Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge

Abstract

Designing functional molecules and advanced materials requires complex design choices: tuning continuous process parameters such as temperatures or flow rates, while simultaneously selecting catalysts or solvents. To date, the development of data-driven experiment planning strategies for autonomous experimentation has largely focused on continuous process parameters despite the urge to devise efficient strategies for the selection of categorical variables. Here, we introduce Gryffin, a general purpose optimization framework for the autonomous selection of categorical variables driven by expert knowledge. Gryffin augments Bayesian optimization based on kernel density estimation with smooth approximations to categorical distributions. Leveraging domain knowledge in the form of physicochemical descriptors, Gryffin can significantly accelerate the search for promising molecules and materials. Gryffin can further highlight relevant correlations between the provided descriptors to inspire physical insights and foster scientific intuition. In addition to comprehensive benchmarks, we demonstrate the capabilities and performance of Gryffin on three examples in materials science and chemistry: (i) the discovery of non-fullerene acceptors for organic solar cells, (ii) the design of hybrid organic-inorganic perovskites for light harvesting, and (iii) the identification of ligands and process parameters for Suzuki-Miyaura reactions. Our results suggest that Gryffin, in its simplest form, is competitive with state-of-the-art categorical optimization algorithms. However, when leveraging domain knowledge provided via descriptors, Gryffin outperforms other approaches while simultaneously refining this domain knowledge to promote scientific understanding.

19 pages, 6 figures (SI: 16 pages, 14 figures). Expanded background, discussion, minor fixes and changes

References in corpus (15)

• Practical Bayesian Optimization of Machine Learning Algorithms
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Scalable Bayesian Optimization Using Deep Neural Networks
• Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
• Autonomous discovery in the chemical sciences part I: Progress
• Autonomous discovery in the chemical sciences part II: Outlook
• Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge
• Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space
• Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
• Mixed-Variable Bayesian Optimization
• Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?
• Bayesian Optimisation over Multiple Continuous and Categorical Inputs
• Compositional ADAM: An Adaptive Compositional Solver
• Achieving Robustness to Aleatoric Uncertainty with Heteroscedastic Bayesian Optimisation
• Optimal experimental design via Bayesian optimization: active causal structure learning for Gaussian process networks

Cited by in corpus (9)

• Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge
• Bayesian optimization with known experimental and design constraints for chemistry applications
• El Agente: An Autonomous Agent for Quantum Chemistry
• Golem: An algorithm for robust experiment and process optimization
• Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design
• Fast Bayesian Optimization of Needle-in-a-Haystack Problems using Zooming Memory-Based Initialization (ZoMBI)
• Designing Materials Acceleration Platforms for Heterogeneous CO2 Photo(thermal)catalysis
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Bayesian optimal design accelerates discovery of material properties from bubble dynamics