def read_bam(f, output_df=False, mapq=0, required_flag=0, filter_flag=1540):
df = bamread.read_bam(f, mapq, required_flag, filter_flag)
if output_df:
return df
else:
return PyRanges(df)
return bamread.read_bam(f, mapq, required_flag, filter_flag)
def read_bam(f,
sparse=True,
output_df=False,
mapq=0,
required_flag=0,
filter_flag=1540):
try:
import bamread
except ModuleNotFoundError as e:
print(
"bamread must be installed to read bam. Use `conda install -c bioconda bamread` or `pip install bamread` to install it."
)
sys.exit(1)
if sparse:
df = bamread.read_bam(f, mapq, required_flag, filter_flag)
else:
try:
df = bamread.read_bam_full(f, mapq, required_flag, filter_flag)
except AttributeError:
print(
"bamread version 0.0.6 or higher is required to read bam non-sparsely."
)
if output_df:
return df
else:
return PyRanges(df)
def read_bam(f, output_df=False, mapq=0, required_flag=0, filter_flag=1540):
try:
import bamread
except ModuleNotFoundError:
print(
"bamread must be installed to read bam. Use `conda install -c bioconda bamread` or `pip install bamread` to install it."
)
sys.exit(1)
df = bamread.read_bam(f, mapq, required_flag, filter_flag)
if output_df:
return df
else:
return PyRanges(df)
return bamread.read_bam(f, mapq, required_flag, filter_flag)
def read_bam(f,
sparse=True,
as_df=False,
mapq=0,
required_flag=0,
filter_flag=1540):
"""Return bam file as PyRanges.
Parameters
----------
f : str
Path to bam file
sparse : bool, default True
Whether to return only.
as_df : bool, default False
Whether to return as pandas DataFrame instead of PyRanges.
mapq : int, default 0
Minimum mapping quality score.
required_flag : int, default 0
Flags which must be present for the interval to be read.
filter_flag : int, default 1540
Ignore reads with these flags. Default 1540, which means that either
the read is unmapped, the read failed vendor or platfrom quality
checks, or the read is a PCR or optical duplicate.
Notes
-----
This functionality requires the library `bamread`. It can be installed with
`pip install bamread` or `conda install -c bioconda bamread`.
Examples
--------
>>> path = pr.get_example_path("control.bam")
>>> pr.read_bam(path)
+--------------+-----------+-----------+--------------+------------+
| Chromosome | Start | End | Strand | Flag |
| (category) | (int32) | (int32) | (category) | (uint16) |
|--------------+-----------+-----------+--------------+------------|
| chr1 | 887771 | 887796 | + | 16 |
| chr1 | 994660 | 994685 | + | 16 |
| chr1 | 1770383 | 1770408 | + | 16 |
| chr1 | 1995141 | 1995166 | + | 16 |
| ... | ... | ... | ... | ... |
| chrY | 57402214 | 57402239 | + | 16 |
| chrY | 10643526 | 10643551 | - | 0 |
| chrY | 11776321 | 11776346 | - | 0 |
| chrY | 20557165 | 20557190 | - | 0 |
+--------------+-----------+-----------+--------------+------------+
Stranded PyRanges object has 10,000 rows and 5 columns from 25 chromosomes.
For printing, the PyRanges was sorted on Chromosome and Strand.
>>> pr.read_bam(path, sparse=False, as_df=True)
Chromosome Start End Strand Flag QueryStart QueryEnd Name Cigar Quality
0 chr1 887771 887796 + 16 0 25 U0 25M None
1 chr1 994660 994685 + 16 0 25 U0 25M None
2 chr1 1041102 1041127 - 0 0 25 U0 25M None
3 chr1 1770383 1770408 + 16 0 25 U0 25M None
4 chr1 1995141 1995166 + 16 0 25 U0 25M None
... ... ... ... ... ... ... ... ... ... ...
9995 chrM 3654 3679 - 0 0 25 U0 25M None
9996 chrM 3900 3925 + 16 0 25 U0 25M None
9997 chrM 13006 13031 + 16 0 25 U0 25M None
9998 chrM 14257 14282 - 0 0 25 U0 25M None
9999 chrM 14257 14282 - 0 0 25 U0 25M None
<BLANKLINE>
[10000 rows x 10 columns]
"""
try:
import bamread
except ModuleNotFoundError as e:
print(
"bamread must be installed to read bam. Use `conda install -c bioconda bamread` or `pip install bamread` to install it."
)
sys.exit(1)
if sparse:
df = bamread.read_bam(f, mapq, required_flag, filter_flag)
else:
try:
df = bamread.read_bam_full(f, mapq, required_flag, filter_flag)
except AttributeError:
print(
"bamread version 0.0.6 or higher is required to read bam non-sparsely."
)
if as_df:
return df
else:
return PyRanges(df)