Mercurial > repos > iuc > ena_upload

comparison extract_tables.py @ 10:e7995727674f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ena_upload commit 6428c6a64979e4a1f745066a62280e38ad98d249
author iuc
date Mon, 27 Jan 2025 18:12:01 +0000
parents 69fc9c4a68b7
children
comparison
equal deleted inserted replaced
9:69fc9c4a68b7 10:e7995727674f
38 dt_oobj = datetime.now(tz=None) 38 dt_oobj = datetime.now(tz=None)
39 timestamp = dt_oobj.strftime("%Y%m%d_%H:%M:%S") 39 timestamp = dt_oobj.strftime("%Y%m%d_%H:%M:%S")
40 for study_index, study in enumerate(studies_dict): 40 for study_index, study in enumerate(studies_dict):
41 study_alias = 'study_' + str(study_index) + '_' + timestamp 41 study_alias = 'study_' + str(study_index) + '_' + timestamp
42 studies_table.write('\t'.join([study_alias, action, study['title'], 42 studies_table.write('\t'.join([study_alias, action, study['title'],
43 study['type'], study['abstract'], study['pubmed_id'], 43 study['type'], study['abstract'], study['pubmed_id']]))
44 ])) 44 if "host_subject_id" in study['samples'][0].keys(): # sample belongs to a viral sample
45 if "geo_location" in study['samples'][0].keys(): # sample belongs to a viral sample
46 samples_table.write('\t'.join(['alias', 'status', 'title', 'scientific_name', 45 samples_table.write('\t'.join(['alias', 'status', 'title', 'scientific_name',
47 'taxon_id', 'sample_description', 'collection date', 46 'taxon_id', 'sample_description', 'collection date',
48 'geographic location (country and/or sea)', 'host common name', 'host subject id', 47 'geographic location (country and/or sea)', 'host common name', 'host subject id',
49 'host health state', 'host sex', 'host scientific name', 48 'host health state', 'host sex', 'host scientific name',
50 'collector name', 'collecting institution', 'isolate', 49 'collector name', 'collecting institution', 'isolate']) + '\n')
51 ]) + '\n')
52 else: 50 else:
53 samples_table.write('\t'.join(['alias', 'status', 'title', 'scientific_name', 51 samples_table.write('\t'.join(['alias', 'status', 'title', 'scientific_name',
54 'taxon_id', 'sample_description']) + '\n') 52 'taxon_id', 'sample_description', 'collection date',
53 'geographic location (country and/or sea)']) + '\n')
55 for sample_index, sample in enumerate(study['samples']): 54 for sample_index, sample in enumerate(study['samples']):
56 sample_alias = 'sample_' + str(sample_index) + '_' + timestamp 55 sample_alias = 'sample_' + str(sample_index) + '_' + timestamp
57 if "geo_location" in sample.keys(): # sample belongs to a viral sample 56 if "host_subject_id" in sample.keys(): # sample belongs to a viral sample
58 if sample['collector_name'] == '': 57 if sample['collector_name'] == '':
59 sample['collector_name'] = 'unknown' 58 sample['collector_name'] = 'unknown'
60 samples_table.write('\t'.join([sample_alias, action, sample['title'], 59 samples_table.write('\t'.join([sample_alias, action, sample['title'],
61 sample['tax_name'], sample['tax_id'], 60 sample['tax_name'], sample['tax_id'],
62 sample['description'], sample['collection_date'], 61 sample['description'], sample['collection_date'],
63 sample['geo_location'], sample['host_common_name'], 62 sample['geo_location'], sample['host_common_name'],
64 sample['host_subject_id'], sample['host_health_state'], 63 sample['host_subject_id'], sample['host_health_state'],
65 sample['host_sex'], sample['host_scientific_name'], 64 sample['host_sex'], sample['host_scientific_name'],
66 sample['collector_name'], 65 sample['collector_name'],
67 sample['collecting_institution'], sample['isolate'], 66 sample['collecting_institution'], sample['isolate']
68 ]) + '\n') 67 ]) + '\n')
69 else: 68 else:
70 samples_table.write('\t'.join([sample_alias, action, sample['title'], 69 samples_table.write('\t'.join([sample_alias, action, sample['title'],
71 sample['tax_name'], sample['tax_id'], 70 sample['tax_name'], sample['tax_id'],
72 sample['description']]) + '\n') 71 sample['description'], sample['collection_date'],
72 sample['geo_location']]) + '\n')
73 for exp_index, exp in enumerate(sample['experiments']): 73 for exp_index, exp in enumerate(sample['experiments']):
74 exp_alias = 'experiment_' + str(exp_index) + '.' + str(sample_index) + '_' + timestamp 74 exp_alias = 'experiment_' + str(exp_index) + '.' + str(sample_index) + '_' + timestamp
75 lib_alias = 'library_' + str(exp_index) + '_' + str(sample_index) 75 lib_alias = 'library_' + str(exp_index) + '_' + str(sample_index)
76 experiments_table.write('\t'.join([exp_alias, action, exp['title'], 76 experiments_table.write('\t'.join([exp_alias, action, exp['title'],
77 study_alias, sample_alias, exp['experiment_design'], 77 study_alias, sample_alias, exp['experiment_design'],
78 lib_alias, exp['library_strategy'], 78 lib_alias, exp['library_strategy'],
79 exp['library_source'], exp['library_selection'], 79 exp['library_source'], exp['library_selection'],
80 exp['library_layout'].lower(), exp['insert_size'], 80 exp['library_layout'].lower(), exp['insert_size'],
81 exp['library_construction_protocol'], 81 exp['library_construction_protocol'],
82 exp['platform'], exp['instrument_model'], 82 exp['platform'], exp['instrument_model']]) + '\n')
83 ]) + '\n')
84 run_index = 0 83 run_index = 0
85 # exp['runs'] is a list of lists 84 # exp['runs'] is a list of lists
86 for (base_run, run_files) in exp['runs']: 85 for (base_run, run_files) in exp['runs']:
87 run_index += 1 86 run_index += 1
88 if base_run != '': 87 if base_run != '':