drug-discovery

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

Updated Jun 7, 2026
One-click install
npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill drug-discovery-chensihakniroth
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: drug-discovery
Source: https://github.com/Chensihakniroth/ANAKOT-AGENT/tree/main/optional-skills/research/drug-discovery
Command: npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill drug-discovery-chensihakniroth

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 searches, molecular property calculations, and drug interaction lookups through free public APIs. ## Core Features & Use Cases - Bioactive Compound Search: Query ChEMBL by target name or ID to retrieve compounds with bioactivity data filtered by pChEMBL thresholds. - Drug-Likeness Screening: Calculate Lipinski Rule of Five, Veber rules, TPSA, and QED scores for any compound via the PubChem API, including batch screening of multiple molecules. - Safety & Interaction Lookup: Retrieve drug-drug interactions from OpenFDA labels and top reported adverse events, plus gene-disease associations from OpenTargets. - 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 in batch, and check FDA adverse event profiles in one workflow. ## Quick Start Ask the agent to screen aspirin, ibuprofen, and a candidate molecule against Lipinski's Rule of Five and report which compounds pass oral bioavailability criteria.

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 API 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 and lists unique molecules ranked by potency.

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

Fetch MolecularWeight, XLogP, HBD, HBA, TPSA, and rotatable bond count from the PubChem PUG REST API, then apply the Ro5 thresholds in Python. The ro5_screen.py script batch-screens multiple compounds against both Lipinski and Veber rules.

Does this require API keys or paid database access?▼

No API keys are required. ChEMBL, PubChem, OpenFDA, and OpenTargets all provide free public endpoints, and the scripts use only Python standard library modules with curl for HTTP requests.

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

Yes, the OpenFDA drug label endpoint returns drug_interactions sections for a given drug name, and the drug event endpoint lists the most frequently reported adverse reactions. FDA data reflects reported events, not confirmed causation.

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

PubChem property lookups depend on exact compound name resolution and may fail for novel or unnamed structures. ChEMBL rate limits require delays between batch requests, and predicted properties do not replace experimental ADMET assays.