EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Infer global, predict local: Quantity-relevance trade-off in protein fitness predictions from sequence data

Lorenzo Posani iD, Francesca Rizzato, Rémi Monasson iD, Simona Cocco iD

PLOS Computational Biology · 2023

DOI: 10.1371/journal.pcbi.1011521 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2023. Verfasst von Lorenzo Posani und 3 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Physics of the Ecole Normale Supérieure, CNRS UMR8023 & PSL Research, Sorbonne Université, Paris, France. Hauptthemen laut MEDLINE: Proteins, Biological Evolution. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agence Nationale de la Recherche.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting the effects of mutations on protein function is an important issue in evolutionary biology and biomedical applications. Computational approaches, ranging from graphical models to deep-learning architectures, can capture the statistical properties of sequence data and predict the outcome of high-throughput mutagenesis experiments probing the fitness landscape around some wild-type protein. However, how the complexity of the models and the characteristics of the data combine to determine the predictive performance remains unclear. Here, based on a theoretical analysis of the prediction error, we propose descriptors of the sequence data, characterizing their quantity and relevance relative to the model. Our theoretical framework identifies a trade-off between these two quantities, and determines the optimal subset of data for the prediction task, showing that simple models can outperform complex ones when inferred from adequately-selected sequences. We also show how repeated subsampling of the sequence data is informative about how much epistasis in the fitness landscape is not captured by the computational model. Our approach is illustrated on several protein families, as well as on in silico solvable protein models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsBiological EvolutionMutagenesisMutationComputer SimulationGenetic FitnessModels, Genetic

Substanzen

Proteins

Autor:innen und Institutionen

  • Laboratory of Physics of the Ecole Normale Supérieure, CNRS UMR8023 & PSL Research, Sorbonne Université, Paris, France.

ORCID-Profile: Lorenzo Posani, Rémi Monasson, Simona Cocco

Förderung

  • Agence Nationale de la Recherche

Zitieren

APA

Posani, L., Rizzato, F., Monasson, R., & Cocco, S. (2023). Infer global, predict local: Quantity-relevance trade-off in protein fitness predictions from sequence data. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1011521

Vancouver

Posani L, Rizzato F, Monasson R, Cocco S. Infer global, predict local: Quantity-relevance trade-off in protein fitness predictions from sequence data. PLOS Computational Biology. 2023. doi:10.1371/journal.pcbi.1011521

BibTeX
@article{Posani2023,
  author = {Posani, Lorenzo and Rizzato, Francesca and Monasson, Rémi and Cocco, Simona},
  title = {Infer global, predict local: Quantity-relevance trade-off in protein fitness predictions from sequence data},
  journal = {PLOS Computational Biology},
  year = {2023},
  doi = {10.1371/journal.pcbi.1011521}
}
Kostenlos starten →