def main():
global options, args
# Read essay state json
essay = Essay()
essay.read_essay(options.essay_path)
print 'Launching prepare4genesys jobs for essay', essay.get_name()
# Create GeneSys compatible file
annotation = FileData(name=essay.get_name() + '_annotation.vcf', data_type='analysis', modifier='-i ',
add_args='annotation', path=essay.get_path())
genesys_psv = FileData(name=essay.get_name() + '_GeneSys.psv', data_type='trash', modifier='-o ',
add_args='prepare4genesys', path=essay.get_path())
hold_jobs = essay.submit_from_essay(job_name='genesys', command='vcf2GeneSys.py', input_data=annotation,
output_data=genesys_psv, module=module)
# Export result files via jenkins task (cURL) (only if not exome)
if essay.get_target_name() is not None and not (
essay.get_target_name().startswith('exome') or essay.get_target_name().startswith('exoma')):
if 'gluster2' in essay.get_path():
param = '\'http://*****:*****@10.0.0.82:8080/view/Bioinfo/job/Pipeta_Baming_G2/buildWithParameters?token=SOCELTOKENG2&path=' + essay.get_path() + '&project=' + essay.get_project_name() + '&analysis=' + essay.get_name() + '\''
else:
param = '\'http://*****:*****@10.0.0.82:8080/view/Bioinfo/job/Pipeta_Baming_G1/buildWithParameters?token=SOCELTOKENG1&path=' + essay.get_path() + '&project=' + essay.get_project_name() + '&analysis=' + essay.get_name() + '\''
hold_jobs = essay.submit_from_essay(job_name='curl2UGM', command='curl', add_args=param, module=module,
hold_jobs=hold_jobs)
# Call the vcf2DBNLVar script
#hold_jobs.append(
# essay.submit_from_essay(job_name='vcf2DBNLVar', command='vcf2DBNLVar', input_data=annotation,
# module=module))
return hold_jobs
def sample_stats_json_reader(essay_path):
#Create essay object
essay = Essay()
#Read essay
essay.read_essay(essay_path)
#Get sample list
essay_sample_id_list = sorted(essay.get_samples())
#Create empty sample_structure
mapping_stats_sample_list = []
for sample in essay_sample_id_list:
mapping_performance_file = essay.get_arg(info_type='tree',
folder_type='analysis',
keys=[
'stats',
'{0}'.format(sample),
'replicate1',
'mapping_performance.txt'
])
seq_platform = essay.get_arg(
info_type='samples',
folder_type='{0}'.format(sample),
keys=['replicates', 'replicate1', 'seq_platform'])
sequencer = essay.get_arg(
info_type='samples',
folder_type='{0}'.format(sample),
keys=['replicates', 'replicate1', 'sequencer'])
size = essay.get_arg(info_type='samples',
folder_type='{0}'.format(sample),
keys=['replicates', 'replicate1', 'size'])
mapping_stats_sample_list.append({
sample: {
'mapping_performance': mapping_performance_file,
'mapping_stats': []
}
})
for sample_item in mapping_stats_sample_list:
for sample_id in sample_item.keys():
mapping_performance_file = sample_item.get(sample_id).get(
'mapping_performance')
mapping_stats = sample_item.get(sample_id).get('mapping_stats')
mapping_stats.extend(get_mapping_stats(mapping_performance_file))
return essay_sample_id_list, mapping_stats_sample_list, seq_platform, sequencer, size
def main():
global options, args
# Read essay state json
essay = Essay()
essay.read_essay(options.essay_path)
print 'Launching prepare4genesys jobs for essay', essay.get_name()
# Create GeneSys compatible file
annotation = FileData(name=essay.get_name() + '_annotation.vcf',
data_type='analysis',
modifier='-i ',
add_args='annotation',
path=essay.get_path())
genesys_psv = FileData(name=essay.get_name() + '_GeneSys.psv',
data_type='trash',
modifier='-o ',
add_args='prepare4genesys',
path=essay.get_path())
hold_jobs = essay.submit_from_essay(job_name='genesys',
command='vcf2GeneSys.py',
input_data=annotation,
output_data=genesys_psv,
module=module)
# Export result files via jenkins task (cURL) (only if not exome)
if essay.get_target_name() is not None and not (
essay.get_target_name().startswith('exome')
or essay.get_target_name().startswith('exoma')):
if 'gluster2' in essay.get_path():
param = '\'http://*****:*****@10.0.0.82:8080/view/Bioinfo/job/Pipeta_Baming_G2/buildWithParameters?token=SOCELTOKENG2&path=' + essay.get_path(
) + '&project=' + essay.get_project_name(
) + '&analysis=' + essay.get_name() + '\''
else:
param = '\'http://*****:*****@10.0.0.82:8080/view/Bioinfo/job/Pipeta_Baming_G1/buildWithParameters?token=SOCELTOKENG1&path=' + essay.get_path(
) + '&project=' + essay.get_project_name(
) + '&analysis=' + essay.get_name() + '\''
hold_jobs = essay.submit_from_essay(job_name='curl2UGM',
command='curl',
add_args=param,
module=module,
hold_jobs=hold_jobs)
# Call the vcf2DBNLVar script
#hold_jobs.append(
# essay.submit_from_essay(job_name='vcf2DBNLVar', command='vcf2DBNLVar', input_data=annotation,
# module=module))
return hold_jobs
def sample_stats_json_reader(essay_path):
# Create essay object
essay = Essay()
# Read essay
essay.read_essay(essay_path)
# Get sample list
essay_sample_id_list = sorted(essay.get_samples())
# Create empty sample_structure
mapping_stats_sample_list = []
for sample in essay_sample_id_list:
mapping_performance_file = essay.get_arg(
info_type="tree",
folder_type="analysis",
keys=["stats", "{0}".format(sample), "replicate1", "mapping_performance.txt"],
)
seq_platform = essay.get_arg(
info_type="samples", folder_type="{0}".format(sample), keys=["replicates", "replicate1", "seq_platform"]
)
sequencer = essay.get_arg(
info_type="samples", folder_type="{0}".format(sample), keys=["replicates", "replicate1", "sequencer"]
)
size = essay.get_arg(
info_type="samples", folder_type="{0}".format(sample), keys=["replicates", "replicate1", "size"]
)
mapping_stats_sample_list.append(
{sample: {"mapping_performance": mapping_performance_file, "mapping_stats": []}}
)
for sample_item in mapping_stats_sample_list:
for sample_id in sample_item.keys():
mapping_performance_file = sample_item.get(sample_id).get("mapping_performance")
mapping_stats = sample_item.get(sample_id).get("mapping_stats")
mapping_stats.extend(get_mapping_stats(mapping_performance_file))
return essay_sample_id_list, mapping_stats_sample_list, seq_platform, sequencer, size