drug-discovery

Retrieve bioactivity data and compute Lipinski Ro5 and Veber properties from public APIs.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/MarbleSodas/Mavis --skill drug-discovery-marblesodas
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/MarbleSodas/Mavis/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/MarbleSodas/Mavis --skill drug-discovery-marblesodas

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Reduces the time and effort needed to evaluate small molecules for discovery research by combining target finding, drug-likeness scoring, interaction lookups, and safety/ADMET-style interpretation into one workflow.

Core Features & Use Cases

  • Bioactive compound search (ChEMBL): Find targets and retrieve top bioactive compounds by potency (e.g., pChEMBL thresholds) and fetch molecule details by ChEMBL ID.
  • Drug-likeness scoring (PubChem): Compute key property inputs for Lipinski Ro5 and Veber oral bioavailability rules using publicly accessible PubChem property endpoints.
  • Drug interaction and safety signals (OpenFDA): Look up reported drug-drug interaction labels and adverse event counts to support early safety and interaction assessment.
  • Gene–disease association context (OpenTargets): Query disease associations for a given gene/target and surface scored top links for hypothesis generation.

Quick Start

Run the drug-discovery skill to search a molecule or target, compute Ro5/Veber properties, and summarize interaction and safety signals using public APIs.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I compute Lipinski Ro5 and Veber oral bioavailability thresholds for a small molecule?

To compute Lipinski Ro5 and Veber oral bioavailability thresholds, the Skill retrieves molecular properties like MW, LogP, HBD, HBA, TPSA, and rotatable bonds from PubChem, then evaluates them against established drug-likeness rules to estimate oral bioavailability.

How can I find bioactive compounds for a specific target using ChEMBL?

To find bioactive compounds via ChEMBL, the Skill searches for a specific target and retrieves top compounds filtered by potency thresholds such as pChEMBL values, then fetches detailed molecule information by ChEMBL ID for lead optimization.

Can I retrieve drug-drug interaction labels and adverse event counts from OpenFDA?

Yes, the Skill queries OpenFDA to look up reported drug-drug interaction labels and adverse event counts, summarizing interaction and safety signals to support early safety assessment during clinical pharmacology workflows.

How do I query gene-disease associations for hypothesis generation using OpenTargets?

To query gene-disease associations, the Skill uses OpenTargets to search disease associations for a given gene or target, surfacing scored top links that provide context for hypothesis generation in open-science drug discovery.

Do I need API keys to access PubChem, ChEMBL, OpenFDA, and OpenTargets for drug discovery?

No, the Skill requires only public, unauthenticated API calls to access ChEMBL, PubChem, OpenFDA, and OpenTargets, providing command-line friendly parsing for computing molecular properties and summarizing safety signals.