adme-property-predictor

Predict ADME properties and drug-likeness scores from SMILES strings.

Updated Apr 9, 2026

Search Tags:#cheminformatics #batch-processing #predictions #drug-design #adme #qsar #pharmacokinetics

Ready to run

npx skills add https://github.com/jakechen1/echo-research-framework --skill adme-property-predictor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: adme-property-predictor
Source: https://github.com/jakechen1/echo-research-framework/tree/main/skills-available/adme-property-predictor
Command: npx skills add https://github.com/jakechen1/echo-research-framework --skill adme-property-predictor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rdkit, dataclasses, and includes scripts (resource) and references (resource) components.

What problem does it solve?

ADME property prediction enables rapid evaluation of drug-like behavior for candidate molecules, reducing unnecessary experimental screening and guiding choice of which compounds to advance.

Core Features & Use Cases

Multi-Property Prediction: Absorption, Distribution, Metabolism, Excretion
Drug-Likeness Scoring: Lipinski compliance, PSA and other metrics
Batch Processing: Analyze libraries of molecules efficiently
Integrated Scoring: Combines ADME data into an overall drug-likeness score
Use Case: Prioritize compounds for synthesis with PK-friendly profiles

Quick Start

Provide a SMILES string to run a complete ADME prediction and receive a structured result.

Frequently Asked Questions about adme-property-predictor

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

FAQPage Schema

How do I predict ADME properties for drug candidates using SMILES strings?▼

Predict ADME properties by providing a SMILES string to the local Python API, which calculates molecular descriptors to assess absorption, distribution, metabolism, and excretion profiles for drug candidates.

Can I run batch processing for ADME predictions on a molecular library?▼

Yes, batch processing supports analyzing entire molecule libraries efficiently, evaluating ADME profiles and drug-likeness scores across multiple compounds to prioritize synthesis.

What metrics are included in the drug-likeness scoring for lead optimization?▼

Drug-likeness scoring combines ADME data with Lipinski compliance and PSA metrics into an integrated score to guide lead optimization and early safety filtering.

Do I need rdkit installed to calculate pharmacokinetic profiles locally?▼

Yes, rdkit is a required dependency for calculating cheminformatics models and molecular descriptors needed to execute pharmacokinetic predictions locally.

What is the best way to filter compounds for early safety and PK-friendly profiles?▼

Use integrated drug-likeness scoring to filter compounds during library screening, combining ADME predictions and Lipinski compliance to prioritize molecules with PK-friendly profiles for synthesis.

Are ADME predictions from this cheminformatics model suitable for in vitro testing prioritization?▼

Yes, the cheminformatics models evaluate drug-like behavior to reduce unnecessary experimental screening and prioritize which compounds to advance for in vitro testing.