Dictionary learning for integrative, multimodal and scalable single-cell analysis

Yuhan Hao, Tim Stuart, Madeline H. Kowalski, Saket Choudhary, Paul Hoffman, Austin Hartman, Avi Srivastava, Gesmira Molla, Shaista Madad, Carlos Fernandez-Granda, Rahul Satija

This work presents dictionary learning strategies used in Seurat v5 for integrative and scalable analysis of multimodal single-cell data. The study connects computational representation learning with practical single-cell tasks such as cross-dataset integration, modality alignment and annotation transfer across complex biological atlases.