{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T02:27:03Z","timestamp":1776824823786,"version":"3.51.2"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T00:00:00Z","timestamp":1651104000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100015668","name":"Ontario Ministry of Research and Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015668","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"crossref","award":["Frederick Banting and Charles Best Canada Graduate Scholarship"],"award-info":[{"award-number":["Frederick Banting and Charles Best Canada Graduate Scholarship"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Variant allele frequencies (VAF) encode ongoing evolution and subclonal selection in growing tumours. However, existing methods that utilize VAF information for cancer evolutionary inference are compressive, slow, or incorrectly specify the underlying cancer evolutionary dynamics. Here, we provide a proof-of-principle synthetic supervised learning method, TumE, that integrates simulated models of cancer evolution with Bayesian neural networks, to infer ongoing selection in bulk-sequenced single tumour biopsies. Analyses in synthetic and patient tumours show that TumE significantly improves both accuracy and inference time per sample when detecting positive selection, deconvoluting selected subclonal populations, and estimating subclone frequency. Importantly, we show how transfer learning can leverage stored knowledge within TumE models for related evolutionary inference tasks\u2014substantially reducing data and computational time for further model development and providing a library of recyclable deep learning models for the cancer evolution community. This extensible framework provides a foundation and future directions for harnessing progressive computational methods for the benefit of cancer genomics and, in turn, the cancer patient.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1010007","type":"journal-article","created":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T13:41:11Z","timestamp":1651153271000},"page":"e1010007","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["Inferring ongoing cancer evolution from single tumour biopsies using synthetic supervised learning"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5052-7797","authenticated-orcid":true,"given":"Tom W.","family":"Ouellette","sequence":"first","affiliation":[]},{"given":"Philip","family":"Awadalla","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2022,4,28]]},"reference":[{"issue":"5","key":"pcbi.1010007.ref001","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.cell.2011.02.013","article-title":"Hallmarks of Cancer: The Next Generation","volume":"144","author":"D Hanahan","year":"2011","journal-title":"Cell"},{"issue":"8","key":"pcbi.1010007.ref002","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1038\/nrc3971","article-title":"Tumorigenesis: it takes a village","volume":"15","author":"DP Tabassum","year":"2015","journal-title":"Nat Rev Cancer"},{"issue":"1","key":"pcbi.1010007.ref003","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.trecan.2015.11.003","article-title":"Cancer Evolution and the Limits of Predictability in Precision Cancer Medicine","volume":"2","author":"KA Lipinski","year":"2016","journal-title":"Trends Cancer"},{"key":"pcbi.1010007.ref004","first-page":"1","article-title":"Breast tumours maintain a reservoir of subclonal diversity during expansion","author":"DC Minussi","year":"2021","journal-title":"Nature"},{"issue":"1","key":"pcbi.1010007.ref005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13073-019-0632-z","article-title":"Translating insights into tumor evolution to clinical practice: promises and challenges","volume":"11","author":"MW Fittall","year":"2019","journal-title":"Genome Med"},{"issue":"14","key":"pcbi.1010007.ref006","doi-asserted-by":"crossref","first-page":"4413","DOI":"10.1158\/1078-0432.CCR-19-0006","article-title":"Multidrug Cancer Therapy in Metastatic Castrate-Resistant Prostate Cancer: An Evolution-Based Strategy","volume":"25","author":"JB West","year":"2019","journal-title":"Clin Cancer Res"},{"issue":"6","key":"pcbi.1010007.ref007","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1038\/s41588-018-0128-6","article-title":"Quantification of subclonal selection in cancer from bulk sequencing data","volume":"50","author":"MJ Williams","year":"2018","journal-title":"Nat Genet"},{"issue":"5","key":"pcbi.1010007.ref008","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2017.09.042","article-title":"Universal Patterns of Selection in Cancer and Somatic Tissues","volume":"171","author":"I Martincorena","year":"2017","journal-title":"Cell"},{"issue":"11","key":"pcbi.1010007.ref009","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1038\/s41571-020-0411-1","article-title":"Integrating evolutionary dynamics into cancer therapy","volume":"17","author":"RA Gatenby","year":"2020","journal-title":"Nat Rev Clin Oncol"},{"issue":"10","key":"pcbi.1010007.ref010","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The Cancer Genome Atlas Pan-Cancer analysis project","volume":"45","author":"JN Weinstein","year":"2013","journal-title":"Nat Genet"},{"issue":"7793","key":"pcbi.1010007.ref011","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1038\/s41586-020-1969-6","article-title":"Pan-cancer analysis of whole genomes","volume":"578","author":"PJ Campbell","year":"2020","journal-title":"Nature"},{"issue":"3","key":"pcbi.1010007.ref012","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1038\/ng.3489","article-title":"Identification of neutral tumor evolution across cancer types","volume":"48","author":"MJ Williams","year":"2016","journal-title":"Nat Genet"},{"issue":"7","key":"pcbi.1010007.ref013","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1038\/ng.3891","article-title":"Between-region genetic divergence reflects the mode and tempo of tumor evolution","volume":"49","author":"R Sun","year":"2017","journal-title":"Nat Genet"},{"issue":"9","key":"pcbi.1010007.ref014","doi-asserted-by":"crossref","first-page":"e1007368","DOI":"10.1371\/journal.pcbi.1007368","article-title":"On measuring selection in cancer from subclonal mutation frequencies","volume":"15","author":"I Bozic","year":"2019","journal-title":"PLOS Comput Biol"},{"key":"pcbi.1010007.ref015","article-title":"Inferring parameters of cancer evolution from sequencing and clinical data","author":"N Lee","year":"2020","journal-title":"bioRxiv"},{"issue":"9","key":"pcbi.1010007.ref016","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1038\/s41588-020-0675-5","article-title":"Subclonal reconstruction of tumors by using machine learning and population genetics","volume":"52","author":"G Caravagna","year":"2020","journal-title":"Nat Genet"},{"issue":"2","key":"pcbi.1010007.ref017","doi-asserted-by":"crossref","first-page":"e1008701","DOI":"10.1371\/journal.pcbi.1008701","article-title":"Signatures of neutral evolution in exponentially growing tumors: A theoretical perspective","volume":"17","author":"H-R Tung","year":"2021","journal-title":"PLOS Comput Biol"},{"key":"pcbi.1010007.ref018","volume-title":"An introduction to population genetics theory","author":"JF Crow","year":"1970"},{"issue":"1","key":"pcbi.1010007.ref019","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1038\/s41467-020-14407-9","article-title":"Estimating growth patterns and driver effects in tumor evolution from individual samples","volume":"11","author":"L Salichos","year":"2020","journal-title":"Nat Commun"},{"issue":"3","key":"pcbi.1010007.ref020","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1093\/genetics\/123.3.585","article-title":"Statistical Method for Testing the Neutral Mutation Hypothesis by DNA Polymorphism","volume":"123","author":"F. Tajima","year":"1989","journal-title":"Genetics"},{"issue":"3","key":"pcbi.1010007.ref021","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.1093\/genetics\/155.3.1405","article-title":"Hitchhiking under positive Darwinian selection","volume":"155","author":"JC Fay","year":"2000","journal-title":"Genetics"},{"issue":"3","key":"pcbi.1010007.ref022","doi-asserted-by":"crossref","first-page":"e1004845","DOI":"10.1371\/journal.pcbi.1004845","article-title":"Deep Learning for Population Genetic Inference","volume":"12","author":"S Sheehan","year":"2016","journal-title":"PLOS Comput Biol"},{"key":"pcbi.1010007.ref023","article-title":"Summary Statistics in Approximate Bayesian Computation","author":"D. Prangle","year":"2015","journal-title":"ArXiv151205633 Math Stat"},{"issue":"8","key":"pcbi.1010007.ref024","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","author":"CA Miller","year":"2014","journal-title":"PLOS Comput Biol"},{"issue":"4","key":"pcbi.1010007.ref025","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","author":"A Roth","year":"2014","journal-title":"Nat Methods"},{"key":"pcbi.1010007.ref026","article-title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","author":"Y Gal","year":"2016","journal-title":"ArXiv150602142 Cs Stat"},{"key":"pcbi.1010007.ref027","article-title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","author":"Y Gal","year":"2016","journal-title":"ArXiv150602158 Cs Stat"},{"key":"pcbi.1010007.ref028","article-title":"Using Synthetic Data to Train Neural Networks is Model-Based Reasoning","author":"TA Le","year":"2017","journal-title":"ArXiv170300868 Cs Stat"},{"issue":"42","key":"pcbi.1010007.ref029","doi-asserted-by":"crossref","first-page":"15138","DOI":"10.1073\/pnas.1404341111","article-title":"Tug-of-war between driver and passenger mutations in cancer and other adaptive processes","volume":"111","author":"CD McFarland","year":"2014","journal-title":"Proc Natl Acad Sci"},{"issue":"29","key":"pcbi.1010007.ref030","doi-asserted-by":"crossref","first-page":"11682","DOI":"10.1073\/pnas.1309667110","article-title":"Large population solution of the stochastic Luria\u2013Delbr\u00fcck evolution model","volume":"110","author":"DA Kessler","year":"2013","journal-title":"Proc Natl Acad Sci"},{"issue":"3","key":"pcbi.1010007.ref031","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.cels.2015.08.015","article-title":"Optimizing Cancer Genome Sequencing and Analysis","volume":"1","author":"M Griffith","year":"2015","journal-title":"Cell Syst"},{"issue":"5","key":"pcbi.1010007.ref032","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1016\/j.cell.2012.04.023","article-title":"The Life History of 21 Breast Cancers","volume":"149","author":"S Nik-Zainal","year":"2012","journal-title":"Cell"},{"issue":"1","key":"pcbi.1010007.ref033","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1038\/s41467-019-13915-7","article-title":"Extreme intratumour heterogeneity and driver evolution in mismatch repair deficient gastro-oesophageal cancer","volume":"11","author":"K von Loga","year":"2020","journal-title":"Nat Commun"},{"issue":"7793","key":"pcbi.1010007.ref034","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1038\/s41586-019-1907-7","article-title":"The evolutionary history of 2,658 cancers","volume":"578","author":"M Gerstung","year":"2020","journal-title":"Nature"},{"issue":"8","key":"pcbi.1010007.ref035","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2021.03.009","article-title":"Characterizing genetic intra-tumor heterogeneity across 2,658 human cancer genomes","volume":"184","author":"SC Dentro","year":"2021","journal-title":"Cell"},{"key":"pcbi.1010007.ref036","article-title":"An introduction to domain adaptation and transfer learning","author":"WM Kouw","year":"2019","journal-title":"ArXiv181211806 Cs Stat"},{"key":"pcbi.1010007.ref037","doi-asserted-by":"crossref","unstructured":"Busto PP, Gall J. Open Set Domain Adaptation. In: 2017 IEEE International Conference on Computer Vision (ICCV) [Internet]. Venice: IEEE; 2017 [cited 2021 Oct 8]. p. 754\u201363. Available from: http:\/\/ieeexplore.ieee.org\/document\/8237350\/.","DOI":"10.1109\/ICCV.2017.88"},{"issue":"12","key":"pcbi.1010007.ref038","doi-asserted-by":"crossref","first-page":"1633","DOI":"10.1038\/s41588-018-0256-z","article-title":"Reply to \u2018Neutral tumor evolution?","volume":"50","author":"T Heide","year":"2018","journal-title":"Nat Genet"},{"issue":"3","key":"pcbi.1010007.ref039","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1038\/ng.3214","article-title":"A Big Bang model of human colorectal tumor growth","volume":"47","author":"A Sottoriva","year":"2015","journal-title":"Nat Genet"},{"issue":"4","key":"pcbi.1010007.ref040","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1038\/nrg.2016.170","article-title":"The evolution of tumour phylogenetics: principles and practice","volume":"18","author":"R Schwartz","year":"2017","journal-title":"Nat Rev Genet"},{"issue":"17","key":"pcbi.1010007.ref041","doi-asserted-by":"crossref","first-page":"i671","DOI":"10.1093\/bioinformatics\/bty589","article-title":"SPhyR: tumor phylogeny estimation from single-cell sequencing data under loss and error","volume":"34","author":"M. El-Kebir","year":"2018","journal-title":"Bioinformatics"},{"issue":"7","key":"pcbi.1010007.ref042","doi-asserted-by":"crossref","first-page":"e1007243","DOI":"10.1371\/journal.pcbi.1007243","article-title":"Spatially constrained tumour growth affects the patterns of clonal selection and neutral drift in cancer genomic data","volume":"15","author":"K Chkhaidze","year":"2019","journal-title":"PLOS Comput Biol"},{"issue":"1","key":"pcbi.1010007.ref043","doi-asserted-by":"crossref","first-page":"2060","DOI":"10.1038\/s41467-021-22123-1","article-title":"Normal tissue architecture determines the evolutionary course of cancer","volume":"12","author":"J West","year":"2021","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1010007.ref044","doi-asserted-by":"crossref","first-page":"4469","DOI":"10.1038\/s41467-020-18169-2","article-title":"FastClone is a probabilistic tool for deconvoluting tumor heterogeneity in bulk-sequencing samples","volume":"11","author":"Y Xiao","year":"2020","journal-title":"Nat Commun"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1010007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T13:42:03Z","timestamp":1651153323000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1010007"}},"subtitle":[],"editor":[{"given":"Niko","family":"Beerenwinkel","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,4,28]]},"references-count":44,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1010007","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2021.11.22.469566","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,28]]}}}