Industry panel for students at University of Washington
It was a great pleasure to participate in the industry panel at the one-day Connectome conference, organized by the UW Computational Neuroscience Center (CNC). I enjoyed sharing my journey from computational neuroscience to biotechnology and AI, including my current work at SandboxAQ. It was especially meaningful to speak with the students about the many different career paths that can follow graduate training in neuroscience: from wearable neurotechnology, to AI and deep lea
Predicting binding affinity
I wanted to share a small personal project I have been working on: an end-to-end machine learning pipeline for protein–ligand binding prediction. The question I wanted to explore was: Can protein foundation model embeddings, combined with molecular fingerprints, help predict whether a small molecule is likely to bind a protein? In this project, I used ESM-2 to generate protein sequence embeddings and combined them with ligand representations such as Morgan fingerprints, MACCS
