drugbank-database

Files (7)

• SKILL.md
• chemical-analysis.md · references/
• data-access.md · references/
• drug-queries.md · references/
• interactions.md · references/
• targets-pathways.md · references/
• drugbank_helper.py · scripts/

SKILL.md (first lines)

# DrugBank Database

## Overview

DrugBank is a comprehensive bioinformatics and cheminformatics database containing detailed information on drugs and drug targets. This skill enables programmatic access to DrugBank data including ~9,591 drug entries (2,037 FDA-approved small molecules, 241 biotech drugs, 96 nutraceuticals, and 6,000+ experimental compounds) with 200+ data fields per entry.

## Core Capabilities

### 1. Data Access and Authentication

Download and access DrugBank data using Python with proper authentication. The skill provides guidance on:

- Installing and configuring the `drugbank-downloader` package
- Managing credentials securely via environment variables or config files
- Downloading specific or latest database versions
- Opening and parsing XML data efficiently
- Working with cached data to optimize performance

**When to use**: Setting up DrugBank access, downloading database updates, initial project configuration.

**Reference**: See `references/data-access.md` for detailed authentication, download procedures, API access, caching strategies, and troubleshooting.

### 2. Drug Information Queries

Extract comprehensive drug information from the database including identifiers, chemical properties, pharmacology, clinical data, and cross-references to external databases.

**Query capabilities**:
- Search by DrugBank ID, name, CAS number, or keywords
- Extract basic drug information (name, type, description, indication)
- Retrieve chemical properties (SMILES, InChI, molecular formula)
- Get pharmacology data (mechanism of action, pharmacodynamics, ADME)
- Access external identifiers (PubChem, ChEMBL, UniProt, KEGG)
- Build searchable drug datasets and export to DataFrames
- Filter drugs by type (small molecule, biotech, nutraceutical)

**When to use**: Retrieving specific drug information, building drug databases, pharmacology research, literature review, drug profiling.

**Reference**: See `references/drug-queries.md` for XML navigation, query functions, data extraction methods, and performance optimization.

### 3. Drug-Drug Interactions Analysis

Analyze drug-drug interactions (DDIs) including mechanism, clinical significance, and interaction networks for pharmacovigilance and clinical decision support.

**Analysis capabilities**:
- Extract all interactions for specific drugs
- Build bidirectional interaction networks
- Classify interactions by severity and mechanism
- Check interactions between drug pairs
- Identify drugs with most interactions
- Analyze polypharmacy regimens for safety
- Create interaction matrices and network graphs
- Perform community detection in interaction networks
- Calculate interaction risk scores

**When to use**: Polypharmacy safety analysis, clinical decision support, drug interaction prediction, pharmacovigilance research, identifying contraindications.

**Reference**: See `references/interactions.md` for interaction extraction, classification methods, network analysis, and clinical applications.

### 4. Drug Targets and Pathways

Access detailed information about drug-protein interactions including targets, enzymes, transporters, carriers, and biological pathways.

**Target analysis capabilities**:
- Extract drug targets with actions (inhibitor, agonist, antagonist)
- Identify metabolic enzymes (CYP450, Phase II enzymes)
- Analyze transporters (uptake, efflux) for ADME studies
- Map drugs to biological pathways (SMPDB)
- Find drugs targeting specific proteins
- Identify drugs with shared targets for repurposing
- Analyze polypharmacology and off-target effects
- Extract Gene Ontology (GO) terms for targets
- Cross-reference with UniProt for protein data

**When to use**: Mechanism of action studies, drug repurposing research, target identification, pathway analysis, predicting off-target effects, understanding drug metabolism.

**Reference**: See `references/targets-pathways.md` for target extraction, pathway analysis, repurposing strategies, CYP450 profiling, and transporter analysis.

### 5. Chemical Properties and Similarity

Perform structure-based analysis including molecular similarity searches, property calculations, substructure searches, and ADMET predictions.

**Chemical analysis capabilities**:
- Extract chemical structures (SMILES, InChI, molecular formula)
- Calculate physicochemical properties (MW, logP, PSA, H-bonds)
- Apply Lipinski's Rule of Five and Veber's rules
- Calculate Tanimoto similarity between molecules
- Generate molecular fingerprints (Morgan, MACCS, topological)
- Perform substructure searches with SMARTS patterns
- Find structurally similar drugs for repurposing
- Create similarity matrices for drug clustering
- Predict oral absorption and BBB permeability
- Analyze chemical space with PCA and clustering
- Export chemical property databases

**When to use**: Structure-activity relationship (SAR) studies, drug similarity searches, QSAR modeling, drug-likeness assessment, ADMET prediction, chemical space exploration.

**Reference**: See `references/chemical-analysis.md` for structure extraction, similarity calculations, fingerprint generation, ADMET predictions, and chemical space analysis.

## Typical Workflows

### Drug Discovery Workflow
1. Use `data-access.md` to download and access latest DrugBank data
2. Use `drug-queries.md` to build searchable drug database
3. Use `chemical-analysis.md` to find similar compounds
4. Use `targets-pathways.md` to identify shared targets
5. Use `interactions.md` to check safety of candidate combinations

### Polypharmacy Safety Analysis
1. Use `drug-queries.md` to look up patient medications
2. Use `interactions.md` to check all pairwise interactions
3. Use `interactions.md` to classify interaction severity
4. Use `interactions.md` to calculate overall risk score
5. Use `targets-pathways.md` to understand interaction mechanisms

### Drug Repurposing Research
1. Use `targets-pathways.md` to find drugs with shared targets
2. Use `chemical-analysis.md` to find structurally similar drugs
3. Use `drug-queries.md` to extract indication and pharmacology data
4. Use `interactions.md` to assess potential combination therapies

From agent-skills-hub/agent-skills-hub, MIT.

More from agent-skills-hub/agent-skills-hub