Patrick Bryant
Patrick Bryant
Hi, I find the relationship odd. When normalising by population, the curves seem to coincide. I pulled this data yesterday, have you changed it since?  Normalized by 100'000 population...
I noticed, this seems to work with afdb_rep_v4. Perhaps something is missing from the reference genomes?
Hi, Great - thanks. What do you mean with the latest version: 1. Of the database from https://foldcomp.steineggerlab.workers.dev 2. Of Foldcomp 3. Something else(?)
Ok, great. Does this include the binaries you distribute or only the pip installation/git clone? Do you know why mmseqs2 seems to fail on the same files? Is there something...
Ok, thanks for the help!
Hi, you can skip these packages (they are not needed). There's also a pip list with the requirements. We will try to update the environment to avoid these warnings shortly....
Hi, Yes, this would be great. Different users have different requirements, but most seem to like Honda that's why we stick to this. Thanks for the docker recommendation though. Best,...
Hi, Try this: pip install --upgrade "jax[cuda12_pip]" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html pip install --upgrade dm-haiku
You can also try: pip install --upgrade "jax[cuda12_local]" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
Hi, We appreciate that you have made MoLPC work. However, there are more things to consider if the build is to be based on CUDA12 related to HHblits which is...