{"id":40,"date":"2024-04-20T07:54:00","date_gmt":"2024-04-20T07:54:00","guid":{"rendered":"http:\/\/rarathemesdemo.com\/perfect-portfolio\/?post_type=rara-portfolio&p=40"},"modified":"2024-08-06T00:04:38","modified_gmt":"2024-08-06T00:04:38","slug":"molecular-graph-generation-vae","status":"publish","type":"rara-portfolio","link":"https:\/\/alex-jimenez.com\/?rara-portfolio=molecular-graph-generation-vae","title":{"rendered":"Molecular Graph Decomposition"},"content":{"rendered":"\n

Source Code: GitHub<\/a><\/h3>\n\n\n\n

Motivation Behind the Project<\/strong><\/p>\n\n\n\n

The inspiration for this project is from the following paper: Junction Tree Variational Autoencoder for Molecular Graph Generation by Jin et al.<\/em> I wanted to recreate the work done by Jin et al<\/a> to explore junction trees, chem-informatics, and test my coding abilities. The outcome of the decomposition is not identical to Jin et al’s representation, but that’s because I wanted to do this from scratch and likely some design decisions differed. This package could be used in the future as a feature-rich input for machine learning. I see some major advantages to this type of decomposition for Transformers. <\/p>\n\n\n\n

Math Decomposition<\/h2>\n\n\n
\n
\"\"
Figure 1<\/strong>: SMILES Decomposition<\/figcaption><\/figure><\/div>\n\n\n

This project is a Python package that takes chemical SMILES and encodes them into a graph structure using a variety of chemical properties and preprocessing techniques below is an example of what a SMILE projection of a molecule might look like. Background on SMILES can be found here<\/a>. <\/p>\n\n\n\n

The target format of our data looks much different than our SMILES representation. Before we show what this format will look like, here is a list of properties used to decompose a molecule into its unique aspects.<\/p>\n\n\n\n

Chemical Properties<\/h4>\n\n\n\n