Skip to content

Check metadata for each view individually #13

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Check metadata for each view individually #13

wants to merge 1 commit into from

Conversation

@martinrohbeck
Copy link

@martinrohbeck martinrohbeck commented Nov 6, 2023 •
edited
Loading

This PR makes sure that the metadata is checked for each view individually. If this is not the case, then a view without metadata is assumed to have metadat as long as the first view has some. Assuming non-existing metadata leads to a concatenation of empty series, which breaks the code.

Here is a small example to reproduce the bug: Computing HVG on the mrna view leads to the issue, because this operation creates the metadata for the mrna view.

import scanpy as sc
import muon as mu
import pandas as pd
import mofax as mfx

drugs = pd.read_csv("data/cll_drugs.csv", index_col=0).T
metadata = pd.read_csv("data/cll_metadata.csv", index_col=0).T
mrna = pd.read_csv("data/cll_mrna.csv", index_col=0).T

mrna = sc.AnnData(mrna)
drugs = sc.AnnData(drugs)

sc.pp.highly_variable_genes(mrna, n_top_genes=10)
mrna = mrna[:, mrna.var["highly_variable"]]

mods = {"mrna": mrna, "drugs": drugs}

obs = pd.read_csv("data/cll_metadata.csv", sep=",", index_col=0)

mdata = mu.MuData(mods)
mdata.obs = mdata.obs.join(obs)

mu.tl.mofa(
    mdata,
    use_obs="union",
    n_factors=3,
    convergence_mode="medium",
    outfile="models/temp.hdf5",
    save_metadata=True,
    save_data=True,
    verbose=False,
)

model = mfx.mofa_model("models/temp.hdf5")

Note that

  1. use_var also does not work in this case (due to the added view-prefix), but I'll provide a fix in another PR.
  2. a simple .copy() of the rna data frame does not help

@martinrohbeck martinrohbeck requested a review from gtca November 6, 2023 19:44
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@gtca gtca Awaiting requested review from gtca

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@martinrohbeck