Open access
Jul 2026
Unify learns cellular evolution with universal multimodal embeddings
The authors report a transfer learning framework designed to integrate scRNA-seq data across species by combining RNA expression with embeddings from protein language models and general-purpose language models, establishing Unify as a powerful method for comparative single-cell genomics and evolutionary biology.
Hua-Wen Zhong, Wenkai Han, Guo-Xin Cui et al.
· Nature Communications · 0 citations