diff options
author | AndreaGuarracino | 2020-08-28 11:16:24 +0200 |
---|---|---|
committer | AndreaGuarracino | 2020-08-28 11:16:24 +0200 |
commit | 3165a31e321cbf4641f9afdcbea511ee66f673bb (patch) | |
tree | 7140a760be5903c6f5e63a38da7e0f76493530a8 /scripts | |
parent | cc8f99d50236b7d0c365990398785ecc319323ea (diff) | |
download | bh20-seq-resource-3165a31e321cbf4641f9afdcbea511ee66f673bb.tar.gz bh20-seq-resource-3165a31e321cbf4641f9afdcbea511ee66f673bb.tar.lz bh20-seq-resource-3165a31e321cbf4641f9afdcbea511ee66f673bb.zip |
added control (locally and in the validation) that sample_id has to be the same in the metadata and in the FASTA header #103
Diffstat (limited to 'scripts')
-rwxr-xr-x | scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py | 2 |
1 files changed, 2 insertions, 0 deletions
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 8ef76e1..8f765d7 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 @@ -412,6 +412,8 @@ for path_metadata_xxx_xml in [os.path.join(dir_metadata, name_metadata_xxx_xml) not_created_accession_dict[accession_version].append('host_species not found') if len(GBSeq_sequence.text) < min_len_to_count: + if accession_version not in not_created_accession_dict: + not_created_accession_dict[accession_version] = [] not_created_accession_dict[accession_version].append('sequence shorter than {} bp'.format(min_len_to_count)) if accession_version not in not_created_accession_dict: |