|
4
|
1 import argparse
|
|
|
2 import json
|
|
|
3 import os
|
|
|
4 import pathlib
|
|
|
5
|
|
21
|
6 from datetime import datetime
|
|
|
7
|
|
4
|
8 parser = argparse.ArgumentParser()
|
|
|
9 parser.add_argument('--studies',dest='studies_json_path', required=True)
|
|
|
10 parser.add_argument('--out_dir',dest='out_path', required=True)
|
|
|
11 args = parser.parse_args()
|
|
|
12
|
|
|
13
|
|
|
14 with open(args.studies_json_path,'r') as studies_json_file:
|
|
|
15 studies_dict = json.load(studies_json_file)
|
|
|
16
|
|
|
17 studies_table = open(pathlib.Path(args.out_path) / 'studies.tsv', 'w')
|
|
|
18 studies_table.write('\t'.join(['alias','status','accession','title','study_type','study_abstract','pubmed_id','submission_date']) + '\n')
|
|
|
19
|
|
|
20 samples_table = open(pathlib.Path(args.out_path) / 'samples.tsv', 'w')
|
|
|
21
|
|
|
22 experiments_table = open(pathlib.Path(args.out_path) / 'experiments.tsv', 'w')
|
|
|
23 experiments_table.write('\t'.join(['alias','status','accession','title','study_alias','sample_alias','design_description','library_name','library_strategy','library_source','library_selection','library_layout','insert_size','library_construction_protocol','platform','instrument_model','submission_date'])+ '\n')
|
|
|
24
|
|
|
25 runs_table = open(pathlib.Path(args.out_path) / 'runs.tsv', 'w')
|
|
|
26 runs_table.write('\t'.join(['alias','status','accession','experiment_alias','file_name','file_format','file_checksum','submission_date'])+ '\n')
|
|
|
27
|
|
|
28 action = 'add'
|
|
15
|
29 viral_submission = False
|
|
21
|
30
|
|
|
31 dt_oobj = datetime.now(tz=None)
|
|
|
32 timestamp = dt_oobj.strftime("%Y%m%d_%H:%M:%S")
|
|
4
|
33 for study_index, study in enumerate(studies_dict):
|
|
21
|
34 study_alias = 'study_'+str(study_index)+'_'+timestamp
|
|
4
|
35 studies_table.write('\t'.join([study_alias,action,'ENA_accession',study['title'], study['type'],study['abstract'],study['pubmed_id'],'ENA_submission_data']))
|
|
15
|
36 if "geo_location" in study['samples'][0].keys(): # sample belongs to a viral sample
|
|
|
37 samples_table.write('\t'.join(['alias','status','accession','title','scientific_name','taxon_id','sample_description','collection_date','geographic_location','host_common_name','host_subject_id','host_health_state','host_sex','host_scientific_name','collector_name','collecting_institution','isolate','submission_date']) + '\n')
|
|
|
38 else:
|
|
|
39 samples_table.write('\t'.join(['alias','status','accession','title','scientific_name','taxon_id','sample_description','submission_date']) + '\n')
|
|
4
|
40 for sample_index,sample in enumerate(study['samples']):
|
|
21
|
41 sample_alias = 'sample_'+str(sample_index)+'_'+timestamp
|
|
15
|
42 if "geo_location" in sample.keys(): # sample belongs to a viral sample
|
|
|
43 if sample['collector_name'] == '':
|
|
|
44 sample['collector_name'] = 'unknown'
|
|
|
45 samples_table.write('\t'.join([sample_alias,action,'ena_accession',sample['title'],sample['tax_name'], sample['tax_id'],sample['description'],sample['collection_date'],sample['geo_location'],sample['host_common_name'],sample['host_subject_id'],sample['host_health_state'],sample['host_sex'],sample['host_scientific_name'],sample['collector_name'],sample['collecting_institution'],sample['isolate'],'ENA_submission_date'])+ '\n')
|
|
|
46 else:
|
|
|
47 samples_table.write('\t'.join([sample_alias,action,'ena_accession',sample['title'],sample['tax_name'], sample['tax_id'],sample['description'],'ENA_submission_date'])+ '\n')
|
|
4
|
48 for exp_index,exp in enumerate(sample['experiments']):
|
|
21
|
49 exp_alias = 'experiment_'+str(exp_index)+'.'+str(sample_index)+'_'+timestamp
|
|
4
|
50 lib_alias = 'library_'+str(exp_index)+'_'+str(sample_index)
|
|
15
|
51 experiments_table.write('\t'.join([exp_alias,action,'accession_ena',exp['title'],study_alias,sample_alias,exp['experiment_design'],lib_alias,exp['library_strategy'],exp['library_source'],exp['library_selection'],exp['library_layout'].lower(),exp['insert_size'],exp['library_construction_protocol'],exp['platform'],exp['instrument_model'],'submission_date_ENA']) + '\n')
|
|
4
|
52 run_index = 0
|
|
|
53 # exp['runs'] is a list of lists
|
|
|
54 for run in exp['runs']:
|
|
|
55 run_index += 1
|
|
21
|
56 run_alias = '.'.join(['run_'+str(run_index),str(exp_index),str(sample_index)]) + '_' +timestamp
|
|
4
|
57 for file_entry in run:
|
|
15
|
58 file_format = 'fastq'
|
|
4
|
59 runs_table.write('\t'.join([run_alias,action,'ena_run_accession',exp_alias,file_entry,file_format,'file_checksum','submission_date_ENA']) + '\n')
|
|
|
60
|
|
|
61 studies_table.close()
|
|
|
62 samples_table.close()
|
|
|
63 experiments_table.close()
|
|
|
64 runs_table.close()
|
