Mercurial > repos > iuc > bedtools

changeset 6:d25966c8ddeb draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bedtools commit 6ce9a5a91d803b9ac9e743d9721ff0ccd2a5a59f-dirty
author iuc
date Sun, 22 May 2016 12:33:32 -0400
parents f8b7dc21b4ee
children 8e6b7c3597a8
files closestBed.xml coverageBed.xml shuffleBed.xml
diffstat 3 files changed, 33 insertions(+), 30 deletions(-) [+]
line wrap: on
line diff
--- a/closestBed.xml	Sat Feb 27 12:56:56 2016 -0500
+++ b/closestBed.xml	Sun May 22 12:33:32 2016 -0400
@@ -7,7 +7,7 @@
     <expand macro="stdio" />
     <command>
 <![CDATA[
-        #set inputBs = ' '.join( [ str( $file ) for $file in $inputB ] )
+        #set inputBs = "' '".join([str( $file ) for $file in $inputB])
 
         closestBed
         $strand
@@ -23,8 +23,8 @@
         #if $k:
             -k $k
         #end if
-        -a $inputA
-        -b $inputBs
+        -a '$inputA'
+        -b '$inputBs'
         > $output
 ]]>
     </command>
--- a/coverageBed.xml	Sat Feb 27 12:56:56 2016 -0500
+++ b/coverageBed.xml	Sun May 22 12:33:32 2016 -0400
@@ -1,5 +1,5 @@
 <tool id="bedtools_coveragebed" name="Compute both the depth and breadth of coverage" version="@WRAPPER_VERSION@.1">
-    <description>of features in file A across the features in file B (coverageBed)</description>
+    <description>of features in file B on the features in file A (bedtools coverage)</description>
     <macros>
         <import>macros.xml</import>
     </macros>
@@ -7,36 +7,34 @@
     <expand macro="stdio" />
     <command>
 <![CDATA[
-        coverageBed
-        #if $inputA.ext == "bam"
-            -abam '$inputA'
-        #else
-            -a '$inputA'
-        #end if
-        -b '$inputB'
+        #set inputBs = "' '".join([str($file) for $file in $inputB])
+
+        bedtools coverage
         $d
         $hist
         $split
         $strandedness
+        -a '$inputA'
+        -b '$inputBs'
         | sort -k1,1 -k2,2n
         > '$output'
 ]]>
     </command>
     <inputs>
-        <param format="bed,bam,gff,gg3,vcf" name="inputA" type="data" label="Count how many intervals in this BED/VCF/GFF/BAM file (source)" />
-        <param format="bed,gff,gff3,vcf" name="inputB" type="data" label="overlap the intervals in this BED file (target)" />
+        <param format="bam,bed,gff,gff3,vcf" name="inputA" type="data" label="File A (on which coverage is calculated)" help="BAM/BED/GFF/VCF format" />
+        <param format="bam,bed,gff,gff3,vcf" name="inputB" type="data" multiple="true" label="File(s) B (for which coverage is calculated)" help="BAM/BED/GFF/VCF format" />
         <expand macro="split" />
         <param name="strandedness" type="boolean" label="Force strandedness" truevalue="-s" falsevalue="" checked="false" 
-            help="That is, only features in A are only counted towards coverage in B if they are the same strand. (-s)"/>
+            help="Only report hits in B that overlap A on the same strand. By default, overlaps are reported without respect to strand (-s)"/>
         <param name="d" type="boolean" checked="false" truevalue="-d" falsevalue=""
-            label="Report the depth at each position in each B feature"
-            help="Positions reported are one based.  Each position and depth follow the complete B feature. (-d)" />
+            label="Report the depth at each position in each A feature"
+            help="Positions reported are one based. Each position and depth follow the complete B feature (-d)" />
         <param name="hist" type="boolean" checked="false" truevalue="-hist" falsevalue=""
-            label="Report a histogram of coverage for each feature in B as well as a summary histogram for all features in B"
-            help="Additonal columns after each feature in B: 1) depth 2) # bases at depth 3) size of B 4) % of B at depth. (-hist)" />
+            label="Report a histogram of coverage for each feature in A as well as a summary histogram for all features in A"
+            help="Additional columns after each feature in A: 1) depth 2) # bases at depth 3) size of A 4) % of A at depth (-hist)" />
     </inputs>
     <outputs>
-        <data format="bed" name="output" metadata_source="inputB" label="Count of overlaps in ${inputA.name} on ${inputB.name}"/>
+        <data format="bed" name="output" metadata_source="inputA" label="Count of overlaps on ${inputA.name}"/>
     </outputs>
     <tests>
         <test>
@@ -49,18 +47,23 @@
 <![CDATA[
 **What it does**
 
-coverageBed_ computes both the depth and breadth of coverage of features in 
-file A across the features in file B. For example, coverageBed can compute the coverage of sequence alignments 
-(file A) across 1 kilobase (arbitrary) windows (file B) tiling a genome of interest. 
-One advantage that coverageBed offers is that it not only counts the number of features that 
-overlap an interval in file B, it also computes the fraction of bases in B interval that were overlapped by one or more features.
-Thus, coverageBed also computes the breadth of coverage for each interval in B.
+`bedtools coverage`_ computes both the *depth* and *breadth* of coverage of features in 
+file B on the features in file A. For example, ``bedtools coverage`` can compute the coverage of sequence alignments 
+(file B) across 1 kilobase (arbitrary) windows (file A) tiling a genome of interest. 
+One advantage that ``bedtools coverage`` offers is that it not only *counts* the number of features that 
+overlap an interval in file A, it also computes the fraction of bases in the interval in A that were overlapped by one or more features.
+Thus, ``bedtools coverage`` also computes the *breadth* of coverage for each interval in A.
 
-.. _coverageBed: http://bedtools.readthedocs.org/en/latest/content/tools/coverage.html
+.. _bedtools coverage: http://bedtools.readthedocs.org/en/latest/content/tools/coverage.html
 
 .. class:: infomark
 
-The output file will be comprised of each interval from your original target BED file, plus an additional column indicating the number of intervals in your source file that overlapped that target interval.
+The lines in the output will be comprised of each interval in A, followed by:
+
+1. The number of features in B that overlapped (by at least one base pair) the A interval.
+2. The number of bases in A that had non-zero coverage from features in B.
+3. The length of the entry in A.
+4. The fraction of bases in A that had non-zero coverage from features in B.
 
 @REFERENCES@
 ]]>
--- a/shuffleBed.xml	Sat Feb 27 12:56:56 2016 -0500
+++ b/shuffleBed.xml	Sun May 22 12:33:32 2016 -0400
@@ -15,10 +15,10 @@
             -seed $seed.seed
         #end if
         #if str($add_bed.add_bed_select) == "not_be":
-            -excl $add_bed_select.excl
-            -f $add_bed_select.overlap
+            -excl $add_bed.excl
+            -f $add_bed.overlap
         #elif str($add_bed.add_bed_select) == "be":
-            -incl $add_bed_select.incl
+            -incl $add_bed.incl
         #end if
         $chrom
         $chromfirst