Christian Dallago

[WIP] Restructure and rewrite of structure and function predictions

25

Please: consider this a draft to see the direction I'm taking. Help would be very welcome! While writing, I noticed that the restructuring that was needed was more extensive than...

Update section: Protein secondary and tertiary structure

4

Hi. First: great idea :) I've noticed a bunch of people I follow on twitter bumping this up... I wasn't confident enough to contribute in the first iteration years ago,...

Future direction: embeddings for DNA and RNA

1

- DNA: https://www.biorxiv.org/content/10.1101/836163v1.full

Add merck/sapiens

1

https://github.com/merck/sapiens

https://huggingface.co/nferruz/ProtGPT2

It seems like the web-worker and pipeline images don't build on the same error. The webserver does. I assume the error is in thus somewhere in the Dockerfile? Unlucky dependencies...

Basically address the TODOs from 9a1d7574e793b98d720b5d005b1ff155e7fe6c85 , which are a fix to #156

Update stages and notebooks to account for original id in h5

4

Affected are visualize and extract. The most basic notebooks must be updated, too.

Remove embedders from GPU memory post-embed phase in pipeline

12

I once had a situation in which the pipeline was in a "visualize" stage, but the GPU was still occupied by the embedder (SeqVec). I had assumed that the embedder...

CI testing of the notebooks

3

#81 and #83 highlight something discussed a while ago, which is CI testing of notebooks and examples. The strategy up until now has been to manually test notebooks and examples...