From 18e228a6f732904b4762c010da6f757fccbe99d4 Mon Sep 17 00:00:00 2001
From: Martijn Vermaat <martijn@vermaat.name>
Date: Mon, 10 Oct 2011 14:43:31 +0000
Subject: [PATCH] Give an error on protein reference sequences
Until protein reference sequences are supported, give an error with a message
instead of crashing. Fixes #62.
git-svn-id: https://humgenprojects.lumc.nl/svn/mutalyzer/trunk@388 eb6bd6ab-9ccd-42b9-aceb-e2899b4a52f1
---
mutalyzer/Retriever.py | 11 ++++++++++-
mutalyzer/parsers/genbank.py | 5 +++++
tests/test_website.py | 13 +++++++++++++
3 files changed, 28 insertions(+), 1 deletion(-)
diff --git a/mutalyzer/Retriever.py b/mutalyzer/Retriever.py
index d77f7fa6..ded70bcc 100644
--- a/mutalyzer/Retriever.py
+++ b/mutalyzer/Retriever.py
@@ -19,6 +19,7 @@ import StringIO # StringIO()
from Bio import SeqIO # read()
from Bio import Entrez # efetch(), read(), esearch(), esummary()
from Bio.Seq import UnknownSeq
+from Bio.Alphabet import ProteinAlphabet
from xml.dom import DOMException, minidom
from xml.parsers import expat
@@ -734,7 +735,15 @@ class GenBankRetriever(Retriever):
# Now we have the file, so we can parse it.
GenBankParser = genbank.GBparser()
- return GenBankParser.create_record(filename)
+ record = GenBankParser.create_record(filename)
+
+ # Todo: This will change once we support protein references
+ if isinstance(record.seq.alphabet, ProteinAlphabet):
+ self._output.addMessage(__file__, 4, 'EPROTEINREF',
+ 'Protein reference sequences are not supported.')
+ return None
+
+ return record
#loadrecord
#GenBankRetriever
diff --git a/mutalyzer/parsers/genbank.py b/mutalyzer/parsers/genbank.py
index 0e5bf2ee..060e9a52 100644
--- a/mutalyzer/parsers/genbank.py
+++ b/mutalyzer/parsers/genbank.py
@@ -6,6 +6,7 @@ mutalyzer GenRecord. Record populated with data from a GenBank file.
import bz2
from Bio import SeqIO, Entrez
+from Bio.Alphabet import ProteinAlphabet
from mutalyzer.config import Config
from mutalyzer import Db
@@ -455,6 +456,10 @@ class GBparser():
record.version = biorecord.id.split('.')[1]
+ # Todo: This will change once we support protein references
+ if isinstance(biorecord.seq.alphabet, ProteinAlphabet):
+ return record
+
exonList = []
geneDict = {}
diff --git a/tests/test_website.py b/tests/test_website.py
index 29ba034f..97a67cd5 100644
--- a/tests/test_website.py
+++ b/tests/test_website.py
@@ -175,6 +175,19 @@ class TestWSGI():
'0 Warnings',
'Details of the parse error')
+ def test_check_protein_reference(self):
+ """
+ Submit the name checker form with a protein reference sequence (not
+ supported).
+ """
+ r = self.app.get('/check')
+ form = r.forms[0]
+ form['mutationName'] = 'BAA81889.1:c.274G>T'
+ r = form.submit()
+ r.mustcontain('1 Error',
+ '0 Warnings',
+ 'Protein reference sequences are not supported')
+
def test_check_noninteractive(self):
"""
Submit the name checker form non-interactively.
--
GitLab