{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T15:07:15Z","timestamp":1785424035990,"version":"3.56.0"},"posted":{"date-parts":[[2026,6,19]]},"group-title":"Bioinformatics","reference-count":43,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:00:00Z","timestamp":1781827200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"award":["R01CA310281"],"award-info":[{"award-number":["R01CA310281"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004281","name":"Polish National Science Centre","doi-asserted-by":"crossref","award":["UMO-2021\/41\/B\/NZ2\/04134"],"award-info":[{"award-number":["UMO-2021\/41\/B\/NZ2\/04134"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,19]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Recent evidence shows that despite considerable effort, currently available algorithms for estimating intratumor heterogeneity (ITH) remain limited. We developed DECODE (\n                  <jats:underline>De<\/jats:underline>\n                  ciphering\n                  <jats:underline>C<\/jats:underline>\n                  ancer\n                  <jats:underline>O<\/jats:underline>\n                  rigin from\n                  <jats:underline>D<\/jats:underline>\n                  NA\n                  <jats:underline>E<\/jats:underline>\n                  volution), a novel mutation clustering method that incorporates the impact of sample-specific sequencing coverage and mutation calling biases. On synthetic data, DECODE outperformed existing methods across multiple clonality metrics and accurately detected and characterized the neutral tail in the site frequency spectrum (SFS), which encodes the tumor\u2019s ongoing expansion mode. In acute myeloid leukemia, accounting for the neutral tail enabled DECODE to yield more parsimonious clonal decompositions that align more closely with known subclonal dynamics that drive relapse. Applied to data from The Cancer Genome Atlas, DECODE not only detected a neutral SFS tail in most samples across tumor types but also uncovered a clinically meaningful link between ITH and survival in low-grade glioma. By jointly inferring clonality and expansion mode, DECODE provides two complementary and prognostically relevant readouts of tumor evolution from single tumor genomic samples.\n                <\/jats:p>","DOI":"10.64898\/2026.06.15.732415","type":"posted-content","created":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:15:23Z","timestamp":1781914523000},"source":"Crossref","is-referenced-by-count":0,"title":["Accurate detection of tumor clonality and ongoing expansion mode from genomic data"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6223-7391","authenticated-orcid":false,"given":"Yanjie","family":"Chen","sequence":"first","affiliation":[{"name":"Irving Institute for Cancer Dynamics, Columbia University, New York, NY, USA"},{"name":"Department of Statistics, Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1866-6380","authenticated-orcid":false,"given":"Roman","family":"Jaksik","sequence":"additional","affiliation":[{"name":"Department of Systems Biology and Engineering, Silesian University of Technology, Gliwice, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Terranova","sequence":"additional","affiliation":[{"name":"Irving Institute for Cancer Dynamics, Columbia University, New York, NY, USA"},{"name":"Fordham University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"El Baghdadi","sequence":"additional","affiliation":[{"name":"Irving Institute for Cancer Dynamics, Columbia University, New York, NY, USA"},{"name":"\u00c9cole Polytechnique, Paris, France"},{"name":"Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Koval","sequence":"additional","affiliation":[{"name":"Departments of Statistics and Bioengineering, Rice University, Houston, TX, USA"},{"name":"Benaroya Research Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7635-8437","authenticated-orcid":false,"given":"Monika K.","family":"Kurpas","sequence":"additional","affiliation":[{"name":"Department of Systems Biology and Engineering, Silesian University of Technology, Gliwice, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3716-4952","authenticated-orcid":false,"given":"Simon","family":"Tavar\u00e9","sequence":"additional","affiliation":[{"name":"Irving Institute for Cancer Dynamics, Columbia University, New York, NY, USA"},{"name":"Department of Statistics, Columbia University, New York, NY, USA"},{"name":"Department of Biological Sciences, Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8161-890X","authenticated-orcid":false,"given":"Marek","family":"Kimmel","sequence":"additional","affiliation":[{"name":"Department of Systems Biology and Engineering, Silesian University of Technology, Gliwice, Poland"},{"name":"Departments of Statistics and Bioengineering, Rice University, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0010-4251","authenticated-orcid":false,"given":"Khanh N.","family":"Dinh","sequence":"additional","affiliation":[{"name":"Irving Institute for Cancer Dynamics, Columbia University, New York, NY, USA"},{"name":"Department of Statistics, Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026062304001364000_2026.06.15.732415v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/nm.3984"},{"key":"2026062304001364000_2026.06.15.732415v1.2","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.Cd-23-1249"},{"key":"2026062304001364000_2026.06.15.732415v1.3","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asp052"},{"key":"2026062304001364000_2026.06.15.732415v1.4","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":"2026062304001364000_2026.06.15.732415v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-020-0675-5"},{"key":"2026062304001364000_2026.06.15.732415v1.6","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.2203"},{"issue":"1","key":"2026062304001364000_2026.06.15.732415v1.7","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1186\/s12916-017-0900-y","article-title":"The role of tumour heterogeneity and clonal cooperativity in metastasis, immune evasion and clinical outcome","volume":"15","year":"2017","journal-title":"BMC Medicine"},{"key":"2026062304001364000_2026.06.15.732415v1.8","first-page":"1","article-title":"Distributional Random Forests: Heterogeneity adjustment and multivariate distributional regression","volume":"23","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"2026062304001364000_2026.06.15.732415v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.2514"},{"issue":"2","key":"2026062304001364000_2026.06.15.732415v1.10","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1038\/nrclinonc.2017.166","article-title":"Tumour heterogeneity and resistance to cancer therapies","volume":"15","year":"2018","journal-title":"Nature Reviews Clinical Oncology"},{"key":"2026062304001364000_2026.06.15.732415v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/ng.806"},{"key":"2026062304001364000_2026.06.15.732415v1.12","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-015-0602-8"},{"key":"2026062304001364000_2026.06.15.732415v1.13","doi-asserted-by":"publisher","DOI":"10.1214\/19-sts7561"},{"issue":"6","key":"2026062304001364000_2026.06.15.732415v1.14","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s11222-025-10748-x","article-title":"Approximate Bayesian computation sequential Monte Carlo via random forests","volume":"35","year":"2025","journal-title":"Statistics and Computing"},{"issue":"1","key":"2026062304001364000_2026.06.15.732415v1.15","first-page":"230","article-title":"Population genetics of neutral mutations in exponentially growing cancer cell populations","volume":"23","year":"2013","journal-title":"The Annals of Applied Probability"},{"issue":"7","key":"2026062304001364000_2026.06.15.732415v1.16","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1038\/nmeth.3407","article-title":"Combining tumor genome simulation with crowdsourcing to benchmark somatic single-nucleotide-variant detection","volume":"12","year":"2015","journal-title":"Nature Methods"},{"key":"2026062304001364000_2026.06.15.732415v1.17","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-13-2098"},{"key":"2026062304001364000_2026.06.15.732415v1.18","doi-asserted-by":"publisher","DOI":"10.1080\/15326349808807471"},{"key":"2026062304001364000_2026.06.15.732415v1.19","unstructured":"T. Heide . TEMULATOR: Creation of synthetic tumour sequencing data, 2022. R package version 1.0."},{"key":"2026062304001364000_2026.06.15.732415v1.20","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/83.4.875"},{"key":"2026062304001364000_2026.06.15.732415v1.21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0151664"},{"key":"2026062304001364000_2026.06.15.732415v1.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2017.09.042"},{"key":"2026062304001364000_2026.06.15.732415v1.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2017.01.018"},{"key":"2026062304001364000_2026.06.15.732415v1.24","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-016-0974-4"},{"issue":"8","key":"2026062304001364000_2026.06.15.732415v1.25","doi-asserted-by":"crossref","first-page":"e1003665","DOI":"10.1371\/journal.pcbi.1003665","article-title":"SciClone: inferring clonal architecture and tracking the spatial and temporal patterns of tumor evolution","volume":"10","year":"2014","journal-title":"PLOS Computational Biology"},{"key":"2026062304001364000_2026.06.15.732415v1.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2012.04.023"},{"issue":"4","key":"2026062304001364000_2026.06.15.732415v1.27","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1038\/nmeth.2883","article-title":"PyClone: statistical inference of clonal population structure in cancer","volume":"11","year":"2014","journal-title":"Nature Methods"},{"key":"2026062304001364000_2026.06.15.732415v1.28","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-019-0364-z"},{"issue":"4","key":"2026062304001364000_2026.06.15.732415v1.29","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1038\/s41587-024-02250-y","article-title":"Crowd-sourced benchmarking of single-sample tumor subclonal reconstruction","volume":"43","year":"2025","journal-title":"Nature Biotechnology"},{"key":"2026062304001364000_2026.06.15.732415v1.30","doi-asserted-by":"crossref","unstructured":"L. Scrucca , C. Fraley , T. B. Murphy , and A. E. Raftery . Model-based clustering, classification, and density estimation using mclust in R. Chapman and Hall\/CRC, 2023.","DOI":"10.1201\/9781003277965"},{"key":"2026062304001364000_2026.06.15.732415v1.31","doi-asserted-by":"publisher","DOI":"10.1038\/nature22993"},{"key":"2026062304001364000_2026.06.15.732415v1.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.stem.2025.04.012"},{"key":"2026062304001364000_2026.06.15.732415v1.33","doi-asserted-by":"publisher","DOI":"10.1634\/theoncologist.2008-0075"},{"key":"2026062304001364000_2026.06.15.732415v1.34","doi-asserted-by":"publisher","DOI":"10.1038\/sj.bjc.6604125"},{"issue":"2","key":"2026062304001364000_2026.06.15.732415v1.35","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1038\/s41592-020-01013-2","article-title":"A practical guide to cancer subclonal reconstruction from DNA sequencing","volume":"18","year":"2021","journal-title":"Nature Methods"},{"key":"2026062304001364000_2026.06.15.732415v1.36","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1402121"},{"key":"2026062304001364000_2026.06.15.732415v1.37","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaf2784"},{"issue":"10","key":"2026062304001364000_2026.06.15.732415v1.38","doi-asserted-by":"crossref","first-page":"1805","DOI":"10.1093\/neuonc\/noae107","article-title":"The biological significance of tumor grade, age, enhancement, and extent of resection in IDH-mutant gliomas: How should they inform treatment decisions in the era of IDH inhibitors?","volume":"26","year":"2024","journal-title":"Neuro-Oncology"},{"key":"2026062304001364000_2026.06.15.732415v1.39","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1009843107"},{"key":"2026062304001364000_2026.06.15.732415v1.40","doi-asserted-by":"publisher","DOI":"10.1016\/0040-5809(75)90020-9"},{"key":"2026062304001364000_2026.06.15.732415v1.41","doi-asserted-by":"publisher","DOI":"10.1038\/ng.2764"},{"key":"2026062304001364000_2026.06.15.732415v1.42","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3489"},{"issue":"17","key":"2026062304001364000_2026.06.15.732415v1.43","doi-asserted-by":"crossref","first-page":"2101230","DOI":"10.1002\/advs.202101230","article-title":"IDH mutation subgroup status associates with intratumor heterogeneity and the tumor microenvironment in intrahepatic cholangiocarcinoma","volume":"8","year":"2021","journal-title":"Advanced Science"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.06.15.732415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T11:08:57Z","timestamp":1782212937000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.06.15.732415"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.64898\/2026.06.15.732415","relation":{},"subject":[],"published":{"date-parts":[[2026,6,19]]},"subtype":"preprint"}}