{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Cross-Zamirski JO"],"funding":["BBSRC DTP","AstraZeneca, Sweden","AstraZeneca","Wellcome Trust","Biotechnology and Biological Sciences Research Council","Engineering and Physical Sciences Research Council"],"pagination":["10001"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9200748"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["12(1)"],"pubmed_abstract":["Cell Painting is a high-content image-based assay applied in drug discovery to predict bioactivity, assess toxicity and understand mechanisms of action of chemical and genetic perturbations. We investigate label-free Cell Painting by predicting the five fluorescent Cell Painting channels from brightfield input. We train and validate two deep learning models with a dataset representing 17 batches, and we evaluate on batches treated with compounds from a phenotypic set. The mean Pearson correlation coefficient of the predicted images across all channels is 0.84. Without incorporating features into the model training, we achieved a mean correlation of 0.45 with ground truth features extracted using a segmentation-based feature extraction pipeline. Additionally, we identified 30 features which"],"journal":["Scientific reports"],"pubmed_title":["Label-free prediction of cell painting from brightfield images."],"pmcid":["PMC9200748"],"funding_grant_id":["21-3688","EP/N014588/1","EP/S026045/1","215733/Z/19/Z","221633/Z/20/Z","EP/T003553/1","EP/T017961/1"],"pubmed_authors":["Turkki R","Cross-Zamirski JO","Mouchet E","Schonlieb CB","Williams G","Wang Y"],"additional_accession":[]},"is_claimable":false,"name":"Label-free prediction of cell painting from brightfield images.","description":"Cell Painting is a high-content image-based assay applied in drug discovery to predict bioactivity, assess toxicity and understand mechanisms of action of chemical and genetic perturbations. We investigate label-free Cell Painting by predicting the five fluorescent Cell Painting channels from brightfield input. We train and validate two deep learning models with a dataset representing 17 batches, and we evaluate on batches treated with compounds from a phenotypic set. The mean Pearson correlation coefficient of the predicted images across all channels is 0.84. Without incorporating features into the model training, we achieved a mean correlation of 0.45 with ground truth features extracted using a segmentation-based feature extraction pipeline. Additionally, we identified 30 features which","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Jun","modification":"2025-04-22T21:29:57.594Z","creation":"2025-02-19T02:15:10.93Z"},"accession":"S-EPMC9200748","cross_references":{"pubmed":["35705591"],"doi":["10.1038/s41598-022-12914-x"]}}