Machine learning for the prediction of safe and biologically active organophosphorus molecules
This work addresses the need for safer alternatives to toxic organophosphorus compounds in drug discovery, but it is incremental as it builds on existing fragment-based and neural network methods.
The authors tackled the problem of designing safer organophosphorus molecules by proposing an RNN with attention framework to sample chemical space using fragment-based drug design, generating molecules with bulky side chains to reduce toxicity while maintaining biological activity.
Drug discovery is a complex process with a large molecular space to be considered. By constraining the search space, the fragment-based drug design is an approach that can effectively sample the chemical space of interest. Here we propose a framework of Recurrent Neural Networks (RNN) with an attention model to sample the chemical space of organophosphorus molecules using the fragment-based approach. The framework is trained with a ZINC dataset that is screened for high druglikeness scores. The goal is to predict molecules with similar biological action modes as organophosphorus pesticides or chemical warfare agents yet less toxic to humans. The generated molecules contain a starting fragment of PO2F but have a bulky hydrocarbon side chain limiting its binding effectiveness to the targeted protein.