Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens
Researchers release AssayBench-Loop, a 1,389-screen CRISPR benchmark, and AssayLoop, a framework that learns adaptive hit discovery policies.
The paper introduces AssayBench-Loop, a large-scale benchmark of 1,389 CRISPR screens across five phenotype categories for adaptive hit discovery under budget constraints. It also introduces AssayLoop, which combines AssayFormer, a transformer-based amortized acquisition policy trained across historical screens, with LLM-derived biological priors via an adaptive handoff. On temporally held-out screens, AssayLoop achieves 5.67-fold enrichment over random selection and recovers 27.7% of hits after assaying roughly 5% of the candidate library, outperforming existing adaptive-design methods and standalone LLMs.
- AssayBench-Loop spans 1,389 CRISPR screens across five phenotype categories
- AssayFormer learns amortized acquisition policies from historical screens
- AssayLoop reaches 5.67x enrichment over random selection on held-out screens
- Recovers 27.7% of hits while assaying about 5% of candidates
- AssayLLM extends the approach via task-specific post-training of an LLM
From the original article
1 min read at arxiv.orgMany biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhaustive perturbation testing is often infeasible and candidate perturbations must instead be prioritized over multiple experimental rounds.
By Carl Edwards · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.