Mercurial > repos > ieguinoa > ena_upload
comparison extract_tables.py @ 0:5d59238cd3f4 draft
Uploaded
| author | ieguinoa |
|---|---|
| date | Wed, 02 Feb 2022 17:16:15 +0000 |
| parents | |
| children | 2f7a70c0d3ab |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:5d59238cd3f4 |
|---|---|
| 1 import argparse | |
| 2 import json | |
| 3 import pathlib | |
| 4 from datetime import datetime | |
| 5 | |
| 6 """ | |
| 7 Parse the configfile generated by the Galaxy tool. | |
| 8 This file is JSON-formatted and should be converted to a set of tabular files. | |
| 9 """ | |
| 10 | |
| 11 FILE_FORMAT = 'fastq' | |
| 12 | |
| 13 parser = argparse.ArgumentParser() | |
| 14 parser.add_argument('--studies', dest='studies_json_path', required=True) | |
| 15 parser.add_argument('--out_dir', dest='out_path', required=True) | |
| 16 parser.add_argument('--action', dest='action', required=True) | |
| 17 args = parser.parse_args() | |
| 18 | |
| 19 with open(args.studies_json_path, 'r') as studies_json_file: | |
| 20 studies_dict = json.load(studies_json_file) | |
| 21 studies_table = open(pathlib.Path(args.out_path) / 'studies.tsv', 'w') | |
| 22 studies_table.write('\t'.join(['alias', 'status', 'accession', 'title', 'study_type', | |
| 23 'study_abstract', 'pubmed_id', 'submission_date']) + '\n') | |
| 24 samples_table = open(pathlib.Path(args.out_path) / 'samples.tsv', 'w') | |
| 25 experiments_table = open(pathlib.Path(args.out_path) / 'experiments.tsv', 'w') | |
| 26 experiments_table.write('\t'.join(['alias', 'status', 'accession', 'title', 'study_alias', | |
| 27 'sample_alias', 'design_description', 'library_name', | |
| 28 'library_strategy', 'library_source', 'library_selection', | |
| 29 'library_layout', 'insert_size', | |
| 30 'library_construction_protocol', 'platform', 'instrument_model', | |
| 31 'submission_date']) + '\n') | |
| 32 runs_table = open(pathlib.Path(args.out_path) / 'runs.tsv', 'w') | |
| 33 runs_table.write('\t'.join(['alias', 'status', 'accession', 'experiment_alias', 'file_name', | |
| 34 'file_format', 'file_checksum', 'submission_date']) + '\n') | |
| 35 | |
| 36 action = args.action | |
| 37 | |
| 38 dt_oobj = datetime.now(tz=None) | |
| 39 timestamp = dt_oobj.strftime("%Y%m%d_%H:%M:%S") | |
| 40 for study_index, study in enumerate(studies_dict): | |
| 41 study_alias = 'study_' + str(study_index) + '_' + timestamp | |
| 42 studies_table.write('\t'.join([study_alias, action, 'ENA_accession', study['title'], | |
| 43 study['type'], study['abstract'], study['pubmed_id'], | |
| 44 'ENA_submission_data'])) | |
| 45 if "geo_location" in study['samples'][0].keys(): # sample belongs to a viral sample | |
| 46 samples_table.write('\t'.join(['alias', 'status', 'accession', 'title', 'scientific_name', | |
| 47 'taxon_id', 'sample_description', 'collection_date', | |
| 48 'geographic_location', 'host_common_name', 'host_subject_id', | |
| 49 'host_health_state', 'host_sex', 'host_scientific_name', | |
| 50 'collector_name', 'collecting_institution', 'isolate', | |
| 51 'submission_date']) + '\n') | |
| 52 else: | |
| 53 samples_table.write('\t'.join(['alias', 'status', 'accession', 'title', 'scientific_name', | |
| 54 'taxon_id', 'sample_description', 'submission_date']) + '\n') | |
| 55 for sample_index, sample in enumerate(study['samples']): | |
| 56 sample_alias = 'sample_' + str(sample_index) + '_' + timestamp | |
| 57 if "geo_location" in sample.keys(): # sample belongs to a viral sample | |
| 58 if sample['collector_name'] == '': | |
| 59 sample['collector_name'] = 'unknown' | |
| 60 samples_table.write('\t'.join([sample_alias, action, 'ena_accession', sample['title'], | |
| 61 sample['tax_name'], sample['tax_id'], | |
| 62 sample['description'], sample['collection_date'], | |
| 63 sample['geo_location'], sample['host_common_name'], | |
| 64 sample['host_subject_id'], sample['host_health_state'], | |
| 65 sample['host_sex'], sample['host_scientific_name'], | |
| 66 sample['collector_name'], | |
| 67 sample['collecting_institution'], sample['isolate'], | |
| 68 'ENA_submission_date']) + '\n') | |
| 69 else: | |
| 70 samples_table.write('\t'.join([sample_alias, action, 'ena_accession', sample['title'], | |
| 71 sample['tax_name'], sample['tax_id'], | |
| 72 sample['description'], 'ENA_submission_date']) + '\n') | |
| 73 for exp_index, exp in enumerate(sample['experiments']): | |
| 74 exp_alias = 'experiment_' + str(exp_index) + '.' + str(sample_index) + '_' + timestamp | |
| 75 lib_alias = 'library_' + str(exp_index) + '_' + str(sample_index) | |
| 76 experiments_table.write('\t'.join([exp_alias, action, 'accession_ena', exp['title'], | |
| 77 study_alias, sample_alias, exp['experiment_design'], | |
| 78 lib_alias, exp['library_strategy'], | |
| 79 exp['library_source'], exp['library_selection'], | |
| 80 exp['library_layout'].lower(), exp['insert_size'], | |
| 81 exp['library_construction_protocol'], | |
| 82 exp['platform'], exp['instrument_model'], | |
| 83 'submission_date_ENA']) + '\n') | |
| 84 run_index = 0 | |
| 85 # exp['runs'] is a list of lists | |
| 86 for (base_run, run_files) in exp['runs']: | |
| 87 run_index += 1 | |
| 88 if base_run != '': | |
| 89 run_alias = base_run | |
| 90 else: | |
| 91 # no alias provided, generated a unique one | |
| 92 run_alias = '_'.join(['run_' + str(run_index), str(exp_index), | |
| 93 str(sample_index)]) + '_' + timestamp | |
| 94 for file_entry in run_files: | |
| 95 runs_table.write('\t'.join([run_alias, action, 'ena_run_accession', exp_alias, | |
| 96 file_entry, FILE_FORMAT, 'file_checksum', | |
| 97 'submission_date_ENA']) + '\n') | |
| 98 | |
| 99 studies_table.close() | |
| 100 samples_table.close() | |
| 101 experiments_table.close() | |
| 102 runs_table.close() |