drug-discovery

Query ChEMBL, PubChem, OpenFDA, and OpenTargets APIs for compound screening and drug-likeness analysis.

Updated May 3, 2026
One-click install
npx skills add https://github.com/80portisfound/vibe-learning --skill drug-discovery-80portisfound
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/80portisfound/vibe-learning/tree/main/packages/hermes/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/80portisfound/vibe-learning --skill drug-discovery-80portisfound

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Pharmaceutical research requires querying multiple public databases and applying drug-likeness rules manually, which is slow and error-prone. This Skill automates bioactive compound search, molecular property screening, drug interaction lookup, and ADMET reasoning using free public APIs. ## Core Features & Use Cases - Bioactive Compound Search: Query ChEMBL by target name or ID to retrieve compounds with pChEMBL activity values, no API key required. - Drug-Likeness Screening: Batch-screen compounds against Lipinski Ro5 and Veber rules using PubChem property data via the included ro5_screen.py script. - Safety & Interaction Lookup: Pull drug interaction labels and adverse event reports from OpenFDA, plus gene-disease associations from OpenTargets. - Use Case: A medicinal chemist evaluating a lead series can run ro5_screen.py on candidate molecules, check CYP450 liabilities using the ADMET reference, and look up adverse events for comparator drugs in one workflow. ## Quick Start Ask the assistant to screen aspirin, ibuprofen, and your candidate compound for Lipinski Rule of Five compliance and summarize any violations.

Frequently Asked Questions about drug-discovery

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

FAQPage Schema
How do I search ChEMBL for compounds active against a target?▼

Use the ChEMBL target search API with a target name like EGFR to get a ChEMBL target ID, then query the activity endpoint filtered by pChEMBL value. The included chembl_target.py script automates this and lists top active molecules.

How to check Lipinski Rule of Five for a compound without RDKit?▼

Fetch molecular weight, LogP, H-bond donors, and acceptors from the PubChem PUG REST API, then apply the Ro5 thresholds in Python. The ro5_screen.py script batch-screens compounds this way using only the standard library.

Does this skill require API keys or paid database access?▼

No. All four data sources—ChEMBL, PubChem, OpenFDA, and OpenTargets—are free public APIs requiring no authentication. Only curl and python3 are needed as prerequisites.

Can I look up drug-drug interactions from FDA data?▼

Yes. Query the OpenFDA drug label endpoint searching the drug_interactions field by drug name to retrieve interaction text from official FDA labels. You can also pull top reported adverse events from the drug event endpoint.

What are the limitations of OpenFDA adverse event data?▼

OpenFDA adverse event reports reflect reported reactions, not proven causation, and counts are not incidence rates. The skill notes that clinical decisions should always be confirmed with a licensed pharmacist or physician.