search

theislab / scarches

Reference mapping for single-cell genomics
https://docs.scarches.org/en/latest/
BSD 3-Clause "New" or "Revised" License
328 stars 51 forks source link

Bioconda recipe #79

Open mjsteinbaugh opened 3 years ago

mjsteinbaugh commented 3 years ago

Would it be possible to publish this on Bioconda in addition to PyPi? I'm happy to help write and submit a recipe.

M0hammadL commented 3 years ago

HI @mjsteinbaugh , i would be happy if you submit the PR

mjsteinbaugh commented 3 years ago

OK great I'll work on that when I have some free time

M0hammadL commented 2 years ago

@Koncopd can we make Bioconda release?

mjsteinbaugh commented 2 years ago

I'll try to work on making this happen

M0hammadL commented 2 years ago

that would be great since we are releasing a new version next week

mjsteinbaugh commented 2 years ago

OK @M0hammadL I'll work on a draft recipe over the weekend

adamgayoso commented 2 years ago

@mjsteinbaugh is there a reason for bioconda as opposed to conda-forge? Most scanpy-related stuff is on conda-forge and I'm trying to move scvi-tools there right now.

mjsteinbaugh commented 2 years ago

Either should be fine although most bioinformatics tools, including single-cell genomics utilities, are currently on bioconda

adamgayoso commented 2 years ago

I always found it harder to get anything updated quickly with bioconda unfortunately. I like that conda-forge seems to have better infrastructure for managing things yourself.

dannykwells-sab commented 1 year ago

Hi everyone - @mjsteinbaugh - did scarches ever end up on conda at all? Would love it if so, please let me know anything I can do to help.

adamgayoso commented 1 year ago

I should add that scvi-tools is on conda and contains the functionality to use scarches with scVI, scANVI, and totalVI.

dannykwells-sab commented 1 year ago

Oh that's helpful. Can you point to docs on how to do this?

adamgayoso commented 1 year ago

https://docs.scvi-tools.org/en/stable/tutorials/notebooks/scarches_scvi_tools.html

adamgayoso commented 1 year ago

To be clear, any scvi-tools model that is in this repo is directly using the scvi-tools implementation, instead of a reimplementation.

M0hammadL commented 1 year ago

@dannykwells-sab @Koncopd we will have the conda release nextweek containing 11 reference models

mjsteinbaugh commented 1 year ago

@dannykwells-sab Haven't had free time to work on this, but may have some bandwidth this weekend.

dannykwells-sab commented 1 year ago

I have another issue, maybe for @adamgayoso

When we're using scarches-scvi with GPU, we are getting this message

sca.models.SCVI.setup_anndata(source_adata, batch_key=condition_key) WARNING:jax._src.lib.xla_bridge:No GPU/TPU found, falling back to CPU. (Set TF_CPP_MIN_LOG_LEVEL=0 and rerun for more info.)

Even given this, the GPU acceleration is clearly working. when we do 

vae = sca.models.SCVI()
vae.train()

We can confirm that pytorch can see cuda.

Any thought on what we can do to address this, or what it's doing?

adamgayoso commented 1 year ago

This is nothing to worry about, models are trained using pytorch. What you're seeing there is a warning derived from a jax-based function we use to check if the user supplied data is count data.

If the train command says that it's using the gpu then it's using the gpu.