Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions
This work addresses the challenge of automating reaction condition prediction in organic chemistry, representing an incremental advance in molecular machine learning.
The authors tackled the problem of predicting substrate-specific organic reaction conditions by evaluating seven graph neural network architectures on a dataset of four common reactions, achieving accurate predictions by identifying relevant graph features.
We present a systematic investigation using graph neural networks (GNNs) to model organic chemical reactions. To do so, we prepared a dataset collection of four ubiquitous reactions from the organic chemistry literature. We evaluate seven different GNN architectures for classification tasks pertaining to the identification of experimental reagents and conditions. We find that models are able to identify specific graph features that affect reaction conditions and lead to accurate predictions. The results herein show great promise in advancing molecular machine learning.