{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:57:24Z","timestamp":1791910644444,"version":"4.3.4"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T00:00:00Z","timestamp":1737331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92470124"],"award-info":[{"award-number":["92470124"]}],"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":["62373200"],"award-info":[{"award-number":["62373200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,2,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The drug\u2013disease, gene\u2013disease, and drug\u2013gene relationships, as high-frequency edge types, describe complex biological processes within the biomedical knowledge graph. The structural patterns formed by these three edges are the graph motifs of (disease, drug, gene) triplets. Among them, the triangle is a steady and important motif structure in the network, and other various motifs different from the triangle also indicate rich semantic relationships. However, existing methods only focus on the triangle representation learning for classification, and fail to further discriminate various motifs of triplets. A comprehensive method is needed to predict the various motifs within triplets, which will uncover new pharmacological mechanisms and improve our understanding of disease\u2013gene\u2013drug interactions. Identifying complex motif structures within triplets can also help us to study the structural properties of triangles.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We consider the seven typical motifs within the triplets and propose a novel graph contrastive learning-based method for triplet motif prediction (TriMoGCL). TriMoGCL utilizes a graph convolutional encoder to extract node features from the global network topology. Next, node pooling and edge pooling extract context information as the triplet features from global and local views. To avoid the redundant context information and motif imbalance problem caused by dense edges, we use node and class-prototype contrastive learning to denoise triplet features and enhance discrimination between motifs. The experiments on two different-scale knowledge graphs demonstrate the effectiveness and reliability of TriMoGCL in identifying various motif types. In addition, our model reveals new pharmacological mechanisms, providing a comprehensive analysis of triplet motifs.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Codes and datasets are available at https:\/\/github.com\/zhanglabNKU\/TriMoGCL and https:\/\/doi.org\/10.5281\/zenodo.14633572.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf023","type":"journal-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:26:51Z","timestamp":1737397611000},"source":"Crossref","is-referenced-by-count":2,"title":["A comprehensive graph neural network method for predicting triplet motifs in disease\u2013drug\u2013gene interactions"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4635-523X","authenticated-orcid":false,"given":"Chuanze","family":"Kang","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Nankai University , Tianjin 300350,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zonghuan","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University , Tianjin 300350,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8498-3451","authenticated-orcid":false,"given":"Han","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nankai University , Tianjin 300350,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,1,20]]},"reference":[{"key":"2025030422253496400_btaf023-B1","doi-asserted-by":"crossref","first-page":"14692","DOI":"10.1073\/pnas.0802675105","article-title":"Epigallocatechin-3-gallate inhibits il-6 synthesis and suppresses transsignaling by enhancing soluble gp130 production","volume":"105","author":"Ahmed","year":"2008","journal-title":"Proc Natl Acad Sci USA"},{"key":"2025030422253496400_btaf023-B2","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1038\/s41592-021-01252-x","article-title":"Effective gene expression prediction from sequence by integrating long-range interactions","volume":"18","author":"Avsec","year":"2021","journal-title":"Nat Methods"},{"key":"2025030422253496400_btaf023-B3","first-page":"35","author":"Besta","year":"2022"},{"key":"2025030422253496400_btaf023-B4","first-page":"4535","author":"Chavan","year":"2020"},{"key":"2025030422253496400_btaf023-B5","doi-asserted-by":"crossref","first-page":"2651","DOI":"10.1093\/bioinformatics\/btab169","article-title":"Muffin: multi-scale feature fusion for drug\u2013drug interaction prediction","volume":"37","author":"Chen","year":"2021","journal-title":"Bioinformatics"},{"key":"2025030422253496400_btaf023-B6","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1016\/j.annonc.2023.09.3103","article-title":"Open-label, phase ii, multicenter study of lasofoxifene plus abemaciclib for treating women with metastatic er+\/her2- breast cancer and an esr1 mutation after disease progression on prior therapies: Elaine 2","volume":"34","author":"Damodaran","year":"2023","journal-title":"Ann Oncol"},{"key":"2025030422253496400_btaf023-B7","first-page":"22118","article-title":"Open graph benchmark: datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025030422253496400_btaf023-B8","doi-asserted-by":"crossref","first-page":"3601","DOI":"10.1038\/s41591-024-03233-x","article-title":"A foundation model for clinician-centered drug repurposing","volume":"30","author":"Huang","year":"2024","journal-title":"Nat Med"},{"key":"2025030422253496400_btaf023-B9","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1109\/JBHI.2024.3467101","article-title":"Self-supervised contrastive learning on attribute and topology graphs for predicting relationships among lncrnas, mirnas and diseases","volume":"29","author":"Huang","year":"2024","journal-title":"IEEE J Biomed Health Inform"},{"key":"2025030422253496400_btaf023-B10","author":"Ioannidis"},{"key":"2025030422253496400_btaf023-B11","first-page":"401","author":"Jiang","year":"2022"},{"key":"2025030422253496400_btaf023-B12","author":"Kipf"},{"key":"2025030422253496400_btaf023-B13","doi-asserted-by":"crossref","first-page":"2538","DOI":"10.1093\/bioinformatics\/btz965","article-title":"Neural inductive matrix completion with graph convolutional networks for mirna-disease association prediction","volume":"36","author":"Li","year":"2020","journal-title":"Bioinformatics"},{"key":"2025030422253496400_btaf023-B14","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.1038\/s41551-022-00942-x","article-title":"Graph representation learning in biomedicine and healthcare","volume":"6","author":"Li","year":"2022","journal-title":"Nat Biomed Eng"},{"key":"2025030422253496400_btaf023-B15","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.1093\/bioinformatics\/btab767","article-title":"Deepkg: an end-to-end deep learning-based workflow for biomedical knowledge graph extraction, optimization and applications","volume":"38","author":"Li","year":"2022","journal-title":"Bioinformatics"},{"key":"2025030422253496400_btaf023-B16","first-page":"233","article-title":"Regulation of nf-\u03bab by the htlv-1 tax protein","volume":"7","author":"Li","year":"1999","journal-title":"Gene Expression"},{"key":"2025030422253496400_btaf023-B17","first-page":"4829","author":"Liu","year":"2023"},{"key":"2025030422253496400_btaf023-B18","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s40259-016-0162-9","article-title":"Trastuzumab in the treatment of breast cancer","volume":"30","author":"Maximiano","year":"2016","journal-title":"BioDrugs"},{"key":"2025030422253496400_btaf023-B19","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1111\/j.1349-7006.2002.tb01331.x","article-title":"Estradiol stabilizes p53 protein in breast cancer cell line, mcf\u20137","volume":"93","author":"Okumura","year":"2002","journal-title":"Jpn J Cancer Res"},{"key":"2025030422253496400_btaf023-B20","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1097\/CRD.0000000000000326","article-title":"Andersen\u2013Tawil syndrome: a comprehensive. Review","volume":"29","author":"P\u00e9rez-Riera","year":"2021","journal-title":"Cardiol Rev"},{"key":"2025030422253496400_btaf023-B21","doi-asserted-by":"crossref","first-page":"e235703","DOI":"10.1136\/bcr-2020-235703","article-title":"Compound heterozygous mutations in kcnj2 and kcnh2 in a patient with severe Andersen\u2013Tawil syndrome","volume":"13","author":"Polyak","year":"2020","journal-title":"BMJ Case Rep"},{"key":"2025030422253496400_btaf023-B22","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/s11239-011-0662-x","article-title":"Human cytomegalovirus infection and atherothrombosis","volume":"33","author":"Popovi\u0107","year":"2012","journal-title":"J Thromb Thrombolysis"},{"key":"2025030422253496400_btaf023-B23","doi-asserted-by":"crossref","first-page":"774","DOI":"10.3389\/fphar.2020.00774","article-title":"Pro-senescence and anti-senescence mechanisms of cardiovascular aging: cardiac microrna regulation of longevity drug-induced autophagy","volume":"11","author":"Pulakat","year":"2020","journal-title":"Front Pharmacol"},{"key":"2025030422253496400_btaf023-B24","first-page":"1619","article-title":"Molecular biology of bcr-abl1\u2013positive chronic myeloid leukemia","volume":"113","author":"Quint\u00e1s-Cardama","year":"2009","journal-title":"Blood J Am Soc Hematol"},{"key":"2025030422253496400_btaf023-B25","doi-asserted-by":"crossref","first-page":"2569","DOI":"10.3892\/ijo.2016.3741","article-title":"Effect of curcumin and paclitaxel on breast carcinogenesis","volume":"49","author":"Quispe-Soto","year":"2016","journal-title":"Int J Oncol"},{"key":"2025030422253496400_btaf023-B26","first-page":"19716","article-title":"Beta embeddings for multi-hop logical reasoning in knowledge graphs","volume":"33","author":"Ren","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025030422253496400_btaf023-B27","doi-asserted-by":"crossref","first-page":"1796","DOI":"10.1038\/s41467-021-21770-8","article-title":"Identification of disease treatment mechanisms through the multiscale interactome","volume":"12","author":"Ruiz","year":"2021","journal-title":"Nat Commun"},{"key":"2025030422253496400_btaf023-B28","doi-asserted-by":"crossref","first-page":"bbad276","DOI":"10.1093\/bib\/bbad276","article-title":"Multi-task prediction-based graph contrastive learning for inferring the relationship among lncrnas, mirnas and diseases","volume":"24","author":"Sheng","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025030422253496400_btaf023-B29","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s12199-021-00938-0","article-title":"Possible mechanisms underlying the association between human t-cell leukemia virus type 1 (htlv-1) and hypertension in elderly japanese population","volume":"26","author":"Shimizu","year":"2021","journal-title":"Environ Health Prev Med"},{"key":"2025030422253496400_btaf023-B30","doi-asserted-by":"crossref","first-page":"e000102","DOI":"10.1136\/openhrt-2014-000102","article-title":"Prerace aspirin to protect susceptible runners from cardiac arrest during marathons: is opportunity knocking?","volume":"2","author":"Siegel","year":"2015","journal-title":"Open Heart"},{"key":"2025030422253496400_btaf023-B31","author":"Wang","year":"2024"},{"key":"2025030422253496400_btaf023-B32","doi-asserted-by":"crossref","first-page":"1844","DOI":"10.1111\/brv.12866","article-title":"New insight into dyslipidemia-induced cellular senescence in atherosclerosis","volume":"97","author":"Xiang","year":"2022","journal-title":"Biol Rev Camb Philos Soc"},{"key":"2025030422253496400_btaf023-B33","doi-asserted-by":"crossref","first-page":"e90","DOI":"10.1002\/cpz1.90","article-title":"Gene set knowledge discovery with enrichr","volume":"1","author":"Xie","year":"2021","journal-title":"Curr Protoc"},{"key":"2025030422253496400_btaf023-B34","first-page":"11548","author":"Xu","year":"2021"},{"key":"2025030422253496400_btaf023-B35","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025030422253496400_btaf023-B36","doi-asserted-by":"crossref","first-page":"bbad155","DOI":"10.1093\/bib\/bbad155","article-title":"Attention-based cross domain graph neural network for prediction of drug\u2013drug interactions","volume":"24","author":"Yu","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025030422253496400_btaf023-B37","first-page":"19172","article-title":"Cone: cone embeddings for multi-hop reasoning over knowledge graphs","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025030422253496400_btaf023-B38","doi-asserted-by":"crossref","first-page":"1610","DOI":"10.1109\/TKDE.2018.2865342","article-title":"Triangle lasso for simultaneous clustering and optimization in graph datasets","volume":"31","author":"Zhao","year":"2019","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf023\/61520704\/btaf023.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/2\/btaf023\/61520704\/btaf023.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/2\/btaf023\/61520704\/btaf023.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T22:25:55Z","timestamp":1741127155000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf023\/7964716"}},"subtitle":[],"editor":[{"given":"Macha","family":"Nikolski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1,20]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf023","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,2]]},"published":{"date-parts":[[2025,1,20]]},"article-number":"btaf023"}}