def setUp(self):
self.dbconfig = 'data/dbconfig.json'
self.platform_json = 'data/platform_db_data.json'
self.seqrun_json = 'data/seqrun_db_data.json'
self.pipeline_json = 'data/pipeline_data.json'
dbparam = read_dbconf_json(self.dbconfig)
base = BaseAdaptor(**dbparam)
self.engine = base.engine
self.dbname = dbparam['dbname']
Base.metadata.create_all(self.engine)
self.session_class = base.get_session_class()
base.start_session()
# load platform data
pl = PlatformAdaptor(**{'session': base.session})
pl.store_platform_data(data=read_json_data(self.platform_json))
# load seqrun data
sra = SeqrunAdaptor(**{'session': base.session})
sra.store_seqrun_and_attribute_data(
data=read_json_data(self.seqrun_json))
# load platform data
pla = PipelineAdaptor(**{'session': base.session})
pla.store_pipeline_data(data=read_json_data(self.pipeline_json))
pipeline_seed_data = [
{
'pipeline_name': 'demultiplexing_fastq',
'seed_id': '1',
'seed_table': 'seqrun'
},
]
pla.create_pipeline_seed(data=pipeline_seed_data)
base.close_session()
def test_create_pipeline_seed(self):
pipeline_seed_data1 = [
{
'seed_id': '1',
'seed_table': 'seqrun'
},
]
pl = PipelineAdaptor(**{'session_class': self.session_class})
pl.start_session()
with self.assertRaises(ValueError):
pl.create_pipeline_seed(data=pipeline_seed_data1)
pl.close_session()
def setUp(self):
self.dbconfig = 'data/dbconfig.json'
dbparam = read_dbconf_json(self.dbconfig)
base = BaseAdaptor(**dbparam)
self.engine = base.engine
self.dbname = dbparam['dbname']
Base.metadata.create_all(self.engine)
self.session_class = base.get_session_class()
base.start_session()
project_data = [{
'project_igf_id': 'IGFP0001_test_22-8-2017_rna_sc',
'project_name': 'test_22-8-2017_rna',
'description': 'Its project 1',
'project_deadline': 'Before August 2017',
'comments': 'Some samples are treated with drug X',
}]
pa = ProjectAdaptor(**{'session': base.session})
pa.store_project_and_attribute_data(data=project_data)
sample_data = [
{
'sample_igf_id': 'IGF00001',
'project_igf_id': 'IGFP0001_test_22-8-2017_rna_sc',
'library_source': 'TRANSCRIPTOMIC_SINGLE_CELL',
'library_strategy': 'RNA-SEQ',
'experiment_type': 'POLYA-RNA'
},
{
'sample_igf_id': 'IGF00003',
'project_igf_id': 'IGFP0001_test_22-8-2017_rna_sc',
'library_source': 'TRANSCRIPTOMIC_SINGLE_CELL',
'experiment_type': 'POLYA-RNA'
},
{
'sample_igf_id': 'IGF00002',
'project_igf_id': 'IGFP0001_test_22-8-2017_rna_sc',
},
]
sa = SampleAdaptor(**{'session': base.session})
sa.store_sample_and_attribute_data(data=sample_data)
experiment_data = [
{
'project_igf_id': 'IGFP0001_test_22-8-2017_rna_sc',
'sample_igf_id': 'IGF00001',
'experiment_igf_id': 'IGF00001_HISEQ4000',
'library_name': 'IGF00001'
},
{
'project_igf_id': 'IGFP0001_test_22-8-2017_rna_sc',
'sample_igf_id': 'IGF00003',
'experiment_igf_id': 'IGF00003_HISEQ4000',
'library_name': 'IGF00001'
},
{
'project_igf_id': 'IGFP0001_test_22-8-2017_rna_sc',
'sample_igf_id': 'IGF00002',
'experiment_igf_id': 'IGF00002_HISEQ4000',
'library_name': 'IGF00002'
},
]
ea = ExperimentAdaptor(**{'session': base.session})
ea.store_project_and_attribute_data(data=experiment_data)
pipeline_data = [{
"pipeline_name": "alignment",
"pipeline_db": "sqlite:////data/aln.db",
"pipeline_init_conf": {
"input_dir": "data/fastq_dir/",
"output_dir": "data"
},
"pipeline_run_conf": {
"output_dir": "data"
}
}]
pl = PipelineAdaptor(**{'session': base.session})
pl.store_pipeline_data(data=pipeline_data)
pipeline_seed_data = [
{
'pipeline_name': 'alignment',
'seed_id': '1',
'seed_table': 'experiment'
},
]
pl.create_pipeline_seed(data=pipeline_seed_data)
base.close_session()
def setUp(self):
self.dbconfig = 'data/dbconfig.json'
dbparam = read_dbconf_json(self.dbconfig)
base = BaseAdaptor(**dbparam)
self.engine = base.engine
self.dbname = dbparam['dbname']
Base.metadata.create_all(self.engine)
self.session_class = base.get_session_class()
base.start_session()
platform_data = [{
"platform_igf_id": "M00001",
"model_name": "MISEQ",
"vendor_name": "ILLUMINA",
"software_name": "RTA",
"software_version": "RTA1.18.54"
}, {
"platform_igf_id": "NB500000",
"model_name": "NEXTSEQ",
"vendor_name": "ILLUMINA",
"software_name": "RTA",
"software_version": "RTA2"
}, {
"platform_igf_id": "K00000",
"model_name": "HISEQ4000",
"vendor_name": "ILLUMINA",
"software_name": "RTA",
"software_version": "RTA2"
}]
flowcell_rule_data = [{
"platform_igf_id": "K00000",
"flowcell_type": "HiSeq 3000/4000 SR",
"index_1": "NO_CHANGE",
"index_2": "NO_CHANGE"
}, {
"platform_igf_id": "K00000",
"flowcell_type": "HiSeq 3000/4000 PE",
"index_1": "NO_CHANGE",
"index_2": "REVCOMP"
}, {
"platform_igf_id": "NB500000",
"flowcell_type": "NEXTSEQ",
"index_1": "NO_CHANGE",
"index_2": "REVCOMP"
}, {
"platform_igf_id": "M00001",
"flowcell_type": "MISEQ",
"index_1": "NO_CHANGE",
"index_2": "NO_CHANGE"
}]
pl = PlatformAdaptor(**{'session': base.session})
pl.store_platform_data(data=platform_data)
pl.store_flowcell_barcode_rule(data=flowcell_rule_data)
seqrun_data = [{
'seqrun_igf_id': '171003_M00001_0089_000000000-TEST',
'flowcell_id': '000000000-D0YLK',
'platform_igf_id': 'M00001',
'flowcell': 'MISEQ',
}]
sra = SeqrunAdaptor(**{'session': base.session})
sra.store_seqrun_and_attribute_data(data=seqrun_data)
seqrun = sra.fetch_seqrun_records_igf_id(
seqrun_igf_id='171003_M00001_0089_000000000-TEST')
pipeline_data = [{
"pipeline_name": "demultiplexing_fastq",
"pipeline_db": "sqlite:////data/bcl2fastq.db",
"pipeline_init_conf": {
"input_dir": "data/seqrun_dir/",
"output_dir": "data"
},
"pipeline_run_conf": {
"output_dir": "data"
}
}]
pipeseed_data = [{
"pipeline_name": "demultiplexing_fastq",
"seed_table": "seqrun",
"seed_id": seqrun.seqrun_id
}]
pp = PipelineAdaptor(**{'session': base.session})
pp.store_pipeline_data(data=pipeline_data)
pp.create_pipeline_seed(
data=pipeseed_data,
required_columns=['pipeline_id', 'seed_id', 'seed_table'])
base.close_session()
self.seqrun_input_list = 'data/reset_samplesheet_md5/seqrun_pipeline_reset_list.txt'
with open(self.seqrun_input_list, 'w') as fp:
fp.write('')
'seed_table': 'seqrun'
},
{
'pipeline_name': 'DemultiplexIlluminaFastq',
'seed_id': 2,
'seed_table': 'seqrun'
},
{
'pipeline_name': 'DemultiplexIlluminaFastq',
'seed_id': 3,
'seed_table': 'seqrun'
},
]
pla = PipelineAdaptor(**{'session': base.session})
pla.store_pipeline_data(data=pipeline_data)
pla.create_pipeline_seed(data=pipeline_seed_data)
pipeline_data = [{
"pipeline_name": "PrimaryAnalysis",
"pipeline_db": "sqlite:////analysis.db",
}]
pipeline_seed_data = [{
'pipeline_name': 'PrimaryAnalysis',
'seed_id': 1,
'seed_table': 'experiment'
}, {
'pipeline_name': 'PrimaryAnalysis',
'seed_id': 2,
'seed_table': 'experiment'
}, {
'pipeline_name': 'PrimaryAnalysis',
def setUp(self):
self.dbconfig = 'data/dbconfig.json'
dbparam = read_dbconf_json(self.dbconfig)
base = BaseAdaptor(**dbparam)
self.engine = base.engine
self.dbname = dbparam['dbname']
Base.metadata.drop_all(self.engine)
if os.path.exists(self.dbname):
os.remove(self.dbname)
Base.metadata.create_all(self.engine)
self.session_class = base.get_session_class()
base.start_session()
# PLATFORM
platform_data = [{
"platform_igf_id": "M03291",
"model_name": "MISEQ",
"vendor_name": "ILLUMINA",
"software_name": "RTA",
"software_version": "RTA1.18.54"
}]
flowcell_rule_data = [{
"platform_igf_id": "M03291",
"flowcell_type": "MISEQ",
"index_1": "NO_CHANGE",
"index_2": "NO_CHANGE"
}]
pl = PlatformAdaptor(**{'session': base.session})
pl.store_platform_data(data=platform_data)
pl.store_flowcell_barcode_rule(data=flowcell_rule_data)
# SEQRUN
seqrun_data = [{
'seqrun_igf_id': '180416_M03291_0139_000000000-TEST',
'flowcell_id': '000000000-TEST',
'platform_igf_id': 'M03291',
'flowcell': 'MISEQ',
}, {
'seqrun_igf_id': '180416_M03291_0140_000000000-TEST',
'flowcell_id': '000000000-TEST',
'platform_igf_id': 'M03291',
'flowcell': 'MISEQ',
}]
sra = SeqrunAdaptor(**{'session': base.session})
sra.store_seqrun_and_attribute_data(data=seqrun_data)
# PROJECT
project_data = [{'project_igf_id': 'IGFQ000123_test_10-4-2018_Miseq'}]
pa = ProjectAdaptor(**{'session': base.session})
pa.store_project_and_attribute_data(data=project_data)
# SAMPLE
sample_data = [{
'sample_igf_id': 'IGF00123',
'project_igf_id': 'IGFQ000123_test_10-4-2018_Miseq'
}, {
'sample_igf_id': 'IGF00124',
'project_igf_id': 'IGFQ000123_test_10-4-2018_Miseq'
}]
sa = SampleAdaptor(**{'session': base.session})
sa.store_sample_and_attribute_data(data=sample_data)
# EXPERIMENT
experiment_data = [{
'project_igf_id': 'IGFQ000123_test_10-4-2018_Miseq',
'sample_igf_id': 'IGF00123',
'experiment_igf_id': 'IGF00123_MISEQ',
'library_name': 'IGF00123',
'library_source': 'TRANSCRIPTOMIC_SINGLE_CELL',
'library_strategy': 'RNA-SEQ',
'experiment_type': 'POLYA-RNA',
'library_layout': 'PAIRED',
'platform_name': 'MISEQ',
'singlecell_chemistry': 'TENX'
}, {
'project_igf_id': 'IGFQ000123_test_10-4-2018_Miseq',
'sample_igf_id': 'IGF00124',
'experiment_igf_id': 'IGF00124_MISEQ',
'library_name': 'IGF00124',
'library_source': 'TRANSCRIPTOMIC_SINGLE_CELL',
'library_strategy': 'RNA-SEQ',
'experiment_type': 'POLYA-RNA',
'library_layout': 'PAIRED',
'platform_name': 'MISEQ',
'singlecell_chemistry': 'TENX'
}]
ea = ExperimentAdaptor(**{'session': base.session})
ea.store_project_and_attribute_data(data=experiment_data)
# RUN
run_data = [{
'experiment_igf_id': 'IGF00123_MISEQ',
'seqrun_igf_id': '180416_M03291_0139_000000000-TEST',
'run_igf_id': 'IGF00123_MISEQ_000000000-TEST_1',
'lane_number': '1'
}]
ra = RunAdaptor(**{'session': base.session})
ra.store_run_and_attribute_data(data=run_data)
# PIPELINE
pipeline_data = [{
"pipeline_name": "PrimaryAnalysis",
"pipeline_db": "sqlite:////aln.db",
}, {
"pipeline_name": "DemultiplexingFastq",
"pipeline_db": "sqlite:////fastq.db",
}]
pipeline_seed_data = [
{
'pipeline_name': 'PrimaryAnalysis',
'seed_id': 1,
'seed_table': 'experiment'
},
{
'pipeline_name': 'PrimaryAnalysis',
'seed_id': 2,
'seed_table': 'experiment'
},
{
'pipeline_name': 'DemultiplexingFastq',
'seed_id': 1,
'seed_table': 'seqrun'
},
{
'pipeline_name': 'DemultiplexingFastq',
'seed_id': 2,
'seed_table': 'seqrun'
},
]
update_data = [{
'pipeline_name': 'PrimaryAnalysis',
'seed_id': 2,
'seed_table': 'experiment',
'status': 'FINISHED'
}, {
'pipeline_name': 'DemultiplexingFastq',
'seed_id': 2,
'seed_table': 'seqrun',
'status': 'FINISHED'
}]
pla = PipelineAdaptor(**{'session': base.session})
pla.store_pipeline_data(data=pipeline_data)
pla.create_pipeline_seed(data=pipeline_seed_data)
pla.update_pipeline_seed(update_data)
base.close_session()