From 3185a420b587a07b06df9894b6c2a7d137e9c220 Mon Sep 17 00:00:00 2001
From: Martijn Vermaat <martijn@vermaat.name>
Date: Mon, 24 Sep 2012 12:04:07 +0000
Subject: [PATCH] Maximum matrix size for description extractor
git-svn-id: https://humgenprojects.lumc.nl/svn/mutalyzer/trunk@607 eb6bd6ab-9ccd-42b9-aceb-e2899b4a52f1
---
mutalyzer/describe.py | 10 +++++++++-
mutalyzer/website.py | 16 ++++++++++------
2 files changed, 19 insertions(+), 7 deletions(-)
diff --git a/mutalyzer/describe.py b/mutalyzer/describe.py
index 0af60af3..3ce67751 100644
--- a/mutalyzer/describe.py
+++ b/mutalyzer/describe.py
@@ -16,6 +16,11 @@ from mutalyzer.util import longest_common_prefix, longest_common_suffix
from mutalyzer.util import palinsnoop, roll
from mutalyzer import models
+
+# Maximum size of the LCS matrix
+MAX_MATRIX_SIZE = 8000000
+
+
class LCS(object):
"""
Class that calculates a Longest Common Substring matrix once and provides
@@ -35,7 +40,7 @@ class LCS(object):
@arg lcp: The length of the longest common prefix of {s1} and {s2}.
@type lcp: int
@arg s1_end: End of the substring in {s1}.
- @type s1_end:
+ @type s1_end:
@arg s2_end: End of the substring in {s2}.
@type s2_end: int
@arg DNA:
@@ -806,6 +811,9 @@ def describe(original, mutated, DNA=True):
s1_end = len(s1) - lcs
s2_end = len(s2) - lcs
+ if (s1_end - lcp) * (s2_end - lcp) > MAX_MATRIX_SIZE:
+ return
+
if not DNA:
M = LCS(s1, s2, lcp, s1_end, s2_end)
return protein_description(M, s1, s2, lcp, s1_end, lcp, s2_end)
diff --git a/mutalyzer/website.py b/mutalyzer/website.py
index f7c9084d..5b223528 100644
--- a/mutalyzer/website.py
+++ b/mutalyzer/website.py
@@ -831,13 +831,17 @@ class Check:
chromosome=raw_variants[0], start=min(positions) - 10,
stop=max(positions) + 10, bed_file=urllib.quote(bed_url))
- extracted = describe.alleleDescription(
- describe.describe(output.getIndexedOutput("original", 0),
- output.getIndexedOutput("mutated", 0)))
+ allele = describe.describe(output.getIndexedOutput("original", 0),
+ output.getIndexedOutput("mutated", 0))
+ prot_allele = describe.describe(output.getIndexedOutput("oldprotein", 0),
+ output.getIndexedOutput("newprotein", 0, default=""), DNA=False)
- extractedProt = describe.alleleDescription(
- describe.describe(output.getIndexedOutput("oldprotein", 0),
- output.getIndexedOutput("newprotein", 0, default=""), DNA=False))
+ extracted = extractedProt = '(skipped)'
+
+ if allele:
+ extracted = describe.alleleDescription(allele)
+ if prot_allele:
+ extractedProt = describe.alleleDescription(prot_allele)
# Todo: Generate the fancy HTML views for the proteins here instead
--
GitLab