John Arévalo

This study evaluates alternative dyes for image-based profiling assays, finding that some substitutions maintain performance while enabling live-cell imaging and expanded feature space.

The paper presents a comprehensive genetic perturbation dataset using Cell Painting to analyze gene expression effects in human cells, revealing novel gene clusters and functional relationships.

The paper introduces a statistical framework using mean average precision (mAP) to evaluate phenotypic activity and consistency in high-dimensional profiling data across various modalities and perturbation types.

The paper introduces CytoSummaryNet, a contrastive learning method for aggregating single-cell features in image-based profiling, improving mechanism of action prediction by 30-68%.

The paper benchmarks seven scRNA-seq batch correction methods on a Cell Painting dataset, finding Harmony performs best across multiple scenarios.

The paper improves drug target prediction by combining gene and compound morphological profiles using a transformer model, showing better performance than direct matching methods.

The paper introduces a dataset of cell morphology images treated with matched chemical and genetic perturbations and evaluates methods for identifying perturbation similarities.

Cell Painting images and profiles for 115,796 compounds in U2OS cells from 12 laboratories; 15.2% of analyzed compounds are phenotypically active, and cross-laboratory replicates cut reference-compound activity by 34%.