# HG changeset patch
# User devteam
# Date 1420822208 18000
# Node ID 71dd32fb0b0a1a6afa24cdc9ddceb30a762843c0
Uploaded
diff -r 000000000000 -r 71dd32fb0b0a bamtools-split.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/bamtools-split.xml Fri Jan 09 11:50:08 2015 -0500
@@ -0,0 +1,119 @@
+
+ BAM datasets on variety of attributes
+
+ bamtools
+
+
+
+ echo "BAM" > $report &&
+
+ #for $bam_count, $input_bam in enumerate( $input_bams ):
+ ln -s "${input_bam.input_bam}" "localbam_${bam_count}.bam" &&
+ ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" &&
+ #end for
+
+ bamtools
+ split
+
+ #if str ( $analysis_type.analysis_type_selector ) == "-tag" :
+
+ ${analysis_type.analysis_type_selector} "${analysis_type.tag_name}"
+
+ #else
+
+ ${analysis_type.analysis_type_selector}
+
+ #end if
+
+ -stub split_bam
+
+ #for $bam_count, $input_bam in enumerate( $input_bams ):
+ -in "localbam_${bam_count}.bam"
+ #end for
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**What is does**
+
+BAMTools split is a utility for splitting BAM files. It is based on BAMtools suite of tools by Derek Barnett (https://github.com/pezmaster31/bamtools).
+
+-----
+
+.. class:: warningmark
+
+**DANGER: Multiple Outputs**
+
+As described below, splitting a BAM dataset(s) on reference name or a tag value can produce very large numbers of outputs. Read below and know what you are doing.
+
+-----
+
+**How it works**
+
+The following options can be specified via "**Split BAM dataset(s) by**" dropdown::
+
+ Mapping status (-mapped) split mapped/unmapped and generate two output files
+ named (MAPPED) and (UNMAPPED) containing mapped and unmapped
+ reads, respectively.
+
+ Pairing status (-paired) split single-end/paired-end alignments and generate two output files
+ named (SINGLE_END) and (PAIRED_END) containing paired and unpaired
+ reads, respectively.
+
+ Reference name (-reference) split alignments by reference name. In cases of unfinished genomes with
+ very large number of reference sequences (scaffolds) it can generate
+ thousands (if not millions) of output datasets.
+
+ Specific tag (-tag) split alignments based on all values of TAG encountered. Choosing this
+ option from the menu will allow you to enter the tag name. As was the
+ case with the reference splitting above, this option can produce very
+ large number of outputs if a tag has a large number of unique values.
+
+-----
+
+.. class:: infomark
+
+**More information**
+
+Additional information about BAMtools can be found at https://github.com/pezmaster31/bamtools/wiki
+
+
+
+ 10.1093/bioinformatics/btr174
+
+
diff -r 000000000000 -r 71dd32fb0b0a shed_upload.tar.gz
Binary file shed_upload.tar.gz has changed
diff -r 000000000000 -r 71dd32fb0b0a test-data/bamtools-input1.bam
Binary file test-data/bamtools-input1.bam has changed
diff -r 000000000000 -r 71dd32fb0b0a test-data/bamtools-split-test1.bam
Binary file test-data/bamtools-split-test1.bam has changed
diff -r 000000000000 -r 71dd32fb0b0a tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Fri Jan 09 11:50:08 2015 -0500
@@ -0,0 +1,6 @@
+
+
+
+
+
+