Umair Khan

This study uses DNA methylation data to predict endometriosis status and menstrual cycle phase, finding strong performance for cycle phase and moderate performance for endometriosis.

CDRPipe integrates single-cell and bulk transcriptomic perturbation data to improve drug repurposing predictions by combining complementary resources.

The paper introduces Rhaister, a perturbation-response predictor that uses summary statistics to predict drug responses, outperforming virtual-cell models in speed and accuracy.

The paper introduces Tahoe-x1, a large-scale perturbation-trained single-cell foundation model with 3 billion parameters, achieving state-of-the-art performance in cancer-related tasks.

The paper uses single-cell transcriptomics to analyze endometrial cells from endometriosis patients, revealing altered cellular features and immune communication networks across the menstrual cycle.

A 100-million-cell atlas: 50 cancer lines pooled as spheroid villages, treated with 379 drugs at several doses, profiled by combinatorial-barcoding scRNA-seq and embedded with a 10-dimensional scVI model.