Triple-effect correction for Cell Painting data with contrastive and domain-adversarial learning
Chengwei Yan, Yu Zhang, Jiuxin Feng, Heyang Hua, Zhihan Ruan, Zhen Li, Siyu Li, Chaoyang Yan, Pingjing Li, Jian Liu, Shengquan Chen
The paper introduces cpDistiller, a method to correct three technical effects in Cell Painting data using contrastive and domain-adversarial learning, improving analysis reliability and phenotypic response detection.
Nature Communications · Jul 25, 2025Peer-reviewedBioinformatics