skills.rest
matt-grain
matt-grainCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

tooluniverse-drug-research

Generates comprehensive drug research reports from PubChem, ChEMBL, FAERS, and ClinicalTrials.gov data.

Updated Mar 13, 2026
Search Tags:#clinical trials#pubchem#pharmacogenomics#drug research#pharmaceutical#admet#faers
One-click install
npx skills add https://github.com/matt-grain/pharma-catalyst --skill tooluniverse-drug-research-matt-grain
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tooluniverse-drug-research
Source: https://github.com/matt-grain/pharma-catalyst/tree/main/.claude/skills/tooluniverse-drug-research
Command: npx skills add https://github.com/matt-grain/pharma-catalyst --skill tooluniverse-drug-research-matt-grain

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires lxml.

What problem does it solve? Researching a drug requires manually querying dozens of disconnected databases—PubChem for chemistry, ChEMBL for targets, ClinicalTrials.gov for trials, FAERS for adverse events, PharmGKB for pharmacogenomics—and synthesizing findings into a coherent, cited report. This Skill automates that entire workflow into a structured 11-section drug research report. ## Core Features & Use Cases - Compound Disambiguation: Resolves drug names to PubChem CIDs, ChEMBL IDs, SMILES, and PharmGKB identifiers before research begins, handling salt forms, isomers, and prodrugs. - Multi-Source Evidence Gathering: Queries 50+ ToolUniverse tools across chemistry, ADMET predictions, clinical trials, FAERS post-marketing safety, FDA Orange Book regulatory data, and pharmacogenomics, with automatic fallback chains when APIs fail. - Evidence-Graded Reporting: Produces a standardized report with inline citations, T1-T4 evidence grading, a drug profile scorecard, and a completeness audit documenting data gaps and tool failures. - Use Case: Ask about metformin and receive a full report covering its mechanism (AMPK activation), ADMET profile, 500+ clinical trials, FAERS safety signals, SLC22A1 pharmacogenomics, and regulatory status—with every claim cited to its source database. ## Quick Start Generate a comprehensive drug research report for metformin covering its chemistry, mechanism, clinical trials, and safety profile.

Frequently Asked Questions about tooluniverse-drug-research

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

FAQPage Schema
How do I generate a comprehensive drug research report?▼

Provide a drug name, ChEMBL ID, or SMILES string and the skill creates a structured report file, then progressively populates 11 sections covering identity, chemistry, mechanism, ADMET, clinical trials, safety, pharmacogenomics, regulatory status, and literature. Every claim includes inline source citations.

What databases does drug research query for safety data?▼

Safety data comes from FDA FAERS for post-marketing adverse events, including disproportionality analysis (ROR, PRR, IC), demographic stratification, and serious event filtering. DailyMed SPL parsing extracts labeled adverse reactions, contraindications, and drug interactions.

Can I research an investigational compound with no clinical data?▼

Yes. For investigational compounds, the report emphasizes chemistry, targets, and ADMET-AI predictions while marking clinical, FAERS, and pharmacogenomics sections as unavailable. All section headers remain present with explicit notes about data gaps.

What happens when ADMET-AI or PharmGKB tools fail?▼

Automatic fallback chains activate: ADMET-AI failures switch to DailyMed clinical pharmacology and pharmacokinetics label sections, while PharmGKB failures fall back to DailyMed pharmacogenomics sections plus PubMed literature. Failed queries are documented in the completeness audit.

How are drug targets identified from ChEMBL data?▼

Targets are derived from ChEMBL activity records filtered to pChEMBL >= 6.0 or IC50/EC50 <= 1 uM, then resolved to UniProt entries. The skill explicitly avoids ChEMBL_get_molecule_targets because it returns unfiltered, irrelevant results.

When should I not use this drug research skill?▼

Use dedicated skills for target research, disease research, or literature-only deep dives. For single property lookups or structure similarity searches, call tools like PubChem_search_compounds_by_similarity directly instead of generating a full report.

Related Skills

Explore More Education & Research Skills→
robotlearning123robotlearning123

chembl-database

Query and analyze bioactive molecules and drug targets from the ChEMBL database.

Community
Advanced
RamanEbrahimiRamanEbrahimi
3

deepchem

Predict molecular properties using deepchem machine learning models.

Community
Advanced
DrugClawDrugClaw
126

target-intelligence-tools

Query public bioinformatics APIs to generate drug-target intelligence dossiers.

Official
Intermediate
80portisfound80portisfound

drug-discovery

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

Community
Intermediate