Predicting protein-protein interactions in the human proteome

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.

Authors

Institutions

Publication Details

Journal
Science
Published
2025-09-25
DOI
https://doi.org/10.1126/science.adt1630
Citations
31
Primary Topic
Bioinformatics and Genomic Networks
Type
article
Field-Weighted Citation Impact
24.99
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Predicting protein-protein interactions in the human proteome

Jimin Pei, Qian Cong, Minkyung Baek, Rongqing Yuan et al.
31 citations
Science
Bioinformatics and Genomic Networks
24.99
article

Predicting protein-protein interactions in the human proteome

Jimin Pei, Qian Cong, Minkyung Baek, Rongqing Yuan, June‐Ki Kim, David A. Baker, Jesse Durham, Hee‐Jung Choi, Siqi Liu, Jing Zhang, Ian R. Humphreys, Chulwon Choi
article en
31 citations

Abstract

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.

ScienceVol. 390(6771)
Children's Medical Center (US), Howard Hughes Medical Institute (US), Seoul National University (KR), Yonsei University (KR), University of Washington (US), Southwestern Medical Center (US), The University of Texas Southwestern Medical Center (US)
Openalex Percentile: Top 0%
Bioinformatics and Genomic Networks
24.99
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.