{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T14:39:06Z","timestamp":1786977546165,"version":"build-2736575974"},"posted":{"date-parts":[[2026,8,13]]},"group-title":"Bioinformatics","reference-count":18,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,13]]},"abstract":"<jats:title>Summary<\/jats:title>\n                <jats:p>\n                  Assigning cell types to single-cell and spatial transcriptomic data remains inconsistent because marker gene knowledge is fragmented across thousands of individual studies. Here we present CellConsensus, a cell typing method built on a consensus corpus of marker genes aggregated from curated atlases (2,607 sources) and de novo mining of 1,174 papers. By reconciling overlapping and conflicting marker evidence into a consensus reference, CellConsensus assigns cell type labels that are more accurate and more reproducible than existing marker- and reference-based approaches, while remaining interpretable and applicable across tissues and platforms. CellConsensus is available as an open-source Python package (\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/tansey-lab\/cellconsensus\">https:\/\/github.com\/tansey-lab\/cellconsensus<\/jats:ext-link>\n                  ), an interactive database (\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/cellconsensus.org\">https:\/\/cellconsensus.org<\/jats:ext-link>\n                  ), and as an agentic MCP server for conversational querying.\n                <\/jats:p>","DOI":"10.64898\/2026.08.07.743503","type":"posted-content","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T21:55:10Z","timestamp":1786658110000},"source":"Crossref","is-referenced-by-count":0,"title":["CellConsensus: An agent-curated atlas for automatic cell typing"],"prefix":"10.64898","author":[{"given":"Antoine","family":"de Mathelin","sequence":"first","affiliation":[{"name":"Computational Oncology, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey F.","family":"Quinn","sequence":"additional","affiliation":[{"name":"Computational Oncology, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Tosh","sequence":"additional","affiliation":[{"name":"Computational Oncology, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Data Science","family":"TeamLab","sequence":"additional","affiliation":[{"name":"Break Through Cancer"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wesley","family":"Tansey","sequence":"additional","affiliation":[{"name":"Computational Oncology, Memorial Sloan Kettering Cancer Center, New York, NY"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026081706300829000_2026.08.07.743503v1.1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.27041"},{"key":"2026081706300829000_2026.08.07.743503v1.2","doi-asserted-by":"publisher","DOI":"10.15252\/msb.20188746"},{"key":"2026081706300829000_2026.08.07.743503v1.3","doi-asserted-by":"publisher","DOI":"10.1038\/s41590-018-0276-y"},{"key":"2026081706300829000_2026.08.07.743503v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/J.CELL.2021.04.048"},{"key":"2026081706300829000_2026.08.07.743503v1.5","doi-asserted-by":"publisher","DOI":"10.1126\/science.abl5197"},{"key":"2026081706300829000_2026.08.07.743503v1.6","doi-asserted-by":"crossref","first-page":"1246","DOI":"10.1038\/s41467-022-28803-w","article-title":"Fully-automated and ultra-fast cell-type identification using specific marker combinations from single-cell transcriptomic data","volume":"13","year":"2022","journal-title":"Nature Communications"},{"key":"2026081706300829000_2026.08.07.743503v1.7","doi-asserted-by":"crossref","first-page":"1462","DOI":"10.1038\/s41592-024-02235-4","article-title":"Assessing GPT-4 for cell type annotation in single-cell RNA-seq analysis","volume":"21","year":"2024","journal-title":"Nature Methods"},{"key":"2026081706300829000_2026.08.07.743503v1.8","first-page":"e37432","article-title":"Exploring the boundaries of reality: investigating the phenomenon of artificial intelligence hallucination in scientific writing through ChatGPT references","volume":"15","year":"2023","journal-title":"Cureus"},{"key":"2026081706300829000_2026.08.07.743503v1.9","doi-asserted-by":"crossref","first-page":"14049","DOI":"10.1038\/ncomms14049","article-title":"Massively parallel digital transcriptional profiling of single cells","volume":"8","year":"2017","journal-title":"Nature Communications"},{"key":"2026081706300829000_2026.08.07.743503v1.10","unstructured":"Luecken, M. D. et al. A sandbox for prediction and integration of DNA, RNA, and proteins in single cells. Advances in Neural Information Processing Systems (Datasets and Benchmarks Track) 34 (2021)."},{"key":"2026081706300829000_2026.08.07.743503v1.11","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.ccell.2025.10.004","article-title":"Multimodal spatial-omics reveal co-evolution of alveolar progenitors and proinflammatory niches in progression of lung precursor lesions","volume":"44","year":"2026","journal-title":"Cancer Cell"},{"key":"2026081706300829000_2026.08.07.743503v1.12","doi-asserted-by":"crossref","first-page":"9232","DOI":"10.1038\/s41467-025-64292-3","article-title":"Systematic benchmarking of high-throughput subcellular spatial transcriptomics platforms across human tumors","volume":"16","year":"2025","journal-title":"Nature Communications"},{"key":"2026081706300829000_2026.08.07.743503v1.13","doi-asserted-by":"crossref","first-page":"8353","DOI":"10.1038\/s41467-023-43458-x","article-title":"High resolution mapping of the tumor microenvironment using integrated single-cell, spatial and in situ analysis","volume":"14","year":"2023","journal-title":"Nature Communications"},{"key":"2026081706300829000_2026.08.07.743503v1.14","doi-asserted-by":"publisher","DOI":"10.3390\/genes10070531"},{"key":"2026081706300829000_2026.08.07.743503v1.15","doi-asserted-by":"crossref","first-page":"5399","DOI":"10.1038\/s41467-025-60900-4","article-title":"Cell marker accordion: interpretable single-cell and spatial omics annotation in health and disease","volume":"16","year":"2025","journal-title":"Nature Communications"},{"key":"2026081706300829000_2026.08.07.743503v1.16","doi-asserted-by":"publisher","DOI":"10.1186\/s13326-016-0088-7"},{"key":"2026081706300829000_2026.08.07.743503v1.17","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2012-13-1-r5"},{"key":"2026081706300829000_2026.08.07.743503v1.18","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btw763"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.07.743503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T13:30:18Z","timestamp":1786973418000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.08.07.743503"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":18,"URL":"https:\/\/doi.org\/10.64898\/2026.08.07.743503","relation":{},"subject":[],"published":{"date-parts":[[2026,8,13]]},"subtype":"preprint"}}