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.
- Search molecules by name or SMILES
- Automatic structure resolution using PubChem
- Molecular descriptor calculation
- Drug-likeness evaluation
- Molecular Weight
- LogP
- TPSA
- Hydrogen Bond Donors
- Hydrogen Bond Acceptors
- Rotatable Bonds
- Synthetic Accessibility
- QED Score
- PAINS Alerts
ChemScope evaluates compounds using industry-standard filters.
β Lipinski Rule of Five
β Veber Rule
β Ghose Filter
β QED
β PAINS Screening
Supports:
- Morgan Fingerprints
- MACCS Keys
- Tanimoto Similarity
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
- QSAR Models
- Toxicity Prediction
- Solubility Prediction
- Bioactivity Prediction
- Molecular Clustering
- Similarity Search
- AI Property Prediction
- React
- Vite
- Bootstrap
- Axios
- Plotly.js
- 3Dmol.js
- FastAPI
- RDKit
- Pandas
- NumPy
- Scikit-Learn
- Requests
ChemScope
β
βββ frontend
β βββ src
β βββ public
β βββ package.json
β
βββ backend
β βββ main.py
β βββ requirements.txt
β βββ verify_pca.py
β
βββ README.md
git clone https://github.com/Bhvya11singh/ChemScope.git
cd ChemScopeCreate a virtual environment
python -m venv venvActivate it
Windows
venv\Scripts\activateLinux / Mac
source venv/bin/activateInstall dependencies
pip install -r requirements.txtRun backend
uvicorn main:app --reloadBackend runs at
http://127.0.0.1:8000
cd frontendInstall packages
npm installRun
npm run devFrontend runs at
http://localhost:5173
GET /
GET /analyze/{compound}
Example
/analyze/Aspirin
or
/analyze/CCO
Returns
- Molecular descriptors
- Fingerprints
- Drug-likeness filters
- QED
- Synthetic accessibility
- PAINS alerts
POST /pca
Input
CSV dataset
Output
- Principal Components
- Explained Variance
- Molecular Search
- Drug-Likeness Rules
- Descriptor Calculation
- Molecular Fingerprints
- FastAPI Backend
- Plotly Charts
- Interactive 2D Molecule Viewer
- Interactive 3D Viewer
- PCA Visualization
- Clustering
- UMAP
- t-SNE
- QSAR Models
- Toxicity Prediction
- Solubility Prediction
- Similarity Search
- Molecular Docking Integration
- AI Chat Assistant
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.
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
Contributions are welcome.
Fork the repository
Create a feature branch
git checkout -b feature-nameCommit changes
git commit -m "Added new feature"Push
git push origin feature-nameCreate a Pull Request.
This project is licensed under the MIT License.
B.Tech Mathematics & Computing
Interested in
- AI for Drug Discovery
- Machine Learning
- Computational Chemistry
- Mathematical Modeling
- Scientific Computing
GitHub:
https://github.com/Bhvya11singh
β If you found this project useful, consider giving it a star!