Genomics Researchers: We Pretend Assays Are Precise; ML Can Denoise Only So Much
anshulkundaje · x · 2026-10-14
arjunrajlab flags a systemic genomics issue: the field collectively pretends its assays are far more accurate than they are, limiting progress with or without AI. Stanford professor Anshul Kundaje responds that ML models can be remarkably effective at denoising noisy data given relevant side information and proper loss functions—AI can compensate, but not replace reckoning with data quality.
Related event: Genomics researcher says assay precision is systematically overstated(2 posts)→
More from Research
- RISE (NeurIPS 2026): evolving attack strategies to break through text-to-image guardrails — rohanpaul_ai · 2026-10-15
- Random Brainfuck programs on a 2D grid spontaneously evolve self-replicators — spikedoanz · 2026-10-15
- Classifier run on 42,000+ ICLR 2027 submissions finds over half nearly fully AI-assisted — nsaphra · 2026-10-15
- LLM4Code workshop at ICSE 2027 opens call for papers, due Nov 13, 2026 — LingmingZhang · 2026-10-15
- ELSA3D, a unified 3D generation and captioning model, hits SOTA at half the FLOPs, accepted at NeurIPS — CSProfKGD · 2026-10-15
- Moving ViT weights 1.3% without changing predictions scrambles representations, challenging Platonic hypothesis — neuroecology · 2026-10-15