Lab notebook

Blog

Short, dated notes on what I'm reading, building, and getting wrong — closer to a lab notebook than a polished essay series. Subscribe via RSS.


Why metric learning for binding affinity, and not direct regression

Most binding-affinity models I looked at before starting BALM-PPI treat the problem as direct regression: concatenate two protein embeddings, feed them into an MLP, and predict ...

Starting this notebook

I’ve wanted a place to write down the smaller stuff for a while - the negative results, the “why is this LoRA config not converging” evenings, the papers I read on the metro. Pu...