Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions
By Raquel Rodríguez-Pérez, Jürgen Bajorath. Journal of Computer-Aided Molecular Design, 2020
617 citations recorded by the source corpus.
Difficulties in interpreting machine learning (ML) models and their predictions limit the practical applicability of and confidence in ML in pharmaceutical research. There is a need for agnostic approaches aiding in the interpretation of ML models regardless of their complexity that is also applicable to deep neural network (DNN) architectures and model ensembles. To these ends, the SHapley Additive exPlanations (SHAP) methodology has recently been introduced. The SHAP approach enables the identification and prioritization of features that determine compound classification and activity prediction using any ML model. Herein, we further extend the evaluation of the SHAP methodology by investigating a variant for exact calculation of Shapley values for decision tree methods and systematically compare this variant in compound activity and potency value predictions with the model-independent SHAP method. Moreover, new applications of the SHAP analysis approach are presented including interpretation of DNN models for the generation of multi-target activity profiles and ensemble regression models for potency prediction.
Subfields: Computational Theory and Mathematics, Materials Chemistry
View Paper: https://www.semanticscholar.org/paper/1e38086cd665eaab8bf88206d428ada3429bb846
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Theory and Mathematics
- Francesca Grisoni
- Gisbert Schneider
- José Jiménez-Luna
- Kenneth Atz
- Roderick E. Hubbard
- Markus Hartenfeller
In Materials Chemistry
Citations in the corpus
- Drug discovery with explainable artificial intelligence (2020, background): “60,61 Hochuli et al. 63 compared several feature attribution methodologies, showing how the visualization of attributions assists in parsing and interpreting of protein-ligand scoring with 3D convolutional neural networks.”