changeset 15:2612bb9caf71

merge heads #2.
author Marius van den Beek <m.vandenbeek@gmail.com>
date Wed, 01 Apr 2015 14:22:11 +0200
parents 77ce882a6060 (current diff) dd09eada7b78 (diff)
children ca7b7890ed20
files mismatch_frequencies.xml test-data/mismatch.tab
diffstat 2 files changed, 4 insertions(+), 32 deletions(-) [+]
line wrap: on
line diff
--- a/mismatch_frequencies.xml	Wed Apr 01 14:15:23 2015 +0200
+++ b/mismatch_frequencies.xml	Wed Apr 01 14:22:11 2015 +0200
@@ -19,8 +19,8 @@
                  --three_p $three_p
   </command>
   <inputs>
-    <repeat name="rep" title="alignment files" min="1">
-      <param name="input_file" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) for which you want to calculate mismatch frequencies."/>
+    <repeat name="rep" title="alignment files">
+      <param name="input_file" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) for which to analyze the mismatches."/>
     </repeat>
     <param name="number_of_mismatches" label="Maximum number of allowed mismatches per read" help="Discard reads with more than the chosen number of mismatches from the frequency calculation" type="integer" value="3"/>
     <param name="min_length" label="Minumum read length to analyse" type="integer" value="21"/>
@@ -35,36 +35,8 @@
   <tests>
     <test>
       <param name="rep_0|input_file" value="3mismatches_ago2ip_s2.bam" ftype="bam" />
-      <param name="rep_1|input_file" value="3mismatches_ago2ip_ovary.bam" ftype="bam" />
+      <param name="rep_1|input_file" value="3mismatches_ago2ip_s2.bam" ftype="bam" />
       <param name="number_of_mismatches" value="1" />
       <param name="min_length" value="21" />
       <param name="max_length" value="21" />
-      <output name="tabular" file="mismatch.tab" ftype="tabular"/>
-    </test>
-  </tests>
-  <help>
-
-.. class:: infomark
-
-
-***What it does***
-
-This tool reconstitues for each aligned read of an alignment file in SAM/BAM format whether
-a mismatch is annotated in the MD tag, and if that is the case counts the identity of the 
-mismatch relative to the reference sequence. The output is a PDF document with the calculated
-frequency for each mismatch that occured relative to the total number of valid reads and a table
-with the corresponding values. Read length can be limited to a specific read length, and 5 prime and 
-3 prime-most nucleotides of a read can be ignored.
-
-----
-
-.. class:: warningmark
-
-***Warning***
-
-This tool skips all read that have insertions and has been tested only with bowtie and bowtie2
-generated alignment files.
-
-Written by Marius van den Beek, m.vandenbeek at gmail . com
-  </help>
 </tool>
--- a/test-data/mismatch.tab	Wed Apr 01 14:15:23 2015 +0200
+++ b/test-data/mismatch.tab	Wed Apr 01 14:22:11 2015 +0200
@@ -1,3 +1,3 @@
-library	readsize	A to C	A to G	A to T	C to A	C to G	C to T	G to A	G to C	G to T	T to A	T to C	T to G	total valid reads
+library	readsize	A to C	A to G	A to T	C to A	C to G	C to T	G to A	G to C	G to T	T to A	T to C	T to G	total_mapped
 3mismatches_ago2ip_s2.bam	21	31	5484	69	25	40	137	156	109	188	51	196	29	43881
 3mismatches_ago2ip_ovary.bam	21	293	879	411	452	231	872	845	191	473	384	818	324	138649