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
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
|
"""
Concatenate sets of intervals.
Preserves format of the first input -- it is possible to concat two files that
have different column orders. Of course, the meta-data of the second will be
lost (and filled with a "."). If all of the files (GenomicInteralReaders) are
the same format, sameformat=True will preserve all columns of the first input,
cuts extra columns on subsequent input, and pads missing columns. If
sameformat=False then extra columns are filled with ".".
"""
from bx.intervals.io import GenomicInterval
from bx.tabular.io import (
Comment,
Header,
)
def concat(readers, comments=True, header=True, sameformat=True):
# Save columns from the first input
chrom_col = readers[0].chrom_col
start_col = readers[0].start_col
end_col = readers[0].end_col
strand_col = readers[0].strand_col
nfields = None
firstdataset = True
output = False
for intervals in readers:
for interval in intervals:
if isinstance(interval, GenomicInterval):
if not nfields:
nfields = interval.nfields
out_interval = interval.copy()
if sameformat or firstdataset:
# everything except the first input has to be
# trimmed or padded to match the first input
if len(out_interval.fields) > nfields:
out_interval.fields = out_interval.fields[0:nfields]
while len(out_interval.fields) < nfields:
out_interval.fields.append(".")
output = True
yield out_interval
else:
chrom = out_interval.chrom
start = out_interval.start
end = out_interval.end
strand = out_interval.strand
out_interval.fields = ["." for col in range(nfields)]
out_interval.fields[chrom_col] = chrom
out_interval.fields[start_col] = str(start)
out_interval.fields[end_col] = str(end)
# Strand is optional, might not exist in output
if strand_col < len(out_interval.fields):
out_interval.fields[strand_col] = strand
yield out_interval
elif isinstance(interval, Header) and header:
yield interval
elif isinstance(interval, Comment) and comments:
yield interval
if output and firstdataset:
firstdataset = False
|
