Machine learning approach for predicting the yield of pyrroles and dipyrromethanes condensation reactions with aldehydes

The utilization of machine learning techniques for investigating chemical reactions is both sought after and challenging. While there are now many high-quality paid and free tools available for planning retrosynthesis, predicting the yield of different reaction types has received less attention, even though it is a crucial parameter for improving the synthesis process. This article aims to contribute to the application of machine learning in forecasting the yield of pyrrole and dipyrromethane condensation reactions with aldehydes. To achieve this, we trained a random forest model with an extended connectivity fingerprint on over 1200 such reactions, resulting in an MAE of 9.6% and R2 of 0.63. To make it easier for users, we created the web application ChemPredictor (http://chem-predictor.isc-ras.ru/reaction/yield/) that allows users to input only the reaction components and temperature to predict the yield of these reactions.