🚀 Space Biology Knowledge Engine

Welcome to the Space Biology Knowledge Engine, a web application designed to explore, search, and analyze decades of NASA's space biology research. This project was built for the NASA Space Apps Challenge.

Our engine transforms a simple CSV list of publications into a rich, interactive, and AI-summarized database, making complex scientific discoveries more accessible to researchers, students, and enthusiasts alike.

🚀 Live Demo

You can view the live project deployment here:

https://zen-1.vercel.app/

---

✨ Key Features

• AI-Powered Summaries: Leverages the Google Gemini AI to read research papers and generate concise, easy-to-understand summaries, categories, and keywords.
• Robust Data Pipeline: A powerful Node.js script uses a headless browser (Puppeteer) to reliably scrape publication data, processes it with AI, and builds a rich JSON database from a simple CSV source.
• Advanced Search & Filtering: Instantly search through hundreds of publications by title or keyword, and filter by specific research categories.
• Thematic UI: A beautiful, responsive interface with a custom-animated "space biology" background, available in both light and dark themes.
• Detailed Research View: Click on any research card to open a detailed modal with the AI summary and a direct link to the full publication on the NCBI website.
• Resilient Data Processing: The data generation script is built to be robust, featuring automatic retries, batch processing, and an API key pool to manage rate limits.

---

🛠️ Technology Stack

Frontend

• Framework: React
• Language: TypeScript
• Build Tool: Vite
• Styling: Tailwind CSS
• Icons: Lucide React

Data Processing & AI

• Runtime: Node.js
• AI Model: Google Gemini
• Web Scraping: Puppeteer & Cheerio
• CSV Parsing: Papaparse
• API Key Management: Dotenv

---

⚙️ Getting Started

Follow these instructions to get a copy of the project up and running on your local machine.

Prerequisites

• Node.js (version 20.x or higher recommended)
• npm (comes with Node.js)
• Google Account(s) to generate Gemini API keys.

1. Installation

Clone the repository to your local machine:

git clone https://github.com/parmarth-kumar/Zen-1.git
cd Zen-1

Install the required npm packages:

npm install

2. Configuration (API Keys)

This project requires API keys from Google AI to power the data generation script.

1. Generate API Keys: Have each team member go to Google AI Studio and create a free API key.

2. Create .env file: In the root of the project, create a file named .env.

3. Add Keys: Open the .env file and add your keys as a comma-separated list.

   GEMINI_API_KEYS=key_from_person_1,key_from_person_2,key_from_person_3
   

3. Data Generation

The application's data is generated by a script that reads the SB_publication_PMC.csv file and processes it with AI. You only need to do this once.

1. Run the Script: In your terminal, run the script. It will process one batch of articles.

   node scripts/generate-dataset.js

2. Repeat: Run the same command again. The script will automatically pick up where it left off.
   • Note: This script is slow but reliable as it uses a real browser. You will need to run it repeatedly over several sessions to process all 600+ articles due to API rate limits.

The final data will be saved in src/data/ai-generated-data.json.

4. Running the Application

Once the data generation is complete, you can run the web application.

npm run dev

Open your browser and navigate to the local URL provided (usually http://localhost:5173).

---

🙏 Acknowledgements

• Data Source: This project uses the "Space Biology Publications" dataset provided by NASA GeneLab. It can be found here.
• Team: Built with ❤️ by ZeN-1.

---

📜 License

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