BioBO: Biology-informed Bayesian Optimization for Perturbation Design

2025-09-24

AI Summary

Genomic perturbation experiments for drug discovery face challenges including high-dimensional search spaces, prohibitive experimental costs, and limited biological interpretability. To address these, we propose BioBO—a Bayesian optimization framework that integrates multimodal gene embeddings with pathway enrichment analysis, explicitly encoding biological prior knowledge into both the surrogate model and acquisition function. Our key innovation is an uncertainty-aware, pathway-guided acquisition strategy that jointly enables biologically informed perturbation design and mechanistic interpretability at the pathway level. Evaluated on multiple public functional genomics datasets, BioBO improves labeling efficiency by 25–40% over state-of-the-art baselines, significantly accelerating optimal target identification while providing interpretable, pathway-level regulatory insights.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Efficient design of genomic perturbation experiments is crucial for accelerating drug discovery and therapeutic target identification, yet exhaustive perturbation of the human genome remains infeasible due to the vast search space of potential genetic interactions and experimental constraints. Bayesian optimization (BO) has emerged as a powerful framework for selecting informative interventions, but existing approaches often fail to exploit domain-specific biological prior knowledge. We propose Biology-Informed Bayesian Optimization (BioBO), a method that integrates Bayesian optimization with multimodal gene embeddings and enrichment analysis, a widely used tool for gene prioritization in biology, to enhance surrogate modeling and acquisition strategies. BioBO combines biologically grounded priors with acquisition functions in a principled framework, which biases the search toward promising genes while maintaining the ability to explore uncertain regions. Through experiments on established public benchmarks and datasets, we demonstrate that BioBO improves labeling efficiency by 25-40%, and consistently outperforms conventional BO by identifying top-performing perturbations more effectively. Moreover, by incorporating enrichment analysis, BioBO yields pathway-level explanations for selected perturbations, offering mechanistic interpretability that links designs to biologically coherent regulatory circuits.

Problem

• Efficiently designing genomic perturbation experiments within vast search spaces
• Improving Bayesian optimization by incorporating biological prior knowledge
• Enhancing perturbation selection accuracy while providing mechanistic interpretability

Innovation

• Integrates Bayesian optimization with gene embeddings
• Combines biological priors with acquisition functions
• Uses enrichment analysis for pathway-level explanations