tox21

Datasets used in the tox21 challenge

A PubChemPy-inspired PUG REST client with throttle-aware retry, caching, BioAssay/gene/protein/Tox21 data, live cross-references into ChEMBL, BindingDB and the PDB, and a local parquet mirror for bulk CID lookups.

MoltiTox: a multimodal fusion model for molecular toxicity prediction

some scripts using deepchem

Dual-encoder Fourier-KAN fusion for chemical toxicity prediction on Tox21 Outperforms DeepTox and AMAZIZ

A Polymer Toxicity Prediction Tool using PSMILE Strings

Stability-Aware GNN Framework for molecular toxicity prediction using Graph Attention Networks. Built on Tox21 dataset with ERI reliability scoring. Live demo on HuggingFace Spaces.

Multi-label classification problem.

Empirical analysis quantifying the 0.009 ROC-AUC gap between PyTorch GNNs (2D graphs) and OLMo-7B (1D SMILES) on Tox21. Exposes the Random Split illusion and provides the baseline justification for Topological State Machine (TSM) integration.

A Machine Learning Framework for Toxicity Prediction in the Tox21 Dataset using hybrid molecular representations.

Descriptive analysis and QSAR modelling for tox_21 datasets

Multi-task toxicity prediction on the Tox21 dataset using Random Forest and XGBoost, with SHAP-based interpretability mapping predictions to real chemical substructures via RDKit.

ChemAI: Multi-property chemical prediction using Random Forest and Graph Neural Networks

Reproducible computational toxicology pipeline - scaffold-split evaluation, calibrated uncertainty, applicability domain (NAMs-oriented)

EPA data on 1,800 chemicals across 700+ assay endpoints

Native fine-tuning of Mistral-7B on the Tox21 dataset using LoRA and 4-bit quantization, achieving a competitive 0.72 ROC-AUC.

GNN + DMPNN ensemble with MC Dropout for multi-task molecular toxicity and activity prediction across 9 datasets · Random Forest fingerprint models · FastAPI web UI with 3D viewer

Scaffold-aware GCN with attention-based substructure pooling for multi-task Tox21 toxicity prediction. 12-task model with scaffold-split evaluation achieving 0.789 AUC-ROC on best assay.

ML project predicting chemical toxicity using XGBoost

Generate the full Tox21 multi-task toxicity dataset from public PubChem BioAssay records