Calculating the gene activity matrix of scATAC-seq

In [1]:

import Epiverse as ev
import scanpy as sc

import Epiverse as ev import scanpy as sc

In [ ]:

!wget -p data https://cf.10xgenomics.com/samples/cell-atac/2.1.0/10k_pbmc_ATACv2_nextgem_Chromium_X/10k_pbmc_ATACv2_nextgem_Chromium_X_filtered_peak_bc_matrix.h5

!wget -p data https://cf.10xgenomics.com/samples/cell-atac/2.1.0/10k_pbmc_ATACv2_nextgem_Chromium_X/10k_pbmc_ATACv2_nextgem_Chromium_X_filtered_peak_bc_matrix.h5

In [2]:

adata = sc.read_10x_h5('data/10k_pbmc_ATACv2_nextgem_Chromium_X_filtered_peak_bc_matrix.h5',gex_only=False)
adata

adata = sc.read_10x_h5('data/10k_pbmc_ATACv2_nextgem_Chromium_X_filtered_peak_bc_matrix.h5',gex_only=False) adata

Out[2]:

AnnData object with n_obs × n_vars = 10273 × 164487
    var: 'gene_ids', 'feature_types', 'genome'

In [ ]:

ev.utils.download_gene_activity_reference(download_file='refer')

ev.utils.download_gene_activity_reference(download_file='refer')

In [3]:

Gene_activity = ev.pp.cal_gene_activity(adata=adata,
                                    genebed='refer/T2TCHM13_refgenes.txt',
                                    decay=float(10000))

Gene_activity = ev.pp.cal_gene_activity(adata=adata, genebed='refer/T2TCHM13_refgenes.txt', decay=float(10000))

......Extract gene information from the provided genebed file
......Calculate gene-peak regulatory scores based on the selected model
peaks number:  164487
peaks number in gene promoters and exons:  19322
peaks number out gene promoters and exons: 145165
......Store the index and total scores for each gene
......Store the maximum score for each gene symbol

In [4]:

Gene_activity

Gene_activity

Out[4]:

AnnData object with n_obs × n_vars = 10273 × 59454

In [5]:

Gene_activity.to_df()

Gene_activity.to_df()

Out[5]:

	5S_rRNA	5_8S_rRNA	7SK	A1BG	A1BG-AS1	A1CF	A2M	A2M-AS1	A2ML1	A2ML1-AS1	...	ZWINT	ZXDA	ZXDB	ZXDC	ZYG11A	ZYG11AP1	ZYXP1	hsa-mir-1253	hsa-mir-423	snoZ196
AAACGAAAGACTAGCG-1	0.000000	0.000000	0.565850	0.0	0.0	0.830326	0.001135	0.007001	0.005824	0.010367	...	0.0	0.000000	0.004062	1.235636	0.006776	0.000611	0.0	0.022758	0.000461	0.000432
AAACGAAAGCAACGGT-1	0.181331	0.000085	1.722540	0.0	0.0	0.000000	0.001917	0.011824	0.000277	0.000573	...	0.0	0.004205	0.000000	1.152631	0.000532	0.000099	0.0	0.002319	0.000000	0.000432
AAACGAAAGCCATTCA-1	0.548799	0.003705	1.874563	0.0	0.0	0.000000	0.269398	0.043671	0.009194	0.011922	...	0.0	0.000000	0.009735	2.964916	0.844313	0.002629	0.0	1.381189	2.111990	0.000000
AAACGAAAGGAGGCGA-1	0.000000	0.000682	2.928587	0.0	0.0	0.183455	1.128043	1.044262	0.000535	0.000953	...	0.0	0.000000	0.016656	1.501693	3.720639	0.014950	0.0	0.013200	0.003754	0.001296
AAACGAAAGGATTAAC-1	1.105243	0.000000	3.732908	0.0	0.0	0.183455	1.146316	1.156889	0.002376	0.001499	...	0.0	0.000000	0.000000	0.821750	3.127061	0.000084	0.0	0.000000	0.000000	0.000000
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
TTTGTGTTCCTGGGAC-1	0.823199	0.000183	1.361867	0.0	0.0	0.000000	0.000567	0.003501	0.000139	0.000247	...	0.0	0.000000	0.000000	2.323623	0.991325	0.002804	0.0	0.000000	0.000000	0.000432
TTTGTGTTCGAGAAGC-1	0.000000	0.000870	1.363589	0.0	0.0	0.183455	0.000000	0.000000	0.094202	0.167682	...	0.0	0.000000	0.000000	1.942213	1.688626	0.001531	0.0	0.012265	0.001182	0.000864
TTTGTGTTCGATATGC-1	0.000074	0.000000	1.165522	0.0	0.0	0.000000	0.297744	0.758031	0.003154	0.002537	...	0.0	0.000000	0.011423	2.095139	0.990995	0.014037	0.0	0.011715	1.053653	0.000432
TTTGTGTTCGCTACCT-1	1.443001	0.000000	5.457284	0.0	0.0	0.183455	0.000378	0.002334	0.006760	0.010668	...	0.0	0.000000	0.000000	1.459977	1.693196	0.000768	0.0	0.000065	0.000000	0.001204
TTTGTGTTCTTAGTGG-1	0.000000	0.000183	0.367145	0.0	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	...	0.0	0.000000	0.000000	0.047682	0.000438	0.000000	0.0	0.000000	0.000000	0.000432

10273 rows × 59454 columns