view extract_tables.py @ 14:5cb6146337d8 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ena_upload commit ab38fa3d5ec06729c1efa86240ec57b8143b21ed
author iuc
date Wed, 12 Jun 2024 16:01:11 +0000
parents 480d9e9d156b
children
line wrap: on
line source

import argparse
import json
import pathlib
from datetime import datetime

"""
Parse the configfile generated by the Galaxy tool.
This file is JSON-formatted and should be converted to a set of tabular files.
"""

FILE_FORMAT = 'fastq'

parser = argparse.ArgumentParser()
parser.add_argument('--studies', dest='studies_json_path', required=True)
parser.add_argument('--out_dir', dest='out_path', required=True)
parser.add_argument('--action', dest='action', required=True)
args = parser.parse_args()

with open(args.studies_json_path, 'r') as studies_json_file:
    studies_dict = json.load(studies_json_file)
studies_table = open(pathlib.Path(args.out_path) / 'studies.tsv', 'w')
studies_table.write('\t'.join(['alias', 'status', 'title', 'study_type',
                               'study_abstract', 'pubmed_id']) + '\n')
samples_table = open(pathlib.Path(args.out_path) / 'samples.tsv', 'w')
experiments_table = open(pathlib.Path(args.out_path) / 'experiments.tsv', 'w')
experiments_table.write('\t'.join(['alias', 'status', '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',
                                   ]) + '\n')
runs_table = open(pathlib.Path(args.out_path) / 'runs.tsv', 'w')
runs_table.write('\t'.join(['alias', 'status', 'experiment_alias', 'file_name',
                            'file_format']) + '\n')

action = args.action

dt_oobj = datetime.now(tz=None)
timestamp = dt_oobj.strftime("%Y%m%d_%H:%M:%S")
for study_index, study in enumerate(studies_dict):
    study_alias = 'study_' + str(study_index) + '_' + timestamp
    studies_table.write('\t'.join([study_alias, action, study['title'],
                                   study['type'], study['abstract'], study['pubmed_id']]))
    if "host_subject_id" in study['samples'][0].keys():           # sample belongs to a viral sample
        samples_table.write('\t'.join(['alias', 'status', 'title', 'scientific_name',
                                       'taxon_id', 'sample_description', 'collection date',
                                       'geographic location (country and/or sea)', 'host common name', 'host subject id',
                                       'host health state', 'host sex', 'host scientific name',
                                       'collector name', 'collecting institution', 'isolate']) + '\n')
    else:
        samples_table.write('\t'.join(['alias', 'status', 'title', 'scientific_name',
                                       'taxon_id', 'sample_description', 'collection date',
                                       'geographic location (country and/or sea)']) + '\n')
    for sample_index, sample in enumerate(study['samples']):
        sample_alias = 'sample_' + str(sample_index) + '_' + timestamp
        if "host_subject_id" in sample.keys():  # sample belongs to a viral sample
            if sample['collector_name'] == '':
                sample['collector_name'] = 'unknown'
            samples_table.write('\t'.join([sample_alias, action, 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']
                                           ]) + '\n')
        else:
            samples_table.write('\t'.join([sample_alias, action, sample['title'],
                                           sample['tax_name'], sample['tax_id'],
                                           sample['description'], sample['collection_date'],
                                           sample['geo_location']]) + '\n')
        for exp_index, exp in enumerate(sample['experiments']):
            exp_alias = 'experiment_' + str(exp_index) + '.' + str(sample_index) + '_' + timestamp
            lib_alias = 'library_' + str(exp_index) + '_' + str(sample_index)
            experiments_table.write('\t'.join([exp_alias, action, 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']]) + '\n')
            run_index = 0
            # exp['runs'] is a list of lists
            for (base_run, run_files) in exp['runs']:
                run_index += 1
                if base_run != '':
                    run_alias = base_run
                else:
                    # no alias provided, generated a unique one
                    run_alias = '_'.join(['run_' + str(run_index), str(exp_index),
                                          str(sample_index)]) + '_' + timestamp
                for file_entry in run_files:
                    runs_table.write('\t'.join([run_alias, action, exp_alias,
                                                file_entry, FILE_FORMAT]) + '\n')

studies_table.close()
samples_table.close()
experiments_table.close()
runs_table.close()