EUVIMEDEUVIMED entdecken
Crossref

Enzyme function prediction using contrastive learning

Tianhao Yu iD, Haiyang Cui iD, Jianan Canal Li, Yunan Luo iD, Guangde Jiang, Huimin Zhao iD

Science · 31.03.2023 · 379 (6639) · 1358-1363

DOI: 10.1126/science.adf2465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science, erschienen am 31.03.2023. Verfasst von Tianhao Yu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA. Hauptthemen laut MEDLINE: Enzymes, Machine Learning, Proteins, Molecular Sequence Annotation. Die Arbeit wurde bisher 463-mal zitiert (Crossref) und nennt 80 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Enzyme function annotation is a fundamental challenge, and numerous computational tools have been developed. However, most of these tools cannot accurately predict functional annotations, such as enzyme commission (EC) number, for less-studied proteins or those with previously uncharacterized functions or multiple activities. We present a machine learning algorithm named CLEAN (contrastive learning–enabled enzyme annotation) to assign EC numbers to enzymes with better accuracy, reliability, and sensitivity compared with the state-of-the-art tool BLASTp. The contrastive learning framework empowers CLEAN to confidently (i) annotate understudied enzymes, (ii) correct mislabeled enzymes, and (iii) identify promiscuous enzymes with two or more EC numbers—functions that we demonstrate by systematic in silico and in vitro experiments. We anticipate that this tool will be widely used for predicting the functions of uncharacterized enzymes, thereby advancing many fields, such as genomics, synthetic biology, and biocatalysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EnzymesMachine LearningProteinsMolecular Sequence AnnotationSequence Analysis, ProteinAlgorithmsComputational BiologyGenomicsReproducibility of ResultsBiocatalysis

Substanzen

EnzymesProteins

Autor:innen und Institutionen

  • Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
  • Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
  • National Science Foundation Molecule Maker Lab Institute, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
  • Department of Computer Science, Cornell University, Ithaca, NY 14850, USA.
  • School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA 30308, USA.
  • US Department of Energy Center for Advanced Bioenergy and Bioproducts Innovation, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.

ORCID-Profile: Tianhao Yu, Haiyang Cui, Yunan Luo, Huimin Zhao

Zitieren

APA

Yu, T., Cui, H., Li, J. C., Luo, Y., Jiang, G., & Zhao, H. (2023). Enzyme function prediction using contrastive learning. Science, 379(6639), 1358-1363. https://doi.org/10.1126/science.adf2465

Vancouver

Yu T, Cui H, Li JC, Luo Y, Jiang G, Zhao H. Enzyme function prediction using contrastive learning. Science. 2023;379(6639):1358-1363. doi:10.1126/science.adf2465

BibTeX
@article{Yu2023,
  author = {Yu, Tianhao and Cui, Haiyang and Li, Jianan Canal and Luo, Yunan and Jiang, Guangde and Zhao, Huimin},
  title = {Enzyme function prediction using contrastive learning},
  journal = {Science},
  year = {2023},
  volume = {379},
  number = {6639},
  pages = {1358--1363},
  doi = {10.1126/science.adf2465}
}
Kostenlos starten →