A next-generation AI platform for pharmaceutical research, drug discovery, and molecular optimization.
MediAI Discovery Platform combines modern web technologies with pharmaceutical research APIs to provide tools for:
- Drug modification suggestions
- Molecular visualization
- Property prediction
- Interactive chat interface for research queries
- Node.js 18+ and npm
- Python 3.9+ (for RDKit integration)
- Docker (optional, for containerized RDKit service)
- Clone the repository:
git clone https://github.com/yourusername/medical-ai-platform.git
cd medical-ai-platform- Install dependencies:
npm install- Create a
.envfile from the template:
cp .env.example .env- Add your API keys to the
.envfile:
# PubChem doesn't require an API key
IBM_RXN_API_KEY=your_ibm_rxn_key_here
# Enable RDKit if you're running the Python service
ENABLE_PYTHON_RDKIT=false
- Start the Next.js development server:
npm run dev- Optional: Start the RDKit Python service (if using)
# Install Python dependencies
cd app/api/rdkit/python
pip install -r requirements.txt
# Start the Flask server
python app.py- Alternative: Run the RDKit service in Docker
cd app/api/rdkit/python
docker build -t rdkit-service .
docker run -p 3001:3001 rdkit-service- Enable RDKit integration by setting
ENABLE_PYTHON_RDKIT=truein your.envfile
For full functionality, you'll need to register for the following services:
-
PubChem (Free, no API key required)
- Documentation at: https://pubchemdocs.ncbi.nlm.nih.gov/pug-rest
- Usage policy: Keep requests under 5 per second to avoid being temporarily blocked
-
IBM RXN for Chemistry (Free tier available)
- Register at: https://rxn.res.ibm.com/
- Get your API key from your account settings
-
SwissADME (Free web service)
- No official API, but our platform includes a wrapper
-
RDKit Python Backend
- Set
ENABLE_PYTHON_RDKIT=truein your.envfile - Requires the Python service to be running
- Set
- Chat Interface: Ask questions about drug modifications and improvements
- Molecule Visualization: View molecular structures as SVG images
- Drug Modification Suggestions: Get AI-powered suggestions for improving drug properties
- API Integration: Connect with multiple pharmaceutical research APIs
- IBM RXN Integration: Predict reaction products and assess synthetic feasibility
Additional configuration options in .env:
# Debug mode for additional logging
ENABLE_DEBUG_MODE=true
# RDKit Python service URL (if running on a different host/port)
RDKIT_SERVICE_URL=http://localhost:3001
# Base URL override for development
NEXT_PUBLIC_API_BASE_URL=http://localhost:3000
This project is licensed under the MIT License - see the LICENSE file for details.