EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Protein language models meet reduced amino acid alphabets

Ioan Ieremie iD, Rob M Ewing, Mahesan Niranjan

Bioinformatics · 01.02.2024 · 40 (2)

DOI: 10.1093/bioinformatics/btae061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 03.02.2024. Verfasst von Ioan Ieremie und 2 weiteren Autor:innen. Beteiligte Einrichtung: Vision, Learning & Control Group, University of Southampton, Southampton SO17 1BJ, United Kingdom. Hauptthemen laut MEDLINE: Protein Folding, Proteins. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council, EPSRC, Artificial and Augmented Intelligence for Automated Scientific Discovery.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Protein language models (PLMs), which borrowed ideas for modelling and inference from natural language processing, have demonstrated the ability to extract meaningful representations in an unsupervised way. This led to significant performance improvement in several downstream tasks. Clustering amino acids based on their physical–chemical properties to achieve reduced alphabets has been of interest in past research, but their application to PLMs or folding models is unexplored. Results Here, we investigate the efficacy of PLMs trained on reduced amino acid alphabets in capturing evolutionary information, and we explore how the loss of protein sequence information impacts learned representations and downstream task performance. Our empirical work shows that PLMs trained on the full alphabet and a large number of sequences capture fine details that are lost in alphabet reduction methods. We further show the ability of a structure prediction model(ESMFold) to fold CASP14 protein sequences translated using a reduced alphabet. For 10 proteins out of the 50 targets, reduced alphabets improve structural predictions with LDDT-Cα differences of up to 19%. Availability and implementation Trained models and code are available at github.com/Ieremie/reduced-alph-PLM.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Protein FoldingProteinsAmino AcidsAmino Acid SequenceAmines

Substanzen

ProteinsAmino AcidsAmines

Autor:innen und Institutionen

  • Vision, Learning & Control Group, University of Southampton, Southampton SO17 1BJ, United Kingdom.
  • Biological Sciences, University of Southampton, Southampton SO17 1BJ, United Kingdom.

ORCID-Profile: Ioan Ieremie

Förderung

  • Engineering and Physical Sciences Research Council
  • EPSRC
  • Artificial and Augmented Intelligence for Automated Scientific Discovery

Zitieren

APA

Ieremie, I., Ewing, R. M., & Niranjan, M. (2024). Protein language models meet reduced amino acid alphabets. Bioinformatics, 40(2). https://doi.org/10.1093/bioinformatics/btae061

Vancouver

Ieremie I, Ewing RM, Niranjan M. Protein language models meet reduced amino acid alphabets. Bioinformatics. 2024;40(2). doi:10.1093/bioinformatics/btae061

BibTeX
@article{Ieremie2024,
  author = {Ieremie, Ioan and Ewing, Rob M and Niranjan, Mahesan},
  title = {Protein language models meet reduced amino acid alphabets},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {2},
  doi = {10.1093/bioinformatics/btae061}
}
Kostenlos starten →