New 79-minute review maps deep learning for gene regulation across cellular contexts, from maxATAC to Bolero

anshulkundaje · x · 2026-11-20

Researchers from CSHL, Stanford, EPFL and others (corresponding authors Peter K. Koo and Anshul Kundaje) published a long-form review on modeling gene regulation across cellular contexts with deep learning. Key points: seq2func models fail when perturbations shift cellular state; context-aware models add proxies like RNA to track state changes. The review taxonomizes methods into local context (maxATAC, EPInformer), cell-wide context (RegFM, scooby, Bolero), and combined context (FactorNet, GenoME, Corgi+), with a detailed figure mapping proxy inputs, representations, and fusion mechanisms (cross-attention, hypernetworks, Conditional LoRA, MoE, FiLM) across output tasks from TF ChIP to scRNA/scATAC.

Original post →

More from AGI Musings

AGI Musings channel →