Nadav Brandes

I'm not sure what's causing this. Maybe try to run this interactively (e.g. in Jupyter notebook) and see at what stage you run out of memory (you can use the...

This file is downloaded directly from the UKB. I'm pretty sure it's comma-delimited and not tab-delimited. Anyway, ukbb_parser assumes that the file is comma-delimited, but it should be very easy...

That's a general machine learning question not specifically related to ProteinBERT. I'd try asking in other ML communities.

At what stage of the process does your GPU memory start running out?

Hi @rdenise, `global_representations` is a 8943-dimensional vector, where each index corresponds to a specific GO annotation. Unfortunately, through a truly negligent act on our side, we have lost the file...

Hi @yelou2022, The global features predicted by ProteinBERT are GO annotations, whether or not it gets them as input. If it gets some GO annotations as input, then it's easier...

@srikrishnan-b I suppose that includes hidden layers via `get_model_with_hidden_layers_as_outputs`.

@namanm04 It's basically the exact same code, just run for the fine-tuned rather than base model.

Hi @rhysnewell, Again I really apologize for this, but we haven't yet been able to recover the ordering of the GO annotation vector or retrain the model. If you have...

1. Just to clarify, I didn't mean going over the GO annotations by hand, but rather writing a program to do it (but it still could be a lot of...