Sarthak

Over the past month, I haven’t really had the time to work on this project. But because of the winter break, I made some progress.

For one, I learned about Jupyter Notebook. One of the things I had to do was find a way to simulate a molecule so I can actually see it.

I’ve attached a screenshot of a Jupyter Notebook converting embeddings and displaying a random molecule (that probably doesn’t exist).

I finished up the API calls from Uniprot, Pubchem and CARD. I also worked on the code that successfully transforms the database data into protein embeddings. Currently, I’m working on the diffusion model itself.

This project is pretty research heavy, so I researched a bit online and accordingly designed the file structure.

I also finished writing the code for the api request part. It can now successfully connect to 2 external databases and 1 local one!

I also need to learn about sqlite because this plays a key role in my project.

Currently working on the code which asks for API requests.