Genomics ML vet warns center-biased models skew variant effect predictions
anshulkundaje · x · 2026-10-31
Genomics deep learning researcher Anshul Kundaje discusses sequence-model training pitfalls: center-biased models predict variant effects differently depending on the variant's position relative to sequence context. He notes that flanking sequences are highly informative negatives, so very short jitter augmentation is problematic — you see fewer boundary effects. He also recalls that training models on simulated datasets in varied settings was fun and informative in the early days.
Related event: Genome Sequence Models Need 500bp Jitter to Remove Center Bias(4 posts)→
More from Research
- Artifact Distillation: training-free transfer lets Claude Haiku 4.5 beat Sonnet 4.5 at 60% cost — kalyan_kpl · 2026-10-31
- AI researcher argues 90% of research is too vague to be wrong as automated review costs drop to zero — RexDouglass · 2026-10-31
- eSpinor: Anima Anandkumar's team proposes SU(2)-equivariant GNN for magnetic properties — AnimaAnandkumar · 2026-10-31
- Microsoft's ScholarEvolve evolves agent harnesses with frozen models, +14 points on AppWorld — jiqizhixin · 2026-10-31
- Exponential Residual Flows: an ODE sampler for discrete diffusion models — _onionesque · 2026-10-31
- Robots lay 100% of bricks for housing project in Almere, 15 more homes coming — ZeYanjie · 2026-10-31