aboutsummaryrefslogtreecommitdiff
path: root/scripts/from_genbank_to_fasta_and_yaml.py
diff options
context:
space:
mode:
authorPjotr Prins2020-04-19 12:19:01 -0500
committerGitHub2020-04-19 12:19:01 -0500
commitccc4bfa4fe8466b6c19185d7d9d3e2b7a3ce30e2 (patch)
treea7e5de66a4a0aaf04c61e5a0f112341a2d956b02 /scripts/from_genbank_to_fasta_and_yaml.py
parentbbca5ac9b2538e410efe3e09651f87e5573145de (diff)
parentaddbd80878cc4fedaf785c147073bb72ef8b54b4 (diff)
downloadbh20-seq-resource-ccc4bfa4fe8466b6c19185d7d9d3e2b7a3ce30e2.tar.gz
bh20-seq-resource-ccc4bfa4fe8466b6c19185d7d9d3e2b7a3ce30e2.tar.lz
bh20-seq-resource-ccc4bfa4fe8466b6c19185d7d9d3e2b7a3ce30e2.zip
Merge pull request #22 from AndreaGuarracino/patch-4
added type id check
Diffstat (limited to 'scripts/from_genbank_to_fasta_and_yaml.py')
-rw-r--r--scripts/from_genbank_to_fasta_and_yaml.py12
1 files changed, 9 insertions, 3 deletions
diff --git a/scripts/from_genbank_to_fasta_and_yaml.py b/scripts/from_genbank_to_fasta_and_yaml.py
index 0cc1a57..6a55b5e 100644
--- a/scripts/from_genbank_to_fasta_and_yaml.py
+++ b/scripts/from_genbank_to_fasta_and_yaml.py
@@ -7,7 +7,7 @@ import os
path_ncbi_virus_accession = 'sequences.acc'
-date = '20200414'
+date = '20200415'
path_seq_fasta = 'seq_from_nuccore.{}.fasta'.format(date)
path_metadata_xml = 'metadata_from_nuccore.{}.xml'.format(date)
@@ -19,9 +19,15 @@ for term in term_list:
tmp_list = Entrez.read(
Entrez.esearch(db='nuccore', term=term, idtype='acc', retmax='10000')
)['IdList']
- print(term, len(tmp_list))
-
+
+ # Remove mRNAs, ncRNAs, Proteins, and predicted models (more information here: https://en.wikipedia.org/wiki/RefSeq)
+ tmp_list = [x for x in tmp_list if x[:2] not in ['NM', 'NR', 'NP', 'XM', 'XR', 'XP', 'WP']]
+
# Remove the version in the id
+ tmp_list = [x.split('.')[0] for x in tmp_list]
+
+ print(term, len(tmp_list))
+
id_set.update([x.split('.')[0] for x in tmp_list])
print(term_list, len(id_set))