diff options
Diffstat (limited to 'scripts')
-rw-r--r-- | scripts/dict_ontology_standardization/ncbi_speciesman_source.csv | 2 | ||||
-rwxr-xr-x | scripts/from_genbank_to_fasta_and_yaml.py | 9 |
2 files changed, 7 insertions, 4 deletions
diff --git a/scripts/dict_ontology_standardization/ncbi_speciesman_source.csv b/scripts/dict_ontology_standardization/ncbi_speciesman_source.csv index 2905588..909cf37 100644 --- a/scripts/dict_ontology_standardization/ncbi_speciesman_source.csv +++ b/scripts/dict_ontology_standardization/ncbi_speciesman_source.csv @@ -1,4 +1,4 @@ -nasopharyngeal swab, http://purl.obolibrary.org/obo/NCIT_C155831 +nasopharyngeal swab,http://purl.obolibrary.org/obo/NCIT_C155831 nasopharyngeal exudate,http://purl.obolibrary.org/obo/NCIT_C155831 respiratory swab,http://purl.obolibrary.org/obo/NCIT_C155831 naso-pharyngeal exudate,http://purl.obolibrary.org/obo/NCIT_C155831 diff --git a/scripts/from_genbank_to_fasta_and_yaml.py b/scripts/from_genbank_to_fasta_and_yaml.py index 1a12513..00c0012 100755 --- a/scripts/from_genbank_to_fasta_and_yaml.py +++ b/scripts/from_genbank_to_fasta_and_yaml.py @@ -130,9 +130,12 @@ if not os.path.exists(dir_fasta_and_yaml_today): if field_in_yaml == 'sequencing_coverage': # A regular expression would be better! - info_for_yaml_dict['technology'][field_in_yaml] = ';'.join( - [x.strip('(average)').strip("reads/nt").replace(',', '.').strip(' xX>') for x in tech_info_to_parse.split(';')] - ) + try: + info_for_yaml_dict['technology'][field_in_yaml] = float( + tech_info_to_parse.strip('(average)').strip("reads/nt").replace(',', '.').strip(' xX>')) + except ValueError: + print(accession_version, "Couldn't make sense of Coverage '%s'" % tech_info_to_parse) + pass elif field_in_yaml == 'sample_sequencing_technology': new_seq_tec_list = [] for seq_tec in tech_info_to_parse.split(';'): |