Predicting protein-protein interactions in the human proteome
Science · 23.10.2025 · 390 (6771)
DOI: 10.1126/science.adt1630 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science, erschienen am 23.10.2025. Verfasst von Jing Zhang und 11 weiteren Autor:innen. Beteiligte Einrichtung: Eugene McDermott Center for Human Growth and Development, University of Texas Southwestern Medical Center, Dallas, TX, USA. Hauptthemen laut MEDLINE: Proteome, Deep Learning, Protein Interaction Mapping. Die Arbeit wurde bisher 118-mal zitiert (Crossref) und nennt 102 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIAID NIH HHS, NIGMS NIH HHS.
Abstract (Originalsprache)
Protein-protein interactions (PPIs) are essential for biological function. Coevolutionary analysis and deep-learning (DL)–based protein structure prediction have enabled comprehensive PPI identification in bacteria and yeast, but these approaches have had limited success for the more complex human proteome. We overcame this challenge by enhancing the coevolutionary signals with sevenfold-deeper multiple sequence alignments harvested from 30 petabytes of unassembled genomic data and developing a new DL network trained on augmented datasets of domain-domain interactions from 200 million predicted protein structures. We systematically screened 200 million human protein pairs and predicted 17,849 interactions with an expected precision of 90%, of which 3631 interactions were not identified in previous experimental screens. Three-dimensional models of these predicted interactions provide numerous hypotheses about protein function and mechanisms of human diseases.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Eugene McDermott Center for Human Growth and Development, University of Texas Southwestern Medical Center, Dallas, TX, USA.
- Department of Biophysics, University of Texas Southwestern Medical Center, Dallas, TX, USA.
- Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX, USA.
- Department of Biochemistry, University of Washington, Seattle, WA, USA.
- Institute for Protein Design, University of Washington, Seattle, WA, USA.
- Department of Biological Sciences, Seoul National University, Seoul, Republic of Korea.
ORCID-Profile: Jing Zhang, Ian R Humphreys, Jimin Pei, Jinuk Kim, Chulwon Choi, Rongqing Yuan, Siqi Liu, Hee-Jung Choi, Minkyung Baek, David Baker, Qian Cong
Förderung
- NIAID NIH HHS
- NIGMS NIH HHS
Zitieren
APA
Zhang, J., Humphreys, I. R., Pei, J., Kim, J., Choi, C., Yuan, R., Durham, J., Liu, S., Choi, H. J., Baek, M., Baker, D., & Cong, Q. (2025). Predicting protein-protein interactions in the human proteome. Science, 390(6771). https://doi.org/10.1126/science.adt1630
Vancouver
Zhang J, Humphreys IR, Pei J, Kim J, Choi C, Yuan R, et al. Predicting protein-protein interactions in the human proteome. Science. 2025;390(6771). doi:10.1126/science.adt1630
BibTeX
@article{Zhang2025,
author = {Zhang, Jing and Humphreys, Ian R and Pei, Jimin and Kim, Jinuk and Choi, Chulwon and Yuan, Rongqing and Durham, Jesse and Liu, Siqi and Choi, Hee-Jung and Baek, Minkyung and Baker, David and Cong, Qian},
title = {Predicting protein-protein interactions in the human proteome},
journal = {Science},
year = {2025},
volume = {390},
number = {6771},
doi = {10.1126/science.adt1630}
}
EUVIMED