Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens

Carl Edwards, Edward De Brouwer, Xiner Li, Namkyeong Lee, Ehsan Hajiramezanali et al.|September 10, 2026arXiv

Key Takeaway

By training acquisition policies on historical experimental data and combining them with LLM biological priors, you can dramatically improve the efficiency of sequential biological experiments—recovering 27.7% of hits while testing only 5% of candidates.

Summary

This paper introduces AssayBench-Loop, a large benchmark of 1,389 CRISPR screens, and AssayLoop, a framework that learns which genes to test next by combining a transformer model trained on historical experiments with biological knowledge from LLMs.

reasoning applications

Key Terms

active-learning amortized-inference acquisition-function sequential-experimental-design