ADMET-AI Agent Skill: Predict Drug Developability

ADMET-AI Agent Skill: Predict Drug Developability

The ADMET-AI Agent Skill provides developers with a tool to assess potential drug candidates by predicting their absorption, distribution, metabolism, excretion, and toxicity (ADMET) profiles. This skill translates complex predictions into a simple developability verdict rather than just numerical data, enabling efficient decision-making in drug development.

What this skill does

• Generates batch predictions for a library of chemical structures, evaluating their ADMET properties.
• Interprets individual ADMET prediction results against DrugBank-approved percentiles.
• Flags potential liabilities, such as hERG channel blockades, CYP enzyme inhibitions, poor Caco-2 permeability, high clearance rates, and problematic plasma protein binding.
• Utilizes a Chemprop-RDKit graph network, trained on 41 datasets from the Therapeutics Data Commons, to run assessments at high throughput speeds on standard CPUs.

Who it is for

• Developers and pharmaceutical research teams using AI coding agents like Claude Code, Cursor, and Codex.
• Organizations involved in drug discovery and development processes requiring enhanced ADMET profiling.

Use cases

• Running high-speed ADMET property predictions across extensive chemical libraries in computational drug discovery.
• Screening drug candidates to quickly identify those with favorable developability profiles.
• Determining go/no-go decisions in early-phase drug development to streamline potential candidate selection.

Technical details

• Tool Name: ADMET-AI 2.0.1
• Installation: Available through PyPI, `pip install admet-ai` (requires Python 3.11+).
• No GPU required; optimized for CPU processing.
• Automatically fetches necessary neural network weights upon first usage.
• For additional guidance, consult the detailed reference documentation: [running-admet-ai.md](references/running-admet-ai.md), [endpoints.md](references/endpoints.md), and [interpreting-predictions.md](references/interpreting-predictions.md).

Source & Licence

This package is built on open-source work published by K-Dense-AI (K-Dense-AI/drug-discovery-agent-skills) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.