diff extract_tables.py @ 14:436da36c6114 draft

Uploaded

--- a/extract_tables.py	Fri Sep 18 14:29:47 2020 +0000
+++ b/extract_tables.py	Tue Sep 22 20:36:41 2020 +0000
@@ -34,14 +34,14 @@
         for exp_index,exp in enumerate(sample['experiments']):
             exp_alias = 'experiment_'+str(exp_index)+'_'+str(sample_index)
             lib_alias = 'library_'+str(exp_index)+'_'+str(sample_index)
-            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')
+            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'],exp['insert_size'],exp['library_construction_protocol'],exp['platform'],exp['instrument_model'],'submission_date_ENA']) + '\n')
             run_index = 0
             # exp['runs'] is a list of lists
             for run in exp['runs']:
                 run_index += 1
                 run_alias = '_'.join(['run',str(exp_index),str(sample_index),str(run_index)])
                 for file_entry in run:
-                    file_format = 'fastq'
+                    file_format = 'fastq.gz' if os.path.splitext(file_entry)[-1] == '.gz' else 'fastq.bz2'
                     runs_table.write('\t'.join([run_alias,action,'ena_run_accession',exp_alias,file_entry,file_format,'file_checksum','submission_date_ENA']) + '\n')
 
 studies_table.close()