Tox21

The Tox21 dataset is a benchmark that contains data on various toxicological endpoints used to evaluate the predictive performance of models in assessing molecular properties and activities related to toxicity.

Papers using Tox21 (6)

What Molecular Structure Cannot Tell Us: A Taxonomy of Explainability Gaps in GNN-Based Drug Toxicity Prediction2026Combining Deep Learning and Explainable AI for Toxicity Prediction of Chemical Compounds2025 · 1 citesDo Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction2026Budget-Sensitive Discovery Scoring: A Formally Verified Framework for Evaluating AI-Guided Scientific Selection2026Task-Specific Sparse Feature Masks for Molecular Toxicity Prediction with Chemical Language Models2025Measuring AI Progress in Drug Discovery: A Reproducible Leaderboard for the Tox21 Challenge2025