admet-prediction

Predict ADMET properties of small molecules using multiple models.

6|2|Updated Jun 11, 2026

Search Tags:#drug discovery #cheminformatics #safety assessment #admet #compound prediction

Ready to run

npx skills add https://github.com/pradyumnasagar/open-research-skills --skill admet-prediction-pradyumnasagar

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: admet-prediction
Source: https://github.com/pradyumnasagar/open-research-skills/tree/main/skills/chemoinformatics/admet-prediction
Command: npx skills add https://github.com/pradyumnasagar/open-research-skills --skill admet-prediction-pradyumnasagar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rdkit, requests, deepchem, chemprop, admet-ai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill predicts ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties of compounds, aiding in drug discovery and safety assessment.

Core Features & Use Cases

ADMET Property Prediction: Predicts various ADMET properties using multiple models.
Drug Likeness: Identifies compounds with potential drug-like properties.
Safety Assessment: Evaluates potential safety issues of compounds.
Use Case: When a researcher needs to prioritize compounds for further development based on their predicted ADMET properties.

Quick Start

Predict the ADMET properties of the compound with SMILES string 'CCO' using the admet-prediction skill.

Frequently Asked Questions about admet-prediction

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I predict ADMET properties for small molecules to assess drug safety?▼

ADMET prediction evaluates a compound's absorption, distribution, metabolism, excretion, and toxicity using SMILES strings. It leverages models like ADMETlab 3.0 and DeepChem MolNet to assess drug-likeness and prioritize compounds for further development.

What models are used for compound ADMET prediction and drug-likeness evaluation?▼

ADMET prediction utilizes ADMETlab 3.0, ADMET-AI, DeepChem MolNet, and chemprop D-MPNN models. These frameworks collectively evaluate small molecules to determine their safety profile and drug-likeness for drug discovery.

Do I need RDKit and chemprop installed to run ADMET predictions?▼

Yes, you need RDKit, chemprop, DeepChem, admet-ai, and requests installed. These dependencies are required to execute the cheminformatics models and perform compound safety assessments successfully for drug discovery.

Can I use SMILES strings to evaluate compound toxicity and safety assessment?▼

Yes, you can input SMILES strings like 'CCO' to evaluate compound toxicity. The skill processes these chemical structures to predict ADMET properties, enabling researchers to assess potential safety issues during drug discovery.

What is the best way to prioritize compounds for drug discovery using cheminformatics?▼

The best way to prioritize compounds is by predicting their ADMET properties. By evaluating drug-likeness and safety profiles across multiple endpoints, researchers can filter out unfavorable molecules early in the drug discovery pipeline.

Are there limitations when using DeepChem MolNet for ADMET property prediction?▼

While metadata does not specify exact limitations, ADMET prediction using DeepChem MolNet and chemprop D-MPNN relies on computational models. Predictions should be validated experimentally before final safety assessment in drug development.