This is one of the project from the 2019 internship at GSI Technology. This project focuses on the topic of cheminformatics, specifically, molecule similarity search.
There are detailed instructions in each notebook.
Notebook1 contains introductions to:
- Module RDKit
- Similarity Search (Tanimoto)
- Loading cheEMBL database
Notebook2 contains introductions to:
- Word2Vec
- Mol2Vec
- Morgan Fingerprints
- Similarity Distances
- Tanimoto
- Cosine
- Visualizations and Comparisons
For more details on this project, please visit the blogs: