A Decade in a Systematic Review: The Evolution and Impact of Cell Painting

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Май 7, 2024

ABSTRACT High-content image-based assays have fueled significant discoveries in the life sciences past decade (2013-2023), including novel insights into disease etiology, mechanism of action, new therapeutics, and toxicology predictions. Here, we systematically review substantial methodological advancements applications Cell Painting. Advancements include improvements Painting protocol, assay adaptations for different types perturbations applications, improved methodologies feature extraction, quality control, batch effect correction. Moreover, machine learning methods recently surpassed classical approaches their ability to extract biologically useful information from images. data been used alone or combination with other - omics decipher action a compound, its toxicity profile, many biological effects. Overall, key advances expanded Painting’s capture cellular responses various perturbations. Future will likely lie advancing computational experimental techniques, developing publicly available datasets, integrating them high-content types.

Язык: Английский

Unleashing the potential of cell painting assays for compound activities and hazards prediction

Frontiers in Toxicology, Год журнала: 2024, Номер 6

Опубликована: Июль 17, 2024

The cell painting (CP) assay has emerged as a potent imaging-based high-throughput phenotypic profiling (HTPP) tool that provides comprehensive input data for in silico prediction of compound activities and potential hazards drug discovery toxicology. CP enables the rapid, multiplexed investigation various molecular mechanisms thousands compounds at single-cell level. resulting large volumes image provide great opportunities but also pose challenges to analysis routines well property models. This review addresses integration CP-based together with or substitute structural information from into machine (ML) deep learning (DL) models predict human-relevant disease endpoints identify underlying modes-of-action (MoA) while avoiding unnecessary animal testing. successful application combination powerful ML/DL promises further advances understanding responses cells guiding therapeutic development risk assessment. Therefore, this highlights importance unlocking assays when combined fingerprints evaluation discusses current are associated approach.

Язык: Английский

Quantitative Structure–Activity Relationship Models to Predict Cardiac Adverse Effects

Chemical Research in Toxicology, Год журнала: 2024, Номер 37(12), С. 1924 - 1933

Опубликована: Ноя. 13, 2024

Drug-induced cardiotoxicity represents one of the most common causes attrition drug candidates in preclinical and clinical development. For this reason, evaluation cardiac toxicity is essential during development regulatory review. In present study, drug-induced postmarket adverse event combinations from FDA Adverse Event Reporting System were extracted for 2002 drugs using 243 toxicity-related preferred terms (PTs). These PTs combined into 12 groups based on their relevance to serve as training sets. The optimal classification scheme was determined a combination data sources that included labeling information, published literature, study data, surveillance data. Two commercial QSAR platforms used construct models, including general toxicity, ischemia, heart failure, valve disease, myocardial pericardial structural arrhythmia, Torsades de Pointes, long QT syndrome, atrial fibrillation ventricular arrest. cross-validated performance new models reached sensitivity up 80% negative predictivity 80%. covering wide range endpoints will provide fast, reliable, comprehensive predictions potential cardiotoxic compounds discovery safety assessment.

Язык: Английский