# HG changeset patch
# User peterjc
# Date 1417192354 18000
# Node ID a7c7f10488f5f8007ec9d3dce3ef1a554af703f0
# Parent e37a71ffaff232d2e52c0df8256328db75787751
Uploaded v0.0.5, better error messages, embeds citation
diff -r e37a71ffaff2 -r a7c7f10488f5 tools/align_back_trans/README.rst
--- a/tools/align_back_trans/README.rst Wed Jun 04 08:44:06 2014 -0400
+++ b/tools/align_back_trans/README.rst Fri Nov 28 11:32:34 2014 -0500
@@ -43,11 +43,12 @@
-You will also need to install Biopython 1.62 or later. If you want to run
-the unit tests, include this line in ``tools_conf.xml.sample`` and the sample
-FASTA files under the ``test-data`` directory. Then::
+You will also need to install Biopython 1.62 or later.
- ./run_functional_tests.sh -id align_back_trans
+If you wish to run the unit tests, also move/copy the ``test-data/`` files
+under Galaxy's ``test-data/`` folder. Then::
+
+ ./run_tests.sh -id align_back_trans
That's it.
@@ -63,6 +64,8 @@
v0.0.3 - First official release
v0.0.4 - Simplified XML to apply input format to output data.
- Fixed error message when sequence length not a multiple of three.
+v0.0.5 - More explicit error messages when seqences lengths do not match.
+ - Tool definition now embeds citation information.
======= ======================================================================
diff -r e37a71ffaff2 -r a7c7f10488f5 tools/align_back_trans/align_back_trans.py
--- a/tools/align_back_trans/align_back_trans.py Wed Jun 04 08:44:06 2014 -0400
+++ b/tools/align_back_trans/align_back_trans.py Fri Nov 28 11:32:34 2014 -0500
@@ -15,8 +15,6 @@
* http://toolshed.g2.bx.psu.edu/view/peterjc/align_back_trans
See accompanying text file for licence details (MIT licence).
-
-This is version 0.0.3 of the script.
"""
import sys
@@ -28,7 +26,7 @@
from Bio.Data.CodonTable import ambiguous_generic_by_id
if "-v" in sys.argv or "--version" in sys.argv:
- print "v0.0.4"
+ print "v0.0.5"
sys.exit(0)
def stop_err(msg, error_level=1):
@@ -49,19 +47,20 @@
#Allow this...
t = t[:-1]
nuc = nuc[:-3] #edit return value
- if len(t) != len(p) and p in t:
- stop_err("%s translation matched but only as subset of nucleotides, "
- "wrong start codon?" % identifier)
- if len(t) != len(p) and p[1:] in t:
- stop_err("%s translation matched (ignoring first base) but only "
- "as subset of nucleotides, wrong start codon?" % identifier)
if len(t) != len(p):
- stop_err("Inconsistent lengths for %s, ungapped protein %i, "
- "tripled %i vs ungapped nucleotide %i" %
- (identifier,
- len(p),
- len(p) * 3,
- len(nuc)))
+ err = ("Inconsistent lengths for %s, ungapped protein %i, "
+ "tripled %i vs ungapped nucleotide %i." %
+ (identifier, len(p), len(p) * 3, len(nuc)))
+ if t.endswith(p):
+ err += "\nThere are %i extra nucleotides at the start." % (len(t) - len(p))
+ elif t.startswith(p):
+ err += "\nThere are %i extra nucleotides at the end." % (len(t) - len(p))
+ elif p in t:
+ #TODO - Calculate and report the number to trim at start and end?
+ err += "\nHowever, protein sequence found within translated nucleotides."
+ elif p[1:] in t:
+ err += "\nHowever, ignoring first amino acid, protein sequence found within translated nucleotides."
+ stop_err(err)
if t == p:
diff -r e37a71ffaff2 -r a7c7f10488f5 tools/align_back_trans/align_back_trans.xml
--- a/tools/align_back_trans/align_back_trans.xml Wed Jun 04 08:44:06 2014 -0400
+++ b/tools/align_back_trans/align_back_trans.xml Fri Nov 28 11:32:34 2014 -0500
@@ -1,4 +1,4 @@
-
+
Gives a codon aware alignment
biopython
@@ -122,4 +122,8 @@
This tool is available to install into other Galaxy Instances via the Galaxy
Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/align_back_trans
+
+ 10.7717/peerj.167
+ 10.1093/bioinformatics/btp163
+