From addbd80878cc4fedaf785c147073bb72ef8b54b4 Mon Sep 17 00:00:00 2001
From: Andrea Guarracino
Date: Wed, 15 Apr 2020 15:54:26 +0200
Subject: added type id check

what is not genomic DNA is removed---
 scripts/from_genbank_to_fasta_and_yaml.py | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'scripts')

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))
-- 
cgit v1.2.3