MorphoCLIP: Text-Supervised Contrastive Learning for Perturbation Matching in Cell Painting Images
2026-08-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed MorphoCLIP, a computer model that links pictures of cells with descriptions of the chemicals or genetic changes affecting them. Their method works by comparing cell images and text descriptions to find matches, doing better than random guessing when tested on new data. They also tried ways to improve consistency across repeated experiments, but some problems, like matching genes to chemicals precisely, remain unsolved. Overall, the study shows that using text with cell images helps organize biological data, but some challenges still need more work.
Cell Paintingcontrastive learningchemical perturbationgenetic perturbationCRISPR knockoutmorphological profilingmachine learningrepresentation learningimage-text matching
Authors
Sukhrobbek Ilyosbekov, Shubham Gajjar, Rongfei Jin
Abstract
Cell Painting microscopy captures how cells change after a chemical or genetic perturbation. Connecting these images to the perturbations that produced them could make large imaging screens easier to search and interpret, but the task remains difficult because biological effects are subtle and technical variation is substantial. We introduce MorphoCLIP, a contrastive model that links Cell Painting profiles with text descriptions of compounds, CRISPR knockouts, and ORF overexpressions. The model keeps its vision and language backbones frozen and trains only a compact cross-channel module and projection layers, so it can be trained on a single consumer GPU. On held-out CPJUMP1 data, MorphoCLIP searches in both directions: from a cell image to its perturbation description and from a description to matching cell images. In both cases, a correct match appears among the top ten results much more often than expected by chance. Adding a replicate-alignment loss makes profiles from repeated experiments more consistent, although this improvement does not yet translate into reliable gene-compound matching. Gene-aware labels and plate correction also show no consistent retrieval benefit. These findings suggest that text supervision can help organize chemical and genetic Cell Painting data. Matching compounds with genetic perturbations, however, remains an open problem.