Skip to content

Kernel-Science/metascience_platform

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

18 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

FQxI Metascience Platform

A comprehensive open-source research analysis platform combining a modern Next.js frontend with a powerful Python/FastAPI backend to help academics, researchers, and curious individuals understand scientific literature through AI-driven insights and analytics.

License: MIT

Try it here https://metascience.fqxi.org

🌟 Overview

The Metascience Platform consists of two main components working together:

  1. Frontend (/frontend): A Next.js 15 application providing an intuitive interface for searching papers, visualizing citation networks, and viewing AI-generated insights.
  2. Backend (/backend): A Python/FastAPI service that integrates with multiple academic data sources (ArXiv, OpenAlex, Semantic Scholar) and AI models (Claude 4.5 Sonnet, Google Gemini 3 Flash) to power the analysis.

Key Features

  • πŸ” Multi-Database Search: Unified search across ArXiv, Semantic Scholar, and OpenAlex.
  • πŸ€– AI-Driven Insights: Natural language query processing and automated paper reviews using Claude 4.5 Sonnet and Gemini 3 Flash.
  • πŸ•ΈοΈ Citation Network Analysis: Visualize relationships between papers and identify influential research.
  • πŸ“Š Advanced Analytics: Trend discovery, author collaboration networks, and key metrics.

πŸš€ Quick Start

Prerequisites

  • Node.js: 18.x or higher
  • Python: 3.11+ or 3.13+
  • pnpm (recommended) or npm/yarn
  • Anthropic API Key (for AI features)
  • Google API Key (for Gemini features)

Installation & Setup

Clone the repository:

git clone https://github.com/Kernel-Science/Metascience_Platform.git
cd Metascience_Platform

1. Backend Setup

Navigate to the backend directory and start the server:

cd backend
python -m venv .venv
source .venv/bin/activate  # Windows: .\.venv\Scripts\Activate.ps1
pip install -r requirements.txt

# Configure environment
cp .env.example .env
# Edit .env to add your ANTHROPIC_API_KEY and GOOGLE_API_KEY

# Start the server
uvicorn app.main:app --reload

The backend API will be available at http://localhost:8000.

2. Frontend Setup

In a new terminal, navigate to the frontend directory:

cd frontend
pnpm install

# Configure environment
cp .env.example .env.local
# Add required environment variables (e.g., Supabase config if needed)

# Start the development server if you want the next.js controls visible on the frontend
pnpm dev
# If running in prod, build and serve the static files
pnpm build
pnpm start

Open http://localhost:3000 to view the application.

πŸ“ Repository Structure

metascience-platform/
β”œβ”€β”€ frontend/           # Next.js Frontend Application
β”‚   β”œβ”€β”€ app/            # Application routes and pages
β”‚   β”œβ”€β”€ components/     # UI Components
β”‚   └── ...
β”œβ”€β”€ backend/            # FastAPI Backend Service
β”‚   β”œβ”€β”€ app/            # Application logic (routes, services)
β”‚   β”œβ”€β”€ services/       # AI & Data integrations
β”‚   └── ...
└── README.md           # This file

πŸ“š Documentation

For detailed documentation on each component, please refer to their respective README files:

🀝 Contributing

Contributions are welcome! Please read the Contributing Guidelines and our Code of Conduct.

πŸ“„ License

This project is licensed under the MIT License.

πŸ›‘οΈ Security

To report a security vulnerability, please see our Security Policy.

About

Metascience Platform by Kernel Science SRL for FQXI

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors