EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Expert-guided protein language models enable accurate and blazingly fast fitness prediction

Céline Marquet, Julius Schlensok, Marina Abakarova, Burkhard Rost, Elodie Laine iD

Bioinformatics · 01.11.2024 · 40 (11)

DOI: 10.1093/bioinformatics/btae621 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 22.11.2024. Verfasst von Céline Marquet und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computation, Information, and Technology, Department of Informatics, Bioinformatics and Computational Biology, Technical University of Muni…. Hauptthemen laut MEDLINE: Drosophila melanogaster. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Research Council, Deutsche Forschungsgemeinschaft, German Ministry for Research and Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Exhaustive experimental annotation of the effect of all known protein variants remains daunting and expensive, stressing the need for scalable effect predictions. We introduce VespaG, a blazingly fast missense amino acid variant effect predictor, leveraging protein language model (pLM) embeddings as input to a minimal deep learning model. Results To overcome the sparsity of experimental training data, we created a dataset of 39 million single amino acid variants from the human proteome applying the multiple sequence alignment-based effect predictor GEMME as a pseudo standard-of-truth. This setup increases interpretability compared to the baseline pLM and is easily retrainable with novel or updated pLMs. Assessed against the ProteinGym benchmark (217 multiplex assays of variant effect—MAVE—with 2.5 million variants), VespaG achieved a mean Spearman correlation of 0.48 ± 0.02, matching top-performing methods evaluated on the same data. VespaG has the advantage of being orders of magnitude faster, predicting all mutational landscapes of all proteins in proteomes such as Homo sapiens or Drosophila melanogaster in under 30 min on a consumer laptop (12-core CPU, 16 GB RAM). Availability and implementation VespaG is available freely at https://github.com/jschlensok/vespag. The associated training data and predictions are available at https://doi.org/10.5281/zenodo.11085958.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drosophila melanogasterHumansComputational BiologyDeep LearningProteomeSoftwareProteinsAnimalsMutation, MissenseDatabases, Protein

Substanzen

ProteomeProteins

Autor:innen und Institutionen

  • School of Computation, Information, and Technology, Department of Informatics, Bioinformatics and Computational Biology, Technical University of Munich, Garching/Munich 85748, Germany.
  • Laboratory of Computational and Quantitative Biology, UMR 7238, Sorbonne Université, CNRS, IBPS, Paris 75005, France.
  • UMR U1284, Universite Paris Cité, INSERM, Paris 75004, France.
  • School of Life Sciences Weihenstephan, Technical University of Munich, Freising, Germany.
  • Institut Universitaire de France, Paris 75005, France.

ORCID-Profile: Elodie Laine

Förderung

  • European Research Council
  • Deutsche Forschungsgemeinschaft
  • German Ministry for Research and Education

Zitieren

APA

Marquet, C., Schlensok, J., Abakarova, M., Rost, B., & Laine, E. (2024). Expert-guided protein language models enable accurate and blazingly fast fitness prediction. Bioinformatics, 40(11). https://doi.org/10.1093/bioinformatics/btae621

Vancouver

Marquet C, Schlensok J, Abakarova M, Rost B, Laine E. Expert-guided protein language models enable accurate and blazingly fast fitness prediction. Bioinformatics. 2024;40(11). doi:10.1093/bioinformatics/btae621

BibTeX
@article{Marquet2024,
  author = {Marquet, Céline and Schlensok, Julius and Abakarova, Marina and Rost, Burkhard and Laine, Elodie},
  title = {Expert-guided protein language models enable accurate and blazingly fast fitness prediction},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {11},
  doi = {10.1093/bioinformatics/btae621}
}
Kostenlos starten →