GeneDisco: A Benchmark for Experimental Design in Drug Discovery

Abstract

In vitro cellular experimentation with genetic interventions, using for example CRISPR technologies, is an essential step in early-stage drug discovery and target validation that serves to assess initial hypotheses about causal associations between biological mechanisms and disease pathologies. With billions of potential hypotheses to test, the experimental design space for in vitro genetic experiments is extremely vast, and the available experimental capacity - even at the largest research institutions in the world - pales in relation to the size of this biological hypothesis space. Machine learning methods, such as active and reinforcement learning, could aid in optimally exploring the vast biological space by integrating prior knowledge from various information sources as well as extrapolating to yet unexplored areas of the experimental design space based on available data. However, there exist no standardised benchmarks and data sets for this challenging task and little research has been conducted in this area to date. Here, we introduce GeneDisco, a benchmark suite for evaluating active learning algorithms for experimental design in drug discovery. GeneDisco contains a curated set of multiple publicly available experimental data sets as well as open-source implementations of state-of-the-art active learning policies for experimental design and exploration.

References in corpus (14)

• Scikit-learn: Machine Learning in Python
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Bayesian Active Learning for Classification and Preference Learning
• Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
• Two Optimal Strategies for Active Learning of Causal Models from Interventional Data
• Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networks
• Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
• Learning Neural Causal Models from Unknown Interventions
• CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
• Learning Neural Causal Models with Active Interventions
• Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
• NCoRE: Neural Counterfactual Representation Learning for Combinations of Treatments
• BayesIMP: Uncertainty Quantification for Causal Data Fusion
• Learning and Sampling of Atomic Interventions from Observations