Drug Repurposing Agent 💊🤖

A sophisticated multi-agent AI system for medical diagnosis, drug repurposing analysis, and clinical insights. This platform combines symptom prediction, medical knowledge retrieval, and clinical trial analysis to provide comprehensive healthcare intelligence.

🌟 Features

Multi-Agent Architecture

• Symptom Predictor: ML-based disease prediction from user-described symptoms
• Medical Knowledge Agent: RAG-powered medical information retrieval
• Clinical Trials Agent: Analysis of clinical trial data and drug efficacy
• Market Analysis Agent: Pharmaceutical market intelligence and forecasting
• Orchestrator: Intelligent routing and coordination between agents

Core Capabilities

• 🔍 3-Layer Medical System: Diagnosis → Knowledge → Triage workflow
• 🧠 RAG Integration: Vector database with medical literature (PubMed)
• 🛡️ Safety Validation: Medical integrity guards and audit logging
• 📊 Data-Driven: Operates strictly on curated medical datasets
• 🎯 Urgency Assessment: Triage system for medical condition prioritization

🏗️ Architecture

drug-repurposing-agent/
├── backend/              # FastAPI backend
│   ├── main.py          # API entry point
│   ├── models.py        # Database models
│   ├── routers/         # API endpoints
│   └── ...
├── frontend/            # React/TypeScript UI
│   ├── src/            # Source code
│   ├── public/         # Static assets
│   └── ...
├── agents/             # AI Agents system
│   ├── src/
│   │   ├── agents/     # Agent implementations
│   │   ├── core/       # Core functionality
│   │   ├── rag/        # RAG system
│   │   └── ...
│   ├── data/           # Medical datasets
│   └── docs/           # Agent documentation
└── docs/               # Project documentation

📋 Prerequisites

• Python 3.10+
• Node.js 18+
• Ollama (for local AI agents)
  • Install from ollama.com
  • Pull required model: ollama pull llama3

🚀 Installation

1. Clone the Repository

git clone https://github.com/yourusername/drug-repurposing-agent.git
cd drug-repurposing-agent

2. Backend Setup

# Install Python dependencies
pip install -r backend/requirements.txt

# Initialize database
python backend/init_db.py

3. Frontend Setup

cd frontend
npm install

4. Agents Setup

cd agents
pip install -r requirements.txt

5. Environment Configuration

Create a .env file in the root directory (use .env.example as template):

# Google Search Configuration
GOOGLE_API_KEY=your_google_api_key
GOOGLE_CSE_ID=your_google_cse_id

# AI Configuration
MISTRAL_API_KEY=your_mistral_api_key
GOOGLE_GENAI_KEY=your_google_genai_key
OPENROUTER_API_KEY=your_openrouter_api_key

# Ollama
OLLAMA_MODEL=llama3

# Database
DATABASE_URL=sqlite:///./medical.db

# JWT Secret
SECRET_KEY=your_secret_key_here

🎮 Usage

Start Ollama

Ensure Ollama is running:

ollama serve

Start the Backend

# From root directory
uvicorn backend.main:app --reload --host 127.0.0.1 --port 8000

API will be available at:

• API: http://127.0.0.1:8000
• Docs: http://127.0.0.1:8000/docs

Start the Frontend

# From frontend directory
cd frontend
npm run dev

Application will be available at: http://localhost:5173

🔌 API Endpoints

Agents

• POST /agents/query - Query the multi-agent system

  {
    "query": "What are the symptoms of diabetes?"
  }

Authentication

• POST /auth/register - Register new user
• POST /auth/login - User login
• GET /auth/me - Get current user

Medical Data

• GET /diseases - List diseases
• GET /symptoms - List symptoms
• POST /predict - Predict disease from symptoms

📊 Datasets

The system uses three core medical datasets:

1. symbipredict_cleaned.csv: Symptom-disease mappings for ML prediction
2. disease_knowledge_enriched.csv: Disease information, symptoms, precautions
3. synthetic_medical_triage.csv: Urgency assessment and triage data

🧪 Testing

Backend Tests

pytest backend/tests/

Agent Tests

cd agents
pytest tests/

📚 Documentation

• USAGE.md - Detailed usage instructions
• CHANGELOG.md - Version history
• agents/docs/ - Agent-specific documentation
  • AUDIT_LOG_FORMAT.md
  • DATA_QUALITY_CHECKLIST.md
  • INTEGRITY_GUARD_INTEGRATION.md

🛡️ Safety & Compliance

This system includes:

• Integrity Guards: Validates medical data quality
• Audit Logging: Tracks all agent interactions
• Safety Validators: Ensures responses meet medical standards
• Dataset-Driven: Operates strictly on curated medical data

⚠️ Disclaimer: This system is for research and educational purposes only. It is not a substitute for professional medical advice, diagnosis, or treatment.

🤝 Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Medical datasets from public health repositories
• LangChain for agent orchestration
• FastAPI for backend framework
• React for frontend framework
• Ollama for local LLM inference

📧 Contact

For questions or support, please open an issue on GitHub.

---

Built with ❤️ for advancing medical AI research