def test_get_preprocess_fastq_cmd_per_sample_FASTQ_failure(self):
metadata_dict = {
'SKB8.640193': {'run_prefix': "sample1_failure", 'primer': 'A',
'barcode': 'A', 'center_name': 'ANL',
'platform': 'ILLUMINA',
'library_construction_protocol': 'A',
'experiment_design_description': 'A'}}
md_template = pd.DataFrame.from_dict(metadata_dict, orient='index')
prep_template = PrepTemplate.create(md_template, Study(1), '16S')
# This part should fail
fp1 = self.path_builder('sample1_failure.fastq')
with open(fp1, 'w') as f:
f.write('\n')
self.files_to_remove.append(fp1)
fp2 = self.path_builder('sample1_failure.barcodes.fastq.gz')
with open(fp2, 'w') as f:
f.write('\n')
self.files_to_remove.append(fp2)
forward_filepath_id = convert_to_id('raw_forward_seqs',
'filepath_type')
barcode_filepath_id = convert_to_id('raw_barcodes', 'filepath_type')
fps = [(fp1, forward_filepath_id), (fp2, barcode_filepath_id)]
filetype_id = get_filetypes()['per_sample_FASTQ']
raw_data = RawData.create(filetype_id, [prep_template], fps)
params = [p for p in list(PreprocessedIlluminaParams.iter())
if p.name == 'per sample FASTQ defaults'][0]
with self.assertRaises(ValueError):
_get_preprocess_fastq_cmd(raw_data, prep_template, params)
def test_get_preprocess_fastq_cmd(self):
raw_data = RawData(1)
params = PreprocessedIlluminaParams(1)
prep_template = PrepTemplate(1)
obs_cmd, obs_output_dir = _get_preprocess_fastq_cmd(
raw_data, prep_template, params)
get_raw_path = partial(join, self.db_dir, 'raw_data')
seqs_fp = get_raw_path('1_s_G1_L001_sequences.fastq.gz')
bc_fp = get_raw_path('1_s_G1_L001_sequences_barcodes.fastq.gz')
exp_cmd_1 = ("split_libraries_fastq.py --store_demultiplexed_fastq -i "
"{} -b {} "
"-m ".format(seqs_fp, bc_fp))
exp_cmd_2 = ("-o {0} --barcode_type golay_12 --max_bad_run_length 3 "
"--max_barcode_errors 1.5 "
"--min_per_read_length_fraction 0.75 "
"--phred_quality_threshold 3 "
"--sequence_max_n 0".format(obs_output_dir))
# We are splitting the command into two parts because there is no way
# that we can know the filepath of the mapping file. We thus split the
# command on the mapping file path and we check that the two parts
# of the commands is correct
obs_cmd_1 = obs_cmd[:len(exp_cmd_1)]
obs_cmd_2 = obs_cmd[len(exp_cmd_1):].split(" ", 1)[1]
self.assertEqual(obs_cmd_1, exp_cmd_1)
self.assertEqual(obs_cmd_2, exp_cmd_2)
def test_get_preprocess_fastq_cmd(self):
raw_data = RawData(1)
params = PreprocessedIlluminaParams(1)
prep_template = PrepTemplate(1)
obs_cmd, obs_output_dir = _get_preprocess_fastq_cmd(
raw_data, prep_template, params)
get_raw_path = partial(join, self.db_dir, 'raw_data')
seqs_fp = get_raw_path('1_s_G1_L001_sequences.fastq.gz')
bc_fp = get_raw_path('1_s_G1_L001_sequences_barcodes.fastq.gz')
exp_cmd_1 = ("split_libraries_fastq.py --store_demultiplexed_fastq -i "
"{} -b {} "
"-m ".format(seqs_fp, bc_fp))
exp_cmd_2 = ("-o {0} --barcode_type golay_12 --max_bad_run_length 3 "
"--max_barcode_errors 1.5 "
"--min_per_read_length_fraction 0.75 "
"--phred_quality_threshold 3 "
"--sequence_max_n 0".format(obs_output_dir))
# We are splitting the command into two parts because there is no way
# that we can know the filepath of the mapping file. We thus split the
# command on the mapping file path and we check that the two parts
# of the commands is correct
obs_cmd_1 = obs_cmd[:len(exp_cmd_1)]
obs_cmd_2 = obs_cmd[len(exp_cmd_1):].split(" ", 1)[1]
self.assertEqual(obs_cmd_1, exp_cmd_1)
self.assertEqual(obs_cmd_2, exp_cmd_2)
def test_get_preprocess_fastq_cmd_per_sample_FASTQ(self):
metadata_dict = {
'SKB8.640193': {'run_prefix': "sample1", 'primer': 'A',
'barcode': 'A', 'center_name': 'ANL',
'platform': 'ILLUMINA',
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'A',
'experiment_design_description': 'A'},
'SKD8.640184': {'run_prefix': "sample2", 'primer': 'A',
'barcode': 'A', 'center_name': 'ANL',
'platform': 'ILLUMINA',
'instrument_model': 'Illumina MiSeq',
'library_construction_protocol': 'A',
'experiment_design_description': 'A'}}
md_template = pd.DataFrame.from_dict(metadata_dict, orient='index')
prep_template = PrepTemplate.create(md_template, Study(1), '16S')
fp1 = self.path_builder('sample1.fastq')
with open(fp1, 'w') as f:
f.write('\n')
self.files_to_remove.append(fp1)
fp2 = self.path_builder('sample2.fastq.gz')
with open(fp2, 'w') as f:
f.write('\n')
self.files_to_remove.append(fp2)
filepath_id = convert_to_id('raw_forward_seqs', 'filepath_type')
fps = [(fp1, filepath_id), (fp2, filepath_id)]
filetype_id = get_filetypes()['per_sample_FASTQ']
raw_data = RawData.create(filetype_id, [prep_template], fps)
params = [p for p in list(PreprocessedIlluminaParams.iter())
if p.name == 'per sample FASTQ defaults'][0]
obs_cmd, obs_output_dir = _get_preprocess_fastq_cmd(raw_data,
prep_template,
params)
raw_fps = ','.join([fp for _, fp, _ in
sorted(raw_data.get_filepaths())])
exp_cmd = (
"split_libraries_fastq.py --store_demultiplexed_fastq -i "
"{} --sample_ids 1.SKB8.640193,1.SKD8.640184 -o {} --barcode_type "
"not-barcoded --max_bad_run_length 3 --max_barcode_errors 1.5 "
"--min_per_read_length_fraction 0.75 --phred_quality_threshold 3 "
"--sequence_max_n 0").format(raw_fps, obs_output_dir)
self.assertEqual(obs_cmd, exp_cmd)
