Prediction of the Chemical Context for Buchwald‐Hartwig Coupling Reactions

Abstract

We present machine learning models for predicting the chemical context for Buchwald-Hartwig coupling reactions, i. e., what chemicals to add to the reactants to give a productive reaction. Using reaction data from inhouse electronic lab notebooks, we train two models: one based on single-label data and one based on multi-label data. Both models show excellent top-3 accuracy of approximately 90 %, which suggests strong predictivity. Furthermore, there seems to be an advantage of including multi-label data because the multi-label model shows higher accuracy and better sensitivity for the individual contexts than the single-label model. Although the models are performant, we also show that such models need to be re-trained periodically as there is a strong temporal characteristic to the usage of different contexts. Therefore, a model trained on historical data will decrease in usefulness with time as newer and better contexts emerge and replace older ones. We hypothesize that such significant transitions in the context-usage will likely affect any model predicting chemical contexts trained on historical data. Consequently, training context prediction models warrants careful planning of what data is used for training and how often the model needs to be re-trained.

Machine Learning C–N Couplings: Obstacles for a General-Purpose Reaction Yield Prediction

“…Several concepts can be designed to harness data-driven technology for the purpose of optimizing reaction conditions. Work by Gao et al., 10 Genheden et al, 11 as well as Li and Eastgate 12 used neural networks that predict the success probability for a set of substances in each relevant reagent class. In these approaches, often the accuracy of the top- N most probable predictions is evaluated, which rates if the proposed set of N conditions contains the one that achieved the highest yield.…”

Data Sharing in Chemistry: Lessons Learned and a Case for Mandating Structured Reaction Data

“…Predictive chemistry and reaction informatics is one such field where there have been numerous impressive developments over the past few years despite only a handful of data sets being accessible to researchers, even commercially. Many of these developments are driven by applications of machine learning to, e.g., forward reaction prediction, − retrosynthesis planning, − and reaction condition prediction − where predictions can be made even with relatively small data sets. We and others − have asserted that to advance the role of AI in organic synthesis, there must be significant improvements in the reporting of laboratory synthesis procedures, including reaction conditions.…”

When Yield Prediction Does Not Yield Prediction: An Overview of the Current Challenges

“…6,7 There are also condition or reagent models suggesting suitable catalysts, solvents, temperatures, etc. 8,9 Finally, there are yield or reactivity models estimating the success of a reaction, which is the topic of this perspective and will be reviewed below. Although many encouraging studies have been reported, ML models for chemistry are not without critique.…”

“…Such tools typically fall under the umbrella of computer-assisted synthesis planning and include many different tools and models that can help chemists with several tasks. Retrosynthesis models suggest how to break a compound, either as a single-step prediction or multistep prediction, which provides a sequence of steps for how to synthesize a compound from simpler starting material. − Furthermore, there are a range of product prediction models, or forward models that predict what the product of two or more reactants will be, , or can provide guidance on regioselectivity issues. , There are also condition or reagent models suggesting suitable catalysts, solvents, temperatures, etc. , Finally, there are yield or reactivity models estimating the success of a reaction, which is the topic of this perspective and will be reviewed below. Although many encouraging studies have been reported, ML models for chemistry are not without critique. , Furthermore, while many studies emphasize general reaction properties, such as yield prediction in regression and classification tasks, properties tied to physical chemistry, such as reaction rates and activation energies, have received less attention.…”