fabilab / northstar Goto Github PK

Hi Fabio,

I hope you and doing well (and still monitoring this repository).
I'm trying to generate Atlases from the Tabula Sapiens h5ad files that you can download from figshare.

I want to use them to classify tissue-matched samples.
I've gotten northstar to run through (the "subsample" version) but maybe classify 10% of new cells.

I was wondering what type of processing I should do before reading these files with annData and calling the northstar.average_atlas()/northstar.subsample_atlas() and northstar.Averages()/northstar.Subsample functions.

Also, what kind of preprocessing should I do on in let's say Seurat on a standard 10x run?

Would really appreciate the help! All other cell assignment pipelines I have tried are basically unusable.

Thanks,
Chris

Hi, all
I try to use the northstar to annotate my single cell dataset following the Tutorial:

...
af = northstar.AtlasFetcher()
af.list_atlases()
myatlas = af.fetch_atlas('Darmanis_2015_nofetal', kind='subsample')
cell_types_ns = model.membership
pd.DataFrame(cell_types_ns).to_csv("/Users/.../..celltype.csv")

but when i open the ..csv, i just see the numbers:

....

is this right? how could i get the right celltype annotation into my adata in the scanpy?

many thanks!
CC

Leidenalg no longer supports the param fixed_nodes in optimise_partition as of 26Aug. This results in the below error. fixed_nodes should be changed to is_membership_fixed.

Error:

Lines to fix to optimise_partition in northstar:

https://github.com/northstaratlas/northstar/blob/7fe63704dc50680366460d20c8ff42b9cf94d718/northstar/cluster_with_annotations.py#L82-L113

Commit in Leidenalg updating the params:

vtraag/leidenalg@808bfdf#diff-e55f439ba556c8d66c1c73c19874c80a110699da462ea70f36cad3515e2565d9

MRE:

import northstar
from anndata import AnnData
import pandas as pd
import numpy as np
import string

# Choose an atlas
atlas_name = 'Darmanis_2015'

# Get a gene expression matrix of the new dataset (here a
# random matrix for simplicity)
N = 200
L = 50
af = northstar.AtlasFetcher()
dar_atlas = af.fetch_atlas( "Darmanis_2015")
dar_genes = dar_atlas.var_names
new_dataset = pd.DataFrame(
    data=np.random.rand(L, N).astype(np.float32),
    index=list(np.random.choice(list(dar_genes), L)),
    columns=['cell_'+str(i+1) for i in range(N)],
    )

# Initialize northstar classes
model = northstar.Averages(
        atlas='Darmanis_2015',
        n_neighbors=5,
        n_pcs=10,
        )

# Run the classifier
model.fit(new_dataset)

# Get the cluster memberships for the new cells
membership = model.membership