Machine Learning-Guided Computational Screening of New Candidate Reactions with High Bioorthogonal Click Potential

Bioorthogonal click chemistry has become an indispensable part of the biochemist's toolbox. Despite the wide variety of applications that have been developed in recent years, only a limited number of bioorthogonal click reactions have been discovered so far, most of them based on (substituted) azides. In this work, we present a computational workflow to discover new candidate reactions with promising kinetic and thermodynamic properties for bioorthogonal click applications. Sampling only around 0.05 % of an overall search space of over 10,000,000 dipolar cycloadditions, we develop a machine learning model able to predict DFT-computed activation and reaction energies within similar to 2-3 kcal/mol across the entire space. Applying this model to screen the full search space through iterative rounds of learning, we identify a broad pool of candidate reactions with rich structural diversity, which can be used as a starting point or source of inspiration for future experimental development of both azide-based and non-azide-based bioorthogonal click reactions.

Automated summary

Bioorthogonal click chemistry is an essential tool for biochemists. This study presents a computational workflow to discover new bioorthogonal click reactions with promising properties. By sampling a small portion of the search space, a machine learning model is developed and able to accurately predict activation and reaction energies. The screened search space identifies a diverse pool of candidate reactions for future experimental development.