Predicting protein-protein interactions in the human proteome
成果类型：
Article
署名作者：
Zhang, Jing; Humphreys, Ian R.; Pei, Jimin; Kim, Jinuk; Choi, Chulwon; Yuan, Rongqing; Durham, Jesse; Liu, Siqi; Choi, Hee-Jung; Baek, Minkyung; Baker, David; Cong, Qian
署名单位：
University of Texas System; University of Texas Southwestern Medical Center; University of Texas System; University of Texas Southwestern Medical Center; University of Texas System; University of Texas Southwestern Medical Center; University of Washington; University of Washington Seattle; University of Washington; University of Washington Seattle; Seoul National University (SNU); Yonsei University; University of Texas System; University of Texas Southwestern Medical Center; University of Texas System; University of Texas Southwestern Medical Center; Seoul National University (SNU); Howard Hughes Medical Institute; University of Washington; University of Washington Seattle
刊物名称：
SCIENCE
ISSN/ISSBN：
0036-8075; 1095-9203
DOI：
10.1126/science.adt1630
发表日期：
2025-10-23
页码：
eadt1630
关键词：
map
摘要：
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.
来源URL：