Stanford Scholars Debate Whether Observational Data Can Reveal Causal Structure
Stanford computational biologist Anshul Kundaje and the Nimwegen lab publicly debate whether models trained on in-vivo observational data can recover the causal determinants of transcription factor binding, with Kundaje arguing causal sequence grammar is recoverable while critics question the reliability of causal inference from such data.
2026-11-19 ~ 2026-11-19 · 3 related posts
- Biologists debate whether in vivo TF binding data can reveal causal determinants — NimwegenLab · 2026-11-19
- Anshul Kundaje argues trained models recover causal sequence syntax from in vivo data — anshulkundaje · 2026-11-19
- Debate: can models trained on observational data recover causal structure? — anshulkundaje · 2026-11-19