admet-prediction

Predict ADMET properties from SMILES using GraphMVP ensemble models.

1.1k|132|Updated Apr 13, 2023
One-click install
npx skills add https://github.com/PharMolix/OpenBioMed --skill admet-prediction
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: admet-prediction
Source: https://github.com/PharMolix/OpenBioMed/tree/main/skills/admet-prediction
Command: npx skills add https://github.com/PharMolix/OpenBioMed --skill admet-prediction

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Predict comprehensive ADMET properties for drug candidate molecules using GraphMVP ensemble models to accelerate early-stage drug discovery.

Core Features & Use Cases

  • Load a molecule from SMILES and build an ensemble of ADMET predictors.
  • Predict BBB penetration, SIDER side effects, Caco-2 permeability, half-life, and LD50.
  • Use case: rapidly screen candidates for safety and pharmacokinetic risk before synthesis.

Quick Start

Input a molecule's SMILES string and run the GraphMVP ADMET ensemble to obtain BBB penetration, SIDER probabilities, Caco-2 permeability, half-life, and LD50 estimates.

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 a drug candidate molecule using SMILES?

To predict ADMET properties, input a molecule's SMILES string and run the GraphMVP ensemble to output BBB penetration, SIDER side effects, Caco-2 permeability, half-life, and LD50 estimates.

What pharmacokinetic and toxicity indicators can I evaluate during early-stage drug discovery?

During early-stage drug discovery, you can evaluate safety and pharmacokinetic risk profiles by predicting BBB penetration, SIDER side effects, Caco-2 permeability, half-life, and LD50 using GraphMVP ensemble models.

Do I need GraphMVP checkpoints and configuration YAMLs to run ADMET predictions?

Yes, performing deterministic ADMET inference via the OpenBioMed pipeline requires SMILES input along with access to GraphMVP checkpoints and configuration YAMLs.

Can I use GraphMVP ensemble models to screen Caco-2 permeability and LD50 before synthesis?

Yes, you can rapidly screen drug candidates for Caco-2 permeability and LD50 safety profiles before synthesis by running the GraphMVP ensemble ADMET predictors.

What are the limitations of using GraphMVP for ADMET prediction?

GraphMVP ADMET prediction is limited to deterministic inference via the OpenBioMed pipeline, requiring specific checkpoints and YAML configurations to output BBB, SIDER, Caco-2, half-life, and LD50 metrics.