In [1]:
%config InlineBackend.figure_format = 'retina'
%pylab inline

from glob import glob

import anndata
import pandas as pd

Populating the interactive namespace from numpy and matplotlib
In [2]:
datasets = [
    anndata.read('../Data/output/10x v3 HEK293T.h5ad'),
    anndata.read('../Data/output/10x v3 NIH3T3.h5ad'),
    anndata.read('../Data/output/Klein et al 2015.h5ad'),
    anndata.read('../Data/output/Macosko et al 2015.h5ad'),
    anndata.read('../Data/output/Svensson et al 2017 (1).h5ad'),
    anndata.read('../Data/output/Svensson et al 2017 (2).h5ad'),
    anndata.read('../Data/output/Zheng et al 2017.h5ad'),
    anndata.read('../Data/output/Padovan-Merhar et al 2015 (SMARTer).h5ad'),
    anndata.read('../Data/output/10x v3 PBMC.h5ad')
]
In [ ]:
In [9]:
for adata in datasets:
    print(adata.uns['name'])
    print(f'{adata.obs.shape[0]} cells, {adata.var.shape[0]} genes')
    difference = adata.var['empirical_zero_fraction'] - adata.var['global_zero_fraction']
    absdiff = np.abs(difference)
    print('c', (absdiff > 0.01).sum(), (absdiff > 0.05).sum(), (absdiff > 0.1).sum(), (absdiff > 0.2).sum())
    difference = adata.var['empirical_zero_fraction'] - adata.var['genewise_zero_fraction']
    absdiff = np.abs(difference)
    print('g', (absdiff > 0.01).sum(), (absdiff > 0.05).sum(), (absdiff > 0.1).sum(), (absdiff > 0.2).sum())
    difference = adata.var['empirical_zero_fraction'] - adata.var['poisson_zero_fraction']
    absdiff = np.abs(difference)
    print('p', (absdiff > 0.01).sum(), (absdiff > 0.05).sum(), (absdiff > 0.1).sum(), (absdiff > 0.2).sum())
    print()

10x v3 HEK293T
2378 cells, 57905 genes
c 8957 4903 2412 66
g 4311 977 123 1
p 6958 2306 360 16

10x v3 NIH3T3
2458 cells, 54232 genes
c 2925 392 134 40
g 1178 120 41 8
p 3864 541 186 46

Klein et al 2015
953 cells, 25435 genes
c 3705 4 0 0
g 2036 1 0 0
p 3515 4 0 0

Macosko et al 2015
84 cells, 80 genes
c 54 37 28 16
g 26 4 0 0
p 54 35 28 16

Svensson et al 2017 (1)
2000 cells, 24116 genes
c 101 1 0 0
g 6 0 0 0
p 103 1 0 0

Svensson et al 2017 (2)
2000 cells, 24116 genes
c 1134 16 1 0
g 117 3 1 0
p 1134 16 1 0

Zheng et al 2017
1015 cells, 92 genes
c 19 3 1 0
g 28 12 7 1
p 17 3 1 0

Padovan-Merhar et al 2015 (SMARTer)
96 cells, 25590 genes
c 15174 13188 10852 6392
g 12865 7539 4091 912
p 15342 13841 12697 10787

10x v3 PBMC
1222 cells, 33538 genes
c 3236 800 353 151
g 1281 288 86 25
p 3750 1088 445 182
In [ ]:
In [ ]: