drug-discovery

Queries ChEMBL, PubChem, OpenFDA, and OpenTargets APIs for compound bioactivity and drug-likeness analysis.

1|Updated Feb 17, 2026
One-click install
npx skills add https://github.com/brittb-dev/zerogravityclaw --skill drug-discovery-brittb-dev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/brittb-dev/zerogravityclaw/tree/main/src/hermes-core/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/brittb-dev/zerogravityclaw --skill drug-discovery-brittb-dev

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 compound search, property calculation, 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 bioactivity data with pChEMBL thresholds, no API key required. - Drug-Likeness Screening: Calculate Lipinski Ro5, Veber rules, TPSA, and QED for any compound via the PubChem API, with batch screening through the included ro5_screen.py script. - Safety & Interaction Lookup: Retrieve drug-drug interactions from OpenFDA labels and top reported adverse events from FDA event data. - Use Case: A medicinal chemist evaluating lead compounds for an EGFR inhibitor program can search ChEMBL for known actives, screen candidates against Ro5 and Veber rules, and check interaction liabilities in one workflow. ## Quick Start Ask the assistant to check whether aspirin passes the Lipinski Rule of Five and look up its known drug interactions.

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?▼

Query the ChEMBL target search endpoint with a target name like EGFR to get its ChEMBL ID, then fetch activities filtered by pChEMBL value. The included chembl_target.py script automates this with a minimum pChEMBL threshold and result limit.

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

Fetch MolecularWeight, XLogP, HBondDonorCount, and HBondAcceptorCount from the PubChem PUG REST API, then apply the thresholds MW≤500, LogP≤5, HBD≤5, HBA≤10. The ro5_screen.py script batch-screens multiple compounds this way.

Do ChEMBL, PubChem, and OpenFDA APIs require API keys?▼

No, all APIs used here are free and public with no authentication required. ChEMBL recommends adding a short sleep between batch requests to respect rate limits.

Can I use OpenFDA data to determine drug safety?▼

OpenFDA adverse event data reflects reported events, not proven causation, so it indicates signal frequency rather than confirmed risk. Always recommend consulting a licensed pharmacist or physician for clinical decisions.

What are the limitations of API-based drug-likeness screening?▼

PubChem property lookups depend on the compound existing in the database by name, so novel or unnamed structures cannot be screened. The approach also computes rule-based filters only, not full ADMET predictions like hERG binding or metabolic rates.