Improved the heterodimer protein complex prediction with protein language models
Briefings in Bioinformatics · 20.07.2023 · 24 (4)
DOI: 10.1093/bib/bbad221 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 16.06.2023. Verfasst von Bo Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Technology, Tsinghua University, Beijing, China. Hauptthemen laut MEDLINE: Proteins, Algorithms. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: Technology and Innovation Major Project of the Ministry of Science and Technology of China, NSFC for Distinguished Young Scholar, Zhejiang Lab.
Abstract (Originalsprache)
AlphaFold-Multimer has greatly improved the protein complex structure prediction, but its accuracy also depends on the quality of the multiple sequence alignment (MSA) formed by the interacting homologs (i.e. interologs) of the complex under prediction. Here we propose a novel method, ESMPair, that can identify interologs of a complex using protein language models. We show that ESMPair can generate better interologs than the default MSA generation method in AlphaFold-Multimer. Our method results in better complex structure prediction than AlphaFold-Multimer by a large margin (+10.7% in terms of the Top-5 best DockQ), especially when the predicted complex structures have low confidence. We further show that by combining several MSA generation methods, we may yield even better complex structure prediction accuracy than Alphafold-Multimer (+22% in terms of the Top-5 best DockQ). By systematically analyzing the impact factors of our algorithm we find that the diversity of MSA of interologs significantly affects the prediction accuracy. Moreover, we show that ESMPair performs particularly well on complexes in eucaryotes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Computer Science and Technology, Tsinghua University, Beijing, China.
- Toyota Technological Institute at Chicago, Chicago, IL 60637, USA.
- Zhejiang Lab.
- MOE Key Laboratory of Bioinformatics, School of Medicine, Tsinghua University, Beijing 100084, China.
Förderung
- Technology and Innovation Major Project of the Ministry of Science and Technology of China
- NSFC for Distinguished Young Scholar
- Zhejiang Lab
Zitieren
APA
Chen, B., Xie, Z., Qiu, J., Ye, Z., Xu, J., & Tang, J. (2023). Improved the heterodimer protein complex prediction with protein language models. Briefings in Bioinformatics, 24(4). https://doi.org/10.1093/bib/bbad221
Vancouver
Chen B, Xie Z, Qiu J, Ye Z, Xu J, Tang J. Improved the heterodimer protein complex prediction with protein language models. Briefings in Bioinformatics. 2023;24(4). doi:10.1093/bib/bbad221
BibTeX
@article{Chen2023,
author = {Chen, Bo and Xie, Ziwei and Qiu, Jiezhong and Ye, Zhaofeng and Xu, Jinbo and Tang, Jie},
title = {Improved the heterodimer protein complex prediction with protein language models},
journal = {Briefings in Bioinformatics},
year = {2023},
volume = {24},
number = {4},
doi = {10.1093/bib/bbad221}
}
EUVIMED