def test_run_raises_AttributeError_if_pbs_file_not_set(self):
bp = BasePipe()
with self.assertRaisesRegex(AttributeError, r'file.*not set'):
bp.run()
def test_run_raises_OSError_if_pbs_file_not_found(self):
bp = BasePipe()
bp.pbs_file = 'script.pbs'
with patch.object(os.path, 'isfile', return_value=False):
with self.assertRaises(OSError):
bp.run()
def pipe(file_list, genome, project_dir, force=False):
timestamp = time.strftime("%y%m%d-%H%M%S")
for f in file_list:
name = f[0]
files = f[1:]
out_dir = os.path.join(project_dir, name)
path.makedirs(out_dir)
# # 1st fast qc
# fastqc_1 = FastqcCmd(*files, o=out_dir)
#
# # trimming
# out_prefix = os.path.join(out_dir, name)
# trim = SkewerCmd(*files, o=out_prefix)
# trimmed_fastq = trim.output()
#
# # 2nd fastqc
# fastqc_2 = FastqcCmd(*trimmed_fastq, o=out_dir)
#
# # setup alignment
# # NOTE: need to check for encoding
# align_kwargs = {
# '-x': genome,
# '-S': '{}_{}.sam'.format(
# out_prefix,
# os.path.basename(genome),
# ),
# '-p': 3, # set for local (should use pbs paramters on qsub)
# }
# if len(trimmed_fastq) == 1:
# align_kwargs['U'] = trimmed_fastq[0]
# else:
# align_kwargs['1'], align_kwargs['2'] = trimmed_fastq
# align = HisatCmd(timestamp=timestamp, **align_kwargs)
# # human_kw = [m for m in ['human', 'sapien', 'G37RCh'] if m in genome]
# # if human_kw:
# # align = HisatCmd(timestamp=timestamp, **align_kwargs)
# # else:
# # align = Bowtie2Cmd(timestamp=timestamp, **align_kwargs)
#
# # samtools
# sam_sort = SamtoolsSortCmd(*(align.output()))
# sam_index = SamtoolsIndexCmd(*(sam_sort.output()))
# UPDATED
fastqc_1 = FastqcCmd(*files, o=out_dir)
# trimming
out_prefix = os.path.join(out_dir, name)
trim = SkewerCmd(*files, o=out_prefix)
# 2nd fastqc
fastqc_2 = FastqcCmd(o=out_dir)
# setup alignment
# NOTE: need to check for encoding
align_kwargs = {
'-x': genome,
'-S': '{}_{}.sam'.format(
out_prefix,
os.path.basename(genome),
),
'-p': 3, # set for local (should use pbs paramters on qsub)
}
align = HisatCmd(timestamp=timestamp, **align_kwargs)
# samtools
sam_sort = SamtoolsSortCmd()
sam_index = SamtoolsIndexCmd()
# count
kwargs = {'-bed': genome}
bedtools_multicov = BedtoolsMulticovCmd(**kwargs)
# Setup pipe
# NOTE: This is the alpha test of the pipe class.
job_name = name + '_' + os.path.basename(genome)
pipe = BasePipe(job_name=job_name, force=force)
pipe.add(
fastqc_1, trim, fastqc_2, align, sam_sort, sam_index,
bedtools_multicov,
)
# write pbs file & run
# pbs_file = '{} , timestamp, os.path.basename(genome))
pipe.write_script()
pipe.run()
