Mercurial > repos > peterjc > align_back_trans

changeset 7:a7c7f10488f5 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded v0.0.5, better error messages, embeds citation
author peterjc
date Fri, 28 Nov 2014 11:32:34 -0500
parents e37a71ffaff2
children 174a38262fae
files tools/align_back_trans/README.rst tools/align_back_trans/align_back_trans.py tools/align_back_trans/align_back_trans.xml
diffstat 3 files changed, 26 insertions(+), 20 deletions(-) [+]
line wrap: on
line diff
--- 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 @@
 
     <tool file="align_back_trans/align_back_trans.xml" />
 
-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.
 ======= ======================================================================
 
 
--- 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:
--- 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 @@
-<tool id="align_back_trans" name="Thread nucleotides onto a protein alignment (back-translation)" version="0.0.4">
+<tool id="align_back_trans" name="Thread nucleotides onto a protein alignment (back-translation)" version="0.0.5">
     <description>Gives a codon aware alignment</description>
     <requirements>
         <requirement type="package" version="1.63">biopython</requirement>
@@ -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
     </help>
+    <citations>
+        <citation type="doi">10.7717/peerj.167</citation>
+        <citation type="doi">10.1093/bioinformatics/btp163</citation>
+    </citations>
 </tool>