def test_pacbio():
b = PacbioSubreads(sequana_data("test_pacbio_subreads.bam"))
assert len(b) == 130
b.df
#assert b.nb_pass[1] == 130
with TempFile() as fh:
b.filter_length(fh.name, threshold_min=500)
print(b) # check length
assert b.stats['mean_GC'] > 62.46
assert b.stats['mean_GC'] < 65.47
b.summary()
b = PacbioSubreads(sequana_data("test_pacbio_subreads.bam"))
# test hist_snr from scratch
b._df = None
b.hist_snr()
# test hist_len from scratch
b._df = None
b.hist_read_length()
b.hist_nb_passes()
b.get_mean_nb_passes()
# test from scratch
b._df = None
b.hist_GC()
# test from scratch
b._df = None
b.plot_GC_read_len()
# test from scratch
b._df = None
with TempFile() as fh:
b.to_fasta(fh.name, threads=1)
with TempFile() as fh:
b.to_fastq(fh.name, threads=1)
with TempFile() as fh:
b.save_summary(fh.name)
def test_pacbio():
b = PacbioSubreads(sequana_data("test_pacbio_subreads.bam"))
assert len(b) == 130
b.df
#assert b.nb_pass[1] == 130
with TempFile() as fh:
b.filter_length(fh.name, threshold_min=500)
print(b) # check length
assert b.stats['mean_GC'] > 62.46
assert b.stats['mean_GC'] < 65.47
b.summary()
b = PacbioSubreads(sequana_data("test_pacbio_subreads.bam"))
# test hist_snr from scratch
b._df = None
b.hist_snr()
# test hist_len from scratch
b._df = None
b.hist_read_length()
b.hist_nb_passes()
b.get_mean_nb_passes()
# test from scratch
b._df = None
b.hist_GC()
# test from scratch
b._df = None
b.plot_GC_read_len()
# test from scratch
b._df = None
with TempFile() as fh:
b.to_fasta(fh.name, threads=1)
with TempFile() as fh:
b.to_fastq(fh.name, threads=1)
with TempFile() as fh:
b.save_summary(fh.name)
"""
read length histograms pacbio data
=====================================
QC pacbio example
"""
########################################
# First, let us get a data set example.
# Note the .bam extension
from sequana import sequana_data
dataset = sequana_data("test_pacbio_subreads.bam")
#############################################
# Create a :class:`sequana.pacbio.BAMPacbio` instance
from sequana.pacbio import PacbioSubreads
qc = PacbioSubreads(dataset)
#########################################
# plot the histogram of read length
qc.hist_read_length()
#################################################
# plot the histogram of the SNRs for each base
qc.hist_snr()