Abstract:High-throughput gene perturbation experiments can test several genetic interventions in parallel, yet experimental budgets remain limited. A central goal is hit discovery: identifying as many perturbations as possible whose phenotypic effect exceeds a predefined threshold. Pure exploration strategies are statistically inefficient, wasting budget on low-value regions. Bayesian optimization methods offer a principled alternative but target a single global optimum, over-exploiting dominant modes while neglecting other high-value regions. We formalize hit discovery as a sequential experimental design problem and propose Probability-of-Hit, an acquisition function that directly targets threshold exceedance by ranking candidates according to their posterior probability of being a hit. We prove asymptotic optimality of this approach and demonstrate strong empirical performance on both synthetic benchmarks and real biological immunology datasets, including up to 6.4% improvement over baselines on the Schmidt IL-2 dataset.
| Comments: | To be published in International Conference on Machine Learning (ICML) 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.10196 [cs.LG] |
| (or arXiv:2605.10196v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.10196 arXiv-issued DOI via DataCite (pending registration) |
From: Arpit Merchant [view email]
[v1]
Mon, 11 May 2026 08:45:19 UTC (2,118 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。