What question did this study set out to answer?

The central aim is to create an interpretable QSAR model that accurately predicts acute oral toxicity (LD₅₀).

April 22, 2026Open Access

Interpretable QSAR models for acute oral toxicity via tuned XGBoost and hybrid data sampling techniques

Key Points

The central aim is to create an interpretable QSAR model that accurately predicts acute oral toxicity (LD₅₀).
Developed a QSAR framework integrating 2D and 3D descriptors.
Applied hybrid SMOTE-RUS resampling to address dataset imbalance.
Optimized seven machine learning models, focusing on XGBoost for its superior performance.
XGBoost model achieved an F₁ score of 0.62 and 87% accuracy.
Permutation Feature Importance identified key features like nP and TDB01m.
SHAP analysis highlighted local determinants, enhancing model interpretability.

Abstract

Accurate, interpretable prediction of acute oral toxicity (LD₅₀) is challenged by severe dataset imbalance and complex structure-activity relationships. This study develops a transparent QSAR framework by integrating 2D topological and 3D conformational descriptors with hybrid SMOTE-RUS resampling to classify rat oral LD₅₀ into Very Toxic vs. Not Very Toxic. Using 8,396 compounds from NICEATM–EPA NCCT, features were refined via sequential filtering, correlation pruning, and Random Forest ranking. Among seven optimized machine learning models, XGBoost achieved superior external performance (F₁=0.62, accuracy = 0.87). The model’s interpretability was ensured via Explainable AI: Permutation Feature Importance highlighted global contributors like nP and TDB01m; SHAP analysis identified local determinants such as TPSA(Tot); and surrogate decision trees distilled the logic into rule-based thresholds with high fidelity (≥ 0.88). This pipeline aligns with OECD principles, offering a regulatory-grade, explainable QSAR model that balances predictive power with mechanistic transparency for chemical safety assessment.

AI से पूछें

Bookmark

View Full Paper