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 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 = BaseAdaptor(**{'session_class':self.session_class}) base.start_session() platform_data=[{ "platform_igf_id" : "M001", "model_name" : "MISEQ" , "vendor_name" : "ILLUMINA" , "software_name" : "RTA", "software_version" : "RTA1.18.54"}] # platform data flowcell_rule_data=[{"platform_igf_id":"M001", "flowcell_type":"MISEQ", "index_1":"NO_CHANGE", "index_2":"NO_CHANGE"}] # flowcell rule data pl=PlatformAdaptor(**{'session':base.session}) pl.store_platform_data(data=platform_data) # loading platform data pl.store_flowcell_barcode_rule(data=flowcell_rule_data) # loading flowcell rules data project_data=[{'project_igf_id':'ProjectA'}] # project data pa=ProjectAdaptor(**{'session':base.session}) pa.store_project_and_attribute_data(data=project_data) # load project data sample_data=[{'sample_igf_id':'SampleA', 'project_igf_id':'ProjectA'}] # sample data sa=SampleAdaptor(**{'session':base.session}) sa.store_sample_and_attribute_data(data=sample_data) # store sample data seqrun_data=[{'seqrun_igf_id':'SeqrunA', 'flowcell_id':'000000000-D0YLK', 'platform_igf_id':'M001', 'flowcell':'MISEQ'}] # seqrun data sra=SeqrunAdaptor(**{'session':base.session}) sra.store_seqrun_and_attribute_data(data=seqrun_data) # load seqrun data experiment_data=[{'experiment_igf_id':'ExperimentA', 'sample_igf_id':'SampleA', 'library_name':'SampleA', 'platform_name':'MISEQ', 'project_igf_id':'ProjectA'}] # experiment data ea=ExperimentAdaptor(**{'session':base.session}) ea.store_project_and_attribute_data(data=experiment_data) # load experiment data base.commit_session() base.close_session()
def test_fetch_flowcell_barcode_rules_for_seqrun(self): sra=SeqrunAdaptor(**{'session_class': self.session_class}) sra.start_session() sra_data=sra.fetch_flowcell_barcode_rules_for_seqrun(seqrun_igf_id='170101_K00001_0001_AHABCDEFGH') sra.close_session() sra_data=sra_data.to_dict(orient='records')[0] self.assertEqual(sra_data['index_2'],'REVCOMP')
def load_new_seqrun_data(data_file, dbconfig): ''' A method for loading new data for seqrun table ''' try: formatted_data=read_json_data(data_file) dbparam=read_dbconf_json(dbconfig) sr=SeqrunAdaptor(**dbparam) sr.start_session() sr.store_seqrun_and_attribute_data(data=formatted_data) sr.close_session() except: raise
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' self.flowcell_rules_json='data/flowcell_rules.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)) pl.store_flowcell_barcode_rule(data=read_json_data(self.flowcell_rules_json)) # load seqrun data sra=SeqrunAdaptor(**{'session':base.session}) sra.store_seqrun_and_attribute_data(data=read_json_data(self.seqrun_json)) base.close_session()
def test_reset_pipeline_seed_for_rerun(self): base = BaseAdaptor(**{'session_class': self.session_class}) base.start_session() sra = SeqrunAdaptor(**{'session': base.session}) seqrun = sra.fetch_seqrun_records_igf_id( seqrun_igf_id='171003_M00001_0089_000000000-TEST') pp = PipelineAdaptor(**{'session': base.session}) pipeline = pp.fetch_pipeline_records_pipeline_name( 'demultiplexing_fastq') pipe_seed = pp.fetch_pipeline_seed(pipeline_id=pipeline.pipeline_id, seed_id=seqrun.seqrun_id, seed_table='seqrun') self.assertEqual(pipe_seed.status, 'SEEDED') pp.update_pipeline_seed(data=[{ 'pipeline_id': pipeline.pipeline_id, 'seed_id': seqrun.seqrun_id, 'seed_table': 'seqrun', 'status': 'FINISHED', }]) pipe_seed2 = pp.fetch_pipeline_seed(pipeline_id=pipeline.pipeline_id, seed_id=seqrun.seqrun_id, seed_table='seqrun') self.assertEqual(pipe_seed2.status, 'FINISHED') base.close_session() with open(self.seqrun_input_list, 'w') as fp: fp.write('171003_M00001_0089_000000000-TEST') mps = Modify_pipeline_seed(igf_id_list=self.seqrun_input_list, table_name='seqrun', pipeline_name='demultiplexing_fastq', dbconfig_file=self.dbconfig, log_slack=False, log_asana=False, clean_up=True) mps.reset_pipeline_seed_for_rerun(seeded_label='SEEDED') base.start_session() sra = SeqrunAdaptor(**{'session': base.session}) seqrun = sra.fetch_seqrun_records_igf_id( seqrun_igf_id='171003_M00001_0089_000000000-TEST') pp = PipelineAdaptor(**{'session': base.session}) pipeline = pp.fetch_pipeline_records_pipeline_name( 'demultiplexing_fastq') pipe_seed = pp.fetch_pipeline_seed(pipeline_id=pipeline.pipeline_id, seed_id=seqrun.seqrun_id, seed_table='seqrun') self.assertEqual(pipe_seed.status, 'SEEDED') base.close_session()
def test_load_seqrun_files_to_db(self): valid_seqrun_dir = find_new_seqrun_dir(path=self.path, dbconfig=self.dbconfig) new_seqrun_and_md5 = calculate_file_md5(seqrun_info=valid_seqrun_dir, md5_out=self.md5_out_path, seqrun_path=self.path) load_seqrun_files_to_db(seqrun_info=valid_seqrun_dir, seqrun_md5_info=new_seqrun_and_md5, dbconfig=self.dbconfig) # check in db dbparam = None with open(self.dbconfig, 'r') as json_data: dbparam = json.load(json_data) sra = SeqrunAdaptor(**dbparam) sra.start_session() sra_data = sra.fetch_seqrun_records_igf_id(seqrun_igf_id='seqrun1') sra.close_session() self.assertEqual(sra_data.flowcell_id, 'HXXXXXXXX') seed_pipeline_table_for_new_seqrun( pipeline_name='demultiplexing_fastq', dbconfig=self.dbconfig) # check in db dbparam = None with open(self.dbconfig, 'r') as json_data: dbparam = json.load(json_data) base = BaseAdaptor(**dbparam) base.start_session() seeds=base.fetch_records(query=base.session.query(Seqrun.seqrun_igf_id).\ join(Pipeline_seed, Pipeline_seed.seed_id==Seqrun.seqrun_id).\ join(Pipeline, Pipeline.pipeline_id==Pipeline_seed.pipeline_id).\ filter(Pipeline.pipeline_name=='demultiplexing_fastq').\ filter(Pipeline_seed.seed_table=='seqrun'), output_mode='object') base.close_session() self.assertTrue('seqrun1' in [s.seqrun_igf_id for s in seeds])
def setUp(self): self.path = 'data/seqrun_dir' self.dbconfig = 'data/dbconfig.json' self.md5_out_path = 'data/md5_dir' self.pipeline_name = 'demultiplexing_fastq' seqrun_json = 'data/seqrun_db_data.json' platform_json = 'data/platform_db_data.json' pipeline_json = 'data/pipeline_data.json' os.mkdir(self.md5_out_path) dbparam = None with open(self.dbconfig, 'r') as json_data: dbparam = json.load(json_data) base = BaseAdaptor(**dbparam) self.engine = base.engine self.dbname = dbparam['dbname'] self.pipeline_name = '' Base.metadata.create_all(self.engine) base.start_session() user_data = [ { 'name': 'user1', 'email_id': '*****@*****.**', 'username': '******' }, ] ua = UserAdaptor(**{'session': base.session}) ua.store_user_data(data=user_data) project_data = [{ 'project_igf_id': 'project_1', '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) project_user_data = [{ 'project_igf_id': 'project_1', 'email_id': '*****@*****.**', 'data_authority': True }] pa.assign_user_to_project(data=project_user_data) sample_data = [ { 'sample_igf_id': 'IGF0001', 'project_igf_id': 'project_1', }, { 'sample_igf_id': 'IGF0002', 'project_igf_id': 'project_1', }, { 'sample_igf_id': 'IGF0003', 'project_igf_id': 'project_1', }, ] sa = SampleAdaptor(**{'session': base.session}) sa.store_sample_and_attribute_data(data=sample_data) base.commit_session() with open(pipeline_json, 'r') as json_data: # store pipeline data to db pipeline_data = json.load(json_data) pa = PipelineAdaptor(**{'session': base.session}) pa.store_pipeline_data(data=pipeline_data) with open(platform_json, 'r') as json_data: # store platform data to db platform_data = json.load(json_data) pl = PlatformAdaptor(**{'session': base.session}) pl.store_platform_data(data=platform_data) with open(seqrun_json, 'r') as json_data: # store seqrun data to db seqrun_data = json.load(json_data) sra = SeqrunAdaptor(**{'session': base.session}) sra.store_seqrun_and_attribute_data(data=seqrun_data) base.close_session()
def run(self): try: igf_session_class = self.param_required('igf_session_class') seqrun_igf_id = self.param_required('seqrun_igf_id') seqrun_local_dir = self.param_required('seqrun_local_dir') base_work_dir = self.param_required('base_work_dir') samplesheet_filename = self.param('samplesheet_filename') index2_label = self.param('index2_label_in_db') revcomp_label = self.param('revcomp_label') singlecell_tag = self.param('singlecell_tag') adapter_trim_check = self.param('adapter_trim_check') adapter_section = self.param('adapter_section') read1_adapter_label = self.param('read1_adapter_label') read2_adapter_label = self.param('read2_adapter_label') project_type = self.param('project_type') job_name = self.job_name() work_dir = \ os.path.join(\ base_work_dir, seqrun_igf_id, job_name) # get work directory name if not os.path.exists(work_dir): os.makedirs(work_dir, mode=0o770) # create work directory output_file = \ os.path.join(\ work_dir, samplesheet_filename) # get name of the output file if os.path.exists(output_file): raise IOError('seqrun: {0}, reformatted samplesheet {1} already present'.\ format(seqrun_igf_id,output_file)) samplesheet_file = \ os.path.join(\ seqrun_local_dir, seqrun_igf_id, samplesheet_filename) if not os.path.exists(samplesheet_file): raise IOError('seqrun: {0}, samplesheet file {1} not found'.\ format(seqrun_igf_id,samplesheet_file)) samplesheet_sc = \ SampleSheet(infile=samplesheet_file) # read samplesheet for single cell check samplesheet_sc.\ filter_sample_data(\ condition_key='Description', condition_value=singlecell_tag, method='include') # get 10X samplesheet if len(samplesheet_sc._data) > 0: project_type = singlecell_tag # check if 10x samples are present in samplesheet samplesheet = \ SampleSheet(infile=samplesheet_file) # read samplesheet samplesheet.\ filter_sample_data(\ condition_key='Description', condition_value=singlecell_tag, method='exclude') # filter 10X samplesheet if adapter_trim_check: read1_val = \ samplesheet.\ check_sample_header(\ section=adapter_section, condition_key=read1_adapter_label) read2_val = \ samplesheet.\ check_sample_header(\ section=adapter_section, condition_key=read2_adapter_label) if read1_val == 0 or read2_val == 0: message = \ 'seqrun {0} samplesheet does not have adapter trim option, read1: {1}, read2:{2}'.\ format(seqrun_igf_id,read1_val,read2_val) self.post_message_to_slack(message, reaction='pass') self.comment_asana_task( task_name=seqrun_igf_id, comment=message ) # send info about adapter trip to slack and asana sa = SeqrunAdaptor(**{'session_class': igf_session_class}) sa.start_session() rules_data = \ sa.fetch_flowcell_barcode_rules_for_seqrun(seqrun_igf_id) # convert index based on barcode rules sa.close_session() rules_data_set = rules_data.to_dict( orient='records') # convert dataframe to dictionary if len(rules_data_set) > 0: rules_data = rules_data_set[0] # consider only the first rule if rules_data[index2_label] == revcomp_label: samplesheet.\ get_reverse_complement_index(index_field='index2') # reverse complement index2 based on the rules else: message = \ 'no rules found for seqrun {0}, using original samplesheet'.\ format(seqrun_igf_id) self.post_message_to_slack(message, reaction='pass') self.comment_asana_task(task_name=seqrun_igf_id, comment=message) if len(samplesheet_sc._data) > 0: # merge 10x samplesheet samplesheet._data.extend(samplesheet_sc._data) message = \ 'seqrun: {0}, merging 10X samples with reformatted samplesheet'.\ format(seqrun_igf_id) self.post_message_to_slack(message, reaction='pass') self.comment_asana_task(task_name=seqrun_igf_id, comment=message) samplesheet.print_sampleSheet(outfile=output_file) self.param('dataflow_params', { 'samplesheet': output_file, 'project_type': project_type }) message = \ 'seqrun: {0}, reformatted samplesheet:{1}'.\ format(\ seqrun_igf_id, output_file) self.post_message_to_slack(message, reaction='pass') self.comment_asana_task(task_name=seqrun_igf_id, comment=message) except Exception as e: message = \ 'seqrun: {2}, Error in {0}: {1}'.\ format(\ self.__class__.__name__, e, seqrun_igf_id) self.warning(message) self.post_message_to_slack( message, reaction='fail') # post msg to slack for failed jobs raise
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": "M03291", "model_name": "MISEQ", "vendor_name": "ILLUMINA", "software_name": "RTA", "software_version": "RTA1.18.54" }, { "platform_igf_id": "NB501820", "model_name": "NEXTSEQ", "vendor_name": "ILLUMINA", "software_name": "RTA", "software_version": "RTA2" }, { "platform_igf_id": "K00345", "model_name": "HISEQ4000", "vendor_name": "ILLUMINA", "software_name": "RTA", "software_version": "RTA2" }] flowcell_rule_data = [{ "platform_igf_id": "K00345", "flowcell_type": "HiSeq 3000/4000 SR", "index_1": "NO_CHANGE", "index_2": "NO_CHANGE" }, { "platform_igf_id": "K00345", "flowcell_type": "HiSeq 3000/4000 PE", "index_1": "NO_CHANGE", "index_2": "REVCOMP" }, { "platform_igf_id": "NB501820", "flowcell_type": "NEXTSEQ", "index_1": "NO_CHANGE", "index_2": "REVCOMP" }, { "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_data = [{ 'seqrun_igf_id': '180416_M03291_0139_000000000-BRN47', 'flowcell_id': '000000000-BRN47', 'platform_igf_id': 'M03291', 'flowcell': 'MISEQ', }, { 'seqrun_igf_id': '180416_NB03291_013_000000001-BRN47', 'flowcell_id': '000000001-BRN47', 'platform_igf_id': 'NB501820', 'flowcell': 'NEXTSEQ', }] sra = SeqrunAdaptor(**{'session': base.session}) sra.store_seqrun_and_attribute_data(data=seqrun_data) project_data = [{'project_igf_id': 'projectA'}] pa = ProjectAdaptor(**{'session': base.session}) pa.store_project_and_attribute_data(data=project_data) sample_data = [ { 'sample_igf_id': 'sampleA', 'project_igf_id': 'projectA', 'species_name': 'HG38' }, { 'sample_igf_id': 'sampleB', 'project_igf_id': 'projectA', 'species_name': 'UNKNOWN' }, ] sa = SampleAdaptor(**{'session': base.session}) sa.store_sample_and_attribute_data(data=sample_data) experiment_data = [ { 'project_igf_id': 'projectA', 'sample_igf_id': 'sampleA', 'experiment_igf_id': 'sampleA_MISEQ', 'library_name': 'sampleA', 'library_source': 'TRANSCRIPTOMIC_SINGLE_CELL', 'library_strategy': 'RNA-SEQ', 'experiment_type': 'TENX-TRANSCRIPTOME-3P', 'library_layout': 'PAIRED', 'platform_name': 'MISEQ', }, { 'project_igf_id': 'projectA', 'sample_igf_id': 'sampleA', 'experiment_igf_id': 'sampleA_NEXTSEQ', 'library_name': 'sampleA', 'library_source': 'UNKNOWN', 'library_strategy': 'RNA-SEQ', 'experiment_type': 'TENX-TRANSCRIPTOME-3P', 'library_layout': 'PAIRED', 'platform_name': 'NEXTSEQ', }, { 'project_igf_id': 'projectA', 'sample_igf_id': 'sampleB', 'experiment_igf_id': 'sampleB_MISEQ', 'library_name': 'sampleB', 'library_source': 'TRANSCRIPTOMIC_SINGLE_CELL', 'library_strategy': 'RNA-SEQ', 'experiment_type': 'TENX-TRANSCRIPTOME-3P', 'library_layout': 'PAIRED', 'platform_name': 'MISEQ', }, ] ea = ExperimentAdaptor(**{'session': base.session}) ea.store_project_and_attribute_data(data=experiment_data) run_data = [{ 'experiment_igf_id': 'sampleA_MISEQ', 'seqrun_igf_id': '180416_M03291_0139_000000000-BRN47', 'run_igf_id': 'sampleA_MISEQ_000000000-BRN47_1', 'lane_number': '1' }, { 'experiment_igf_id': 'sampleA_NEXTSEQ', 'seqrun_igf_id': '180416_NB03291_013_000000001-BRN47', 'run_igf_id': 'sampleA_NEXTSEQ_000000001-BRN47_2', 'lane_number': '2' }, { 'experiment_igf_id': 'sampleB_MISEQ', 'seqrun_igf_id': '180416_M03291_0139_000000000-BRN47', 'run_igf_id': 'sampleB_MISEQ_HVWN7BBXX_1', 'lane_number': '1' }] ra = RunAdaptor(**{'session': base.session}) ra.store_run_and_attribute_data(data=run_data) file_data = [ { 'file_path': '/path/sampleA_MISEQ_000000000-BRN47_1_R1.fastq.gz', 'location': 'HPC_PROJECT', 'md5': 'fd5a95c18ebb7145645e95ce08d729e4', 'size': '1528121404', }, { 'file_path': '/path/sampleA_NEXTSEQ_000000001-BRN47_2_R1.fastq.gz', 'location': 'HPC_PROJECT', 'md5': 'fd5a95c18ebb7145645e95ce08d729e4', 'size': '1528121404', }, { 'file_path': '/path/sampleB_MISEQ_HVWN7BBXX_1_R1.fastq.gz', 'location': 'HPC_PROJECT', 'md5': 'fd5a95c18ebb7145645e95ce08d729e4', 'size': '1528121404', }, ] fa = FileAdaptor(**{'session': base.session}) fa.store_file_and_attribute_data(data=file_data) collection_data = [{ 'name': 'sampleA_MISEQ_000000000-BRN47_1', 'type': 'demultiplexed_fastq', 'table': 'run' }, { 'name': 'sampleA_NEXTSEQ_000000001-BRN47_2', 'type': 'demultiplexed_fastq', 'table': 'run' }, { 'name': 'sampleB_MISEQ_HVWN7BBXX_1', 'type': 'demultiplexed_fastq', 'table': 'run' }] collection_files_data = [{ 'name': 'sampleA_MISEQ_000000000-BRN47_1', 'type': 'demultiplexed_fastq', 'file_path': '/path/sampleA_MISEQ_000000000-BRN47_1_R1.fastq.gz' }, { 'name': 'sampleA_NEXTSEQ_000000001-BRN47_2', 'type': 'demultiplexed_fastq', 'file_path': '/path/sampleA_NEXTSEQ_000000001-BRN47_2_R1.fastq.gz' }, { 'name': 'sampleB_MISEQ_HVWN7BBXX_1', 'type': 'demultiplexed_fastq', 'file_path': '/path/sampleB_MISEQ_HVWN7BBXX_1_R1.fastq.gz' }] ca = CollectionAdaptor(**{'session': base.session}) ca.store_collection_and_attribute_data(data=collection_data) ca.create_collection_group(data=collection_files_data) base.close_session()
}, { 'run_igf_id': 'RunC', 'experiment_igf_id': 'ExperimentA', 'seqrun_igf_id': '180410_K00345_0063_AHWL7CBBXX', 'lane_number': '1' }] # run data base.start_session() pl = PlatformAdaptor(**{'session': base.session}) pl.store_platform_data(data=platform_data) # loading platform data pl.store_flowcell_barcode_rule( data=flowcell_rule_data) # loading flowcell rules data pa = ProjectAdaptor(**{'session': base.session}) pa.store_project_and_attribute_data(data=project_data) # load project data sa = SampleAdaptor(**{'session': base.session}) sa.store_sample_and_attribute_data(data=sample_data) # store sample data sra = SeqrunAdaptor(**{'session': base.session}) sra.store_seqrun_and_attribute_data(data=seqrun_data) # load seqrun data ea = ExperimentAdaptor(**{'session': base.session}) ea.store_project_and_attribute_data( data=experiment_data) # load experiment data ra = RunAdaptor(**{'session': base.session}) ra.store_run_and_attribute_data(data=run_data) # load run data pipeline_data = [{ "pipeline_name": "DemultiplexIlluminaFastq", "pipeline_db": "sqlite:////bcl2fastq.db", }] pipeline_seed_data = [ { 'pipeline_name': 'DemultiplexIlluminaFastq', 'seed_id': 1,
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() self.temp_work_dir = get_temp_dir() self.temp_base_dir = get_temp_dir() self.input_list = ['a.cram', 'a.vcf.gz', 'b.tar.gz'] for file_name in self.input_list: file_path = os.path.join(self.temp_work_dir, file_name) with open(file_path, 'w') as fq: fq.write('AAAA') # create input files base = BaseAdaptor(**{'session_class': self.session_class}) base.start_session() platform_data = [{ "platform_igf_id": "M001", "model_name": "MISEQ", "vendor_name": "ILLUMINA", "software_name": "RTA", "software_version": "RTA1.18.54" }] # platform data flowcell_rule_data = [{ "platform_igf_id": "M001", "flowcell_type": "MISEQ", "index_1": "NO_CHANGE", "index_2": "NO_CHANGE" }] # flowcell rule data pl = PlatformAdaptor(**{'session': base.session}) pl.store_platform_data(data=platform_data) # loading platform data pl.store_flowcell_barcode_rule( data=flowcell_rule_data) # loading flowcell rules data project_data = [{'project_igf_id': 'ProjectA'}] # project data pa = ProjectAdaptor(**{'session': base.session}) pa.store_project_and_attribute_data( data=project_data) # load project data sample_data = [{ 'sample_igf_id': 'SampleA', 'project_igf_id': 'ProjectA' }] # sample data sa = SampleAdaptor(**{'session': base.session}) sa.store_sample_and_attribute_data( data=sample_data) # store sample data seqrun_data = [{ 'seqrun_igf_id': 'SeqrunA', 'flowcell_id': '000000000-D0YLK', 'platform_igf_id': 'M001', 'flowcell': 'MISEQ' }] # seqrun data sra = SeqrunAdaptor(**{'session': base.session}) sra.store_seqrun_and_attribute_data( data=seqrun_data) # load seqrun data experiment_data = [{ 'experiment_igf_id': 'ExperimentA', 'sample_igf_id': 'SampleA', 'library_name': 'SampleA', 'platform_name': 'MISEQ', 'project_igf_id': 'ProjectA' }] # experiment data ea = ExperimentAdaptor(**{'session': base.session}) ea.store_project_and_attribute_data( data=experiment_data) # load experiment data run_data = [{ 'run_igf_id': 'RunA', 'experiment_igf_id': 'ExperimentA', 'seqrun_igf_id': 'SeqrunA', 'lane_number': '1' }] # run data ra = RunAdaptor(**{'session': base.session}) ra.store_run_and_attribute_data(data=run_data) # load run data base.commit_session() 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() # load platform data platform_data=\ [{"platform_igf_id" : "M03291" , "model_name" : "MISEQ" , "vendor_name" : "ILLUMINA" , "software_name" : "RTA" , "software_version" : "RTA1.18.54" }, {"platform_igf_id" : "NB501820", "model_name" : "NEXTSEQ", "vendor_name" : "ILLUMINA", "software_name" : "RTA", "software_version" : "RTA2" }, {"platform_igf_id" : "K00345", "model_name" : "HISEQ4000", "vendor_name" : "ILLUMINA", "software_name" : "RTA", "software_version" : "RTA2" }] flowcell_rule_data=\ [{"platform_igf_id":"K00345", "flowcell_type":"HiSeq 3000/4000 SR", "index_1":"NO_CHANGE", "index_2":"NO_CHANGE"}, {"platform_igf_id":"K00345", "flowcell_type":"HiSeq 3000/4000 PE", "index_1":"NO_CHANGE", "index_2":"REVCOMP"}, {"platform_igf_id":"NB501820", "flowcell_type":"NEXTSEQ", "index_1":"NO_CHANGE", "index_2":"REVCOMP"}, {"platform_igf_id":"M03291", "flowcell_type":"MISEQ", "index_1":"NO_CHANGE", "index_2":"NO_CHANGE"}] pl = PlatformAdaptor(**{'session_class': base.session_class}) pl.start_session() pl.store_platform_data(data=platform_data) pl.store_flowcell_barcode_rule(data=flowcell_rule_data) pl.close_session() # load project data project_data = [{'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA'}] pa = ProjectAdaptor(**{'session_class': base.session_class}) pa.start_session() pa.store_project_and_attribute_data(data=project_data) pa.close_session() # load samples sample_data = [ { 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109792', 'expected_read': 40000000 }, { 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109793', 'expected_read': 40000000 }, { 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109794', 'expected_read': 40000000 }, { 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109795', 'expected_read': 40000000 }, { 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109796', 'expected_read': 40000000 }, { 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109797', 'expected_read': 40000000 }, { 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109797_1', 'expected_read': 40000000 }, ] sa = SampleAdaptor(**{'session_class': base.session_class}) sa.start_session() sa.store_sample_and_attribute_data(data=sample_data) sa.close_session() # load seqrun data seqrun_data = [{ 'flowcell_id': 'HV2GJBBXX', 'platform_igf_id': 'K00345', 'seqrun_igf_id': '180518_K00345_0047_BHV2GJBBXX' }] sra = SeqrunAdaptor(**{'session_class': base.session_class}) sra.start_session() sra.store_seqrun_and_attribute_data(data=seqrun_data) sra.close_session() # load experiment data experiment_data=\ [{'experiment_igf_id': 'IGF109792_HISEQ4000', 'library_name': 'IGF109792', 'platform_name': 'HISEQ4000', 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109792', }, {'experiment_igf_id': 'IGF109793_HISEQ4000', 'library_name': 'IGF109793', 'platform_name': 'HISEQ4000', 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109793', }, {'experiment_igf_id': 'IGF109794_HISEQ4000', 'library_name': 'IGF109794', 'platform_name': 'HISEQ4000', 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109794', }, {'experiment_igf_id': 'IGF109795_HISEQ4000', 'library_name': 'IGF109795', 'platform_name': 'HISEQ4000', 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109795', }, {'experiment_igf_id': 'IGF109796_HISEQ4000', 'library_name': 'IGF109796', 'platform_name': 'HISEQ4000', 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109796', }, {'experiment_igf_id': 'IGF109797_HISEQ4000', 'library_name': 'IGF109797', 'platform_name': 'HISEQ4000', 'project_igf_id': 'IGFQ000472_avik_28-3-2018_RNA', 'sample_igf_id': 'IGF109797', }, ] ea = ExperimentAdaptor(**{'session_class': base.session_class}) ea.start_session() ea.store_project_and_attribute_data(data=experiment_data) ea.close_session() # load run data run_data=\ [{'experiment_igf_id': 'IGF109792_HISEQ4000', 'lane_number': '7', 'run_igf_id': 'IGF109792_HISEQ4000_H2N3MBBXY_7', 'seqrun_igf_id': '180518_K00345_0047_BHV2GJBBXX', 'R1_READ_COUNT':288046541 }, {'experiment_igf_id': 'IGF109793_HISEQ4000', 'lane_number': '7', 'run_igf_id': 'IGF109793_HISEQ4000_H2N3MBBXY_7', 'seqrun_igf_id': '180518_K00345_0047_BHV2GJBBXX', 'R1_READ_COUNT':14666330 }, {'experiment_igf_id': 'IGF109794_HISEQ4000', 'lane_number': '7', 'run_igf_id': 'IGF109794_HISEQ4000_H2N3MBBXY_7', 'seqrun_igf_id': '180518_K00345_0047_BHV2GJBBXX', 'R1_READ_COUNT':5009143 }, {'experiment_igf_id': 'IGF109795_HISEQ4000', 'lane_number': '7', 'run_igf_id': 'IGF109795_HISEQ4000_H2N3MBBXY_7', 'seqrun_igf_id': '180518_K00345_0047_BHV2GJBBXX', 'R1_READ_COUNT':1391747 }, {'experiment_igf_id': 'IGF109796_HISEQ4000', 'lane_number': '7', 'run_igf_id': ' IGF109796_HISEQ4000_H2N3MBBXY_7', 'seqrun_igf_id': '180518_K00345_0047_BHV2GJBBXX', 'R1_READ_COUNT':1318008 }, {'experiment_igf_id': 'IGF109797_HISEQ4000', 'lane_number': '7', 'run_igf_id': 'IGF109797_HISEQ4000_H2N3MBBXY_7', 'seqrun_igf_id': '180518_K00345_0047_BHV2GJBBXX', 'R1_READ_COUNT':1216324 }, ] ra = RunAdaptor(**{'session_class': base.session_class}) ra.start_session() ra.store_run_and_attribute_data(data=run_data) ra.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('')
def setUp(self): self.dbconfig = 'data/dbconfig.json' self.fastq_dir = 'data/collect_fastq_dir/sc_1_8' self.model_name = 'NEXTSEQ' self.flowcell_id = 'TESTABC' self.seqrun_igf_id = '171003_NB500000_0089_TESTABC' self.file_location = 'HPC_PROJECT' self.samplesheet_file = 'data/collect_fastq_dir/sc_1_8/SampleSheet.csv' self.samplesheet_filename = 'SampleSheet.csv' self.manifest_name = 'file_manifest.csv' 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.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) 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', }, { '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) seqrun_data = [{ 'seqrun_igf_id': '171003_NB500000_0089_TESTABC', 'flowcell_id': 'TESTABC', 'platform_igf_id': 'NB500000', 'flowcell': 'NEXTSEQ', }] sra = SeqrunAdaptor(**{'session': base.session}) sra.store_seqrun_and_attribute_data(data=seqrun_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": "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) project_data = [{'project_igf_id': 'IGFQ000123_avik_10-4-2018_Miseq'}] pa = ProjectAdaptor(**{'session': base.session}) pa.store_project_and_attribute_data(data=project_data) sample_data = [{ 'sample_igf_id': 'IGF103923', 'project_igf_id': 'IGFQ000123_avik_10-4-2018_Miseq', 'species_name': 'HG38' }] sa = SampleAdaptor(**{'session': base.session}) sa.store_sample_and_attribute_data(data=sample_data) seqrun_data = [ { 'seqrun_igf_id': '180416_M03291_0139_000000000-BRN47', 'flowcell_id': '000000000-BRN47', 'platform_igf_id': 'M03291', 'flowcell': 'MISEQ' }, ] sra = SeqrunAdaptor(**{'session': base.session}) sra.store_seqrun_and_attribute_data(data=seqrun_data) pipeline_data = [ { "pipeline_name": "PrimaryAnalysis", "pipeline_db": "sqlite:////bcl2fastq.db" }, { "pipeline_name": "DemultiplexIlluminaFastq", "pipeline_db": "sqlite:////bcl2fastq.db" }, ] pla = PipelineAdaptor(**{'session': base.session}) pla.store_pipeline_data(data=pipeline_data) file_data = [ { 'file_path': '/path/S20180405S_S1_L001_R1_001.fastq.gz', 'location': 'HPC_PROJECT', 'md5': 'fd5a95c18ebb7145645e95ce08d729e4', 'size': '1528121404' }, { 'file_path': '/path/S20180405S_S1_L001_R2_001.fastq.gz', 'location': 'HPC_PROJECT', 'md5': 'fd5a95c18ebb7145645e95ce08d729e4', 'size': '1467047580' }, { 'file_path': '/path/S20180405S_S3_L001_R2_001.fastq.gz', 'location': 'HPC_PROJECT', 'md5': 'fd5a95c18ebb7145645e95ce08d729e4', 'size': '1467047580' }, ] fa = FileAdaptor(**{'session': base.session}) fa.store_file_and_attribute_data(data=file_data) collection_data = [ { 'name': 'IGF103923_MISEQ_000000000-BRN47_1', 'type': 'demultiplexed_fastq', 'table': 'run' }, { 'name': 'IGF103923_MISEQ1_000000000-BRN47_1', 'type': 'demultiplexed_fastq', 'table': 'run' }, ] collection_files_data = [ { 'name': 'IGF103923_MISEQ_000000000-BRN47_1', 'type': 'demultiplexed_fastq', 'file_path': '/path/S20180405S_S1_L001_R1_001.fastq.gz' }, { 'name': 'IGF103923_MISEQ_000000000-BRN47_1', 'type': 'demultiplexed_fastq', 'file_path': '/path/S20180405S_S1_L001_R2_001.fastq.gz' }, { 'name': 'IGF103923_MISEQ1_000000000-BRN47_1', 'type': 'demultiplexed_fastq', 'file_path': '/path/S20180405S_S3_L001_R2_001.fastq.gz' }, ] ca = CollectionAdaptor(**{'session': base.session}) ca.store_collection_and_attribute_data(data=collection_data) ca.create_collection_group(data=collection_files_data) experiment_data = [{ 'project_igf_id': 'IGFQ000123_avik_10-4-2018_Miseq', 'sample_igf_id': 'IGF103923', 'experiment_igf_id': 'IGF103923_MISEQ', 'library_name': 'IGF103923', 'library_source': 'TRANSCRIPTOMIC_SINGLE_CELL', 'library_strategy': 'RNA-SEQ', 'experiment_type': 'TENX-TRANSCRIPTOME-3P', 'library_layout': 'PAIRED', 'platform_name': 'MISEQ' }, { 'project_igf_id': 'IGFQ000123_avik_10-4-2018_Miseq', 'sample_igf_id': 'IGF103923', 'experiment_igf_id': 'IGF103923_MISEQ1', 'library_name': 'IGF103923_1', 'library_source': 'GENOMIC_SINGLE_CELL', 'library_strategy': 'WGS', 'experiment_type': 'UNKNOWN', 'library_layout': 'PAIRED', 'platform_name': 'MISEQ' }] ea = ExperimentAdaptor(**{'session': base.session}) ea.store_project_and_attribute_data(data=experiment_data) run_data = [{ 'experiment_igf_id': 'IGF103923_MISEQ', 'seqrun_igf_id': '180416_M03291_0139_000000000-BRN47', 'run_igf_id': 'IGF103923_MISEQ_000000000-BRN47_1', 'lane_number': '1' }, { 'experiment_igf_id': 'IGF103923_MISEQ1', 'seqrun_igf_id': '180416_M03291_0139_000000000-BRN47', 'run_igf_id': 'IGF103923_MISEQ1_000000000-BRN47_1', 'lane_number': '1' }] ra = RunAdaptor(**{'session': base.session}) ra.store_run_and_attribute_data(data=run_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.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()