{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T12:56:47Z","timestamp":1781269007513,"version":"3.54.1"},"reference-count":41,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100011084","name":"Sigma Xia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011084","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Quant. Biol."],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Comorbidity, the co\u2010occurrence of multiple medical conditions in a single patient, profoundly impacts disease management and outcomes. Understanding these complex interconnections is crucial, especially in contexts where comorbidities exacerbate outcomes. Leveraging insights from the human interactome and advancements in graph\u2010based methodologies, this study introduces transformer with subgraph positional encoding (TSPE) for disease comorbidity prediction. Inspired by biologically supervised embedding, TSPE employs transformer\u2019s attention mechanisms and subgraph positional encoding (SPE) to capture interactions between nodes and disease associations. Our proposed SPE proves more effective than Laplacian positional encoding, as used in Dwivedi et\u00a0al.\u2019s graph transformer, underscoring the importance of integrating clustering and disease\u2010specific information for improved predictive accuracy. Evaluated on real clinical benchmark datasets (RR0 and RR1), TSPE demonstrates substantial performance enhancements over the state\u2010of\u2010the\u2010art method, achieving up to 28.24% higher ROC AUC (receiver operating characteristic\u2013area under the curve) and 4.93% higher accuracy. This method shows promise for adaptation to other complex graph\u2010based tasks and applications. The source code is available at GitHub website (xihan\u2010qin\/TSPE\u2010GraphTransformer).<\/jats:p>","DOI":"10.1002\/qub2.70008","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T01:25:42Z","timestamp":1750987542000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Graph transformer with disease subgraph positional encoding for improved comorbidity prediction"],"prefix":"10.1002","volume":"13","author":[{"given":"Xihan","family":"Qin","sequence":"first","affiliation":[{"name":"Department of Computer and Information Sciences University of Delaware  Newark Delaware USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Sciences University of Delaware  Newark Delaware USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,6,26]]},"reference":[{"key":"e_1_2_11_2_1","volume-title":"Mental disorders and medical comorbidity","author":"Goodell S","year":"2011"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12920-019-0629-x"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42399-020-00363-4"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.18632\/aging.103579"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.00547-2020"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/00273171.2019.1614898"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12035-020-02266-w"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-022-03816-9"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac822"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1257601"},{"key":"e_1_2_11_12_1","first-page":"178","volume-title":"Computational Advances in Bio and Medical Sciences. ICCABS 2023","author":"Xihan Q","year":"2025"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12920-019-0605-5"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2319"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.1.4877.1451"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2015.00028"},{"key":"e_1_2_11_17_1","article-title":"Attention is all you need","volume":"30","author":"Vaswani A","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_11_18_1","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin J","year":"2019"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1039\/D3DT04178F"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"e_1_2_11_21_1","first-page":"1","article-title":"Multimodal fusion transformer for remote sensing image classification","volume":"61","author":"Roy SK","year":"2023","journal-title":"IEEE Trans Geosci Rem Sens"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13095521"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c01618"},{"issue":"2","key":"e_1_2_11_24_1","first-page":"1","article-title":"GraphsformerCPI: graph transformer for compound\u2013protein interaction prediction","volume":"16","author":"Ma J","year":"2024","journal-title":"Interdiscipl Sci Comput Life Sci"},{"key":"e_1_2_11_25_1","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Poulain R","year":"2024"},{"key":"e_1_2_11_26_1","volume-title":"A generalization of transformer networks to graphs","author":"Dwivedi VP","year":"2012"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/0005-2795(75)90109-9"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.21248"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr356"},{"key":"e_1_2_11_31_1","unstructured":"ZhangJ ZhangH XiaC SunL.Graph\u2010BERT: only attention is needed for learning graph representations.2020. Preprint at arXiv: 2001.05140."},{"key":"e_1_2_11_32_1","first-page":"304","volume-title":"Encyclopedia of measurement and statistics","author":"Abdi H","year":"2007"},{"key":"e_1_2_11_33_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Kipf TN","year":"2017"},{"issue":"20","key":"e_1_2_11_34_1","first-page":"10","article-title":"Graph attention networks","volume":"1050","author":"Velickovic P","year":"2017","journal-title":"Stat"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac104"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa524"},{"key":"e_1_2_11_38_1","unstructured":"BCEWithLogitsLoss \u2013 PyTorch 2.2 documentation[cited 2024 Apr 8]. Available from PyTorch website."},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225073"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-62269-4_36"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-021-00244-z"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"}],"container-title":["Quantitative Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/qub2.70008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T04:55:21Z","timestamp":1758344121000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/qub2.70008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,26]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1002\/qub2.70008"],"URL":"https:\/\/doi.org\/10.1002\/qub2.70008","archive":["Portico"],"relation":{},"ISSN":["2095-4689","2095-4697"],"issn-type":[{"value":"2095-4689","type":"print"},{"value":"2095-4697","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,26]]},"assertion":[{"value":"2024-11-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70008"}}