What can attribution methods show us about chemical language models?

ABSTRACT: Language models trained on molecular string representations have shown strong performance in predictive and generative tasks. However, practical applications require not only making accurate predictions, but also explainability - the ability to explain the reasons and rationale behind the predictions. In this work, we explore explainability for a chemical language model by adapting a transformer-specific and a model-agnostic input attribution technique. We fine-tune a pretrained model to predict aqueous solubility, compare training and architecture variants, and evaluate visualizations of attributed relevance. The model-agnostic SHAP technique provides sensible attributions, highlighting the positive influence of individual electronegative atoms, but does not explain the model in terms of

SUBMITTER: Hodl S 

PROVIDER: S-EPMC11389796 | biostudies-literature | 2024 Sep

REPOSITORIES: biostudies-literature