From d5e13c37b957e6ffa365e0ea905e28d8ebf132c2 Mon Sep 17 00:00:00 2001 From: Lan Hui Date: Wed, 16 Apr 2025 16:01:21 +0800 Subject: Include sample id and study id in the JSON output --- Code/parse_ena_xml.py | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/Code/parse_ena_xml.py b/Code/parse_ena_xml.py index c22ec2a..1e5a514 100644 --- a/Code/parse_ena_xml.py +++ b/Code/parse_ena_xml.py @@ -315,15 +315,17 @@ if __name__ == '__main__': for k in sorted(d_run_keys): d = {} k2 = d_run[k]['experiment_id'] - k3 = d_experiment[k2]['sample_id'] if k2 in d_experiment else 'SAM_UNKNOWN' - k4 = d_experiment[k2]['study_id'] if k2 in d_experiment else 'PRJ_UNKNOWN' - d['tissue'] = d['library_strategy'] = d['library_source'] = d['sample_id'] = '' + d['experiment_id'] = k2 + d['tissue'] = '' + d['sample_id'] = d['study_id'] = d['library_strategy'] = d['library_source'] = d['detail'] = '' if k2 in d_experiment: - d['sample_id'] = d_experiment[k2]['sample_id'] + k3 = d_experiment[k2]['sample_id'] + k4 = d_experiment[k2]['study_id'] + d['sample_id'] = k3 + d['study_id'] = k4 d['tissue'] = get_tissue(k, d_run, k2, d_experiment, k3, d_sample, k4, d_study) d['library_strategy'] = d_experiment[k2]['library_strategy'] d['library_source'] = d_experiment[k2]['library_source'] - d['detail'] = 'TBA' json_dict[k] = d if d['library_source'] == 'TRANSCRIPTOMIC': count_transcriptomic += 1 -- cgit v1.2.1