Computational methods for training set selection and error assessment applied to catalyst design: Guidelines for deciding which reactions to run first and which to run next

The application of machine learning (ML) to problems in homogeneous catalysis has emerged as a promising avenue for catalyst optimization. An important aspect of such optimization campaigns is determining which reactions to run at the outset of experimentation and which future predictions are the most reliable. Herein, we explore methods for these two tasks in the context of our previously developed chemoinformatics workflow. First, different methods for training set selection for library-based optimization problems are compared, including algorithmic selection and selection informed by unsupervised learning methods. Next, an array of different metrics for assessment of prediction confidence are examined in multiple catalyst manifolds. These approaches will inform future computer-guided studies to accelerate catalyst selection and reaction optimization. Finally, this work demonstrates the generality of the average steric occupancy (ASO) and average electronic indicator field (AEIF) descriptors in their application to transition metal catalysts for the first time.