<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><submitter>Xiong D</submitter><pubmed_abstract>Human genome sequencing studies have identified numerous loci associated with complex diseases. However, translating human genetic and genomic findings to disease pathobiology and therapeutic discovery remains a major challenge at multiscale interactome network levels. Here, we present a deep-learning-based ensemble framework, termed PIONEER (&lt;b>P&lt;/b>rotein-protein &lt;b>I&lt;/b>nteracti&lt;b>O&lt;/b>n i&lt;b>N&lt;/b>t&lt;b>E&lt;/b>rfac&lt;b>E&lt;/b> p&lt;b>R&lt;/b>ediction), that accurately predicts protein binding partner-specific interfaces for all protein interactions in humans and seven other common model organisms. We demonstrate that PIONEER outperforms existing state-of-the-art methods. We further systematically validated PIONEER predictions experimentally through generating 2,395 mutations and testing their impact o</pubmed_abstract><journal>bioRxiv : the preprint server for biology</journal><pagination>2023.04.24.538110</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC10168245</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>3D structural human interactome reveals proteome-wide perturbations by disease mutations.</pubmed_title><pmcid>PMC10168245</pmcid><pubmed_authors>Liang S</pubmed_authors><pubmed_authors>Gupta S</pubmed_authors><pubmed_authors>Cheng F</pubmed_authors><pubmed_authors>Lu W</pubmed_authors><pubmed_authors>Kang JJ</pubmed_authors><pubmed_authors>Loscalzo J</pubmed_authors><pubmed_authors>Zhou Y</pubmed_authors><pubmed_authors>Lee D</pubmed_authors><pubmed_authors>Yu H</pubmed_authors><pubmed_authors>Qiu Y</pubmed_authors><pubmed_authors>Xiong D</pubmed_authors><pubmed_authors>Zhao J</pubmed_authors><pubmed_authors>Eng C</pubmed_authors></additional><is_claimable>false</is_claimable><name>3D structural human interactome reveals proteome-wide perturbations by disease mutations.</name><description>Human genome sequencing studies have identified numerous loci associated with complex diseases. However, translating human genetic and genomic findings to disease pathobiology and therapeutic discovery remains a major challenge at multiscale interactome network levels. Here, we present a deep-learning-based ensemble framework, termed PIONEER (&lt;b>P&lt;/b>rotein-protein &lt;b>I&lt;/b>nteracti&lt;b>O&lt;/b>n i&lt;b>N&lt;/b>t&lt;b>E&lt;/b>rfac&lt;b>E&lt;/b> p&lt;b>R&lt;/b>ediction), that accurately predicts protein binding partner-specific interfaces for all protein interactions in humans and seven other common model organisms. We demonstrate that PIONEER outperforms existing state-of-the-art methods. We further systematically validated PIONEER predictions experimentally through generating 2,395 mutations and testing their impact o</description><dates><release>2023-01-01T00:00:00Z</release><publication>2023 Apr</publication><modification>2025-04-04T10:19:53.686Z</modification><creation>2025-02-19T00:12:26.644Z</creation></dates><accession>S-EPMC10168245</accession><cross_references><pubmed>37162909</pubmed><doi>10.1101/2023.04.24.538110</doi></cross_references></HashMap>