Journal
JOURNAL OF MEDICINAL CHEMISTRY
Volume 63, Issue 16, Pages 8761-8777Publisher
AMER CHEMICAL SOC
DOI: 10.1021/acs.jmedchem.9b01101
Keywords
-
Categories
Funding
- European Union's Horizon 2020 Research and Innovation program under the Marie Sklodowska-Curie Grant [676434]
Ask authors/readers for more resources
In qualitative or quantitative studies of structure-activity relationships (SARs), machine learning (ML) models are trained to recognize structural patterns that differentiate between active and inactive compounds. Understanding model decisions is challenging but of critical importance to guide compound design. Moreover, the interpretation of ML results provides an additional level of model validation based on expert knowledge. A number of complex ML approaches, especially deep learning (DL) architectures, have distinctive black-box character. Herein, a locally interpretable explanatory method termed Shapley additive explanations (SHAP) is introduced for rationalizing activity predictions of any ML algorithm, regardless of its complexity. Models resulting from random forest (RF), nonlinear support vector machine (SVM), and deep neural network (DNN) learning are interpreted, and structural patterns determining the predicted probability of activity are identified and mapped onto test compounds. The results indicate that SHAP has high potential for rationalizing predictions of complex ML models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available