Christian Dallago comments

Results 89 comments of


                                            Christian Dallago

The relevent source/paper to cite for each method

Hi @Xinxinatg , thanks for bringing this up. It's been a long standing issue for me to rewamp the documentation and give proper credit to model authors. For the majority...

The relevent source/paper to cite for each method

@mheinzinger do you remember how that was done?

EZ viz of distance/attention?

CC @akirasosa ; thanks for the initial work :P this helps out a lot

ProteinBert Support?

Hi @ddofer , thanks for the ping. We atomicize the operations. So what you would propose has two components: 1. The embedder (gets a protein sequence --> returns a per-residue/protein...

Update stages and notebooks to account for original id in h5

This should be part of #125

Models (https://docs.bioembeddings.com/v0.1.6/api/bio_embeddings.embed.html) should document what options can be passed in kwargs, e.g. `model_directory` to pass model weights (potentially put link to data.bioembeddings?) or `weights_file` and `options_file` for SeqVec. CC @konstin

Documentation improvements

- The software engineer in me says by replacing **kwargs - The "I'm afraid by how many things we'll miss" in me says by doc comments Your opinion? I think...

Protocol unirep: ImportError: cannot import name 'cusolver' from 'jaxlib' (/mnt/lsf-nas-1/os-shared/anaconda3/envs/hannes_bio_embeddings/lib/python3.7/site-packages/jaxlib/init.py)

Probably related to #161

UniRep memory usage issue on CPU

I would wait for the maintainers of that repo to get back to you on [107](https://github.com/ElArkk/jax-unirep/issues/107). @tijeco : in the meantime, I would suggest you to use ESM-1b or ProtBert/T5

Getting basic disorder prediction scores

Hi @prihoda , thanks for the proposal :) I'd love to see more community effort into development of ~our~ **everyones!** tools, so yes: if you believe this is helpful, you...