{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T03:16:14Z","timestamp":1788837374113,"version":"build-2803163510"},"posted":{"date-parts":[[2026,3,5]]},"group-title":"Bioinformatics","reference-count":41,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"award":["U24CA264007"],"award-info":[{"award-number":["U24CA264007"]}],"id":[{"id":"https:\/\/ror.org\/040gcmg81","id-type":"ROR","asserted-by":"publisher"}]},{"award":["R01CA270108"],"award-info":[{"award-number":["R01CA270108"]}],"id":[{"id":"https:\/\/ror.org\/040gcmg81","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,3,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  DNA extracted from tissue samples typically derives from a complex mixture of cell types. Without single cell analysis, it has been generally impossible to determine the cell type of origin for most molecules. One clear example of this is in the complex milieu of a human neoplasm. Here, we develop ROCIT (\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/tobybaker\/rocit\">https:\/\/github.com\/tobybaker\/rocit<\/jats:ext-link>\n                  ), a transformer-based model to classify the tumor or non-tumor origin of individual reads from bulk tumor samples sequenced with long-read whole genome sequencing. Using somatic mutations to derive training data, ROCIT uses read-level methylation patterns to accurately classify reads from any-where in the genome without requiring the adjacent normal tissue or the explicit identification of tumor differentially methylated regions. We apply ROCIT to a cohort of prostate and ovarian tumors and demonstrate high classification accuracy across the entire genome. We then demonstrate the potential of ROCIT predictions to improve somatic variant calling. ROCIT represents a major step forward in the analysis of bulk tumors with long-reads, enabling the accurate and sensitive identification of reads with specific cell types of origin genome-wide.\n                <\/jats:p>","DOI":"10.64898\/2026.03.03.709085","type":"posted-content","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T05:20:45Z","timestamp":1772774445000},"source":"Crossref","is-referenced-by-count":1,"title":["Genome-wide classification of tumor-derived reads from bulk long-read sequencing"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5183-9047","authenticated-orcid":false,"given":"Toby M.","family":"Baker","sequence":"first","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7624-3090","authenticated-orcid":false,"given":"Nedas","family":"Matulionis","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5781-293X","authenticated-orcid":false,"given":"Cassidy","family":"Andrasz","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"},{"name":"Department of Genetics, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4866-6860","authenticated-orcid":false,"given":"Dan","family":"Gerke","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6717-0534","authenticated-orcid":false,"given":"Natalia","family":"Garcia-Dutton","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"},{"name":"Department of Genetics, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4788-4687","authenticated-orcid":false,"given":"David","family":"Atkinson","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5466-4019","authenticated-orcid":false,"given":"Kami","family":"Chiotti","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5206-0150","authenticated-orcid":false,"given":"Selina","family":"Wu","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"},{"name":"Department of Genetics, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2301-2951","authenticated-orcid":false,"given":"Suchita","family":"Lulla","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"},{"name":"Department of Genetics, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8961-8645","authenticated-orcid":false,"given":"Jieun","family":"Oh","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"},{"name":"Department of Genetics, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1001-5316","authenticated-orcid":false,"given":"Helena","family":"Winata","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"},{"name":"Department of Genetics, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong-Rong","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jenny","family":"Lester","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9451-2933","authenticated-orcid":false,"given":"Beth Y.","family":"Karlan","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4810-0022","authenticated-orcid":false,"given":"Paul T.","family":"Spellman","sequence":"additional","affiliation":[{"name":"Division of Hematology Oncology, Department of Medicine David Geffen School of Medicine, University of California Los Angeles"},{"name":"Department of Genetics, David Geffen School of Medicine University of California Los Angeles"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026030910501250000_2026.03.03.709085v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccell.2023.02.016"},{"key":"2026030910501250000_2026.03.03.709085v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms9971"},{"key":"2026030910501250000_2026.03.03.709085v1.3","doi-asserted-by":"publisher","DOI":"10.3390\/cancers11111741"},{"key":"2026030910501250000_2026.03.03.709085v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/nature12477"},{"key":"2026030910501250000_2026.03.03.709085v1.5","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-24-0296"},{"key":"2026030910501250000_2026.03.03.709085v1.6","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky423"},{"key":"2026030910501250000_2026.03.03.709085v1.7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-55920-z"},{"key":"2026030910501250000_2026.03.03.709085v1.8","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab250"},{"key":"2026030910501250000_2026.03.03.709085v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41418-023-01213-1"},{"key":"2026030910501250000_2026.03.03.709085v1.10","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaz1646"},{"key":"2026030910501250000_2026.03.03.709085v1.11","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1009843107"},{"key":"2026030910501250000_2026.03.03.709085v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.esmoop.2022.100611"},{"key":"2026030910501250000_2026.03.03.709085v1.13","doi-asserted-by":"publisher","DOI":"10.1038\/ng.2760"},{"key":"2026030910501250000_2026.03.03.709085v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05580-6"},{"key":"2026030910501250000_2026.03.03.709085v1.15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1810.04805"},{"key":"2026030910501250000_2026.03.03.709085v1.16","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"2026030910501250000_2026.03.03.709085v1.17","doi-asserted-by":"crossref","unstructured":"RC Fong and A Vedaldi . Interpretable explanations of black boxes by meaningful perturbation. Proceedings of the IEEE international conference on computer vision. 2017, 3429\u20133437.","DOI":"10.1109\/ICCV.2017.371"},{"key":"2026030910501250000_2026.03.03.709085v1.18","unstructured":"A Dhurandhar et al. Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives. Advances in Neural Information Processing Systems. Vol. 31. Curran Associates, Inc., 2018."},{"key":"2026030910501250000_2026.03.03.709085v1.19","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-020-00791-w"},{"key":"2026030910501250000_2026.03.03.709085v1.20","doi-asserted-by":"crossref","unstructured":"J Park et al. Accurate somatic small variant discovery for multiple sequencing technologies with DeepSomatic. Nature Biotechnology (2025), 1\u201310.","DOI":"10.1038\/s41587-025-02839-x"},{"key":"2026030910501250000_2026.03.03.709085v1.21","doi-asserted-by":"publisher","DOI":"10.1002\/path.5017"},{"key":"2026030910501250000_2026.03.03.709085v1.22","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0900571106"},{"issue":"4","key":"2026030910501250000_2026.03.03.709085v1.23","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1002\/gcc.20746","article-title":"A catalog of genes homozygously deleted in human lung cancer and the candidacy of PTPRD as a tumor suppressor gene. Genes","volume":"49","year":"2010","journal-title":"Chromosomes and Cancer"},{"key":"2026030910501250000_2026.03.03.709085v1.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccr.2014.07.028"},{"key":"2026030910501250000_2026.03.03.709085v1.25","doi-asserted-by":"publisher","DOI":"10.1101\/2020.11.03.366252"},{"key":"2026030910501250000_2026.03.03.709085v1.26","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4060"},{"key":"2026030910501250000_2026.03.03.709085v1.27","unstructured":"J Broadbent . nanomix. https:\/\/github.com\/Jonbroad15\/nanomix. 2022."},{"key":"2026030910501250000_2026.03.03.709085v1.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2024.10.039"},{"key":"2026030910501250000_2026.03.03.709085v1.29","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab705"},{"key":"2026030910501250000_2026.03.03.709085v1.30","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4235"},{"key":"2026030910501250000_2026.03.03.709085v1.31","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae042"},{"key":"2026030910501250000_2026.03.03.709085v1.32","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.15189387"},{"key":"2026030910501250000_2026.03.03.709085v1.33","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-0439-x"},{"key":"2026030910501250000_2026.03.03.709085v1.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2012.04.023"},{"key":"2026030910501250000_2026.03.03.709085v1.35","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a026625"},{"key":"2026030910501250000_2026.03.03.709085v1.36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.08415"},{"key":"2026030910501250000_2026.03.03.709085v1.37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.05101"},{"key":"2026030910501250000_2026.03.03.709085v1.38","doi-asserted-by":"publisher","DOI":"10.1214\/12-AOS1000. 1102.4807"},{"key":"2026030910501250000_2026.03.03.709085v1.39","doi-asserted-by":"publisher","DOI":"10.2307\/1931034"},{"key":"2026030910501250000_2026.03.03.709085v1.40","doi-asserted-by":"publisher","DOI":"10.1101\/gr.279095.124"},{"key":"2026030910501250000_2026.03.03.709085v1.41","doi-asserted-by":"crossref","unstructured":"MR Vollger et al. A haplotype-resolved view of human gene regulation. bioRxiv (2025), 2024\u201306.","DOI":"10.1101\/2024.06.14.599122"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.03.03.709085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T17:50:18Z","timestamp":1773078618000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.03.03.709085"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,5]]},"references-count":41,"URL":"https:\/\/doi.org\/10.64898\/2026.03.03.709085","relation":{},"subject":[],"published":{"date-parts":[[2026,3,5]]},"subtype":"preprint"}}