1481-TranscriptFormer: Model for Evolutionary Cell Biology

Paper Talk · Aug 24, 2026 · 23m

The research article introduces TranscriptFormer, a sophisticated generative foundation model designed to analyze single-cell transcriptomics across a vast evolutionary timeline of 1.5 billion years. By utilizing protein sequence embeddings and an autoregressive architecture, the model maps gene expression data into a shared embedding space that allows for direct comparisons between highly diverse species without requiring common orthologous genes. The study demonstrates that TranscriptFormer excels at cell type classification and zero-shot disease detection, significantly outperforming…