Madeline H. Kowalski

Dictionary learning enables assumption-free cross-modality single-cell mapping via multi-omic bridge datasets and scales single-modality integration to millions of cells in under an hour via atomic sketching.

The paper introduces CPA-Perturb-seq, a multiplexed perturbation screen dataset, and uses it to identify polyA site regulators and their functional properties.

This study uses TOPMed whole genome sequences to improve imputation quality and detect rare variant associations in admixed African and Hispanic/Latino populations, identifying two novel associations with hematological traits.