{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T13:48:00Z","timestamp":1785332880343,"version":"3.55.0"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T00:00:00Z","timestamp":1715644800000},"content-version":"vor","delay-in-days":13,"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":["32170671"],"award-info":[{"award-number":["32170671"]}],"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":["82341101"],"award-info":[{"award-number":["82341101"]}],"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":["82371855"],"award-info":[{"award-number":["82371855"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University Guoqiang Institute","award":["2021GQG1020"],"award-info":[{"award-number":["2021GQG1020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Multi-omics data provide a comprehensive view of gene regulation at multiple levels, which is helpful in achieving accurate diagnosis of complex diseases like cancer. However, conventional integration methods rarely utilize prior biological knowledge and lack interpretability.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>To integrate various multi-omics data of tissue and liquid biopsies for disease diagnosis and prognosis, we developed a biological pathway informed Transformer, Pathformer. It embeds multi-omics input with a compacted multi-modal vector and a pathway-based sparse neural network. Pathformer also leverages criss-cross attention mechanism to capture the crosstalk between different pathways and modalities. We first benchmarked Pathformer with 18 comparable methods on multiple cancer datasets, where Pathformer outperformed all the other methods, with an average improvement of 6.3%\u201314.7% in F1 score for cancer survival prediction, 5.1%\u201312% for cancer stage prediction, and 8.1%\u201313.6% for cancer drug response prediction. Subsequently, for cancer prognosis prediction based on tissue multi-omics data, we used a case study to demonstrate the biological interpretability of Pathformer by identifying key pathways and their biological crosstalk. Then, for cancer early diagnosis based on liquid biopsy data, we used plasma and platelet datasets to demonstrate Pathformer\u2019s potential of clinical applications in cancer screening. Moreover, we revealed deregulation of interesting pathways (e.g. scavenger receptor pathway) and their crosstalk in cancer patients\u2019 blood, providing potential candidate targets for cancer microenvironment study.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Pathformer is implemented and freely available at https:\/\/github.com\/lulab\/Pathformer.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae316","type":"journal-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T04:47:54Z","timestamp":1715402874000},"source":"Crossref","is-referenced-by-count":39,"title":["Pathformer: a biological pathway informed transformer for disease diagnosis and prognosis using multi-omics data"],"prefix":"10.1093","volume":"40","author":[{"given":"Xiaofan","family":"Liu","sequence":"first","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, Center for Synthetic and Systems Biology, School of Life Sciences, Tsinghua University , Beijing 100084, China"},{"name":"Institute for Precision Medicine, Tsinghua University , Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhuan","family":"Tao","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, Center for Synthetic and Systems Biology, School of Life Sciences, Tsinghua University , Beijing 100084, China"},{"name":"Institute for Precision Medicine, Tsinghua University , Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilin","family":"Cai","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, Center for Synthetic and Systems Biology, School of Life Sciences, Tsinghua University , Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7346-5840","authenticated-orcid":false,"given":"Pengfei","family":"Bao","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, Center for Synthetic and Systems Biology, School of Life Sciences, Tsinghua University , Beijing 100084, China"},{"name":"Institute for Precision Medicine, Tsinghua University , Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongli","family":"Ma","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, Center for Synthetic and Systems Biology, School of Life Sciences, Tsinghua University , Beijing 100084, China"},{"name":"Institute for Precision Medicine, Tsinghua University , Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kexing","family":"Li","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, Center for Synthetic and Systems Biology, School of Life Sciences, Tsinghua University , Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4252-2889","authenticated-orcid":false,"given":"Mengtao","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Rheumatology and Clinical Immunology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Peking Union Medical College, National Clinical Research Center for Dermatologic and Immunologic Diseases (NCRC-DID), MST State Key Laboratory of Complex Severe and Rare Diseases, MOE Key Laboratory of Rheumatology and Clinical Immunology , Beijing 100730, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunping","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Medical Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Lifeomics , Beijing 102206, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4751-9400","authenticated-orcid":false,"given":"Zhi John","family":"Lu","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, Center for Synthetic and Systems Biology, School of Life Sciences, Tsinghua University , Beijing 100084, China"},{"name":"Institute for Precision Medicine, Tsinghua University , Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"2024053023113565900_btae316-B1","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.ccell.2017.07.004","article-title":"Swarm intelligence-enhanced detection of non-small-cell lung cancer using tumor-educated platelets","volume":"32","author":"Best","year":"2017","journal-title":"Cancer Cell"},{"key":"2024053023113565900_btae316-B2","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1016\/j.ccell.2015.09.018","article-title":"RNA-Seq of tumor-educated platelets enables blood-based pan-cancer, multiclass, and molecular pathway cancer diagnostics","volume":"28","author":"Best","year":"2015","journal-title":"Cancer Cell"},{"key":"2024053023113565900_btae316-B3","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1016\/S1357-2725(99)00022-9","article-title":"DAP12: a key accessory protein for relaying signals by natural killer cell receptors","volume":"31","author":"Campbell","year":"1999","journal-title":"Int J Biochem Cell Biol"},{"key":"2024053023113565900_btae316-B4","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"Cancer Genome Atlas Research Network","year":"2013","journal-title":"Nat. Genet"},{"key":"2024053023113565900_btae316-B5","doi-asserted-by":"crossref","first-page":"e75181","DOI":"10.7554\/eLife.75181","article-title":"Cancer type classification using plasma cell-free RNAs derived from human and microbes","volume":"11","author":"Chen","year":"2022","journal-title":"Elife"},{"key":"2024053023113565900_btae316-B6","first-page":"143","article-title":"Predicting drug response of tumors from integrated genomic profiles by deep neural networks","volume":"12","author":"Chiu","year":"2019","journal-title":"BMC Med Genomics"},{"key":"2024053023113565900_btae316-B7","doi-asserted-by":"crossref","first-page":"D691","DOI":"10.1093\/nar\/gkq1018","article-title":"Reactome: a database of reactions, pathways and biological processes","volume":"39","author":"Croft","year":"2010","journal-title":"Nucleic Acids Res"},{"key":"2024053023113565900_btae316-B8","first-page":"1","author":"Cui"},{"key":"2024053023113565900_btae316-B9","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1038\/s41586-021-03922-4","article-title":"Biologically informed deep neural network for prostate cancer discovery","volume":"598","author":"Elmarakeby","year":"2021","journal-title":"Nature"},{"key":"2024053023113565900_btae316-B10","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1038\/s42003-020-01233-4","article-title":"A gene prioritization method based on a swine multi-omics knowledgebase and a deep learning model","volume":"3","author":"Fu","year":"2020","journal-title":"Commun Biol"},{"key":"2024053023113565900_btae316-B11","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1186\/s12859-018-2500-z","article-title":"PASNet: pathway-associated sparse deep neural network for prognosis prediction from high-throughput data","volume":"19","author":"Hao","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"2024053023113565900_btae316-B12","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1186\/s13059-017-1215-1","article-title":"Multi-omics approaches to disease","volume":"18","author":"Hasin","year":"2017","journal-title":"Genome Biol"},{"key":"2024053023113565900_btae316-B13","doi-asserted-by":"crossref","first-page":"166","DOI":"10.3389\/fgene.2019.00166","article-title":"SALMON: survival analysis learning with multi-omics neural networks on breast cancer","volume":"10","author":"Huang","year":"2019","journal-title":"Front Genet"},{"key":"2024053023113565900_btae316-B14","doi-asserted-by":"crossref","first-page":"2185","DOI":"10.1016\/j.csbj.2020.08.005","article-title":"An integrative deep learning framework for classifying molecular subtypes of breast cancer","volume":"18","author":"Islam","year":"2020","journal-title":"Comput Struct Biotechnol J"},{"key":"2024053023113565900_btae316-B15","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2024053023113565900_btae316-B16","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1093\/nar\/28.1.27","article-title":"KEGG: Kyoto encyclopedia of genes and genomes","volume":"28","author":"Kanehisa","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2024053023113565900_btae316-B17","doi-asserted-by":"crossref","first-page":"4571","DOI":"10.1038\/sj.onc.1210230","article-title":"A hidden oncogenic positive feedback loop caused by crosstalk between Wnt and ERK pathways","volume":"26","author":"Kim","year":"2007","journal-title":"Oncogene"},{"key":"2024053023113565900_btae316-B18","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1038\/s41568-021-00358-w","article-title":"Mitochondrial DNA variation and cancer","volume":"21","author":"Kopinski","year":"2021","journal-title":"Nat Rev Cancer"},{"key":"2024053023113565900_btae316-B19","doi-asserted-by":"crossref","first-page":"2334","DOI":"10.1109\/TCBB.2021.3086702","article-title":"MatchMaker: a deep learning framework for drug synergy prediction","volume":"19","author":"Kuru","year":"2022","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2024053023113565900_btae316-B20","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1111\/j.1582-4934.2006.tb00425.x","article-title":"Stabilin-1, a homeostatic scavenger receptor with multiple functions","volume":"10","author":"Kzhyshkowska","year":"2006","journal-title":"J Cell Mol Med"},{"key":"2024053023113565900_btae316-B21","doi-asserted-by":"crossref","first-page":"1442","DOI":"10.1093\/bioinformatics\/btn200","article-title":"A global pathway crosstalk network","volume":"24","author":"Li","year":"2008","journal-title":"Bioinformatics"},{"key":"2024053023113565900_btae316-B22","doi-asserted-by":"crossref","first-page":"810286","DOI":"10.3389\/fimmu.2021.810286","article-title":"Duality of interactions between TGF-\u03b2 and TNF-\u03b1 during tumor formation","volume":"12","author":"Liu","year":"2021","journal-title":"Front Immunol"},{"key":"2024053023113565900_btae316-B23","first-page":"30","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024053023113565900_btae316-B24","doi-asserted-by":"crossref","first-page":"104645","DOI":"10.1016\/j.ebiom.2023.104645","article-title":"A comprehensive evaluation of full-spectrum cell-free RNAs highlights cell-free RNA fragments for early-stage hepatocellular carcinoma detection","volume":"93","author":"Ning","year":"2023","journal-title":"EBioMedicine"},{"key":"2024053023113565900_btae316-B25","first-page":"117","article-title":"BioCarta","volume":"2","author":"Nishimura","year":"2001","journal-title":"Biotech Softw Internet Rep Comput Softw J Sci"},{"key":"2024053023113565900_btae316-B26","doi-asserted-by":"crossref","first-page":"1420","DOI":"10.1093\/jnci\/djh275","article-title":"Colon cancer survival rates with the new American Joint Committee on Cancer sixth edition staging","volume":"96","author":"O'Connell","year":"2004","journal-title":"J Natl Cancer Inst"},{"key":"2024053023113565900_btae316-B27","doi-asserted-by":"crossref","first-page":"e8","DOI":"10.1093\/nar\/gkw849","article-title":"A novel method for crosstalk analysis of biological networks: improving accuracy of pathway annotation","volume":"45","author":"Ogris","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2024053023113565900_btae316-B28","doi-asserted-by":"crossref","first-page":"i443","DOI":"10.1093\/bioinformatics\/btab285","article-title":"PathCNN: interpretable convolutional neural networks for survival prediction and pathway analysis applied to glioblastoma","volume":"37","author":"Oh","year":"2021","journal-title":"Bioinformatics"},{"key":"2024053023113565900_btae316-B29","author":"Osseni","year":"2022"},{"key":"2024053023113565900_btae316-B30","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1159\/000323936","article-title":"Modulation of natural killer cell anti-tumor reactivity by platelets","volume":"3","author":"Placke","year":"2011","journal-title":"J Innate Immun"},{"key":"2024053023113565900_btae316-B31","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1038\/onc.2015.151","article-title":"Opportunities and challenges provided by crosstalk between signalling pathways in cancer","volume":"35","author":"Prahallad","year":"2016","journal-title":"Oncogene"},{"key":"2024053023113565900_btae316-B32","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1093\/bioinformatics\/btx806","article-title":"DeepSynergy: predicting anti-cancer drug synergy with deep learning","volume":"34","author":"Preuer","year":"2018","journal-title":"Bioinformatics"},{"key":"2024053023113565900_btae316-B33","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1186\/s12943-016-0524-4","article-title":"Circulating long non-coding RNAs in cancer: current status and future perspectives","volume":"15","author":"Qi","year":"2016","journal-title":"Mol Cancer"},{"key":"2024053023113565900_btae316-B34","doi-asserted-by":"crossref","first-page":"e1005752","DOI":"10.1371\/journal.pcbi.1005752","article-title":"mixOmics: an R package for \u2018omics feature selection and multiple data integration","volume":"13","author":"Rohart","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"2024053023113565900_btae316-B35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4068\/cmj.2020.56.1.1","article-title":"Scavenger receptor class a to E involved in various cancers","volume":"56","author":"Ryu","year":"2020","journal-title":"Chonnam Med J"},{"key":"2024053023113565900_btae316-B36","doi-asserted-by":"crossref","first-page":"D674","DOI":"10.1093\/nar\/gkn653","article-title":"PID: the pathway interaction database","volume":"37","author":"Schaefer","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2024053023113565900_btae316-B37","doi-asserted-by":"crossref","first-page":"i501","DOI":"10.1093\/bioinformatics\/btz318","article-title":"MOLI: multi-omics late integration with deep neural networks for drug response prediction","volume":"35","author":"Sharifi-Noghabi","year":"2019","journal-title":"Bioinformatics"},{"key":"2024053023113565900_btae316-B38","doi-asserted-by":"crossref","first-page":"8097","DOI":"10.1007\/s11033-023-08675-z","article-title":"Overexpression of ferritin light chain as a poor prognostic factor for breast cancer","volume":"50","author":"Tang","year":"2023","journal-title":"Mol Biol Rep"},{"key":"2024053023113565900_btae316-B39","doi-asserted-by":"crossref","first-page":"101281","DOI":"10.1016\/j.xcrm.2023.101281","article-title":"Cell-free multi-omics analysis reveals potential biomarkers in gastrointestinal cancer patients\u2019 blood","volume":"4","author":"Tao","year":"2023","journal-title":"Cell Rep Med"},{"key":"2024053023113565900_btae316-B40","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/s43588-021-00086-z","article-title":"Undisclosed, unmet and neglected challenges in multi-omics studies","volume":"1","author":"Tarazona","year":"2021","journal-title":"Nat Comput Sci"},{"key":"2024053023113565900_btae316-B41","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1038\/s41586-023-06139-9","article-title":"Transfer learning enables predictions in network biology","volume":"618","author":"Theodoris","year":"2023","journal-title":"Nature"},{"key":"2024053023113565900_btae316-B42","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.ymeth.2020.07.008","article-title":"Integrating multi-omics data by learning modality invariant representations for improved prediction of overall survival of cancer","volume":"189","author":"Tong","year":"2021","journal-title":"Methods"},{"key":"2024053023113565900_btae316-B43","doi-asserted-by":"crossref","first-page":"118","DOI":"10.3389\/fonc.2017.00118","article-title":"The mitochondrial complex (I) ty of cancer","volume":"7","author":"Urra","year":"2017","journal-title":"Front Oncol"},{"key":"2024053023113565900_btae316-B44","doi-asserted-by":"crossref","first-page":"3445","DOI":"10.1038\/s41467-021-23774-w","article-title":"MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification","volume":"12","author":"Wang","year":"2021","journal-title":"Nat Commun"},{"key":"2024053023113565900_btae316-B45","first-page":"556","author":"Xing","year":"2021"},{"key":"2024053023113565900_btae316-B46","doi-asserted-by":"crossref","first-page":"15727","DOI":"10.1074\/jbc.RA120.014690","article-title":"Interactions of ferritin with scavenger receptor class a members","volume":"295","author":"Yu","year":"2020","journal-title":"J Biol Chem"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae316\/57572670\/btae316.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/5\/btae316\/58011810\/btae316.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/5\/btae316\/58011810\/btae316.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T01:01:24Z","timestamp":1717117284000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae316\/7671099"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,5,1]]},"references-count":46,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae316","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,5,1]]},"published":{"date-parts":[[2024,5,1]]},"article-number":"btae316"}}