@bgicli/bgicli 2.1.1 → 2.2.0

package/data/skills/drug-photo/SKILL.md

@@ -0,0 +1,149 @@
+---
+name: drug-photo
+description: Medication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance
+version: 0.1.0
+author: Manuel Corpas
+license: MIT
+tags: [pharmacogenomics, computer-vision, drug-identification, dosage-guidance]
+metadata:
+  openclaw:
+    requires:
+      bins:
+        - python3
+      env: []
+      config: []
+    always: false
+    emoji: "📸"
+    homepage: https://github.com/ClawBio/ClawBio
+    os: [macos, linux]
+    install: []
+    trigger_keywords:
+      - drug photo
+      - medication photo
+      - pill photo
+      - drug image
+---
+
+# 📸 Drug Photo
+
+You are **Drug Photo**, a specialised ClawBio agent for medication identification and personalised dosage guidance. Your role is to identify a drug from a photo and generate a genotype-informed dosage card.
+
+## Why This Exists
+
+- **Without it**: A patient sees a pill and must manually identify it, then cross-reference their genotype against CPIC guidelines
+- **With it**: Snap a photo → Claude vision identifies the drug → instant personalised dosage card against real genotype data
+- **Why ClawBio**: Reuses the validated PharmGx Reporter pipeline (51 drugs, 12 genes) rather than generating ungrounded advice
+
+## Core Capabilities
+
+1. **Drug Identification**: Claude vision extracts drug name and visible dose from medication photo
+2. **Fuzzy Matching**: Brand/generic name resolution with substring matching and Levenshtein distance ≤ 2
+3. **Genotype Lookup**: Reads real 23andMe data (gzip-compressed `.txt.gz` supported) for the relevant gene
+4. **Dosage Card**: Visual classification card with STANDARD / CAUTION / AVOID / INSUFFICIENT labels
+
+## Workflow
+
+1. **Photo** → Claude vision identifies the drug name and visible dose from the image
+2. **Resolve** → Fuzzy drug name matching (brand/generic, substring, Levenshtein ≤ 2)
+3. **Genotype** → Reads real 23andMe data (gzip-compressed `.txt.gz` supported)
+4. **Lookup** → Single-drug CPIC recommendation against the user's actual genotype
+5. **Card** → Visual dosage card with classification, dose context, and FDA references
+
+## Supported Drugs (51)
+
+All drugs from the CPIC guideline set across 12 genes:
+
+| Gene | Example Drugs |
+|------|---------------|
+| CYP2C19 | Clopidogrel (Plavix), Omeprazole (Prilosec), Sertraline (Zoloft), Voriconazole |
+| CYP2D6 | Codeine, Tamoxifen (Nolvadex), Fluoxetine (Prozac), Metoprolol (Lopressor) |
+| CYP2C9 | Phenytoin, Celecoxib (Celebrex), Meloxicam |
+| CYP2C9+VKORC1 | Warfarin (Coumadin) — multi-gene |
+| SLCO1B1 | Simvastatin (Zocor), Atorvastatin (Lipitor) |
+| DPYD | Fluorouracil (5-FU), Capecitabine (Xeloda) |
+| TPMT | Azathioprine (Imuran), Mercaptopurine |
+| UGT1A1 | Irinotecan (Camptosar) |
+| CYP3A5 | Tacrolimus (Prograf) |
+| CYP2B6 | Efavirenz (Sustiva) |
+| CYP1A2 | Clozapine (Clozaril) |
+| NUDT15 | Thiopurines |
+
+## Classification Labels
+
+| Label | Meaning |
+|-------|---------|
+| STANDARD DOSING | Genotype supports recommended dose |
+| USE WITH CAUTION | Dose adjustment or monitoring may be needed |
+| AVOID — DO NOT USE | Genotype contraindicates this drug |
+| INSUFFICIENT DATA | Gene not profiled or phenotype unmapped |
+
+## CLI Reference
+
+```bash
+# Single drug lookup against real 23andMe data
+python skills/pharmgx-reporter/pharmgx_reporter.py \
+  --input patient.txt.gz --drug Plavix
+
+# With visible dose context
+python skills/pharmgx-reporter/pharmgx_reporter.py \
+  --input patient.txt.gz --drug codeine --dose 30mg
+
+# Via ClawBio runner (uses Manuel's real data in --demo mode)
+python clawbio.py run drugphoto --demo --drug Plavix
+python clawbio.py run drugphoto --demo --drug sertraline --dose 50mg
+```
+
+## Demo
+
+```bash
+python clawbio.py run drugphoto --demo --drug Plavix
+```
+
+Expected output: A single-drug dosage card showing CYP2C19 metaboliser phenotype, Clopidogrel (Plavix) classification, and CPIC recommendation based on Manuel Corpas's real genotype.
+
+## Output Structure
+
+The drug photo skill outputs directly to stdout (summary mode) when invoked via `clawbio.py`. The output is a structured dosage card:
+
+```
+Drug:       Clopidogrel (Plavix)
+Gene:       CYP2C19
+Phenotype:  Normal Metaboliser (*1/*1)
+Class:      STANDARD DOSING
+Guidance:   Use recommended dose per label
+Source:     CPIC Guideline (2022)
+```
+
+## Dependencies
+
+**Required**:
+- Python 3.10+ (standard library only)
+- Claude vision API access (for photo identification — handled by RoboTerri or agent)
+
+## Safety
+
+- **Local-first**: Genetic data never leaves the machine
+- **Disclaimer**: Every dosage card includes the ClawBio medical disclaimer
+- **CPIC-grounded**: All recommendations trace to published guidelines
+- **No diagnosis**: Classification labels are informational, not prescriptive
+
+## Telegram Integration
+
+Send a drug photo to RoboTerri. Claude vision identifies the drug and calls:
+```
+clawbio(skill="drugphoto", mode="demo", drug_name="Plavix", visible_dose="75mg")
+```
+
+## Integration with Bio Orchestrator
+
+**Trigger conditions** — the orchestrator routes here when:
+- User sends a photo of a medication or pill
+- User asks "what does this drug do for my genotype"
+
+**Chaining partners**:
+- `pharmgx-reporter`: Drug Photo is powered by PharmGx Reporter's single-drug mode
+
+## Citations
+
+- [CPIC Guidelines](https://cpicpgx.org/) — Clinical Pharmacogenetics Implementation Consortium
+- [FDA Table of Pharmacogenomic Biomarkers](https://www.fda.gov/drugs/science-and-research-drugs/table-pharmacogenomic-biomarkers-drug-labeling) — FDA-approved PGx drug labels

package/data/skills/drugbank-database/SKILL.md

@@ -0,0 +1,184 @@
+---
+name: drugbank-database
+description: Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data. This skill should be used when working with pharmaceutical data, drug discovery research, pharmacology studies, drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions, or any task requiring detailed drug and drug target information from DrugBank.
+---
+
+# 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
+
+### Pharmacology Study
+1. Use `drug-queries.md` to extract drug of interest
+2. Use `targets-pathways.md` to identify all protein interactions
+3. Use `targets-pathways.md` to map to biological pathways
+4. Use `chemical-analysis.md` to predict ADMET properties
+5. Use `interactions.md` to identify potential contraindications
+
+## Installation Requirements
+
+### Python Packages
+```bash
+uv pip install drugbank-downloader  # Core access
+uv pip install bioversions          # Latest version detection
+uv pip install lxml                 # XML parsing optimization
+uv pip install pandas               # Data manipulation
+uv pip install rdkit                # Chemical informatics (for similarity)
+uv pip install networkx             # Network analysis (for interactions)
+uv pip install scikit-learn         # ML/clustering (for chemical space)
+```
+
+### Account Setup
+1. Create free account at go.drugbank.com
+2. Accept license agreement (free for academic use)
+3. Obtain username and password credentials
+4. Configure credentials as documented in `references/data-access.md`
+
+## Data Version and Reproducibility
+
+Always specify the DrugBank version for reproducible research:
+
+```python
+from drugbank_downloader import download_drugbank
+path = download_drugbank(version='5.1.10')  # Specify exact version
+```
+
+Document the version used in publications and analysis scripts.
+
+## Best Practices
+
+1. **Credentials**: Use environment variables or config files, never hardcode
+2. **Versioning**: Specify exact database version for reproducibility
+3. **Caching**: Cache parsed data to avoid re-downloading and re-parsing
+4. **Namespaces**: Handle XML namespaces properly when parsing
+5. **Validation**: Validate chemical structures with RDKit before use
+6. **Cross-referencing**: Use external identifiers (UniProt, PubChem) for integration
+7. **Clinical Context**: Always consider clinical context when interpreting interaction data
+8. **License Compliance**: Ensure proper licensing for your use case
+
+## Reference Documentation
+
+All detailed implementation guidance is organized in modular reference files:
+
+- **references/data-access.md**: Authentication, download, parsing, API access, caching
+- **references/drug-queries.md**: XML navigation, query methods, data extraction, indexing
+- **references/interactions.md**: DDI extraction, classification, network analysis, safety scoring
+- **references/targets-pathways.md**: Target/enzyme/transporter extraction, pathway mapping, repurposing
+- **references/chemical-analysis.md**: Structure extraction, similarity, fingerprints, ADMET prediction
+
+Load these references as needed based on your specific analysis requirements.

package/data/skills/drugbank-search/SKILL.md

@@ -0,0 +1,211 @@
+---
+name: drugbank-search
+description: Search DrugBank comprehensive drug database with natural language queries. Drug mechanisms, interactions, and safety data powered by Valyu.
+keywords:
+  - drugbank
+  - drugs
+  - pharmacology
+  - drug-interactions
+  - adverse-reactions
+  - semantic-search
+license: MIT
+---
+
+
+# DrugBank Search
+
+Search the complete DrugBank database of drug information including mechanisms of action, interactions, targets, and pharmacology using natural language queries powered by Valyu's semantic search API.
+
+## Why This Skill is Powerful
+
+- **No API Parameter Parsing**: Just pass natural language queries directly - no need to construct complex search parameters
+- **Semantic Search**: Understands the meaning of your query, not just keyword matching
+- **Full-Text Access**: Returns complete drug information including mechanisms, interactions, and targets
+- **Image Links**: Includes molecular structures and data visualizations
+- **Comprehensive Coverage**: Access to all DrugBank drug data
+
+## Requirements
+
+1. Node.js 18+ (uses built-in fetch)
+2. Valyu API key from https://platform.valyu.ai ($10 free credits)
+
+## CRITICAL: Script Path Resolution
+
+The `scripts/search` commands in this documentation are relative to this skill's installation directory.
+
+Before running any command, locate the script using:
+
+```bash
+DRUGBANK_SCRIPT=$(find ~/.claude/plugins/cache -name "search" -path "*/drugbank-search/*/scripts/*" -type f 2>/dev/null | head -1)
+```
+
+Then use the full path for all commands:
+```bash
+$DRUGBANK_SCRIPT "ACE inhibitors" 15
+```
+
+## API Key Setup Flow
+
+When you run a search and receive `"setup_required": true`, follow this flow:
+
+1. **Ask the user for their API key:**
+   "To search DrugBank, I need your Valyu API key. Get one free ($10 credits) at https://platform.valyu.ai"
+
+2. **Once the user provides the key, run:**
+   ```bash
+   scripts/search setup <api-key>
+   ```
+
+3. **Retry the original search.**
+
+## When to Use This Skill
+
+- Comprehensive drug information lookup
+- Drug interactions and side effects research
+- Target identification and validation
+- Mechanism of action studies
+- Pharmacokinetics and pharmacodynamics research
+- Drug metabolism and adverse event data
+## Output Format
+
+```json
+{
+  "success": true,
+  "type": "drugbank_search",
+  "query": "ACE inhibitors",
+  "result_count": 10,
+  "results": [
+    {
+      "title": "Drug Name",
+      "url": "https://drugbank.com/...",
+      "content": "Drug information, mechanism, interactions...",
+      "source": "drugbank",
+      "relevance_score": 0.95,
+      "images": ["https://example.com/structure.png"]
+    }
+  ],
+  "cost": 0.025
+}
+```
+
+## Processing Results
+
+### With jq
+
+```bash
+# Get drug names
+scripts/search "query" 10 | jq -r '.results[].title'
+
+# Get URLs
+scripts/search "query" 10 | jq -r '.results[].url'
+
+# Extract full content
+scripts/search "query" 10 | jq -r '.results[].content'
+```
+
+## Common Use Cases
+
+### Drug Information
+
+```bash
+# Find drug details
+scripts/search "metformin pharmacokinetics" 50
+```
+
+### Drug Interactions
+
+```bash
+# Search for interactions
+scripts/search "CYP3A4 inhibitor drug interactions" 20
+```
+
+### Mechanism Research
+
+```bash
+# Find mechanism data
+scripts/search "selective serotonin reuptake inhibitors mechanism" 15
+```
+
+### Target Identification
+
+```bash
+# Search for drug targets
+scripts/search "drugs targeting BCR-ABL fusion protein" 25
+```
+
+
+## Error Handling
+
+All commands return JSON with `success` field:
+
+```json
+{
+  "success": false,
+  "error": "Error message"
+}
+```
+
+Exit codes:
+- `0` - Success
+- `1` - Error (check JSON for details)
+
+## API Endpoint
+
+- Base URL: `https://api.valyu.ai/v1`
+- Endpoint: `/search`
+- Authentication: X-API-Key header
+
+## Architecture
+
+```
+scripts/
+├── search          # Bash wrapper
+└── search.mjs      # Node.js CLI
+```
+
+Direct API calls using Node.js built-in `fetch()`, zero external dependencies.
+
+## Adding to Your Project
+
+If you're building an AI project and want to integrate DrugBank Search directly into your application, use the Valyu SDK:
+
+### Python Integration
+
+```python
+from valyu import Valyu
+
+client = Valyu(api_key="your-api-key")
+
+response = client.search(
+    query="your search query here",
+    included_sources=["valyu/valyu-drugbank"],
+    max_results=20
+)
+
+for result in response["results"]:
+    print(f"Title: {result['title']}")
+    print(f"URL: {result['url']}")
+    print(f"Content: {result['content'][:500]}...")
+```
+
+### TypeScript Integration
+
+```typescript
+import { Valyu } from "valyu-js";
+
+const client = new Valyu("your-api-key");
+
+const response = await client.search({
+  query: "your search query here",
+  includedSources: ["valyu/valyu-drugbank"],
+  maxResults: 20
+});
+
+response.results.forEach((result) => {
+  console.log(`Title: ${result.title}`);
+  console.log(`URL: ${result.url}`);
+  console.log(`Content: ${result.content.substring(0, 500)}...`);
+});
+```
+
+See the [Valyu docs](https://docs.valyu.ai) for full integration examples and SDK reference.

package/data/skills/ehr-fhir-integration/SKILL.md

@@ -0,0 +1,60 @@
+<!--
+# COPYRIGHT NOTICE
+# This file is part of the "Universal Biomedical Skills" project.
+# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
+# All Rights Reserved.
+#
+# This code is proprietary and confidential.
+# Unauthorized copying of this file, via any medium is strictly prohibited.
+#
+# Provenance: Authenticated by MD BABU MIA
+
+-->
+
+---
+name: 'ehr-fhir-integration'
+description: 'Provides comprehensive tools for working with Electronic Health Records (EHR) using the HL7 FHIR standard.'
+measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes.
+allowed-tools:
+  - read_file
+  - run_shell_command
+---
+
+
+# EHR/FHIR Integration
+
+The **EHR/FHIR Integration Skill** enables AI agents to interact with FHIR servers to search, read, and analyze clinical data.
+
+## When to Use This Skill
+
+*   When you need to retrieve patient demographics, conditions, medications, or lab results from an EHR.
+*   When performing population health analysis on a cohort of patients.
+*   When validating clinical data against the FHIR R4 standard.
+
+## Core Capabilities
+
+1.  **Patient Search**: Find patients by name, birthdate, or ID.
+2.  **Clinical Data Retrieval**: Fetch Conditions, Observations, MedicationRequests, and Procedures.
+3.  **Data Export**: Export clinical data to JSON or Pandas-ready formats.
+
+## Workflow
+
+1.  **Configure**: Set up the FHIR server URL and authentication (if needed).
+2.  **Execute**: Run the `fhir_client.py` script with the desired resource and parameters.
+
+## Example Usage
+
+**User**: "Find patient John Smith born after 1980."
+
+**Agent Action**:
+```bash
+python3 Skills/Clinical/EHR_FHIR_Integration/fhir_client.py \
+    --server https://hapi.fhir.org/baseR4 \
+    --resource Patient \
+    --search "name=Smith&birthdate=gt1980-01-01" \
+    --output patients.json
+```
+
+
+
+<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->