From bf8f13af6f083d382b4a3900566ef5e329084cbf Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Mon, 4 Jan 2021 09:41:58 +0000 Subject: Removing refs. No point in guessing terms --- workflows/pull-data/genbank/ref.py | 23 ----------------------- 1 file changed, 23 deletions(-) delete mode 100644 workflows/pull-data/genbank/ref.py diff --git a/workflows/pull-data/genbank/ref.py b/workflows/pull-data/genbank/ref.py deleted file mode 100644 index d2a377e..0000000 --- a/workflows/pull-data/genbank/ref.py +++ /dev/null @@ -1,23 +0,0 @@ -# ---- BELOW IS JUST FOR REFERENCE ---- - -if field_in_yaml == 'sequencing_coverage': - # A regular expression would be better! - try: - technology[field_in_yaml] = [ - float(tech_info_to_parse.replace('(average)', '').replace("reads/nt", ''). - replace('(average for 6 sequences)', '').replace(',', '.').strip(' xX>')) - ] - except ValueError: - print(accession_version, "Couldn't make sense of Coverage '%s'" % tech_info_to_parse) - pass - - -elif GBQualifier_name_text == 'collected_by': - if any([x in GBQualifier_value_text.lower() for x in ['institute', 'hospital', 'city', 'center']]): - sample['collecting_institution'] = GBQualifier_value_text - else: - sample['collector_name'] = GBQualifier_value_text - -elif GBQualifier_name_text == 'isolation_source': -if GBQualifier_value_text.upper() in field_to_term_to_uri_dict['ncbi_speciesman_source']: - GBQualifier_value_text = GBQualifier_value_text.upper() # For example, in case of 'usa: wa' -- cgit v1.2.3