Mapping chemical performance on molecular structures using locally interpretable explanations
This work addresses the interpretability of complex quantitative structure-activity relationship models for researchers in chemistry, but it is incremental as it applies an existing explanation method to a new domain.
The researchers tackled the problem of interpreting black-box models for classifying fuel compounds by applying Locally Interpretable Machine-Agnostic Explanations to 2-D chemical structures, enabling structural interpretations that replicate chemical intuition for synthetic chemists.
In this work, we present an application of Locally Interpretable Machine-Agnostic Explanations to 2-D chemical structures. Using this framework we are able to provide a structural interpretation for an existing black-box model for classifying biologically produced fuel compounds with regard to Research Octane Number. This method of "painting" locally interpretable explanations onto 2-D chemical structures replicates the chemical intuition of synthetic chemists, allowing researchers in the field to directly accept, reject, inform and evaluate decisions underlying inscrutably complex quantitative structure-activity relationship models.