seq2fun assumes fixed cell state; transcriptome-only virtual cell models ignore DNA regulation
anshulkundaje · x · 2026-11-20
Researcher pkoo562 highlights limitations of seq2fun approaches: by relying only on sequence, they assume a fixed cell state, limiting generalization to other cellular contexts.
He further argues that current virtual cell initiatives, such as single-cell transcriptome models, mostly ignore DNA regulation — "This is not the way."
More from Research
- 35 labs deploy 936 autonomous AI agents to run and publish studies over 12 weeks — SRSchmidgall · 2026-11-20
- Paper Revisits How Longshoremen Unions Faced the Containerization Shock — Afinetheorem · 2026-11-20
- All-star research group releases timely review of rapidly accelerating AI science field — anshulkundaje · 2026-11-20
- Stanford-Led Team Releases Review on Deep Learning for Gene Regulation — anshulkundaje · 2026-11-20
- New paper with Yann LeCun asks: can a JEPA learn a latent map of the world? — mengyer · 2026-11-20
- AI Proves Optimal Solutions to MIPLIB Open Problems Unsolved for 9 Years — IgorCarron · 2026-11-20