{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T12:47:54Z","timestamp":1785415674878,"version":"3.56.0"},"posted":{"date-parts":[[2026,7,3]]},"group-title":"Bioinformatics","reference-count":39,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"award":["GM146960"],"award-info":[{"award-number":["GM146960"]}],"id":[{"id":"https:\/\/ror.org\/04q48ey07","id-type":"ROR","asserted-by":"publisher"}]},{"award":["2523717"],"award-info":[{"award-number":["2523717"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["2523716"],"award-info":[{"award-number":["2523716"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Distinguishing malignant from normal cells in single-cell RNA sequencing data remains a critical yet challenging task in cancer genomics. Existing methods often suffer from poor precision, limited generalizability across cancer types, and reduced robustness across different sequencing platforms. We developed DeepMalignant, an unsupervised multimodal graph attention autoencoder for malignant cell identification that jointly integrates gene expression and copy number alteration (CNA) information. We applied DeepMalignant to five datasets covering 26 samples and four cancer types (breast, colorectal, pancreatic, and ovarian cancers), generated by three platforms (10x Genomics, inDrop, and Drop-seq) for benchmarking and compared it with existing state-of-the-art methods including scMalignantFinder, PreCanCell, CopyKAT, ikarus, and Cancer-Finder. DeepMalignant achieved the best overall balance of precision and recall and consistently outperformed the existing methods that used either gene expression or CNA in F1 scores. Ablation studies showed that both CNA-based edge weighting and graph attention aggregation contribute independently to performance, and attribution analysis further indicated that the learned embeddings capture biologically meaningful malignant programs. We further applied DeepMalignant to two ductal carcinoma in situ (DCIS) samples, DCIS2 and DCIS1, that have matched spatial transcriptomics and scRNA-seq data. DeepMalignant identified tumor-enriched regions that were highly consistent with the matched histological image. The downstream cellcell communications analysis revealed that fibroblast-derived C3 and MIF both directed signaling more toward normal epithelial cells than tumor epithelial cells, demonstrating that accurate tumor-normal cell classification by DeepMalignant enables biologically meaningful interrogation of the tumor microenvironment and revealing how stromal cells differentially communicate with malignant versus normal epithelial populations.<\/jats:p>","DOI":"10.64898\/2026.06.29.734828","type":"posted-content","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T09:45:26Z","timestamp":1783071926000},"source":"Crossref","is-referenced-by-count":1,"title":["Multi-modality Graph Representation Learning for Malignant Cell Identification from scRNA-seq using DeepMalignant"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3805-6776","authenticated-orcid":false,"given":"Pankaj","family":"Bhattarai","sequence":"first","affiliation":[{"name":"Florida State University, Tallahassee, FL 32304, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiman","family":"Yuan","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, TN 37235, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongmei","family":"Chi","sequence":"additional","affiliation":[{"name":"Florida A&M University, Tallahassee, FL 32307, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4015-4787","authenticated-orcid":false,"given":"Xin Maizie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Vanderbilt University, Nashville, TN 37235, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0365-0909","authenticated-orcid":false,"given":"Xian","family":"Mallory","sequence":"additional","affiliation":[{"name":"Florida State University, Tallahassee, FL 32304, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026070706051082000_2026.06.29.734828v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-00795-2"},{"key":"2026070706051082000_2026.06.29.734828v1.2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty316"},{"key":"2026070706051082000_2026.06.29.734828v1.3","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-022-02683-1"},{"key":"2026070706051082000_2026.06.29.734828v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-025-07942-y"},{"key":"2026070706051082000_2026.06.29.734828v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-62359-9"},{"key":"2026070706051082000_2026.06.29.734828v1.6","doi-asserted-by":"publisher","DOI":"10.1093\/pcmedi\/pbaf011"},{"key":"2026070706051082000_2026.06.29.734828v1.7","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf076"},{"key":"2026070706051082000_2026.06.29.734828v1.8","doi-asserted-by":"publisher","DOI":"10.3390\/biomedicines12081759"},{"key":"2026070706051082000_2026.06.29.734828v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2023.07.009"},{"key":"2026070706051082000_2026.06.29.734828v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-46413-6"},{"key":"2026070706051082000_2026.06.29.734828v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-020-00726-6"},{"key":"2026070706051082000_2026.06.29.734828v1.12","doi-asserted-by":"publisher","DOI":"10.1126\/SCIENCE.ABL4896\/SUPPL_FILE\/SCIENCE.ABL4896_MDAR_REPRODUCIBILITY_CHECKLIST.PDF"},{"key":"2026070706051082000_2026.06.29.734828v1.13","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-8244458\/v1"},{"key":"2026070706051082000_2026.06.29.734828v1.14","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-8240360\/v1"},{"key":"2026070706051082000_2026.06.29.734828v1.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-41695-z"},{"key":"2026070706051082000_2026.06.29.734828v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/s41422-020-0355-0"},{"key":"2026070706051082000_2026.06.29.734828v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-020-0636-z"},{"key":"2026070706051082000_2026.06.29.734828v1.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2021.109165"},{"key":"2026070706051082000_2026.06.29.734828v1.19","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-019-0392-8"},{"key":"2026070706051082000_2026.06.29.734828v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-022-01233-1"},{"key":"2026070706051082000_2026.06.29.734828v1.21","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-021-00830-w"},{"key":"2026070706051082000_2026.06.29.734828v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-022-01728-4"},{"issue":"16","key":"2026070706051082000_2026.06.29.734828v1.23","doi-asserted-by":"crossref","first-page":"4124","DOI":"10.3390\/cancers13164124","article-title":"Pan-cancer analysis of immune complement signature c3\/c5\/c3ar1\/c5ar1 in association with tumor immune evasion and therapy resistance","volume":"13","year":"2021","journal-title":"Cancers"},{"key":"2026070706051082000_2026.06.29.734828v1.24","doi-asserted-by":"publisher","DOI":"10.1084\/jem.20030286"},{"key":"2026070706051082000_2026.06.29.734828v1.25","doi-asserted-by":"crossref","unstructured":"Hussain Al Ssadh , Patrick S Spencer , Waleed Alabdulmenaim , Rana Alghamdi , Inamul Hasan Madar , Jose M Miranda-Sayago , and Nelson Fern\u00e0ndez . Measurements of heterotypic associations between cluster of differentiation cd74 and cd44 in human breast cancer-derived cells. Oncotarget, 8(54):92143.","DOI":"10.18632\/oncotarget.20922"},{"key":"2026070706051082000_2026.06.29.734828v1.26","doi-asserted-by":"publisher","DOI":"10.3892\/or.2014.3272"},{"key":"2026070706051082000_2026.06.29.734828v1.27","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.11945"},{"key":"2026070706051082000_2026.06.29.734828v1.28","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac194"},{"key":"2026070706051082000_2026.06.29.734828v1.29","doi-asserted-by":"publisher","DOI":"10.1126\/science.1164368"},{"key":"2026070706051082000_2026.06.29.734828v1.30","doi-asserted-by":"publisher","DOI":"10.1038\/nature14169"},{"key":"2026070706051082000_2026.06.29.734828v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccell.2017.07.007"},{"key":"2026070706051082000_2026.06.29.734828v1.32","doi-asserted-by":"publisher","DOI":"10.1038\/s41392-024-01779-3"},{"key":"2026070706051082000_2026.06.29.734828v1.33","doi-asserted-by":"publisher","DOI":"10.1038\/s41523-022-00464-4"},{"key":"2026070706051082000_2026.06.29.734828v1.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.05.031"},{"key":"2026070706051082000_2026.06.29.734828v1.35","doi-asserted-by":"publisher","DOI":"10.1038\/s41590-018-0276-y"},{"key":"2026070706051082000_2026.06.29.734828v1.36","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-017-1382-0"},{"issue":"1","key":"2026070706051082000_2026.06.29.734828v1.37","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1038\/s41467-021-21246-9","article-title":"Inference and analysis of cell-cell communication using cellchat","volume":"12","year":"2021","journal-title":"Nature communications"},{"key":"2026070706051082000_2026.06.29.734828v1.38","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06130-4"},{"key":"2026070706051082000_2026.06.29.734828v1.39","unstructured":"Julie Laffy . infercna: Infer copy number alterations from single-cell RNA-seq data, 2023. URL https:\/\/github.com\/jlaffy\/infercna."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.06.29.734828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T13:14:09Z","timestamp":1783430049000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.06.29.734828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":39,"URL":"https:\/\/doi.org\/10.64898\/2026.06.29.734828","relation":{},"subject":[],"published":{"date-parts":[[2026,7,3]]},"subtype":"preprint"}}