4 Comments
User's avatar
Dom's avatar

Interesting results. Have you tried a train/test split where you hold out one protein family for validation, while training the model on the rest? e.g. train on all non-kinases, then validate on a kinase

Expand full comment
Armand B. Cognetta III's avatar

Epic

Expand full comment
Kevin Lerner's avatar

Very nice! Do you think this predictive modeling can translate to small molecule metabolism? It seems like a logical step to me… if you can predict small molecule binding based on amino acid sequence and chemical formula, may you be able to go one step further and determine if that chemical formula is altered based on the binding event?

Expand full comment
Andrew Blevins's avatar

The dream is that we keep improving this general binding model, and then we can get smaller datasets and fine-tune on those problems. A model that truly learns how to think about how molecules and proteins interacts, should need less data to understand these similar tasks.

Expand full comment