{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T18:16:17Z","timestamp":1787940977284,"version":"build-2784847793"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"vor","delay-in-days":9,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Brain Science and Brain-like Intelligence Technology-National Science and Technology Major","award":["2022ZD0213700"],"award-info":[{"award-number":["2022ZD0213700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302426"],"award-info":[{"award-number":["62302426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473382"],"award-info":[{"award-number":["62473382"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Hunan Provincial Natural Science Foundation of China","doi-asserted-by":"crossref","award":["2025JJ20068"],"award-info":[{"award-number":["2025JJ20068"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Predicting variant pathogenicity is crucial for clinical genetics. Existing approaches face two primary limitations. First, biologically, data for pathogenicity prediction often lacks explicit modeling of the gene-variant-feature association structure. A single gene can harbor multiple variants, and each variant can be characterized by multiple features intrinsically associated with its parent gene. Current methods fail to explicitly model the gene-variant-feature association, thus limiting their performance. Second, methodologically, the variant-pathogenicity association is often assumed to comprise a linear component alongside a nonlinear one. However, current methods typically do not explicitly model the linear component, often failing to disentangle the linear component that might be better addressed with a linear approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>To overcome these limitations, we introduce simultaneous modeling of linear and nonlinear components of knowledge graph (SIMLINK). This novel approach leverages a knowledge graph to model gene-variant-feature associations and a linear model to isolate the linear component. We begin by constructing a variant-centered knowledge graph, comprising over 8 million triplets, which explicitly models the associations between genes, variants, and features. Subsequently, the linear and nonlinear components are learned using a combination of linear and graph neural networks. We train SIMLINK on ClinVar variants. Benchmarking experiments on independent test sets demonstrate its superior prediction on both missense and synonymous variants compared to state-of-the-art methods, including CADD and AlphaMissense. We evaluate the impact of allele frequencies on prediction performance. Applied to variants implicated in Autism Spectrum Disorder, SIMLINK effectively distinguished between high- and low-confidence variants, and critically, the genes harboring top-ranked variants are highly pathogenic.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The source code is freely available at https:\/\/github.com\/Chen-LuWang\/SIMLINK.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag601","type":"journal-article","created":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T11:54:46Z","timestamp":1786190086000},"source":"Crossref","is-referenced-by-count":0,"title":["SIMLINK enables accurate variant pathogenicity prediction through modeling the gene-variant-feature association structure"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3438-739X","authenticated-orcid":false,"given":"Hong-Dong","family":"Li","sequence":"first","affiliation":[{"name":"Central South University School of Computer Science and Engineering, , Changsha, Hunan 410083,","place":["P.R. China"]},{"name":"Hunan Provincial Key Lab on Bioinformatics , Changsha, Hunan 410083,","place":["P.R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenlu","family":"Wang","sequence":"additional","affiliation":[{"name":"Central South University School of Computer Science and Engineering, , Changsha, Hunan 410083,","place":["P.R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongfang","family":"Yan","sequence":"additional","affiliation":[{"name":"Central South University School of Computer Science and Engineering, , Changsha, Hunan 410083,","place":["P.R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenkui","family":"Huang","sequence":"additional","affiliation":[{"name":"Central South University School of Computer Science and Engineering, , Changsha, Hunan 410083,","place":["P.R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongxuan","family":"Li","sequence":"additional","affiliation":[{"name":"Central South University School of Computer Science and Engineering, , Changsha, Hunan 410083,","place":["P.R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaokai","family":"Wang","sequence":"additional","affiliation":[{"name":"Central South University School of Computer Science and Engineering, , Changsha, Hunan 410083,","place":["P.R. China"]},{"name":"Hong Kong University of Science and Technology Department of Mathematics, , Hong Kong,","place":["P.R. China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,10]]},"reference":[{"key":"2026082813172558600_btag601-B1","doi-asserted-by":"crossref","first-page":"1843","DOI":"10.1093\/bioinformatics\/btt308","article-title":"Identification of deleterious synonymous variants in human genomes","volume":"29","author":"Buske","year":"2013","journal-title":"Bioinformatics"},{"key":"2026082813172558600_btag601-B2","first-page":"5:1","article-title":"Knowledge graphs for the life sciences: recent developments, challenges and opportunities","volume":"1","author":"Chen","year":"2023","journal-title":"Trans Graph Data Knowl"},{"key":"2026082813172558600_btag601-B3","doi-asserted-by":"crossref","first-page":"eadg7492","DOI":"10.1126\/science.adg7492","article-title":"Accurate proteome-wide missense variant effect prediction with alphamissense","volume":"381","author":"Cheng","year":"2023","journal-title":"Science"},{"key":"2026082813172558600_btag601-B4","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1093\/bib\/bbz047","article-title":"Comparison and integration of computational methods for deleterious synonymous mutation prediction","volume":"21","author":"Cheng","year":"2020","journal-title":"Brief Bioinform"},{"key":"2026082813172558600_btag601-B5","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1038\/nature13772","article-title":"Synaptic, transcriptional and chromatin genes disrupted in autism","volume":"515","author":"De Rubeis","year":"2014","journal-title":"Nature"},{"key":"2026082813172558600_btag601-B6","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1093\/hmg\/ddu733","article-title":"Comparison and integration of deleteriousness prediction methods for nonsynonymous SNVs in whole exome sequencing studies","volume":"24","author":"Dong","year":"2015","journal-title":"Hum Mol Genet"},{"key":"2026082813172558600_btag601-B7","doi-asserted-by":"crossref","first-page":"D649","DOI":"10.1093\/nar\/gkx1132","article-title":"The reactome pathway knowledgebase","volume":"46","author":"Fabregat","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026082813172558600_btag601-B8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/gcc.2870040102","article-title":"Tp53 tumor suppressor gene: a model for investigating human mutagenesis","volume":"4","author":"Fromentel","year":"1992","journal-title":"Genes Chromosomes Cancer"},{"key":"2026082813172558600_btag601-B9","doi-asserted-by":"crossref","first-page":"2500","DOI":"10.3390\/cells9112500","article-title":"Linking autism risk genes to disruption of cortical development","volume":"9","author":"Garcia-Forn","year":"2020","journal-title":"Cells"},{"key":"2026082813172558600_btag601-B10","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1038\/s41467-017-00141-2","article-title":"Annotating pathogenic non-coding variants in genic regions","volume":"8","author":"Gelfman","year":"2017","journal-title":"Nat Commun"},{"key":"2026082813172558600_btag601-B11","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.conb.2019.04.010","article-title":"Regulation of neuronal connectivity in the mammalian brain by chromatin remodeling","volume":"59","author":"Goodman","year":"2019","journal-title":"Curr Opin Neurobiol"},{"key":"2026082813172558600_btag601-B12","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1002\/humu.22768","article-title":"The evaluation of tools used to predict the impact of missense variants is hindered by two types of circularity","volume":"36","author":"Grimm","year":"2015","journal-title":"Hum Mutat"},{"key":"2026082813172558600_btag601-B13","doi-asserted-by":"crossref","first-page":"2251","DOI":"10.1016\/j.celrep.2016.04.090","article-title":"De novo mutations in DENR disrupt neuronal development and link congenital neurological disorders to faulty mRNA translation re-initiation","volume":"15","author":"Haas","year":"2016","journal-title":"Cell Rep"},{"key":"2026082813172558600_btag601-B14","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1038\/nature13908","article-title":"The contribution of de novo coding mutations to autism spectrum disorder","volume":"515","author":"Iossifov","year":"2014","journal-title":"Nature"},{"key":"2026082813172558600_btag601-B15","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1109\/TNNLS.2021.3070843","article-title":"A survey on knowledge graphs: representation, acquisition, and applications","volume":"33","author":"Ji","year":"2022","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2026082813172558600_btag601-B16","doi-asserted-by":"crossref","first-page":"104593","DOI":"10.1016\/j.ejmg.2022.104593","article-title":"Phenotype of col3a1\/col5a2 deletion patients","volume":"65","author":"Kempers","year":"2022","journal-title":"Eur J Med Genet"},{"key":"2026082813172558600_btag601-B17","author":"Kipf","year":"2017"},{"key":"2026082813172558600_btag601-B18","doi-asserted-by":"crossref","first-page":"D1062","DOI":"10.1093\/nar\/gkx1153","article-title":"ClinVar: improving access to variant interpretations and supporting evidence","volume":"46","author":"Landrum","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026082813172558600_btag601-B19","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1186\/s13073-022-01120-z","article-title":"MetaRNN: differentiating rare pathogenic and rare benign missense snvs and indels using deep learning","volume":"14","author":"Li","year":"2022","journal-title":"Genome Med"},{"key":"2026082813172558600_btag601-B20","doi-asserted-by":"crossref","first-page":"110305","DOI":"10.1016\/j.jbc.2025.110305","article-title":"Calcium triggers calmodulin degradation to induce EGF receptor instability and overcome non-small cell lung cancer resistance to tyrosine kinase inhibitors","volume":"301","author":"Li","year":"2025","journal-title":"J Biol Chem"},{"key":"2026082813172558600_btag601-B21","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1038\/ncb3487","article-title":"Shank proteins limit integrin activation by directly interacting with rap1 and r-Ras","volume":"19","author":"Lilja","year":"2017","journal-title":"Nat Cell Biol"},{"key":"2026082813172558600_btag601-B22","doi-asserted-by":"crossref","first-page":"bbae611","DOI":"10.1093\/bib\/bbae611","article-title":"Limo-GCN: a linear model-integrated graph convolutional network for predicting Alzheimer disease genes","volume":"26","author":"Lin","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026082813172558600_btag601-B23","doi-asserted-by":"crossref","first-page":"263","DOI":"10.3389\/fncel.2016.00263","article-title":"A subset of autism-associated genes regulate the structural stability of neurons","volume":"10","author":"Lin","year":"2016","journal-title":"Front Cell Neurosci"},{"key":"2026082813172558600_btag601-B24","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1186\/s13073-020-00803-9","article-title":"dbNSFP v4: a comprehensive database of transcript-specific functional predictions and annotations for human nonsynonymous and splice-site snvs","volume":"12","author":"Liu","year":"2020","journal-title":"Genome Med"},{"key":"2026082813172558600_btag601-B25","doi-asserted-by":"crossref","first-page":"3812","DOI":"10.1093\/nar\/gkg509","article-title":"SIFT: predicting amino acid changes that affect protein function","volume":"31","author":"Ng","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2026082813172558600_btag601-B26","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1007\/s00439-021-02283-2","article-title":"Missense and truncating variants in chd5 in a dominant neurodevelopmental disorder with intellectual disability, behavioral disturbances, and epilepsy","volume":"140","author":"Parenti","year":"2021","journal-title":"Hum Genet"},{"key":"2026082813172558600_btag601-B27","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1038\/nature09146","article-title":"Functional impact of global rare copy number variation in autism spectrum disorders","volume":"466","author":"Pinto","year":"2010","journal-title":"Nature"},{"key":"2026082813172558600_btag601-B28","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1038\/s41467-020-20847-0","article-title":"MVP predicts the pathogenicity of missense variants by deep learning","volume":"12","author":"Qi","year":"2021","journal-title":"Nat Commun"},{"key":"2026082813172558600_btag601-B29","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1093\/bioinformatics\/btu703","article-title":"DANN: a deep learning approach for annotating the pathogenicity of genetic variants","volume":"31","author":"Quang","year":"2015","journal-title":"Bioinformatics"},{"key":"2026082813172558600_btag601-B30","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/s00439-025-02732-2","article-title":"Critical assessment of missense variant effect predictors on disease-relevant variant data","volume":"144","author":"Rastogi","year":"2025","journal-title":"Hum Genet"},{"key":"2026082813172558600_btag601-B31","doi-asserted-by":"crossref","first-page":"D886","DOI":"10.1093\/nar\/gky1016","article-title":"CADD: predicting the deleteriousness of variants throughout the human genome","volume":"47","author":"Rentzsch","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2026082813172558600_btag601-B32","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/1479-7364-8-11","article-title":"Ranking non-synonymous single nucleotide polymorphisms based on disease concepts","volume":"8","author":"Shihab","year":"2014","journal-title":"Hum Genomics"},{"key":"2026082813172558600_btag601-B33","doi-asserted-by":"crossref","first-page":"1536","DOI":"10.1093\/bioinformatics\/btv009","article-title":"An integrative approach to predicting the functional effects of non-coding and coding sequence variation","volume":"31","author":"Shihab","year":"2015","journal-title":"Bioinformatics"},{"key":"2026082813172558600_btag601-B34","doi-asserted-by":"crossref","first-page":"E4468","DOI":"10.1073\/pnas.1405266111","article-title":"CHD8 regulates neurodevelopmental pathways associated with autism spectrum disorder in neural progenitors","volume":"111","author":"Sugathan","year":"2014","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026082813172558600_btag601-B35","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1038\/s41588-018-0167-z","article-title":"Predicting the clinical impact of human mutation with deep neural networks","volume":"50","author":"Sundaram","year":"2018","journal-title":"Nat Genet"},{"key":"2026082813172558600_btag601-B36","doi-asserted-by":"crossref","first-page":"bbab123","DOI":"10.1093\/bib\/bbab123","article-title":"usDSM: a novel method for deleterious synonymous mutation prediction using undersampling scheme","volume":"22","author":"Tang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2026082813172558600_btag601-B37","doi-asserted-by":"crossref","first-page":"1914","DOI":"10.1093\/bioinformatics\/btw086","article-title":"dbDSM: a manually curated database for deleterious synonymous mutations","volume":"32","author":"Wen","year":"2016","journal-title":"Bioinformatics"},{"key":"2026082813172558600_btag601-B38","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1016\/j.cell.2013.10.020","article-title":"Coexpression networks implicate human midfetal deep cortical projection neurons in the pathogenesis of autism","volume":"155","author":"Willsey","year":"2013","journal-title":"Cell"},{"key":"2026082813172558600_btag601-B39","doi-asserted-by":"crossref","first-page":"4626","DOI":"10.1093\/bioinformatics\/btab529","article-title":"3Cnet: pathogenicity prediction of human variants using multitask learning with evolutionary constraints","volume":"37","author":"Won","year":"2021","journal-title":"Bioinformatics"},{"key":"2026082813172558600_btag601-B40","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1186\/s13229-018-0244-2","article-title":"Autism-associated chd8 deficiency impairs axon development and migration of cortical neurons","volume":"9","author":"Xu","year":"2018","journal-title":"Mol Autism"},{"key":"2026082813172558600_btag601-B41","doi-asserted-by":"crossref","first-page":"178370","DOI":"10.1016\/j.ejphar.2025.178370","article-title":"Disrupted binding dynamics of the CaMD130G mutant to Cav1.2 channels: implications for long QT syndrome pathogenesis","volume":"1008","author":"Zhang","year":"2025","journal-title":"Eur J Pharmacol"},{"key":"2026082813172558600_btag601-B42","doi-asserted-by":"crossref","first-page":"1305","DOI":"10.1038\/s41588-022-01148-2","article-title":"Integrating de novo and inherited variants in 42,607 autism cases identifies mutations in new moderate-risk genes","volume":"54","author":"Zhou","year":"2022","journal-title":"Nat Genet"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag601\/70604835\/btag601.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/8\/btag601\/70604835\/btag601.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/8\/btag601\/70604835\/btag601.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:17:37Z","timestamp":1787937457000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag601\/8758504"}},"subtitle":[],"editor":[{"given":"Russell","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":42,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag601","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,8]]},"article-number":"btag601"}}