Improving Machine Learning Classification Predictions through SHAP and Features Analysis Interpretation

Tree-based machine learning (ML) algorithms, such as Extra Trees (ET), Random Forest (RF), Gradient Boosting Machine (GBM), and XGBoost (XGB) are among the most widely used in early drug discovery, given their versatility and performance. However, models based on these algorithms often suffer from m...

Full description

Saved in:

Bibliographic Details
Main Author:	Leonardo Bernal (22461790) (author)
Other Authors:	Giulio Rastelli (1513714) (author), Luca Pinzi (6268934) (author)
Published:	2025
Subjects:	Pharmacology Developmental Biology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified virtual screening applications three prostate cancer shapley additive explanations reduced interpretability issues range typically associated known antiproliferative activity early drug discovery demonstrating satisfactory accuracy cell lines (< achieved mcc values benchmarked classifiers based based machine learning features value analyses algorithms often suffer shap values revealed lncap test sets likely misclassified compounds improve classifier performance shap values misclassified compounds data sets models based “ raw widely used valuable approach thus providing systematic exclusion shap ”. shap ”, shap ). several approaches prediction performance performing models opposite class novel approach model predictions integrates shap fall within extra trees ecfp4 descriptors e .</ commonly used 8 across
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Improving Machine Learning Classification Predictions through SHAP and Features Analysis Interpretation

Similar Items