domains / families / science / admet-prediction

admet-prediction

separate

Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG/CYP/AMES endpoints, and PAINS / Lipinski / Ro5 / Veber / BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.

When to use

• filtering compounds for drug-likeness
• prioritizing leads by predicted safety
• building an in-house ADMET QSAR model
• predicting absorption, distribution, metabolism, excretion, and toxicity properties
• batch screening with no in-house data
• benchmarking chemprop D-MPNN for single endpoints
• OECD-compliant QSAR for regulatory submission
• assessing hERG/CYP/AMES endpoints

When not to use

• PAINS / Brenk / structural alerts
• QSAR model building from in-house data

Skill page

Source