<HashMap><database>biostudies-literature</database><scores/><additional><submitter>Hanna G</submitter><funding>Wellcome Trust</funding><funding>Biotechnology and Biological Sciences Research Council</funding><pagination>168374</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC7617522</full_dataset_link><repository>biostudies-literature</repository><omics_type>Unknown</omics_type><volume>436(2)</volume><pubmed_abstract>Variant effect predictors assess if a substitution is pathogenic or benign. Most predictors, including those that are structure-based, are designed for globular proteins in aqueous environments and do not consider that the variant residue is located within the membrane. We report Missense3D-TM that provides a structure-based assessment of the impact of a missense variant located within a membrane. On a dataset of 2,078 pathogenic and 1,060 benign variants, spanning 711 proteins from 706 structures, Missense3D-TM achieved an accuracy of 66%, Mathews correlation coefficient of 0.37, sensitivity of 58% and specificity of 81%. Missense3D-TM performed similarly to mCSM-membrane: accuracy 66% vs 61% (p = 0.02) on an unbalanced test set and 70% vs 67% (p = 0.20) on a balanced test set. The Missense3D-TM website provides an analysis of the structural effects of the variant along with its predicted position within the membrane. The web server is available at http://missense3d.bc.ic.ac.uk/.</pubmed_abstract><journal>Journal of molecular biology</journal><pubmed_title>Missense3D-TM: Predicting the Effect of Missense Variants in Helical Transmembrane Protein Regions Using 3D Protein Structures.</pubmed_title><pmcid>PMC7617522</pmcid><funding_grant_id>BB/T010487/1</funding_grant_id><funding_grant_id>218242</funding_grant_id><funding_grant_id>BB/P023959/1</funding_grant_id><funding_grant_id>BB/X01830X/1</funding_grant_id><funding_grant_id>218242/Z/19/Z</funding_grant_id><funding_grant_id>104955</funding_grant_id><funding_grant_id>104955/Z/14/Z</funding_grant_id><pubmed_authors>Khanna T</pubmed_authors><pubmed_authors>Islam SA</pubmed_authors><pubmed_authors>Hanna G</pubmed_authors><pubmed_authors>David A</pubmed_authors><pubmed_authors>Sternberg MJE</pubmed_authors></additional><is_claimable>false</is_claimable><name>Missense3D-TM: Predicting the Effect of Missense Variants in Helical Transmembrane Protein Regions Using 3D Protein Structures.</name><description>Variant effect predictors assess if a substitution is pathogenic or benign. Most predictors, including those that are structure-based, are designed for globular proteins in aqueous environments and do not consider that the variant residue is located within the membrane. We report Missense3D-TM that provides a structure-based assessment of the impact of a missense variant located within a membrane. On a dataset of 2,078 pathogenic and 1,060 benign variants, spanning 711 proteins from 706 structures, Missense3D-TM achieved an accuracy of 66%, Mathews correlation coefficient of 0.37, sensitivity of 58% and specificity of 81%. Missense3D-TM performed similarly to mCSM-membrane: accuracy 66% vs 61% (p = 0.02) on an unbalanced test set and 70% vs 67% (p = 0.20) on a balanced test set. The Missense3D-TM website provides an analysis of the structural effects of the variant along with its predicted position within the membrane. The web server is available at http://missense3d.bc.ic.ac.uk/.</description><dates><release>2024-01-01T00:00:00Z</release><publication>2024 Jan</publication><modification>2026-06-02T07:22:44.203Z</modification><creation>2025-07-05T03:04:13.424Z</creation></dates><accession>S-EPMC7617522</accession><cross_references><pubmed>38182301</pubmed><doi>10.1016/j.jmb.2023.168374</doi></cross_references></HashMap>