# DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design

arXiv: https://arxiv.org/abs/2312.04064 · HTML: https://mlsanity.com/paper/2312.04064/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 54 references that are in the map.
- First posted on arXiv 7 Dec 2023.

## Builds on (most cited first, 17 of 17)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [Learning Active Learning from Data](https://mlsanity.com/paper/1703.03365/) (2017)
- [On Nesting Monte Carlo Estimators](https://mlsanity.com/paper/1709.06181/) (2017)
- [Prediction-Oriented Bayesian Active Learning](https://mlsanity.com/paper/2304.08151/) (2023)
- [Reinforced active learning for image segmentation](https://mlsanity.com/paper/2002.06583/) (2020)
- [BOSS: Bayesian Optimization over String Spaces](https://mlsanity.com/paper/2010.00979/) (2020)
- [Improving black-box optimization in VAE latent space using decoder uncertainty](https://mlsanity.com/paper/2107.00096/) (2021)
- [Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information](https://mlsanity.com/paper/2104.09460/) (2021)
- [Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning](https://mlsanity.com/paper/1806.04798/) (2018)
- [Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers](https://mlsanity.com/paper/2106.11719/) (2021)
- [Constrained Bayesian Optimization for Automatic Chemical Design](https://mlsanity.com/paper/1709.05501/) (2017)
- [A General Recipe for Likelihood-free Bayesian Optimization](https://mlsanity.com/paper/2206.13035/) (2022)
- [GeneDisco: A Benchmark for Experimental Design in Drug Discovery](https://mlsanity.com/paper/2110.11875/) (2021)
- [Deep reinforced active learning for multi-class image classification](https://mlsanity.com/paper/2206.13391/) (2022)

## Built on by (most cited first, 12 of 12)

- [BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments](https://mlsanity.com/paper/2405.17631/) (2024)
- [LLMs for Bayesian Optimization in Scientific Domains: Are We There Yet?](https://mlsanity.com/paper/2509.21403/) (2025)
- [Automated Discovery of Pairwise Interactions from Unstructured Data](https://mlsanity.com/paper/2409.07594/) (2024)
- [Challenges and Considerations in the Evaluation of Bayesian Causal Discovery](https://mlsanity.com/paper/2406.03209/) (2024)
- [In-silico biological discovery with large perturbation models](https://mlsanity.com/paper/2503.23535/) (2025)
- [Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs](https://mlsanity.com/paper/2606.03719/) (2026)
- [Practical Bayesian Algorithm Execution via Posterior Sampling](https://mlsanity.com/paper/2410.20596/) (2024)
- [BioBO: Biology-informed Bayesian Optimization for Perturbation Design](https://mlsanity.com/paper/2509.19988/) (2025)
- [Deep Active Learning based Experimental Design to Uncover Synergistic Genetic Interactions for Host Targeted Therapeutics](https://mlsanity.com/paper/2502.01012/) (2025)
- [Efficient Data Selection for Training Genomic Perturbation Models](https://mlsanity.com/paper/2503.14571/) (2025)
- [g-DPO: Scalable Preference Optimization for Protein Language Models](https://mlsanity.com/paper/2510.19474/) (2025)
- [Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments](https://mlsanity.com/paper/2605.10196/) (2026)

## Abstract (arXiv)

The discovery of therapeutics to treat genetically-driven pathologies relies on identifying genes involved in the underlying disease mechanisms. Existing approaches search over the billions of potential interventions to maximize the expected influence on the target phenotype. However, to reduce the risk of failure in future stages of trials, practical experiment design aims to find a set of interventions that maximally change a target phenotype via diverse mechanisms. We propose DiscoBAX, a sample-efficient method for maximizing the rate of significant discoveries per experiment while simultaneously probing for a wide range of diverse mechanisms during a genomic experiment campaign. We provide theoretical guarantees of approximate optimality under standard assumptions, and conduct a comprehensive experimental evaluation covering both synthetic as well as real-world experimental design tasks. DiscoBAX outperforms existing state-of-the-art methods for experimental design, selecting effective and diverse perturbations in biological systems.