BoostSF-SHAP: Gradient boosting-based software for protein-ligand binding affinity prediction with explanations

Machine learning-based (ML-based) scoring functions (SFs) for protein-ligand binding affinity prediction have exhibited remarkable performance in the field of structure-based drug discovery. However, little attention has been given to the interpretability of these SFs. In this study, we propose a software called BoostSF-SHAP for protein-ligand binding affinity prediction. Specifically, we employed gradient boosting decision trees (GBDTs) to construct the ML-based SF. Forty-one intermolecular interaction features were used as the input of this SF. Notably, the proposed software can provide local and global explanations for the SF by using the SHapley Additive exPlanations (SHAP) approach. This paper presents a description of the architecture, functionalities, and implementation details of the proposed software. An assessment and illustrative examples of how to use this software are also provided. BoostSF-SHAP is written in Python and available on GitHub under the Apache License.