Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

28 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸ§ͺ ChemScope

AI-Powered Molecular Analysis & Drug Discovery Platform

React FastAPI Python RDKit License

ChemScope is a modern web platform for molecular visualization, cheminformatics, and AI-assisted drug discovery. It enables researchers, students, and chemists to analyze molecules using molecular descriptors, drug-likeness filters, molecular fingerprints, dimensionality reduction, clustering, and interactive visualizations.


πŸš€ Features

πŸ”¬ Molecular Analysis

  • Search molecules by name or SMILES
  • Automatic structure resolution using PubChem
  • Molecular descriptor calculation
  • Drug-likeness evaluation

Calculated Properties

  • Molecular Weight
  • LogP
  • TPSA
  • Hydrogen Bond Donors
  • Hydrogen Bond Acceptors
  • Rotatable Bonds
  • Synthetic Accessibility
  • QED Score
  • PAINS Alerts

πŸ’Š Drug Discovery Filters

ChemScope evaluates compounds using industry-standard filters.

βœ… Lipinski Rule of Five

βœ… Veber Rule

βœ… Ghose Filter

βœ… QED

βœ… PAINS Screening


🧬 Molecular Fingerprints

Supports:

  • Morgan Fingerprints
  • MACCS Keys
  • Tanimoto Similarity

πŸ“Š Data Visualization

Interactive charts built with Plotly.

Current visualizations include:

  • Molecular Descriptor Charts
  • Drug-likeness Summary
  • Fingerprint Information

Upcoming:

  • PCA
  • UMAP
  • t-SNE
  • Radar Charts
  • Similarity Networks

πŸ§ͺ Machine Learning (Upcoming)

  • QSAR Models
  • Toxicity Prediction
  • Solubility Prediction
  • Bioactivity Prediction
  • Molecular Clustering
  • Similarity Search
  • AI Property Prediction

πŸ›  Tech Stack

Frontend

  • React
  • Vite
  • Bootstrap
  • Axios
  • Plotly.js
  • 3Dmol.js

Backend

  • FastAPI
  • RDKit
  • Pandas
  • NumPy
  • Scikit-Learn
  • Requests

πŸ“‚ Project Structure

ChemScope
β”‚
β”œβ”€β”€ frontend
β”‚   β”œβ”€β”€ src
β”‚   β”œβ”€β”€ public
β”‚   └── package.json
β”‚
β”œβ”€β”€ backend
β”‚   β”œβ”€β”€ main.py
β”‚   β”œβ”€β”€ requirements.txt
β”‚   └── verify_pca.py
β”‚
└── README.md

βš™ Installation

Clone Repository

git clone https://github.com/Bhvya11singh/ChemScope.git

cd ChemScope

Backend Setup

Create a virtual environment

python -m venv venv

Activate it

Windows

venv\Scripts\activate

Linux / Mac

source venv/bin/activate

Install dependencies

pip install -r requirements.txt

Run backend

uvicorn main:app --reload

Backend runs at

http://127.0.0.1:8000

Frontend Setup

cd frontend

Install packages

npm install

Run

npm run dev

Frontend runs at

http://localhost:5173

API Endpoints

Health Check

GET /

Analyze Molecule

GET /analyze/{compound}

Example

/analyze/Aspirin

or

/analyze/CCO

Returns

  • Molecular descriptors
  • Fingerprints
  • Drug-likeness filters
  • QED
  • Synthetic accessibility
  • PAINS alerts

PCA

POST /pca

Input

CSV dataset

Output

  • Principal Components
  • Explained Variance

Screenshots

Home Page

Screenshot 2026-07-02 141611 Screenshot 2026-07-02 141625

Molecular Workspace

Screenshot 2026-07-02 141644 Screenshot 2026-07-02 141658

Analysis Dashboard

Screenshot 2026-07-02 141829 Screenshot 2026-07-02 141739

Roadmap

βœ… Completed

  • Molecular Search
  • Drug-Likeness Rules
  • Descriptor Calculation
  • Molecular Fingerprints
  • FastAPI Backend
  • Plotly Charts

🚧 In Progress

  • Interactive 2D Molecule Viewer
  • Interactive 3D Viewer
  • PCA Visualization
  • Clustering

πŸ”œ Upcoming

  • UMAP
  • t-SNE
  • QSAR Models
  • Toxicity Prediction
  • Solubility Prediction
  • Similarity Search
  • Molecular Docking Integration
  • AI Chat Assistant

Why ChemScope?

ChemScope combines modern web technologies with cheminformatics to create an intuitive molecular analysis platform suitable for:

  • Students
  • Researchers
  • Pharmaceutical Scientists
  • Computational Chemists
  • Drug Discovery Teams

The goal is to make computational chemistry tools more accessible through an interactive web interface.


Future Vision

ChemScope aims to evolve into a complete AI-powered drug discovery platform featuring:

  • Protein visualization
  • Molecular docking
  • Virtual screening
  • Deep Learning QSAR
  • Explainable AI
  • Multi-omics integration
  • Cloud deployment

Contributing

Contributions are welcome.

Fork the repository

Create a feature branch

git checkout -b feature-name

Commit changes

git commit -m "Added new feature"

Push

git push origin feature-name

Create a Pull Request.


License

This project is licensed under the MIT License.


Author

Bhavya Singh

B.Tech Mathematics & Computing

Interested in

  • AI for Drug Discovery
  • Machine Learning
  • Computational Chemistry
  • Mathematical Modeling
  • Scientific Computing

GitHub:

https://github.com/Bhvya11singh


⭐ If you found this project useful, consider giving it a star!

About

An AI-powered cheminformatics platform for molecular analysis, visualization, and drug-likeness prediction using React, FastAPI, and RDKit.

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages