{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T04:46:16Z","timestamp":1775969176524,"version":"3.50.1"},"posted":{"date-parts":[[2025,5,10]]},"group-title":"Bioinformatics","reference-count":60,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T00:00:00Z","timestamp":1746835200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.biorxiv.org\/about\/FAQ#license"}],"funder":[{"name":"National Cancer Institute"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,5,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Transfer learning considers distinct but related tasks defined over heterogeneous domains and aims to improve generalization and performance through knowledge transfer between tasks. This approach can be especially advantageous in biomedical contexts with insufficient labeled training data, where joint learning across domains can enable inference in otherwise underpowered datasets. High-dimensional biomedical data is characterized with redundancy, rendering non-linear dependencies among features. Existing models often fail to leverage such feature dependencies during inference, limiting their ability to model complex biological systems. We present a Bayesian group factor analysis transfer learning framework that supports multitask, multi-modal learning. Our approach learns a shared latent space within each domain, simultaneously across multiple domains, and uses a feature-wise prior to model complex relationships. We evaluate our framework using controlled synthetic data experiments and four disjoint patient cancer datasets from acute myeloid leukemia and neuroblastoma. We show that our method improves drug response prediction and more readily recapitulates consensus biomarkers of drug response. Similarly, our approach improves tumor purity prediction and identifies a robust gene signature associated with it. Our framework is scalable, interpretable, and adaptable across target phenotypes, offering a robust solution for a wide range of heterogeneous multi-omics problems.<\/jats:p>","DOI":"10.1101\/2025.05.07.648613","type":"posted-content","created":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T22:45:14Z","timestamp":1746917114000},"source":"Crossref","is-referenced-by-count":0,"title":["Transfer learning framework via Bayesian group factor analysis incorporating feature-wise dependencies"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7158-5753","authenticated-orcid":false,"given":"Dharani","family":"Thirumalaisamy","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Oregon Health and Science University, Portland, Oregon, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1189-5934","authenticated-orcid":false,"given":"Natasha","family":"Black","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Oregon Health and Science University, Portland, Oregon, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehmet","family":"G\u00f6nen","sequence":"additional","affiliation":[{"name":"College of Engineering, Ko\u00e7 University, \u0130stanbul, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8105-2440","authenticated-orcid":false,"given":"Olga","family":"Nikolova","sequence":"additional","affiliation":[{"name":"Division of Oncological Sciences, Center for Biomedical Data Science, Oregon Health and Science University, Portland, Oregon, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026041121162378000_2025.05.07.648613v1.1","doi-asserted-by":"publisher","DOI":"10.1002\/jcp.30931"},{"key":"2026041121162378000_2025.05.07.648613v1.2","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-020-1935-5"},{"key":"2026041121162378000_2025.05.07.648613v1.3","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbz171"},{"key":"2026041121162378000_2025.05.07.648613v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/nature11003"},{"key":"2026041121162378000_2025.05.07.648613v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2013.08.003"},{"key":"2026041121162378000_2025.05.07.648613v1.6","doi-asserted-by":"crossref","unstructured":"D. Benjamin , T. Sato , K. Cibulskis , G. Getz , C. Stewart , and L. Lichtenstein . Calling somatic snvs and indels with mutect2. BioRxiv, page 861054, 2019.","DOI":"10.1101\/861054"},{"key":"2026041121162378000_2025.05.07.648613v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccell.2022.07.002"},{"key":"2026041121162378000_2025.05.07.648613v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3519"},{"key":"2026041121162378000_2025.05.07.648613v1.9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026041121162378000_2025.05.07.648613v1.10","doi-asserted-by":"publisher","DOI":"10.1074\/jbc.RA118.006761"},{"key":"2026041121162378000_2025.05.07.648613v1.11","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2042-4"},{"key":"2026041121162378000_2025.05.07.648613v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajhg.2019.07.020"},{"key":"2026041121162378000_2025.05.07.648613v1.13","unstructured":"Gabriella Miller Kids First Pediatric Research Program. Discovering the genetic basis of human neuroblastoma. https:\/\/www.ncbi.nlm.nih.gov\/projects\/gap\/cgi-bin\/study.cgi?study_id=phs001436.v1.p1, 2017."},{"key":"2026041121162378000_2025.05.07.648613v1.14","doi-asserted-by":"crossref","unstructured":"Z. Geng , E. Wafula , R. J. Corbett , Y. Zhang , R. Jin , K. S. Gaonkar , S. Shukla , K. S. Rathi , D. Hill , A. Lahiri , et al. The open pediatric cancer project. bioRxiv, 2024.","DOI":"10.1093\/gigascience\/giaf093"},{"issue":"6","key":"2026041121162378000_2025.05.07.648613v1.15","doi-asserted-by":"crossref","first-page":"188805","DOI":"10.1016\/j.bbcan.2022.188805","article-title":"Tumoral heterogeneity in neuroblastoma","volume":"1877","year":"2022","journal-title":"Biochimica et Biophysica Acta (BBA)-Reviews on Cancer"},{"key":"2026041121162378000_2025.05.07.648613v1.16","unstructured":"E. Hajiramezanali , S. Zamani Dadaneh , A. Karbalayghareh , M. Zhou , and X. Qian . Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data. Advances in Neural Information Processing Systems, 31, 2018."},{"key":"2026041121162378000_2025.05.07.648613v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/nature17987"},{"key":"2026041121162378000_2025.05.07.648613v1.18","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1970.10488634"},{"key":"2026041121162378000_2025.05.07.648613v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopha.2020.110293"},{"key":"2026041121162378000_2025.05.07.648613v1.20","doi-asserted-by":"crossref","unstructured":"J. Ju , I. Ntafoulis , M. Klein , M. JT Reinders , M. Lamfers , A. P Stubbs , and Y. Li . Two-step transfer learning improves deep learning\u2013based drug response prediction in small datasets: A case study of glioblastoma. Bioinformatics and Biology Insights, 19:11779322241301507, 2025.","DOI":"10.1177\/11779322241301507"},{"key":"2026041121162378000_2025.05.07.648613v1.21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2839583"},{"key":"2026041121162378000_2025.05.07.648613v1.22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2870749"},{"key":"2026041121162378000_2025.05.07.648613v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0051-x"},{"key":"2026041121162378000_2025.05.07.648613v1.24","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac979"},{"key":"2026041121162378000_2025.05.07.648613v1.25","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkw227"},{"key":"2026041121162378000_2025.05.07.648613v1.26","doi-asserted-by":"crossref","unstructured":"C. W. Law , M. Alhamdoosh , S. Su , X. Dong , L. Tian , G. K. Smyth , and M. E. Ritchie . Rna-seq analysis is easy as 1-2-3 with limma, glimma and edger. F1000Research, 5:ISCB\u2013 Comm, 2018.","DOI":"10.12688\/f1000research.9005.3"},{"key":"2026041121162378000_2025.05.07.648613v1.27","doi-asserted-by":"publisher","DOI":"10.1080\/1744666X.2024.2356747"},{"key":"2026041121162378000_2025.05.07.648613v1.28","doi-asserted-by":"publisher","DOI":"10.1186\/s12929-025-01122-0"},{"key":"2026041121162378000_2025.05.07.648613v1.29","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/9280841"},{"key":"2026041121162378000_2025.05.07.648613v1.30","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2005.05.571"},{"key":"2026041121162378000_2025.05.07.648613v1.31","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.11160"},{"key":"2026041121162378000_2025.05.07.648613v1.32","unstructured":"S. M. Lundberg and S.-I. Lee . A unified approach to interpreting model predictions. Advances in neural information processing systems, 30, 2017."},{"key":"2026041121162378000_2025.05.07.648613v1.33","unstructured":"S. Mahapatra and K. B. Challagundla . Neuroblastoma. StatPearls Publishing, Treasure Island (FL), 2025. URL https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK448111\/. Updated 2023 Jul 10."},{"key":"2026041121162378000_2025.05.07.648613v1.34","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-21-0410"},{"key":"2026041121162378000_2025.05.07.648613v1.35","doi-asserted-by":"publisher","DOI":"10.3390\/biology12091230"},{"key":"2026041121162378000_2025.05.07.648613v1.36","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2010.30.5425"},{"key":"2026041121162378000_2025.05.07.648613v1.37","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-018-0023-9"},{"key":"2026041121162378000_2025.05.07.648613v1.38","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btw836"},{"key":"2026041121162378000_2025.05.07.648613v1.39","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu651"},{"key":"2026041121162378000_2025.05.07.648613v1.40","doi-asserted-by":"publisher","DOI":"10.1111\/gtc.13148"},{"key":"2026041121162378000_2025.05.07.648613v1.41","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.736"},{"key":"2026041121162378000_2025.05.07.648613v1.42","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"2026041121162378000_2025.05.07.648613v1.43","doi-asserted-by":"publisher","DOI":"10.1038\/ng.2529"},{"key":"2026041121162378000_2025.05.07.648613v1.44","doi-asserted-by":"publisher","DOI":"10.1038\/nchembio.1986"},{"key":"2026041121162378000_2025.05.07.648613v1.45","doi-asserted-by":"crossref","unstructured":"M. T. Ribeiro , S. Singh , and C. Guestrin . \u201cwhy should i trust you?\u201d explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135\u20131144, 2016.","DOI":"10.1145\/2939672.2939778"},{"key":"2026041121162378000_2025.05.07.648613v1.46","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0509182102"},{"key":"2026041121162378000_2025.05.07.648613v1.47","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017467"},{"key":"2026041121162378000_2025.05.07.648613v1.48","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-15-0235"},{"key":"2026041121162378000_2025.05.07.648613v1.49","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13081909"},{"key":"2026041121162378000_2025.05.07.648613v1.50","doi-asserted-by":"crossref","unstructured":"D. Slack , S. Hilgard , E. Jia , S. Singh , and H. Lakkaraju . Fooling lime and shap: Adversarial attacks on post hoc explanation methods. In Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, pages 180\u2013186, 2020.","DOI":"10.1145\/3375627.3375830"},{"key":"2026041121162378000_2025.05.07.648613v1.51","doi-asserted-by":"publisher","DOI":"10.1158\/1538-7445.AM2024-7365"},{"key":"2026041121162378000_2025.05.07.648613v1.52","doi-asserted-by":"publisher","DOI":"10.1111\/J.2517-6161.1996.TB02080.X"},{"key":"2026041121162378000_2025.05.07.648613v1.53","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0623-z"},{"key":"2026041121162378000_2025.05.07.648613v1.54","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13283"},{"key":"2026041121162378000_2025.05.07.648613v1.55","doi-asserted-by":"crossref","unstructured":"V. Vapnik . The nature of statistical learning theory. Springer science & business media, 1999.","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"2026041121162378000_2025.05.07.648613v1.56","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-18-0599"},{"key":"2026041121162378000_2025.05.07.648613v1.57","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gks1111"},{"key":"2026041121162378000_2025.05.07.648613v1.58","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-023-05092-7"},{"key":"2026041121162378000_2025.05.07.648613v1.59","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-74921-0"},{"key":"2026041121162378000_2025.05.07.648613v1.60","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.05.07.648613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T04:16:28Z","timestamp":1775967388000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.05.07.648613"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,10]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1101\/2025.05.07.648613","relation":{},"subject":[],"published":{"date-parts":[[2025,5,10]]},"subtype":"preprint"}}