Ci Chu

X-Cell predicts causal perturbation responses across diverse cellular contexts using a diffusion language model trained on a large CRISPRi Perturb-seq dataset.

This paper introduces a pooled CRISPR screening platform combined with self-supervised deep learning to infer gene function from morphological phenotypes without target-specific biomarkers.

The paper introduces a scalable Perturb-seq platform called FiCS Perturb-seq and releases X-Atlas/Orion, a large Perturb-seq atlas, to improve foundation model development through dose-dependent genetic effects.

This study identifies CD4 T and B cells as driver cell subsets in multiple sclerosis using chromatin accessibility data and genetic fine-mapping.