Low concentration cell painting images enable the identification of highly potent compounds
Open Access
- 17 October 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-12
Abstract
Image-based models that use features extracted from cell microscopy images can estimate the activity of small molecules in various biological assays. Typically, models are trained on images stained by an optimized protocol (e.g. Cell Painting) after exposure to a fairly high small molecule concentration (referred to as ’image concentration’) of $$10\; \upmu {\text{M}}$$ or higher. Low concentration images (e.g. $$0.16$$ μM, $$0.8$$ μM, $$4$$ μM) tend to yield models with worse performance. In this work, we nevertheless report a practical use for low image concentration data. We propose the combination of well-performing models trained at higher image concentrations, with lower image concentration for inference to identify more potent compounds. We show that this approach improves on the conventional method (directly training a high-potency model) in 65 $$\%$$ of assays investigated in terms of AUC-ROC, and 75 $$\%$$ of assays in terms of RIPtoP-corrected AUC-PR.
Keywords
All Related Versions
Funding Information
- Horizon 2020 (956832)
This publication has 15 references indexed in Scilit:
- MELLODDY: Cross-pharma Federated Learning at Unprecedented Scale Unlocks Benefits in QSAR without Compromising Proprietary InformationJournal of Chemical Information and Modeling, 2023
- Leveraging Cell Painting Images to Expand the Applicability Domain and Actively Improve Deep Learning Quantitative Structure–Activity Relationship ModelsChemical Research in Toxicology, 2023
- Identification of bile salt export pump inhibitors using machine learning: Predictive safety from an industry perspectiveArtificial Intelligence in the Life Sciences, 2021
- Acute Metabolic Switch Assay Using Glucose/Galactose Medium in HepaRG Cells to Detect Mitochondrial ToxicityCurrent Protocols in Toxicology, 2019
- Accurate Prediction of Biological Assays with High-Throughput Microscopy Images and Convolutional NetworksJournal of Chemical Information and Modeling, 2019
- Repurposing High-Throughput Image Assays Enables Biological Activity Prediction for Drug DiscoveryCell Chemical Biology, 2018
- Applying Mondrian Cross-Conformal Prediction To Estimate Prediction Confidence on Large Imbalanced Bioactivity Data SetsJournal of Chemical Information and Modeling, 2017
- Drug‐induced phospholipidosisFEBS Letters, 2006
- Predicting ADME properties in silico: methods and modelsDrug Discovery Today, 2002
- The Properties of Known Drugs. 1. Molecular FrameworksJournal of Medicinal Chemistry, 1996