{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"submitter":["Jost TA"],"funding":["NCI NIH HHS"],"pubmed_abstract":["<h4>Motivation</h4>Cells exhibit a wide array of morphological features, enabling computer vision methods to identify and track relevant parameters. Morphological analysis has long been implemented to identify specific cell types and cell responses. Here we asked whether morphological features might also be used to classify transcriptomic subpopulations within <i>in vitro</i> cancer cell lines. Identifying cell subpopulations furthers our understanding of morphology as a reflection of underlying cell phenotype and could enable a better understanding of how subsets of cells compete and cooperate in disease progression and treatment.<h4>Results</h4>We demonstrate that cell morphology can reflect underlying transcriptomic differences <i>in vitro</i> using convolutional neural networks. First,"],"journal":["bioRxiv : the preprint server for biology"],"pagination":["2024.07.02.601576"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11245002"],"repository":["biostudies-literature"],"pubmed_title":["Deep learning identifies heterogeneous subpopulations in breast cancer cell lines."],"pmcid":["PMC11245002"],"funding_grant_id":["U01 CA253540","R01 CA255536","R01 CA226258"],"pubmed_authors":["Gardner AL","Brock A","Jost TA","Morgan D"],"additional_accession":[]},"is_claimable":false,"name":"Deep learning identifies heterogeneous subpopulations in breast cancer cell lines.","description":"<h4>Motivation</h4>Cells exhibit a wide array of morphological features, enabling computer vision methods to identify and track relevant parameters. Morphological analysis has long been implemented to identify specific cell types and cell responses. Here we asked whether morphological features might also be used to classify transcriptomic subpopulations within <i>in vitro</i> cancer cell lines. Identifying cell subpopulations furthers our understanding of morphology as a reflection of underlying cell phenotype and could enable a better understanding of how subsets of cells compete and cooperate in disease progression and treatment.<h4>Results</h4>We demonstrate that cell morphology can reflect underlying transcriptomic differences <i>in vitro</i> using convolutional neural networks. First,","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Jul","modification":"2025-04-04T15:01:37.536Z","creation":"2025-04-04T15:01:37.536Z"},"accession":"S-EPMC11245002","cross_references":{"pubmed":["39005432"],"doi":["10.1101/2024.07.02.601576"]}}