Halfway there!

This past week, I completed my original work portfolio! It was gratifying to see the conclusion of a semester’s worth of research and development, especially since the final product was a pretty binder. I’m happy that I started early with my code and designing my website, because it was a lot of work even with a template. Early on, I knew that it would probably take me more than 12 hours for my original work, and I guessed right. However, it was worth it because I feel like I learned so much from the experience, and I’m looking forward to applying that knowledge second semester. I’ve already decided to work on a TDCommons dataset, probably toxicity, and try to maximize performance on it. The difficult part will be featurizing the data, which is originally available in SMILES string format. This means that I will have to find a way to transform text descriptions of chemical structure into useful predictors of toxicity, like the presence of various functional groups. From there, my mentor suggested using an AutoML solution as a jumping-off point to simplify things. That will take more of the coding out of it but will allow me to do more of the chemistry part. I made sure to decide on this before Winter Break so that I’ll have something to do when I’m bored. I’m happy that the break is only 4 days away, and I’m looking forward to our ISM gift exchange and etiquette lunch before we leave on vacation!