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.
More from AGI Musings
- He Flew to Athens With One Question: What Does AI Mean Where 'Know Thyself' Began — realmeetjames · 2026-11-20
- Report: AI is vastly more compute-intensive than any prior workload, and needs no new user base — BenBajarin · 2026-11-20
- repligate: top models have surpassed philosophers, mind-braiding is next — repligate · 2026-11-20
- UI isn't dead: chat alone is far from enough for human-agent communication — HaijunXia · 2026-11-20
- Dario Amodei: we talk about AI risk because it's preventable — bookwormengr · 2026-11-20
- Robert Wiblin: Anthropic hasn't shown it's on track to actually understand AI internals — GaryMarcus · 2026-11-20