Kimia's D2ML paper: ML models that learn directly from unpurified biology screening data
anshulkundaje · x · 2026-11-16
Kimia Tx's first paper D2ML (arXiv:2610.41070, AI4DD workshop) tackles direct-to-biology screening, where unpurified molecules are tested with uncertain concentrations. Assay-aware models predict activity from single-point screens, relative potency from crude dose-response assays, and absolute potency from purified measurements. A joint cross-stage model beat separate networks, lifting crude dose-response selectivity rank correlation from 0.27 to 0.40; model-guided selection of 84 compounds extended the measured Pareto front for ROS1 potency vs TRKB anti-target activity.
More from Research
- AI/ML for Fluids cohort 2 opens: 60+ live hours over 3 months for $500 — ricardovinuesa · 2026-11-16
- "The conference-paper game is 100% dead": researcher urges GitHub-first research output — DimitrisPapail · 2026-11-16
- DeepMind researcher on doing research in the AI era: minimize friction to excellent work — DimitrisPapail · 2026-11-16
- Google AI Co-Scientist progress presented by Michael Brenner at MLCB 2026 — anshulkundaje · 2026-11-16
- New Paper: Adding Input Noise During Pretraining Distillation Beats Standard Distillation — DimitrisPapail · 2026-11-16
- Auto Weight-Space Programming: Qwen3.5-4B learns to apply logit lens to its own neurons at 99.8% — udmrzn · 2026-11-16