|
|
--- |
|
|
title: MCP Res |
|
|
emoji: 📊 |
|
|
colorFrom: red |
|
|
colorTo: gray |
|
|
sdk: docker |
|
|
sdk_version: 1.46.0 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
short_description: Research |
|
|
--- |
|
|
|
|
|
MedGenesis AI 🧬 |
|
|
Unified Biomedical Research Assistant—AI, Literature, Safety & Knowledge Graphs |
|
|
|
|
|
🚀 Overview |
|
|
MedGenesis AI is the next-generation biomedical research assistant that unifies PubMed, arXiv, UMLS, OpenFDA, and advanced AI (OpenAI GPT-4o) into one seamless platform. |
|
|
Discover, synthesize, and visualize research, drugs, concepts, and safety—all in a single app. |
|
|
|
|
|
Semantic search across top biomedical databases |
|
|
|
|
|
UMLS concept mapping and standardization |
|
|
|
|
|
Drug safety insights powered by OpenFDA |
|
|
|
|
|
AI-powered summaries and follow-up Q&A |
|
|
|
|
|
Interactive knowledge graph for instant relationship exploration |
|
|
|
|
|
Export results as PDF or CSV |
|
|
|
|
|
Workspace to save and revisit your research sessions |
|
|
|
|
|
✨ Key Features |
|
|
Unified Search: Find and aggregate results from PubMed and arXiv, ranked by semantic similarity. |
|
|
|
|
|
Biomedical Concept Augmentation: Map results to UMLS concepts for standardized knowledge. |
|
|
|
|
|
Drug & Safety Insights: Connect literature with latest FDA safety data. |
|
|
|
|
|
AI-Powered Synthesis: Summarize, answer questions, and suggest next research steps using GPT-4o. |
|
|
|
|
|
Knowledge Graph: Visual, interactive network of papers, drugs, and concepts. |
|
|
|
|
|
Export & Workspace: Download data, save sessions, and organize your findings. |
|
|
|
|
|
🖥️ Live Demo |
|
|
Try the app on Hugging Face Spaces |
|
|
|
|
|
🐳 Docker-Based Deployment |
|
|
MedGenesis AI uses a Dockerfile for guaranteed reproducibility and robust dependency management. |
|
|
|
|
|
Run Locally: |
|
|
bash |
|
|
Copy code |
|
|
git clone https://huggingface.co/spaces/MCP_Res |
|
|
cd YOUR_REPO |
|
|
docker build -t medgenesis-ai . |
|
|
docker run -p 7860:7860 medgenesis-ai |
|
|
Then open http://localhost:7860 in your browser. |
|
|
|
|
|
On Hugging Face Spaces: |
|
|
Make sure your Dockerfile, requirements.txt, and app.py are present in your repo root. |
|
|
|
|
|
Push all code to your Space. |
|
|
|
|
|
In the Space settings, select "Docker" as the runtime. |
|
|
|
|
|
Your Space will build and launch automatically. |
|
|
|
|
|
⚡ Quick Start (Streamlit UI) |
|
|
Enter a biomedical research question. |
|
|
|
|
|
Click Run Search to query all sources. |
|
|
|
|
|
Explore: |
|
|
|
|
|
Results: Detailed, AI-synthesized findings. |
|
|
|
|
|
Knowledge Graph: Interactive visualization. |
|
|
|
|
|
Visualizations: Year histogram and more. |
|
|
|
|
|
Download results or save to your workspace. |
|
|
|
|
|
Ask follow-up questions with the integrated AI assistant. |
|
|
|
|
|
🛠️ Customization |
|
|
Add new data sources by extending mcp/ utilities. |
|
|
|
|
|
Update color/theme in .streamlit/config.toml. |
|
|
|
|
|
Want to run in SDK mode? Simply remove the Dockerfile and deploy with requirements.txt as usual. |
|
|
|
|
|
Use the built-in workspace to organize your research projects. |
|
|
|
|
|
🤝 Contributing |
|
|
Pull requests, bug reports, and feature suggestions are welcome! |
|
|
For large features, open an issue first to discuss your ideas. |
|
|
|
|
|
🧑💻 Author |
|
|
Oluwafemi Idiakhoa |
|
|
|
|
|
📝 License |
|
|
MIT License |
|
|
|
|
|
❤️ Acknowledgments |
|
|
Hugging Face Spaces |
|
|
|
|
|
PubMed, arXiv, OpenFDA, UMLS |
|
|
|
|
|
OpenAI GPT-4o |
|
|
|
|
|
The open-source biomedical AI community |
|
|
|
|
|
🔗 Links |
|
|
MedGenesis AI Space |
|
|
|
|
|
OpenFDA |
|
|
|
|
|
UMLS |
|
|
|
|
|
arXiv |
|
|
|
|
|
PubMed |
|
|
|
|
|
Note on Docker |
|
|
If you’re using Docker, all dependencies (including Jinja2, pyvis) are installed as specified in the Dockerfile and requirements.txt—no extra setup needed. |
|
|
If deploying with Hugging Face SDK mode, ensure your requirements.txt matches your dependencies. |
