Repository 'bam_readtagger'
hg clone https://toolshed.g2.bx.psu.edu/repos/mvdbeek/bam_readtagger

Changeset 3:cb9036583afe (2017-02-21)
Previous changeset 2:39d9bc17ec74 (2017-02-17) Next changeset 4:7625c594bc37 (2017-03-02)
Commit message:
planemo upload for repository https://github.com/bardin-lab/readtagger/tree/master/galaxy commit e9d18b939a9172b858c178e6bb4ef9ce2138c94c-dirty
modified:
allow_dovetailing.xml
bam_readtagger.xml
added:
add_matesequence.xml
test-data/dm6_mate_annotated.bam
test-data/proper_pair_discard.bam
test-data/proper_pair_discard_fbti.bam
test-data/proper_pair_discard_out.bam
test-data/proper_pair_discard_verified_empty.bam
test-data/proper_pair_out_suboptimal_tags.bam
b
diff -r 39d9bc17ec74 -r cb9036583afe add_matesequence.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/add_matesequence.xml Tue Feb 21 04:39:31 2017 -0500
[
@@ -0,0 +1,45 @@
+<tool id="add_matesequence" name="Add matesequence" version="0.2.0">
+    <description>into tag field</description>
+    <requirements>
+        <requirement type="package" version="0.2.0">readtagger</requirement>
+    </requirements>
+    <version_command>add_matesequence --version</version_command>
+    <command detect_errors="aggressive"><![CDATA[
+        add_matesequence --file_to_annotate '$file_to_annotate' --annotate_source '$annotate_source' --output_path '$output'
+    ]]></command>
+    <inputs>
+        <param name="file_to_annotate" argument="--file_to_annotate" label="Annotate reads in this file with their mate sequence" type="data" format="bam"/>
+        <param name="annotate_source" argument="--annotate_source" label="Use this file to find the mate sequence (can be same file as file_to_annotate)" type="data" format="bam"/>
+        <param name="mate_sequence_tag" type="text" value="MS"/>
+    </inputs>
+    <outputs>
+        <data name="output" format="bam" label="Add matesequence on $on_string"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="file_to_annotate" value="dm6.bam" ftype="bam"/>
+            <param name="annotate_source" value="dm6.bam" ftype="bam"/>
+            <output name="output" file="dm6_mate_annotated.bam" ftype="bam" lines_diff="2"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+.. code-block::
+
+    usage: add_matesequence [-h] -a FILE_TO_ANNOTATE -s ANNOTATE_SOURE -o
+                            OUTPUT_PATH [--version]
+
+    Annotate reads with Mate Sequence in tag field
+
+    optional arguments:
+      -h, --help            show this help message and exit
+      -a FILE_TO_ANNOTATE, --file_to_annotate FILE_TO_ANNOTATE
+                            Annotate reads in this file with their mate sequence
+      -s ANNOTATE_SOURE, --annotate_soure ANNOTATE_SOURE
+                            Use this file to find the mate sequence (can be same
+                            file as file_to_annotate)
+      -o OUTPUT_PATH, --output_path OUTPUT_PATH
+                            Write resulting BAM file to this path
+      --version             show program's version number and exit
+
+    ]]></help>
+</tool>
b
diff -r 39d9bc17ec74 -r cb9036583afe allow_dovetailing.xml
--- a/allow_dovetailing.xml Fri Feb 17 12:55:58 2017 -0500
+++ b/allow_dovetailing.xml Tue Feb 21 04:39:31 2017 -0500
[
@@ -1,7 +1,7 @@
-<tool id="allow_dovetailing" name="Allow dovetailing" version="0.1.13">
+<tool id="allow_dovetailing" name="Allow dovetailing" version="0.2.0">
     <description>modifies proper_pair flag in bam files</description>
     <requirements>
-        <requirement type="package" version="0.1.13">readtagger</requirement>
+        <requirement type="package" version="0.2.0">readtagger</requirement>
     </requirements>
     <command detect_errors="aggressive"><![CDATA[
         allow_dovetailing -i '$input' -o '$output'
@@ -19,16 +19,17 @@
         </test>
     </tests>
     <help><![CDATA[
-::
-usage: allow_dovetailing [-h] -i INPUT_PATH -o OUTPUT_PATH
+.. code-block::
 
-Allow dovetailing.
+    usage: allow_dovetailing [-h] -i INPUT_PATH -o OUTPUT_PATH
+
+    Allow dovetailing.
 
-optional arguments:
-  -h, --help            show this help message and exit
-  -i INPUT_PATH, --input_path INPUT_PATH
-                        Input alignment file to manipulate
-  -o OUTPUT_PATH, --output_path OUTPUT_PATH
-                        Output alignment file
+    optional arguments:
+      -h, --help            show this help message and exit
+      -i INPUT_PATH, --input_path INPUT_PATH
+                            Input alignment file to manipulate
+      -o OUTPUT_PATH, --output_path OUTPUT_PATH
+                            Output alignment file
     ]]></help>
 </tool>
b
diff -r 39d9bc17ec74 -r cb9036583afe bam_readtagger.xml
--- a/bam_readtagger.xml Fri Feb 17 12:55:58 2017 -0500
+++ b/bam_readtagger.xml Tue Feb 21 04:39:31 2017 -0500
[
@@ -1,10 +1,10 @@
-<tool id="bam_readtagger" name="Tag alignment files" version="0.1.13">
+<tool id="bam_readtagger" name="Tag alignment files" version="0.2.0">
     <description>from multiple bam files</description>
     <macros>
         <import>macros.xml</import>
     </macros>
     <requirements>
-        <requirement type="package" version="0.1.13">readtagger</requirement>
+        <requirement type="package" version="0.2.0">readtagger</requirement>
     </requirements>
     <command detect_errors="aggressive"><![CDATA[
         readtagger -t '$tag_file' -a
@@ -15,6 +15,7 @@
         $keep_suboptimal
         $discarded
         $verified
+        $discard_proper_pairs
         -o '$tagged_file'
     ]]></command>
     <inputs>
@@ -30,6 +31,7 @@
         </repeat>
         <param argument="--allow_dovetailing" type="boolean" truevalue="-d" falsevalue="" label="Allow dovetailing" help="Check this to label reads as proper_pair even if the mates of a pair overlap each other"/>
         <param argument="-k" name="keep_suboptimal" type="boolean" truevalue="-k" falsevalue="" label="Keep suboptimal alternative tags" help="Check this to also keep alternative tags that cannot explain the current read cigar"/>
+        <param argument="-dp" name="discard_proper_pairs" type="boolean" truevalue="-dp" falsevalue="" label="Discard alternative tags for proper pairs" help="Check this to discard alternative tags for reads in proper pairs"/>
         <param argument="-wd" name="discarded" type="boolean" truevalue="-wd discarded.bam" falsevalue="" label="Check this to produce an output file containing only the reads with tags that failed validation"/>
         <param argument="-wv" name="verified" type="boolean" truevalue="-wv verified.bam" falsevalue="" label="Check this to produce an output file containing only the reads with tags that pass validation"/>
     </inputs>
@@ -69,24 +71,62 @@
             <output name="verified_file" file="a_pasteurianus_tagged_with_dm6_verified.bam" ftype="bam" lines_diff="5"/>
             <output name="discarded_file" file="a_pasteurianus_tagged_with_dm6_discarded.bam" ftype="bam" lines_diff="5"/>
         </test>
+        <test> <!-- test that a pair with homology to a TE insertion is discarded, because it is a proper pair -->
+            <param name="tag_file" value="proper_pair_discard.bam" ftype="bam"/>
+            <repeat name="alignment_series">
+                <param name="annotate_with" value="proper_pair_discard_fbti.bam" ftype="bam"/>
+                <param name="r_tag" value="A"/>
+                <param name="m_tag" value="B"/>
+            </repeat>
+            <param name="discarded" value="True"/>
+            <param name="keep_suboptimal" value="True"/>
+            <param name="discard_proper_pairs" value="True"/>
+            <param name="verified" value="True"/>
+            <output name="tagged_file" file="proper_pair_out_suboptimal_tags.bam" ftype="bam" lines_diff="5" />
+            <output name="verified_file" file="proper_pair_discard_verified_empty.bam" ftype="bam" lines_diff="5"/>
+            <output name="discarded_file" file="proper_pair_discard_out.bam" ftype="bam" lines_diff="5"/>
+        </test>
     </tests>
     <help><![CDATA[
-        usage: readtagger [-h] -t TAG_FILE -a ANNOTATE_WITH [ANNOTATE_WITH ...] -o
-                 OUTPUT_FILE
+.. code-block::
 
-Tag reads in an alignment file based on other alignment files
+    usage: readtagger [-h] -t TAG_FILE -a ANNOTATE_WITH [ANNOTATE_WITH ...] -o
+                      OUTPUT_FILE [-d] [-dp] [-k] [-wd WRITE_DISCARDED]
+                      [-wv WRITE_VERIFIED] [--version]
+
+    Tag reads in an alignment file based on other alignment files
 
-optional arguments:
-  -h, --help            show this help message and exit
-  -t TAG_FILE, --tag_file TAG_FILE
-                        Tag reads in this file. (default: None)
-  -a ANNOTATE_WITH [ANNOTATE_WITH ...], --annotate_with ANNOTATE_WITH [ANNOTATE_WITH ...]
-                        Tag reads in readfile if reads are aligned in these
-                        files.Append `:A:B` to tag first letter of tag
-                        describing read as A, and first letter of tag
-                        describing the mate as B (default: None)
-  -o OUTPUT_FILE, --output_file OUTPUT_FILE
-                        Write bam file to this path (default: None)
+    optional arguments:
+      -h, --help            show this help message and exit
+      -t TAG_FILE, --tag_file TAG_FILE
+                            Tag reads in this file. (default: None)
+      -a ANNOTATE_WITH [ANNOTATE_WITH ...], --annotate_with ANNOTATE_WITH [ANNOTATE_WITH ...]
+                            Tag reads in readfile if reads are aligned in these
+                            files.Append `:A:B` to tag first letter of tag
+                            describing read as A, and first letter of tag
+                            describing the mate as B (default: None)
+      -o OUTPUT_FILE, --output_file OUTPUT_FILE
+                            Write bam file to this path (default: None)
+      -d, --allow_dovetailing
+                            Sets the proper pair flag (0x0002) to true if reads
+                            dovetail [reads reach into or surpass the mate
+                            sequence]. (default: False)
+      -dp, --discard_if_proper_pair
+                            Discard an alternative flag if the current read is in
+                            a proper pair. (default: False)
+      -k, --keep_suboptimal_alternate_tags
+                            By default cigarstrings of the alternative tags are
+                            compared and alternates that are not explaining the
+                            current cigar strings are discarded. Use this option
+                            to keep the alternative tags (effectively restoring
+                            the behaviour of readtagger < 0.1.4) (default: False)
+      -wd WRITE_DISCARDED, --write_discarded WRITE_DISCARDED
+                            Write discarded reads into separate file (default:
+                            False)
+      -wv WRITE_VERIFIED, --write_verified WRITE_VERIFIED
+                            Write verified reads into separate file (default:
+                            False)
+      --version             show program's version number and exit
 
     ]]></help>
 </tool>
b
diff -r 39d9bc17ec74 -r cb9036583afe test-data/dm6_mate_annotated.bam
b
Binary file test-data/dm6_mate_annotated.bam has changed
b
diff -r 39d9bc17ec74 -r cb9036583afe test-data/proper_pair_discard.bam
b
Binary file test-data/proper_pair_discard.bam has changed
b
diff -r 39d9bc17ec74 -r cb9036583afe test-data/proper_pair_discard_fbti.bam
b
Binary file test-data/proper_pair_discard_fbti.bam has changed
b
diff -r 39d9bc17ec74 -r cb9036583afe test-data/proper_pair_discard_out.bam
b
Binary file test-data/proper_pair_discard_out.bam has changed
b
diff -r 39d9bc17ec74 -r cb9036583afe test-data/proper_pair_discard_verified_empty.bam
b
Binary file test-data/proper_pair_discard_verified_empty.bam has changed
b
diff -r 39d9bc17ec74 -r cb9036583afe test-data/proper_pair_out_suboptimal_tags.bam
b
Binary file test-data/proper_pair_out_suboptimal_tags.bam has changed