Label-free prediction of cell painting from brightfield images

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 bright...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2022-06, Vol.12 (1), p.10001-10001, Article 10001
Main Authors: Cross-Zamirski, Jan Oscar, Mouchet, Elizabeth, Williams, Guy, Schönlieb, Carola-Bibiane, Turkki, Riku, Wang, Yinhai
Format: Article
Language:English
Subjects:
631/114
631/114/1305
631/114/1564
631/114/2397
631/154
631/154/53
631/154/555
Biological activity
Correlation coefficient
Deep learning
Humanities and Social Sciences
Humidity
Morphology
multidisciplinary
Neural networks
Science
Science (multidisciplinary)
Segmentation
Stains & staining
Toxicity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 correlated greater than 0.8 to the ground truth. Toxicity analysis on the label-free Cell Painting resulted a sensitivity of 62.5% and specificity of 99.3% on images from unseen batches. We provide a breakdown of the feature profiles by channel and feature type to understand the potential and limitations of label-free morphological profiling. We demonstrate that label-free Cell Painting has the potential to be used for downstream analyses and could allow for repurposing imaging channels for other non-generic fluorescent stains of more targeted biological interest.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-022-12914-x