AI models enable cross-species mapping of cell biology
BiologyBiomedical Engineering
THE AI ANGLE
Embedding cross-species gene expression data to map, classify, and generate cellular profilesStanford Medicine researchers developed TranscriptFormer, an AI cell model trained on gene expression profiles from 112 million cells across 12 species that maps cellular biology across 1.5 billion years of evolution into a shared mathematical space. This cross-species foundation model can classify cell types in previously unseen species, distinguish healthy from diseased cells, and propose hypothetical functional cells to inform future cell-based therapies.
THE TEACHING ANGLE
Instructors can use this research to examine how transformer-based models challenge traditional morphological definitions of cell identity, exemplified by findings that sponge choanocytes—rather than neuroid cells—transcriptionally mirror animal neurons.Read the original at phys.org Generate teaching or study materials
More in Biology
- Report covers advances in surgical robots, deploying warehouse automation in the real worldThe Robot Report · September 15, 2026
- Can Culta take Japan’s premium fruit model global?AgFunderNews · September 15, 2026
- AI helps pathologists find signs of preeclampsia, advancing diagnosis and treatmentMedical Xpress · September 15, 2026
- Hear how AI can engineer nature’s comeback at TechCrunch Disrupt 2026TechCrunch · September 14, 2026