What question did this study set out to answer?

The aim is to develop an effective model for accurately predicting protein allosteric sites.

May 1, 2026

AlloEF: An Ensemble Model for Protein Allosteric Site Identification Based on Transfer Entropy and Energetic Frustration.

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved allosteric site prediction in proteins, suggesting advancements in drug development.

The aim is to develop an effective model for accurately predicting protein allosteric sites.
Developed AlloEF using a soft-voting classifier with LightGBM, Random Forest, and XGBoost.
Integrated transfer entropy-based features with traditional characteristics for site prediction.
Employed Boruta algorithm for feature selection and SVM-SMOTE for addressing class imbalance.
AlloEF achieved an F1 score of 0.630 and an MCC of 0.609 on the independent test set.
Model outperformed existing methods for allosteric site prediction.
Successfully detected allosteric sites both within and beyond traditional allosteric pockets.

Zhang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

May 1, 2026

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved allosteric site prediction in proteins, suggesting advancements in drug development.

The aim is to develop an effective model for accurately predicting protein allosteric sites.
Developed AlloEF using a soft-voting classifier with LightGBM, Random Forest, and XGBoost.
Integrated transfer entropy-based features with traditional characteristics for site prediction.
Employed Boruta algorithm for feature selection and SVM-SMOTE for addressing class imbalance.
AlloEF achieved an F1 score of 0.630 and an MCC of 0.609 on the independent test set.
Model outperformed existing methods for allosteric site prediction.
Successfully detected allosteric sites both within and beyond traditional allosteric pockets.

Zhang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark