{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:24:14Z","timestamp":1772173454798,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1012801","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T00:00:00Z","timestamp":1752710400000}}],"reference-count":23,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:00:00Z","timestamp":1752192000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS1764406"],"award-info":[{"award-number":["DMS1764406"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000893","name":"Simons Foundation","doi-asserted-by":"publisher","award":["SFARI 594594"],"award-info":[{"award-number":["SFARI 594594"]}],"id":[{"id":"10.13039\/100000893","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS1764406"],"award-info":[{"award-number":["DMS1764406"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000893","name":"Simons Foundation","doi-asserted-by":"publisher","award":["SFARI 594594"],"award-info":[{"award-number":["SFARI 594594"]}],"id":[{"id":"10.13039\/100000893","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Understanding how stem cells organize to form early tissue layers remains an important open question in developmental biology. Helpful in understanding this process are biomarkers or features that signal when a significant transition or decision occurs. We show such features from the spatial layout of the cells in a colony are sufficient to train neural networks to classify stem cell colonies according to differentiation protocol treatments each colony has received. We use topological data analysis to derive input information about the cells\u2019 positions to a four-layer feedforward neural network. We find that despite the simplicity of this approach, such a network has performance similar to the traditional image classifier ResNet. We also find that network performance may reveal the time window during which differentiation occurs across multiple conditions.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1012801","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T17:56:55Z","timestamp":1752256615000},"page":"e1012801","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Neural network approaches, including use of topological data analysis, enhance classification of human induced pluripotent stem cell colonies by treatment condition"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8563-236X","authenticated-orcid":true,"given":"Alexander Ruys","family":"de Perez","sequence":"first","affiliation":[]},{"given":"Paul E.","family":"Anderson","sequence":"additional","affiliation":[]},{"given":"Elena S.","family":"Dimitrova","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3781-8802","authenticated-orcid":true,"given":"Melissa L.","family":"Kemp","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2025,7,11]]},"reference":[{"issue":"8","key":"pcbi.1012801.ref001","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1038\/nmeth.3016","article-title":"A method to recapitulate early embryonic spatial patterning in human embryonic stem cells","volume":"11","author":"A Warmflash","year":"2014","journal-title":"Nat Methods"},{"key":"pcbi.1012801.ref002","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.ymeth.2015.11.027","article-title":"Aggregate formation and suspension culture of human pluripotent stem cells and differentiated progeny","volume":"101","author":"TA Hookway","year":"2016","journal-title":"Methods"},{"issue":"13","key":"pcbi.1012801.ref003","doi-asserted-by":"crossref","first-page":"2010","DOI":"10.1093\/bioinformatics\/btx069","article-title":"A multi-scale convolutional neural network for phenotyping high-content cellular images","volume":"33","author":"WJ Godinez","year":"2017","journal-title":"Bioinformatics"},{"issue":"1","key":"pcbi.1012801.ref004","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2018.08.028","article-title":"Intelligent image-activated cell sorting","volume":"175","author":"N Nitta","year":"2018","journal-title":"Cell"},{"key":"pcbi.1012801.ref005","doi-asserted-by":"crossref","first-page":"105026","DOI":"10.1016\/j.compbiomed.2021.105026","article-title":"Is the aspect ratio of cells important in deep learning? A robust comparison of deep learning methods for multi-scale cytopathology cell image classification: From convolutional neural networks to visual transformers","volume":"141","author":"W Liu","year":"2022","journal-title":"Comput Biol Med"},{"issue":"4","key":"pcbi.1012801.ref006","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1038\/nmeth.4182","article-title":"Prospective identification of hematopoietic lineage choice by deep learning","volume":"14","author":"F Buggenthin","year":"2017","journal-title":"Nat Methods"},{"issue":"11","key":"pcbi.1012801.ref007","doi-asserted-by":"crossref","first-page":"1925","DOI":"10.1089\/scd.2010.0476","article-title":"Assessment of differentiation aspects by the morphological classification of embryoid bodies derived from human embryonic stem cells","volume":"20","author":"JM Kim","year":"2011","journal-title":"Stem Cells Dev"},{"issue":"1","key":"pcbi.1012801.ref008","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1515\/sagmb-2015-0057","article-title":"Using persistent homology and dynamical distances to analyze protein binding","volume":"15","author":"V Kovacev-Nikolic","year":"2016","journal-title":"Stat Appl Genet Mol Biol"},{"issue":"17","key":"pcbi.1012801.ref009","doi-asserted-by":"crossref","first-page":"4653","DOI":"10.1039\/D1SM00072A","article-title":"Topological data analysis of collective and individual epithelial cells using persistent homology of loops","volume":"17","author":"D Bhaskar","year":"2021","journal-title":"Soft Matter"},{"issue":"5","key":"pcbi.1012801.ref010","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1016\/j.stemcr.2021.04.008","article-title":"Deep neural net tracking of human pluripotent stem cells reveals intrinsic behaviors directing morphogenesis","volume":"16","author":"DA Joy","year":"2021","journal-title":"Stem Cell Reports"},{"issue":"9","key":"pcbi.1012801.ref011","doi-asserted-by":"crossref","first-page":"2271","DOI":"10.1073\/pnas.1621412114","article-title":"Cell population structure prior to bifurcation predicts efficiency of directed differentiation in human induced pluripotent cells","volume":"114","author":"R Bargaje","year":"2017","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"24","key":"pcbi.1012801.ref012","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1089\/scd.2016.0099","article-title":"Prediction of differentiation tendency toward hepatocytes from gene expression in undifferentiated human pluripotent stem cells","volume":"25","author":"K Yanagihara","year":"2016","journal-title":"Stem Cells Dev"},{"key":"pcbi.1012801.ref013","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. p. 2921\u20139.","DOI":"10.1109\/CVPR.2016.319"},{"key":"pcbi.1012801.ref014","unstructured":"Edelsbrunner H, Letscher D, Zomorodian A. Topological persistence and simplification. In: Proceedings 41st Annual Symposium on Foundations of Computer Science. 2000. p. 454\u201363."},{"issue":"3","key":"pcbi.1012801.ref015","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/s41468-021-00071-5","article-title":"Ripser: efficient computation of vietoris\u2013rips persistence barcodes","volume":"5","author":"U Bauer","year":"2021","journal-title":"J Appl Comput Topol"},{"issue":"12","key":"pcbi.1012801.ref016","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1038\/nrm3470","article-title":"The complex world of WNT receptor signalling","volume":"13","author":"C Niehrs","year":"2012","journal-title":"Nat Rev Mol Cell Biol"},{"issue":"1","key":"pcbi.1012801.ref017","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.gendis.2014.07.005","article-title":"Bone Morphogenetic Protein (BMP) signaling in development and human diseases","volume":"1","author":"RN Wang","year":"2014","journal-title":"Genes Dis"},{"issue":"1657","key":"pcbi.1012801.ref018","doi-asserted-by":"crossref","first-page":"20130539","DOI":"10.1098\/rstb.2013.0539","article-title":"Activin\/Nodal signalling before implantation: setting the stage for embryo patterning","volume":"369","author":"C Papanayotou","year":"2014","journal-title":"Philos Trans R Soc Lond B Biol Sci"},{"key":"pcbi.1012801.ref019","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1101\/gad.330837.119","article-title":"Structural basis for distinct roles of SMAD2 and SMAD3 in FOXH1 pioneer-directed TGF-\u03b2 signaling","volume":"33","author":"E Arag\u00f3n","year":"2019","journal-title":"Genes Dev"},{"key":"pcbi.1012801.ref020","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.jsc.2016.03.009","article-title":"A persistence landscapes toolbox for topological statistics","volume":"78","author":"P Bubenik","year":"2017","journal-title":"J Symbol Comput"},{"key":"pcbi.1012801.ref021","first-page":"32","article-title":"Pytorch: an imperative style, high-performance deep learning library","author":"A Paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"pcbi.1012801.ref022","unstructured":"Yandell H. mert-kurttutan\/torchview; 2024. https:\/\/doi.org\/10.5281\/zenodo.14004786"},{"key":"pcbi.1012801.ref023","unstructured":"Omeiza D, Speakman S, Cintas C, Weldermariam K. Smooth grad-cam: an enhanced inference level visualization technique for deep convolutional neural network models. arXiv preprint 2019. https:\/\/arxiv.org\/abs\/1908.01224"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1012801","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T00:00:00Z","timestamp":1752710400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T17:55:58Z","timestamp":1752774958000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012801"}},"subtitle":[],"editor":[{"given":"Serdar","family":"Bozdag","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,7,11]]},"references-count":23,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012801","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2025.01.16.633346","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,11]]}}}