aboutsummaryrefslogtreecommitdiff
path: root/scripts
diff options
context:
space:
mode:
authorAndreaGuarracino2020-08-23 11:28:02 +0200
committerAndreaGuarracino2020-08-23 11:28:02 +0200
commit3b9423891c4e90499a40c1be029ef40160efb557 (patch)
treefd3bcb6d5113161a20d71d89db18e277a2f11e8d /scripts
parent634e266777c7a2e67a4e998845061e250615675a (diff)
downloadbh20-seq-resource-3b9423891c4e90499a40c1be029ef40160efb557.tar.gz
bh20-seq-resource-3b9423891c4e90499a40c1be029ef40160efb557.tar.lz
bh20-seq-resource-3b9423891c4e90499a40c1be029ef40160efb557.zip
genbank/sra scripts update to be more generic with the specimen sources
Diffstat (limited to 'scripts')
-rw-r--r--scripts/create_sra_metadata/create_sra_metadata.py6
-rwxr-xr-xscripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py6
2 files changed, 8 insertions, 4 deletions
diff --git a/scripts/create_sra_metadata/create_sra_metadata.py b/scripts/create_sra_metadata/create_sra_metadata.py
index d02fde8..0e1215e 100644
--- a/scripts/create_sra_metadata/create_sra_metadata.py
+++ b/scripts/create_sra_metadata/create_sra_metadata.py
@@ -128,10 +128,12 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET):
if VALUE_text in term_to_uri_dict:
info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict[VALUE_text]]
else:
- if VALUE_text.lower() in ['np/op', 'np/op swab', 'np/np swab', 'nasopharyngeal and oropharyngeal swab', 'nasopharyngeal/oropharyngeal swab', 'combined nasopharyngeal and oropharyngeal swab']:
+ if VALUE_text.lower() in ['np/op', 'np/op swab', 'np/np swab', 'nasopharyngeal and oropharyngeal swab', 'nasopharyngeal/oropharyngeal swab', 'combined nasopharyngeal and oropharyngeal swab', 'naso and/or oropharyngeal swab']:
info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict['nasopharyngeal swab'], term_to_uri_dict['oropharyngeal swab']]
- elif VALUE_text.lower() in ['nasopharyngeal swab/throat swab', 'nasopharyngeal/throat swab', 'nasopharyngeal swab and throat swab', 'nasal swab and throat swab', 'nasopharyngeal aspirate/throat swab']:
+ elif VALUE_text.lower() in ['nasopharyngeal swab/throat swab', 'nasopharyngeal/throat swab', 'nasopharyngeal swab and throat swab', 'nasal swab and throat swab', 'nasopharyngeal aspirate/throat swab', 'Nasopharyngeal/Throat']:
info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict['nasopharyngeal swab'], term_to_uri_dict['throat swab']]
+ elif VALUE_text.lower() in ['nasopharyngeal aspirate & throat swab', 'nasopharyngeal aspirate and throat swab']:
+ info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict['nasopharyngeal aspirate'], term_to_uri_dict['throat swab']]
elif VALUE_text.lower() in ['nasal swab and throat swab']:
info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict['nasal swab'], term_to_uri_dict['throat swab']]
elif VALUE_text.lower() in ['nasal-swab and oro-pharyngeal swab']:
diff --git a/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py b/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py
index 3c59f8c..f314a1d 100755
--- a/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py
+++ b/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py
@@ -316,10 +316,12 @@ for path_metadata_xxx_xml in [os.path.join(dir_metadata, name_metadata_xxx_xml)
if GBQualifier_value_text in term_to_uri_dict:
info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict[GBQualifier_value_text]]
else:
- if GBQualifier_value_text.lower() in ['np/op', 'np/op swab', 'np/np swab', 'nasopharyngeal and oropharyngeal swab', 'nasopharyngeal/oropharyngeal swab', 'combined nasopharyngeal and oropharyngeal swab']:
+ if GBQualifier_value_text.lower() in ['np/op', 'np/op swab', 'np/np swab', 'nasopharyngeal and oropharyngeal swab', 'nasopharyngeal/oropharyngeal swab', 'combined nasopharyngeal and oropharyngeal swab', 'naso and/or oropharyngeal swab']:
info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict['nasopharyngeal swab'], term_to_uri_dict['oropharyngeal swab']]
- elif GBQualifier_value_text.lower() in ['nasopharyngeal swab/throat swab', 'nasopharyngeal/throat swab', 'nasopharyngeal swab and throat swab', 'nasal swab and throat swab', 'nasopharyngeal aspirate/throat swab']:
+ elif GBQualifier_value_text.lower() in ['nasopharyngeal swab/throat swab', 'nasopharyngeal/throat swab', 'nasopharyngeal swab and throat swab', 'nasal swab and throat swab', 'nasopharyngeal aspirate/throat swab', 'Nasopharyngeal/Throat']:
info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict['nasopharyngeal swab'], term_to_uri_dict['throat swab']]
+ elif GBQualifier_value_text.lower() in ['nasopharyngeal aspirate & throat swab', 'nasopharyngeal aspirate and throat swab']:
+ info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict['nasopharyngeal aspirate'], term_to_uri_dict['throat swab']]
elif GBQualifier_value_text.lower() in ['nasal swab and throat swab']:
info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict['nasal swab'], term_to_uri_dict['throat swab']]
elif GBQualifier_value_text.lower() in ['nasal-swab and oro-pharyngeal swab']: