def test_write(self):
"""Test ClassifySummary.write."""
outFN = op.join(self.testDir, "out/test_ClassifySummary.txt")
stdoutFN = op.join(self.testDir, "stdout/test_ClassifySummary.txt")
obj = ClassifySummary()
obj.num_reads = 100
obj.num_5_seen = 90
obj.num_3_seen = 70
obj.num_polyA_seen = 70
obj.num_filtered_short_reads = 10
obj.num_nfl = 50
obj.num_fl = 40
obj.num_flnc = 39
obj.num_flc = 1
obj.num_flnc_bases = 10001
obj.write(outFN)
self.assertTrue(filecmp.cmp(outFN, stdoutFN))
def __init__(self, reads_fn="test.fa", out_dir="output/",
out_reads_fn="testout.fa", primer_fn=None,
primer_report_fn=None, summary_fn=None,
cpus=1, change_read_id=True,
opts=ChimeraDetectionOptions(50, 10, 100, 50, 100, False),
out_nfl_fn=None, out_flnc_fn=None,
ignore_polyA=False, reuse_dom=False):
self.reads_fn = realpath(reads_fn)
self.out_dir = realpath(out_dir)
self.cpus = cpus
self.change_read_id = change_read_id
self.chimera_detection_opts = opts
self.ignore_polyA = ignore_polyA
self.reuse_dom = reuse_dom
# The input primer file: primers.fa
self.primer_fn = primer_fn if primer_fn is not None else \
op.join(self.data_dir, PRIMERFN)
# The output fasta file.
self.out_all_reads_fn = realpath(out_reads_fn)
# Intermediate output fasta file before chimera detection.
# trimmed full-length reads: fl.trimmed.fasta
# and
# trimmed non-full-length reads: nfl.trimmed.fasta
self._trimmed_fl_reads_fn = op.join(self.out_dir, "fl.trimmed.fasta")
self._trimmed_nfl_reads_fn = op.join(self.out_dir, "nfl.trimmed.fasta")
self.primer_front_back_fn = op.join(self.out_dir, PRIMERFRONTENDFN)
self.primer_chimera_fn = op.join(self.out_dir, PRIMERCHIMERAFN)
# The output primer file: primer_info.csv
self.primer_report_fn = primer_report_fn \
if primer_report_fn is not None else \
".".join(out_reads_fn.split('.')[:-1]) + "." + PRIMERREPORTFN
# primer reports for nfl reads before chimera detection. Note that
# chimera detection is not necessary for nfl reads.
self._primer_report_nfl_fn = op.join(self.out_dir,
"primer_report.nfl.csv")
# primer reports for fl reads after chimera detection. Note that
# chimera detection is required for fl reads.
self._primer_report_fl_fn = op.join(self.out_dir,
"primer_report.fl.csv")
# The matrix file: PBMATRIX.txt
self.pbmatrix_fn = op.join(self.data_dir, PBMATRIXFN)
# The output phmmer Dom file for trimming primers: hmmer.front_end.dom
self.out_front_back_dom_fn = op.join(self.out_dir, FRONTENDDOMFN)
# The output phmmer Dom file for chimera detection:
# hmmer.fl.chimera.dom and hmmer.nfl.chimera.dom
self.out_trimmed_fl_dom_fn = op.join(self.out_dir, FLCHIMERADOMFN)
self.out_trimmed_nfl_dom_fn = op.join(self.out_dir, NFLCHIMERADOMFN)
self.chunked_front_back_reads_fns = None
self.chunked_front_back_dom_fns = None
#self.chunked_trimmed_reads_fns = None
#self.chunked_trimmed_reads_dom_fns = None
# The summary file: *.classify_summary.txt
self.summary = ClassifySummary()
self.summary_fn = summary_fn if summary_fn is not None else \
".".join(out_reads_fn.split('.')[:-1]) + \
"." + CLASSIFYSUMMARY
self.out_nfl_fn = realpath(out_nfl_fn) if out_nfl_fn is not None \
else op.join(self.out_dir, "nfl.fasta")
self.out_nflnc_fn = op.join(self.out_dir, "nflnc.fasta")
self.out_nflc_fn = op.join(self.out_dir, "nflc.fasta")
self.out_flnc_fn = realpath(out_flnc_fn) if out_flnc_fn is not None \
else op.join(self.out_dir, "flnc.fasta")
self.out_flc_fn = op.join(self.out_dir, "flc.fasta")
