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

• URL: http://arxiv.org/abs/2609.11877v1
• Date: Thu, 10 Sep 2026 17:45:18 GMT
• Title: Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens
• Abstract summary: We introduce a large-scale benchmark for adaptive hit discovery comprising 1,389 CRISPR screens across five phenotype categories.<n>Building on this resource, we introduce AssayLoop, a sequential experimental design framework combining AssayFormer, a transformer-based amortized acquisition policy trained across historical screens to adapt from experimental feedback.<n>On temporally held-out screens, AssayLoop achieves a 5.67-fold enrichment over random selection and recovers 27.7% of hits after assaying approximately 5% of the candidate library.
• Score: 22.131233442705284
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many 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. Despite the importance of this problem, existing benchmarks for adaptive hit discovery remain limited in scale and diversity. Here, we introduce AssayBench-Loop, a large-scale benchmark for adaptive hit discovery comprising 1,389 CRISPR screens across five phenotype categories. Beyond enabling systematic evaluation, its scale makes it possible to learn acquisition strategies across historical experiments. Building on this resource, we introduce AssayLoop, a sequential experimental design framework combining AssayFormer, a transformer-based amortized acquisition policy trained across historical screens to adapt from experimental feedback, with LLM-derived biological priors through an adaptive handoff. In this view, completed experiments become training data for learning how accumulated evidence should guide what to test next, while LLMs provide prior biological knowledge to seed the search. We further introduce AssayLLM, showing that the same principle can be extended directly to an LLM through task-specific post-training. On temporally held-out screens, AssayLoop achieves a 5.67-fold enrichment over random selection and recovers 27.7% of hits after assaying approximately 5% of the candidate library, outperforming existing adaptive-design methods and standalone LLMs, and AssayFormer alone. Performance improves with increasing historical training data and transfers to phenotype categories excluded from training. These results demonstrate the value of learning acquisition policies across historical experiments and combining them with broad biological priors for efficient adaptive hit discovery.

Related papers

• DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs [71.85279836937578]
  We introduce DeepBias, an adaptive framework for the in-depth probing of social biases in LVLMs with carefully designed agents.<n>We build a benchmark named DeepBiasBench using our framework. By employing an ensemble of five diverse state-of-the-art LVLMs as anchors, the benchmark captures vulnerabilities shared across architectures.
  arXiv  Detail & Related papers  (2026-07-13T08:19:09Z)
• Closing the Domain Gap in Biomedical Imaging by In-Context Control Samples [10.63308864404537]
  Batch effects in biomedical imaging are systematic technical variations unrelated to biological signal of interest.<n>We propose Control-Stabilized Adaptive Risk Minimization via Batch Normalization (CS-ARM-BN), a meta-learning adaptation method that exploits negative control samples.<n>Our work shows that batch effects in bioimaging data can be effectively neutralized through principled in-context adaptation.
  arXiv  Detail & Related papers  (2026-04-22T17:49:00Z)
• Coreset selection based on Intra-class diversity [4.638022690041187]
  Recent studies have adopted two different approaches to train Deep Learning models: training from scratch and transfer learning.<n>With the growing sizes of datasets, exploring solutions to this problem has recently gained the research community's attention.<n>We propose a method to extract intra-class diversity, forming per-class clusters that are utilized for the final sampling.
  arXiv  Detail & Related papers  (2025-09-23T12:45:53Z)
• How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? [92.90857135952231]
  Transformers pretrained on diverse tasks exhibit remarkable in-context learning (ICL) capabilities. We study ICL in one of its simplest setups: pretraining a linearly parameterized single-layer linear attention model for linear regression.
  arXiv  Detail & Related papers  (2023-10-12T15:01:43Z)
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts [117.72709110877939]
  Test-time adaptation (TTA) has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions.<n>We categorize TTA into several distinct groups based on the form of test data, namely, test-time domain adaptation, test-time batch adaptation, and online test-time adaptation.
  arXiv  Detail & Related papers  (2023-03-27T16:32:21Z)
• DELTA: degradation-free fully test-time adaptation [59.74287982885375]
  We find that two unfavorable defects are concealed in the prevalent adaptation methodologies like test-time batch normalization (BN) and self-learning. First, we reveal that the normalization statistics in test-time BN are completely affected by the currently received test samples, resulting in inaccurate estimates. Second, we show that during test-time adaptation, the parameter update is biased towards some dominant classes.
  arXiv  Detail & Related papers  (2023-01-30T15:54:00Z)
• MetaRF: Differentiable Random Forest for Reaction Yield Prediction with a Few Trails [58.47364143304643]
  In this paper, we focus on the reaction yield prediction problem. We first put forth MetaRF, an attention-based differentiable random forest model specially designed for the few-shot yield prediction. To improve the few-shot learning performance, we further introduce a dimension-reduction based sampling method.
  arXiv  Detail & Related papers  (2022-08-22T06:40:13Z)
• Adaptive Identification of Populations with Treatment Benefit in Clinical Trials: Machine Learning Challenges and Solutions [78.31410227443102]
  We study the problem of adaptively identifying patient subpopulations that benefit from a given treatment during a confirmatory clinical trial. We propose AdaGGI and AdaGCPI, two meta-algorithms for subpopulation construction.
  arXiv  Detail & Related papers  (2022-08-11T14:27:49Z)
• Machine Learning Testing in an ADAS Case Study Using Simulation-Integrated Bio-Inspired Search-Based Testing [7.5828169434922]
  Deeper generates failure-revealing test scenarios for testing a deep neural network-based lane-keeping system. In the newly proposed version, we utilize a new set of bio-inspired search algorithms, genetic algorithm (GA), $(mu+lambda)$ and $(mu,lambda)$ evolution strategies (ES), and particle swarm optimization (PSO) Our evaluation shows the newly proposed test generators in Deeper represent a considerable improvement on the previous version.
  arXiv  Detail & Related papers  (2022-03-22T20:27:40Z)
• Active Learning-Based Optimization of Scientific Experimental Design [1.9705094859539976]
  Active learning (AL) is a machine learning algorithm that can achieve greater accuracy with fewer labeled training instances. This article performs a retrospective study on a drug response dataset using the proposed AL scheme. It shows that scientific experimental design, instead of being manually set, can be optimized by AL.
  arXiv  Detail & Related papers  (2021-12-29T20:02:35Z)
• Object classification from randomized EEG trials [9.745889092027557]
  New results suggest strong limits to the feasibility of classifying human brain activity evoked from image stimuli. To our knowledge, this is the largest such EEG data collection effort from a single subject and is at the bounds of feasibility.
  arXiv  Detail & Related papers  (2020-04-09T22:06:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.