drug-team

Meta-skill that orchestrates a team of specialized AI agents for drug design.

Overview

Purpose: Designs novel drug candidates for a given target/indication with constraints (e.g., "Design drug for pain relief, logP<3").
Agents:
Chem Synth (uses chemistry-query skill): Proposes molecular scaffolds and synthesis routes.
Synth Notebook (uses synth-notebook skill): Visualizes routes, optimizes yields, checks safety.
Lab Inventory (uses lab-inventory skill): Checks stock for reagents, estimates costs.
ADMET: Predicts QED, SA, logP, TPSA, pKa using RDKit/ML proxies.
Tox: Checks PAINS, Brenk alerts, Ames test.
Pharm: Evaluates target binding affinity (docking proxy via web/tools).
Patent Scout (uses patent_scout.py): Scans for prior art patents, computes novelty score, checks for blocking patents via web searches.
Coordination: Iterative polling and messaging between agents to refine candidates.
Output: Table of top 3 molecules (SMILES, route, scores) + visualizations (e.g., mol images).

When triggered, runs scripts/orchestrate.py "{user_query}" .

Integrates chemistry-query for initial scaffolds and routes.
Uses synth-notebook for route visualization, yield optimization, and safety checks.
Incorporates lab-inventory for reagent stock checking and cost estimation.
Ranks candidates including feasibility scores based on yield, safety (with SDS scans for route chemicals, risk scores, and alerts), and inventory availability.
Post-design patent scouting to include novelty scores and blocking status in candidate ranking ("High novelty: no blocking patents").