1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
|
import pyranges as pr
def test_read_gtf():
gr = pr.read_gtf("tests/test_data/ensembl.gtf", full=True)
assert len(gr.columns) == 26
df = gr.df
transcript = df.iloc[1]
assert transcript['tag'] == 'basic'
exon = df[df['exon_id'] == 'ENSE00003812156'].iloc[0]
assert exon['tag'] == 'basic'
gr = pr.read_gtf("tests/test_data/ensembl.gtf",
full=True, duplicate_attr=True)
print(gr.columns)
assert len(gr.columns) == 26
df = gr.df
transcript = df.iloc[1]
assert transcript['tag'] == 'basic'
exon = df[df['exon_id'] == 'ENSE00003812156'].iloc[0]
assert exon['tag'] == 'CCDS,basic'
# assert list(gr.df.columns[:4]) == "Chromosome Start End Strand".split()
def test_read_gff3():
gr = pr.read_gff3("tests/test_data/gencode.gff3")
assert len(gr.columns) == 26
# assert list(gr.df.columns[:4]) == "Chromosome Start End Strand".split()
def test_read_bed():
pr.read_bed("pyranges/example_data/chipseq.bed")
|
