contact prediction, protein design, alignment, and homology search. Despite remarkable progress in these areas, the interpretability of the modeled pairwise parameters remains limited due to complexities arising from coevolution, phylogeny, and entropy. While post-correction methods for contact prediction have been developed to eliminate entropy-related contributions from predicted contact maps, there is currently no direct approach to correct entropy in other applications reliant on raw parameters. In this paper, we investigate the sources of entropy signal and propose a novel spectral regularizer, LH (an abbreviation of Henri Lebesgue), to mitigate its impact during model fitting. By incorporating this regularizer into the GREMLIN framework (utilizing a Markov random field or Potts model), we enable the accurate inference of sparse contact maps while simultaneously improving interpretability and addressing overfitting concerns critical for sequence evaluation and design. To validate the efficacy of our approach, we design multiple protein sequences based on GREMLIN with both L2 and LH regularizers, and subsequently experimentally measure their using cDNA display proteolysis. Our findings demonstrate that proteins designed using the LH regularizer exhibit increased diversity and enhanced folding stability. Published by the American Physical Society 2024
Förderung
- NIH Office of the Director
- Japan Science and Technology Corporation
- Precursory Research for Embryonic Science and Technology
- FAS Division of Science, Harvard University
- University of Illinois at Chicago
- Rush University
- Human Frontier Science Program
- Northwestern University
Zitieren
APA
Wang, H., Feng, S., Tsuboyama, K., Liu, S., Rocklin, G. J., & Ovchinnikov, S. (2024). Disentanglement of Evolutionary Constraints in Statistical Models of Proteins. PRX Life, 2(2). https://doi.org/10.1103/prxlife.2.023005
Vancouver
Wang H, Feng S, Tsuboyama K, Liu S, Rocklin GJ, Ovchinnikov S. Disentanglement of Evolutionary Constraints in Statistical Models of Proteins. PRX Life. 2024;2(2). doi:10.1103/prxlife.2.023005
BibTeX
@article{Wang2024,
author = {Wang, Haobo and Feng, Shihao and Tsuboyama, Kotaro and Liu, Sirui and Rocklin, Gabriel J. and Ovchinnikov, Sergey},
title = {Disentanglement of Evolutionary Constraints in Statistical Models of Proteins},
journal = {PRX Life},
year = {2024},
volume = {2},
number = {2},
doi = {10.1103/prxlife.2.023005}
}
EUVIMED