biostudies-literaturePennica CWellcome TrustBiotechnology and Biological Sciences Research Council168060https://www.ebi.ac.uk/biostudies/studies/S-EPMC7617523biostudies-literatureUnknown435(14)In 2019, we released Missense3D which identifies stereochemical features that are disrupted by a missense variant, such as introducing a buried charge. Missense3D analyses the effect of a missense variant on a single structure and thus may fail to identify as damaging surface variants disrupting a protein interface i.e., a protein-protein interaction (PPI) site. Here we present Missense3D-PPI designed to predict missense variants at PPI interfaces. Our development dataset comprised of 1,279 missense variants (pathogenic n = 733, benign n = 546) in 434 proteins and 545 experimental structures of PPI complexes. Benchmarking of Missense3D-PPI was performed after dividing the dataset in training (320 benign and 320 pathogenic variants) and testing (226 benign and 413 pathogenic). Structural feJournal of molecular biologyMissense3D-PPI: A Web Resource to Predict the Impact of Missense Variants at Protein Interfaces Using 3D Structural Data.PMC7617523BB/T010487/1218242BB/P023959/1218242/Z/19/Z104955104955/Z/14/ZIslam SAPennica CHanna GDavid ASternberg MJEfalseMissense3D-PPI: A Web Resource to Predict the Impact of Missense Variants at Protein Interfaces Using 3D Structural Data.In 2019, we released Missense3D which identifies stereochemical features that are disrupted by a missense variant, such as introducing a buried charge. Missense3D analyses the effect of a missense variant on a single structure and thus may fail to identify as damaging surface variants disrupting a protein interface i.e., a protein-protein interaction (PPI) site. Here we present Missense3D-PPI designed to predict missense variants at PPI interfaces. Our development dataset comprised of 1,279 missense variants (pathogenic n = 733, benign n = 546) in 434 proteins and 545 experimental structures of PPI complexes. Benchmarking of Missense3D-PPI was performed after dividing the dataset in training (320 benign and 320 pathogenic variants) and testing (226 benign and 413 pathogenic). Structural fe2023-01-01T00:00:00Z2023 Jul2026-06-02T12:01:24.567Z2025-07-10T03:08:32.272ZS-EPMC76175233735690510.1016/j.jmb.2023.168060