Find the genes related regions¶

In [1]:

Copied!





import omicverse as ov
import scanpy as sc
import Epiverse as ev
ov.ov_plot_set()
import omicverse as ov
import scanpy as sc
import Epiverse as ev
ov.ov_plot_set()

2023-08-20 21:06:05.193053: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-08-20 21:06:05.800191: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory
2023-08-20 21:06:05.800256: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory
2023-08-20 21:06:05.800262: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.

In [2]:

Copied!

adata=sc.read('data/biodata/cd34_multiome_atac.h5ad')
adata
adata=sc.read('data/biodata/cd34_multiome_atac.h5ad')
adata

Out[2]:

AnnData object with n_obs × n_vars = 6881 × 246113
    obs: 'Sample', 'TSSEnrichment', 'ReadsInTSS', 'ReadsInPromoter', 'ReadsInBlacklist', 'PromoterRatio', 'PassQC', 'NucleosomeRatio', 'nMultiFrags', 'nMonoFrags', 'nFrags', 'nDiFrags', 'BlacklistRatio', 'Clusters', 'ReadsInPeaks', 'FRIP', 'leiden', 'phenograph', 'celltype', 'SEACell'
    var: 'seqnames', 'start', 'end', 'width', 'strand', 'score', 'replicateScoreQuantile', 'groupScoreQuantile', 'Reproducibility', 'GroupReplicate', 'nearestGene', 'distToGeneStart', 'peakType', 'distToTSS', 'nearestTSS', 'GC', 'idx'
    uns: 'celltype_colors'
    obsm: 'X_svd', 'X_umap'

In [4]:

Copied!

atac_anno=ev.utils.Annotation('/mnt/home/zehuazeng/data/gtf/gencode.v43.basic.annotation.gtf')
atac_anno.chrom_dict
atac_anno=ev.utils.Annotation('/mnt/home/zehuazeng/data/gtf/gencode.v43.basic.annotation.gtf')
atac_anno.chrom_dict

Out[4]:

{'chr1': 248937043,
 'chr2': 242175694,
 'chr3': 198228376,
 'chr4': 190196190,
 'chr5': 181472430,
 'chr6': 170745977,
 'chr7': 159233377,
 'chr8': 145066685,
 'chr9': 138320835,
 'chr10': 133778699,
 'chr11': 135075908,
 'chr12': 133238549,
 'chr13': 114346637,
 'chr14': 106879812,
 'chr15': 101979093,
 'chr16': 90222673,
 'chr17': 83240804,
 'chr18': 80247514,
 'chr19': 58605223,
 'chr20': 64327972,
 'chr21': 46691226,
 'chr22': 50801309,
 'chrX': 156027877,
 'chrY': 57214397,
 'chrM': 16023}

In [5]:

Copied!





atac_anno.tss_init(upstream=1000,
                   downstream=100)
atac_anno.distal_init(upstream=[1000,200000],
                      downstream=[1000,200000])
atac_anno.body_init()
atac_anno.tss_init(upstream=1000,
                   downstream=100)
atac_anno.distal_init(upstream=[1000,200000],
                      downstream=[1000,200000])
atac_anno.body_init()

In [6]:

Copied!





%%time
import pandas as pd
k=0
for chr in adata.var['seqnames'].unique():
    if k==0:
        merge_pd=atac_anno.query_multi(query_list=adata.var.loc[adata.var['seqnames']==chr].index.tolist(),
                                chrom=chr,batch=4,ncpus=8)
    else:
        merge_pd1=atac_anno.query_multi(query_list=adata.var.loc[adata.var['seqnames']==chr].index.tolist(),
                                chrom=chr,batch=4,ncpus=8)
        merge_pd=pd.concat([merge_pd,merge_pd1])
    k+=1
%%time
import pandas as pd
k=0
for chr in adata.var['seqnames'].unique():
    if k==0:
        merge_pd=atac_anno.query_multi(query_list=adata.var.loc[adata.var['seqnames']==chr].index.tolist(),
                                chrom=chr,batch=4,ncpus=8)
    else:
        merge_pd1=atac_anno.query_multi(query_list=adata.var.loc[adata.var['seqnames']==chr].index.tolist(),
                                chrom=chr,batch=4,ncpus=8)
        merge_pd=pd.concat([merge_pd,merge_pd1])
    k+=1

100%|██████████| 3073/3073 [00:16<00:00, 187.28it/s]

Start process_querychr6...

 65%|██████▍   | 2337/3599 [00:09<00:05, 212.21it/s]

Start process_querychr6...

100%|██████████| 3599/3599 [00:14<00:00, 244.08it/s]
 59%|█████▉    | 2115/3599 [00:09<00:07, 207.30it/s]

Start process_querychr6...

100%|██████████| 3599/3599 [00:18<00:00, 197.08it/s]
 46%|████▌     | 1653/3599 [00:10<00:11, 162.31it/s]

Start process_querychr6...

 45%|████▍     | 1605/3599 [00:08<00:12, 160.97it/s]

Start process_querychr6...

100%|██████████| 3/3 [00:00<00:00, 169.65it/s]
100%|██████████| 3599/3599 [00:21<00:00, 170.19it/s]
100%|██████████| 3599/3599 [00:19<00:00, 180.60it/s]

Start process_querychr7...

 75%|███████▍  | 2310/3091 [00:09<00:03, 223.19it/s]

Start process_querychr7...

100%|██████████| 3091/3091 [00:12<00:00, 249.46it/s]
 69%|██████▉   | 2144/3091 [00:09<00:04, 219.50it/s]

Start process_querychr7...

100%|██████████| 3091/3091 [00:14<00:00, 219.68it/s]
 59%|█████▉    | 1833/3091 [00:08<00:06, 201.70it/s]

Start process_querychr7...

100%|██████████| 3091/3091 [00:15<00:00, 200.57it/s]
100%|██████████| 3091/3091 [00:16<00:00, 190.75it/s]

Start process_querychr8...

100%|██████████| 2563/2563 [00:09<00:00, 284.09it/s]

Start process_querychr8...

 90%|█████████ | 2307/2563 [00:09<00:01, 211.17it/s]

Start process_querychr8...

100%|██████████| 2563/2563 [00:10<00:00, 247.70it/s]
 79%|███████▉  | 2035/2563 [00:09<00:02, 190.05it/s]

Start process_querychr8...

100%|██████████| 2563/2563 [00:11<00:00, 215.26it/s]
 71%|███████   | 1824/2563 [00:08<00:03, 214.39it/s]

Start process_querychr8...

100%|██████████| 3/3 [00:00<00:00, 186.47it/s]
100%|██████████| 2563/2563 [00:12<00:00, 207.08it/s]

Start process_querychr9...

100%|██████████| 2594/2594 [00:08<00:00, 296.60it/s]

Start process_querychr9...

 88%|████████▊ | 2285/2594 [00:09<00:01, 232.77it/s]

Start process_querychr9...

100%|██████████| 2594/2594 [00:10<00:00, 245.62it/s]
 83%|████████▎ | 2158/2594 [00:09<00:02, 216.28it/s]

Start process_querychr9...

100%|██████████| 2594/2594 [00:11<00:00, 234.16it/s]
 78%|███████▊  | 2032/2594 [00:08<00:02, 216.52it/s]

Start process_querychr9...

100%|██████████| 3/3 [00:00<00:00, 215.96it/s]
100%|██████████| 2594/2594 [00:11<00:00, 228.00it/s]

Start process_querychrX...

100%|██████████| 1524/1524 [00:05<00:00, 283.53it/s]

Start process_querychrX...

100%|██████████| 1524/1524 [00:05<00:00, 269.44it/s]

Start process_querychrX...

100%|██████████| 1524/1524 [00:06<00:00, 237.86it/s]

Start process_querychrX...

100%|██████████| 1524/1524 [00:06<00:00, 220.91it/s]

Start process_querychrX...

100%|██████████| 1/1 [00:00<00:00, 228.14it/s]

CPU times: user 14min 8s, sys: 2min 21s, total: 16min 30s
Wall time: 22min 34s

In [12]:

Copied!

merge_pd.to_csv('temp_merge_pd.csv')
merge_pd.to_csv('temp_merge_pd.csv')

In [5]:

Copied!

import pandas as pd
merge_pd=pd.read_csv('temp_merge_pd.csv',index_col=0)
import pandas as pd
merge_pd=pd.read_csv('temp_merge_pd.csv',index_col=0)

In [8]:

Copied!

merge_pd=atac_anno.merge_info(merge_pd)
merge_pd=atac_anno.merge_info(merge_pd)

In [9]:

Copied!

atac_anno.add_gene_info(adata,merge_pd,
                        columns=['peaktype','neargene','neargene_tss'])
atac_anno.add_gene_info(adata,merge_pd,
                        columns=['peaktype','neargene','neargene_tss'])

In [14]:

Copied!

adata.var[['peaktype','neargene','neargene_tss']].head(20)
adata.var[['peaktype','neargene','neargene_tss']].head(20)

Out[14]:

	peaktype	neargene	neargene_tss
chr1:816070-816570	body	ENSG00000290784	817712
chr1:817092-817592	promoter	ENSG00000290784	817712
chr1:827266-827766	promoter	LINC01128	826832
chr1:838271-838771	body	LINC01128	826832
chr1:842638-843138	body	LINC01128	827673
chr1:856533-857033	body	LINC01128	827598
chr1:858585-859085	body	LINC01128	827598
chr1:860736-861236	promoter	ENSG00000288531	860227
chr1:869632-870132	promoter	FAM41C	870201
chr1:876439-876939	promoter	ENSG00000283040	877234
chr1:890619-891119	down_distal	ENSG00000285268	781937
chr1:897221-897721	down_distal	LINC01409	803934
chr1:898274-898774	down_distal	LINC01409	803934
chr1:904520-905020	down_distal	LINC01409	803934
chr1:905170-905670	promoter	ENSG00000272438	904834
chr1:906630-907130	body	ENSG00000272438	904834
chr1:909981-910481	body	ENSG00000272438	904834
chr1:911150-911650	body	ENSG00000272438	904834
chr1:912768-913268	body	ENSG00000230699	911435
chr1:915682-916182	down_distal	FAM87B	817371

In [ ]: