Shapley Values

Chemically Interpretable Explanations for Molecular Property Prediction via Fragment-Level Shapley Values

This work introduces a fragment-level Shapley value framework that enables the exact computation of feature contributions at the level of chemically meaningful fragments for molecular property predictions without relying on sampling or feature imputation.

Protocol to calculate and compare exact Shapley values for different kernels in support vector machine models using binary features

A protocol to calculate and compare exact Shapley values for support vector machine models with commonly used kernels and binary input features is developed.

Workflow of the porposed method, after the activity prediction, Shapley Values are calculated which are then mapped to chemical substructures.

Machine learning models with distinct Shapley value explanations decouple feature attribution and interpretation for chemical compound predictions

A method for the exact calculation of Shapley Values for Support Vector Machines is introduced and tested for compound prediction tasks.