mlsanityData to 14 Oct 2026

Neural Design for Genetic Perturbation Experiments

arXiv 2207.12805 ↗First posted 26 Jul 2022q-bio.QM cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

The problem of how to genetically modify cells in order to maximize a certain cellular phenotype has taken center stage in drug development over the last few years (with, for example, genetically edited CAR-T, CAR-NK, and CAR-NKT cells entering cancer clinical trials). Exhausting the search space for all possible genetic edits (perturbations) or combinations thereof is infeasible due to cost and experimental limitations. This work provides a theoretically sound framework for iteratively exploring the space of perturbations in pooled batches in order to maximize a target phenotype under an experimental budget. Inspired by this application domain, we study the problem of batch query bandit optimization and introduce the Optimistic Arm Elimination (OAE) principle designed to find an almost optimal arm under different functional relationships between the queries (arms) and the outputs (rewards). We analyze the convergence properties of OAE by relating it to the Eluder dimension of the algorithm's function class and validate that OAE outperforms other strategies in finding optimal actions in experiments on simulated problems, public datasets well-studied in bandit contexts, and in genetic perturbation datasets when the regression model is a deep neural network. OAE also outperforms the benchmark algorithms in 3 of 4 datasets in the GeneDisco experimental planning challenge.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 25 of its 62 references that are in the map. First posted on arXiv 26 Jul 2022.

Builds on

25 of 62 references.

References · 25

  1. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  2. 2015Scalable Bayesian Optimization Using Deep Neural Networkscited by 284
  3. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 158
  4. 2020Effective Diversity in Population Based Reinforcement Learningcited by 119
  5. 2016Corralling a Band of Bandit Algorithmscited by 100
  6. 2019Discriminative Active Learningcited by 98
  7. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  8. 2017Deep Active Learning over the Long Tailcited by 84
  9. 2020Model Selection in Contextual Stochastic Bandit Problemscited by 71
  10. 2020Neural Contextual Bandits with Deep Representation and Shallow Explorationcited by 71
  11. 2019Worst-Case Regret Bounds for Exploration via Randomized Value Functionscited by 57
  12. 2020Regret Bound Balancing and Elimination for Model Selection in Bandits and RLcited by 47
13 more
  1. 2019Batch Active Learning Using Determinantal Point Processescited by 43
  2. 2021Learning Neural Causal Models with Active Interventionscited by 40
  3. 2017Budgeted Experiment Design for Causal Structure Learningcited by 38
  4. 2016Batched Gaussian Process Bandit Optimization via Determinantal Point Processescited by 33
  5. 2020Online Model Selection for Reinforcement Learning with Function Approximationcited by 28
  6. 2021GeneDisco: A Benchmark for Experimental Design in Drug Discoverycited by 18
  7. 2021Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learningcited by 17
  8. 2021Matching a Desired Causal State via Shift Interventionscited by 16
  9. 2017Faster Greedy MAP Inference for Determinantal Point Processescited by 15
  10. 2020Towards Tractable Optimism in Model-Based Reinforcement Learningcited by 11
  11. 2020Quantile Bandits for Best Arms Identificationcited by 7
  12. 2021Neural Pseudo-Label Optimism for the Bank Loan Problemcited by 3
  13. 2016Learning Optimal Interventionscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 3.

6 papers.

  1. 2024Automated Discovery of Pairwise Interactions from Unstructured Datacited by 8
  2. 2023Anytime Model Selection in Linear Banditscited by 6
  3. 2024Experiment Planning with Function Approximationcited by 5
  4. 2025BioBO: Biology-informed Bayesian Optimization for Perturbation Designcited by 2
  5. 2025Deep Active Learning based Experimental Design to Uncover Synergistic Genetic Interactions for Host Targeted Therapeuticscited by 0
  6. 2025Efficient Data Selection for Training Genomic Perturbation Modelscited by 0