Update README.md

README.md

@@ -10,120 +10,102 @@ 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:
+MedGenesis AI
+MedGenesis AI is a biomedical literature discovery workbench that unifies live data from PubMed, arXiv, MyGene.info, ClinicalTrials.gov v2, DisGeNET, openFDA, Open Targets, DrugCentral, UMLS and more—then lets you explore the evidence in a rich Streamlit interface powered by OpenAI or Gemini LLMs.
+
+
+┌────────────────────────────────────────────┐
+│ Streamlit UI  (app.py)                    │
+│  • Results / Genes / Trials / Graph tabs   │
+│  • PDF / CSV export & follow-up Q&A        │
+└──────────────┬─────────────────────────────┘
+               │ async calls
+┌──────────────▼─────────────────────────────┐
+│ Orchestrator (mcp/orchestrator.py)         │
+│  • pulls PubMed, arXiv                     │
+│  • keyword extraction (spaCy)              │
+│  • fans-out to MyGene, CT.gov v2, UMLS…    │
+│  • merges & summarises with LLM            │
+└──────────────┬─────────────────────────────┘
+               │ helpers (mcp/*.py)
+               ▼
+┌────────────────────────────────────────────┐
+│ External APIs + local TSV (DrugBank)       │
+└────────────────────────────────────────────┘
+
+
+
+🔑 Features
+Domain	Source / API	What you get
+Literature	PubMed + arXiv	titles, abstracts, authors, year
+Gene info	MyGene.info + NCBI Gene	symbol, name, GO, ClinVar, MeSH definitions
+Trials	ClinicalTrials.gov v2	NCT ID, phase, status, start date
+Disease ↔ gene	DisGeNET	top associations & scores
+Drug safety	openFDA, DrugCentral	adverse events, approvals, MoA
+Graph edges	Open Targets GraphQL	gene–disease-drug links (+ OT score)
+Ontology	UMLS, HPO, Wikidata	concept CUI, phenotype look-ups
+
+🚀 Quick start
 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.
+Copy
+Edit
+# clone repo
+git clone https://github.com/your-org/medgenesis.git
+cd medgenesis
+
+# build & run locally
+python -m venv .venv && source .venv/bin/activate
+pip install -r requirements.txt
+python -m spacy download en_core_web_sm
+streamlit run app.py
+app.py starts a Streamlit server on localhost:8501.
+Enter a biomedical question (e.g. “CRISPR glioblastoma therapy”) and press Run Search 🚀.
+
+🐳 Docker / Hugging Face Space
+The included Dockerfile is CPU-only and downloads the spaCy model at build time:
 
-⚡ 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
+bash
+Copy
+Edit
+docker build -t medgenesis .
+docker run -p 7860:7860 -e OPENAI_API_KEY=sk-... medgenesis
+HF Spaces: push the repo, set the environment secrets below, and Spaces will pick up Dockerfile.
+
+🔐 Environment variables
+Variable	Description
+OPENAI_API_KEY	OpenAI account key (GPT-4o, GPT-4o-mini …)
+GEMINI_KEY	Google Generative AI key (Gemini 1.5 Flash)
+UMLS_KEY	UMLS Licensing key (ticket auth)
+DISGENET_KEY	DisGeNET Bearer token (optional)
+PUB_KEY	NCBI E-utils key (optional, boosts quota)
+BIO_KEY	NCBI E-utils key for Gene/MeSH (optional)
+
+Set them in .env, your shell, or HF Secrets.
+
+🗃️ Local data
+mcp/data/drugbank_open_structured_drug_links.tsv – DrugBank Open Data
+Download from the DrugBank Open-Data page and place it here.
+
+The file is lazy-loaded and cached; the app still works without it.
+
+🧪 Tests
+bash
+Copy
+Edit
+pytest tests/
+Unit tests mock external APIs and verify parsing, caching and orchestrator merges.
 
-🔗 Links
-MedGenesis AI Space
+🛠️ Contributing
+Fork & create a feature branch.
 
-OpenFDA
+Follow Conventional Commits for PR titles.
 
-UMLS
+Run pre-commit install to auto-format with black & ruff.
 
-arXiv
+Submit a PR; GitHub Actions will run lint + tests.
 
-PubMed
+📄 License
+Apache 2.0 – free for research and commercial use.
+API terms of each external provider still apply.
 
-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.
+Happy discovering!