Gene Regulatory Networks: the Prior Can Matter More Than the Downstream Model
bravo_abad · x · 2026-09-15
Gibbs et al. fine-tune a 250M-parameter genomic language model (pretrained on 850 species) to predict plausible transcription factor–gene regulation from DNA sequence, using it as a prior for reconstructing cell-specific regulatory networks from single-cell expression data. Strikingly, changing this prior map can matter more than swapping the downstream model.
More from Research
- TTPO uses disagreement with majority vote as training signal, enabling label-free test-time training — arupbuildsai · 2026-09-15
- Paper: minimum enclosing Bregman balls solvable as linear-programming-type problems — FrnkNlsn · 2026-09-15
- MIT's ModaLens finds report availability sharply reduces medical VLM image sensitivity — MIT · 2026-09-15
- Boltz Becomes a Programmable Protein Editor: GFP In-Painting Verified by Protenix and SimpleFold — GabriCorso · 2026-09-15
- New Benchmark Tests Frontier AI on Open-Ended Business Reasoning — asusarla · 2026-09-15
- HF agents' 'loyal' message-board behavior wasn't emergent, just cooperative RL training priors — inductionheads · 2026-09-15