Mercurial > repos > nikos > ucsc_tools

changeset 7:eebdd6da9353 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Deleted selected files
author nikos
date Tue, 02 Sep 2014 12:00:04 -0400
parents 558f7f9baa78
children ad32956798e3
files bedClip.sh bedClip.xml bedExtendRanges.xml bigWigSummary.xml bigwig2summary.xml make_ucsc_track.sh make_ucsc_track.xml
diffstat 7 files changed, 0 insertions(+), 335 deletions(-) [+]
line wrap: on
line diff
--- a/bedClip.sh	Tue Jul 15 07:19:46 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,3 +0,0 @@
-#!/bin/bash
-
-bedClip $1 <(fetchChromSizes $2 2> /dev/null) $3
--- a/bedClip.xml	Tue Jul 15 07:19:46 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,53 +0,0 @@
-<tool id="bedClip" name="bedClip">
-  <description> Remove lines from bed file that refer to off-chromosome places.</description>
-  <command interpreter="bash"> 
-	## Set genome assembly 
-
-	#set $Genome = str( $genome_cond.genome )
-	#if str( $genome_cond ) == 'OTHER':
-		#set $Genome = str( $genome_cond.genome_other )
-	#end if
-	
-	bedClip.sh $input $Genome $output
-  </command>
-  <inputs>
-    <param name="input" type="data" format="bed" label="Input"/>
-    <conditional name="genome_cond">
-      <param name="genome" type="select" label="Genome Assembly">
-        <option value="hg19">Human (Homo sapiens): hg19</option>
-        <option value="hg18">Human (Homo sapiens): hg18</option>
-        <option value="mm10">Mouse (Mus musculus): mm10</option>
-        <option value="mm9">Mouse (Mus musculus): mm9</option>
-        <option value="ce10">C. elegans: ce10</option>
-        <option value="ce6">C. elegans: ce6</option>
-        <option value="dm3">D. melanogaster: dm3</option>
-        <option value="OTHER">Other</option>
-      </param>
-      <when value="OTHER">
-        <param name="genome_other" type="text" label="Other genome assemly"/>
-      </when>
-      <when value="hg19" type="text" />
-      <when value="hg18" type="text" />
-      <when value="mm10" type="text" />
-      <when value="mm9" type="text" />
-      <when value="ce10" type="text" />
-      <when value="ce6" type="text" />
-      <when value="dm3" type="text" />
-    </conditional>
-
-  </inputs>
-  
-  <outputs>
-    <data format="input" name="output"/> 
-  </outputs>
-  <help>
-**What it does**
-bedClip - Remove lines from bed file that refer to off-chromosome places.
-
-**Usage**
-
-  bedClip input.bed chrom.sizes output.bed
-
-  </help>
-</tool>
-
--- a/bedExtendRanges.xml	Tue Jul 15 07:19:46 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,68 +0,0 @@
-<tool id="bedExtendRanges" name="bedExtendRanges">
-  <description> Extend length of entries in bed 6+. </description>
-  <command> 
-	## Set genome assembly 
-
-	#set $Genome = str( $genome_cond.genome )
-	#if str( $genome_cond ) == 'OTHER':
-		#set $Genome = str( $genome_cond.genome_other )
-	#end if
-	
-	bedExtendRanges -user=genome -host=genome-mysql.cse.ucsc.edu $Genome $length $input 2> /dev/null > $output
-  </command>
-  <inputs>
-    <param name="input" type="data" format="bed" label="Input"/>
-    <conditional name="genome_cond">
-      <param name="genome" type="select" label="Genome Assembly (-g)">
-        <option value="hg19">Human (Homo sapiens): hg19</option>
-        <option value="hg18">Human (Homo sapiens): hg18</option>
-        <option value="mm10">Mouse (Mus musculus): mm10</option>
-        <option value="mm9">Mouse (Mus musculus): mm9</option>
-        <option value="ce10">C. elegans: ce10</option>
-        <option value="ce6">C. elegans: ce6</option>
-        <option value="dm3">D. melanogaster: dm3</option>
-        <option value="OTHER">Other</option>
-      </param>
-      <when value="OTHER">
-        <param name="genome_other" type="text" label="Other genome assemly"/>
-      </when>
-      <when value="hg19" type="text" />
-      <when value="hg18" type="text" />
-      <when value="mm10" type="text" />
-      <when value="mm9" type="text" />
-      <when value="ce10" type="text" />
-      <when value="ce6" type="text" />
-      <when value="dm3" type="text" />
-    </conditional>
-    <param name="length" type="integer" value="0" label="Length extension (base-pairs)" />
-
-  </inputs>
-  
-  <outputs>
-    <data format="input" name="output"/> 
-  </outputs>
-  <help>
-
-**What it does**
-
-bedExtendRanges - extend length of entries in bed 6+ data to be at least the given length,
-taking strand directionality into account.
-
-**Usage**
-
-   bedExtendRanges database length files(s)
-
-**Example**
-
-  * bedExtendRanges -user=genome -host=genome-mysql.cse.ucsc.edu hg18 250 stdin
-
-  will transform:
-    chr1 500 525 . 100 +
-    chr1 1000 1025 . 100 -
-  to:
-    chr1 500 750 . 100 +
-    chr1 775 1025 . 100 -
-
-  </help>
-</tool>
-
--- a/bigWigSummary.xml	Tue Jul 15 07:19:46 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,33 +0,0 @@
-<tool id="bigWigSummary" name="bigWigSummary">
-  <description> Extract summary information from a bigWig file. </description>
-  <command> 
-	bigWigSummary $input $chrom $start $end $dataPoints -type=$type> $output
-  </command>
-  <inputs>
-    <param name="input" type="data" format="bigwig" label="Input"/>
-    <param name="chrom" type="text" value="chr" label="Chromosome" help="E.g. 'chr7'"/>
-    <param name="start" type="integer" value="" label="Start coordinate" help="BED format (0-based)."/>
-    <param name="end" type="integer" value="" label="End coordinate" help="BED format (0-based)."/>    
-      
-    <param name="dataPoints" type="integer" value="1" label="Number of (equal) parts to break down the selected region."  help="Choose 1 for simple summary."/>
-    <param name="type" type="select" label="Operation">
-	<option value="mean">Average value in region (default)</option>
-        <option value="min">Minimum value in region</option>
-        <option value="max">Maximum value in region</option>
-        <option value="std">Standard deviation in region</option>
-        <option value="coverage">Percentage of region that is covered</option>
-    </param>
-  </inputs>
-  
-  <outputs>
-    <data format="text" name="output"/> 
-  </outputs>
-  <help>
-
-**Usage**
-  * bigWigSummary file.bigWig chrom start end dataPoints
-  * Get summary data from bigWig for indicated region, broken into dataPoints equal parts.  (Use dataPoints=1 for simple summary.)
-
-  </help>
-</tool>
-
--- a/bigwig2summary.xml	Tue Jul 15 07:19:46 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,85 +0,0 @@
-<tool id="bigwig2_summary" name="bigWig2Summary">
-  <description> Extract summary information from a bigWig file across multiple genomic regions specified by the user. </description>
-  <requirements>
-    <requirement type="package">bigWigSummary</requirement>
-    <requirement type="package">bigwig2summary_stdout</requirement>
-    <requirement type="package">bedClip</requirement>
-  </requirements>
-  <command> 
-	/home/jens/bin/bigwig2summary_stdout -f $input_bw -b $input_bed -n $bins -o $assembly -t $type $header > $output
-  </command>
-  <inputs>
-    <param name="input_bw" type="data" format="bigwig" label="Extract summary from" help="bigWig format."/>
-    <param name="input_bed" type="data" format="tabular" label="using genomic regions in" help="TAB delimited BED-like file."/>
-    <param name="bins" type="integer" value="1" label="Number of bins" help="Postitive integer"/>
-    <param name="assembly" type="text" label="Orgamism assembly" help="E.g. hg19" />
-    <param name="header" type="boolean" checked="False" truevalue="-e" falsevalue=" " label="Does the genomic region file contain a header?" />    
-    <param name="type" type="select" label="Operation" help="">
-	<option value="mean">Average value in region (default)</option>
-        <option value="min">Minimum value in region</option>
-        <option value="max">Maximum value in region</option>
-        <option value="std">Standard deviation in region</option>
-        <option value="coverage">Percentage of region that is covered</option>
-    </param>
-  </inputs>
-  
-  <outputs>
-    <data format="tabular" name="output"/> 
-  </outputs>
-  <help>
-
-This tool extracts summary values (mean, min, max, std or coverage) from a **bigWig** file for a number of equal sized bins across genomic regions given in an a "BED-like" file.
-
-The script this tool is based on is written by Jens Vilstrup Johansen and uses bigWigSummary_ and bedClip_.
-
-.. _bigWigSummary: https://github.com/adamlabadorf/ucsc_tools/blob/master/executables/bigWigSummary
-
-.. _bedClip: http://hgdownload.cse.ucsc.edu/admin/exe/linux.x86_64/bedClip
-
------
-
-.. class:: infomark
-
-The file contaning the genomic region must be TAB-delimited with at list 3 columns representing Chromosome, ChrStart and ChrEnd. If the file contains 6 columns (or more), column 6 is expected to contain strand information. Summary values from a negative strand will be reversed.
- 
------
-
-**Example 1**
-
-Input BED file::
-
-  chr19   50178708        50180708
-  chr6    90348174        90350174
-  chr16   58495848        58497848
-  chr5    180580242       180582242
-  chr9    120177017       120179017  
-
-Extract summary (*#* of bins = 3):: 
-
-  0		0		0
-  0.144886	0		0
-  0.507327	1.14649		1.38456
-  0.221471	0.144886	0.309857
-  0.348944	0.426638	0.244495
-
-**Example 2**
-
-Input BED file (with strand information)::
-
-  chr19	  50178708	50180708	NM_198318	0	+	PRMT1
-  chr6	  90348174	90350174	NM_020466	0	-	LYRM2
-  chr16	  58495848	58497848	NM_020465	0	+	NDRG4
-  chr5 	  180580242	180582242	NM_206880	0	+	OR2V2
-  chr9    120177017     120179017       NM_014010       0       -	ASTN2
-
-Extract summary (*#* of bins = 3)::
-
-  0		0		0
-  0		0		0.144886
-  0.507327	1.14649		1.38456
-  0.221471	0.144886	0.309857
-  0.244495	0.426638	0.348944
-
-  </help>
-</tool>
-
--- a/make_ucsc_track.sh	Tue Jul 15 07:19:46 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,59 +0,0 @@
-#!/bin/bash
-
-# This tool creates a UCSC track line given a bigWig or bedGraph input file, a track name and genome assembly.
-
-## Define URL prefix
-
-URL="http://data.bric.dk/galaxy/UCSC"
-
-#parse input
-while getopts hi:t:n:o: myarg
-do      case "$myarg" in
-        h)      echo "Usage: create UCSC track line -i <INPUT_FILE> -t <FILE_TYPE> -n <TRACK_NAME> -o <ASSEMBLY>"
-                exit ;;
-        i)      input_file="$OPTARG" ;;
-	t)	file_type="$OPTARG" ;;
-        n)      track_name="$OPTARG" ;; 
-        o)      org_assembly="$OPTARG" ;;
-        [?])    echo "Usage: create UCSC track line -i <INPUT_FILE> -t <FILE_TYPE> -n <TRACK_NAME> -o <ASSEMBLY>"
-
-                exit 1 ;;
-        esac
-done
-
-####################################################################
-# Check if a link to that file exists in the UCSC webfolder
-flag=0 
-
-for link in `ls -1 $UCSCPATH` 
-do 
-    if [ `readlink -f $input_file` == `readlink -f $UCSCPATH/$link` ] ; then
-        link_path=/$link # use already existing link
-	flag=1 
-    fi
-done
-
-# If link to input file doesn't exist, create anonymous soft-link for input file in a folder accessible from the web.
-
-if [ $flag == 0 ]; then
-    
-    link_path=`mktemp -u --tmpdir=/`
-    ln -s $input_file $UCSCPATH$link_path
-fi
-
-####################################################################
-##Convert 4th character of file_type to uppercase (e.g. bigwig -> bigWig). UCSC browser doesn't recognize the file type otherwise.
-
-##Split file_type string to prefix (big) and suffix (wig, bed) and uppercase the first character of the latter.
-prefix=`echo ${file_type:0:3}`
-suffix=`echo ${file_type:3} | sed -e "s/\b\(.\)/\u\1/g"`
-
-file_type=`echo ${prefix}${suffix}`
-
-####################################################################
-#Contruct URL
-bigURL=`echo ${URL}${link_path}`
-
-####################################################################
-## Print track line
-echo "track name='$track_name' db=$org_assembly type=$file_type visibility=full alwaysZero=ON bigDataUrl=$bigURL"
--- a/make_ucsc_track.xml	Tue Jul 15 07:19:46 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,34 +0,0 @@
-<tool id="make_ucsc_track" name="UCSC Track Line">
-  <description> Create a track line to import a bigWig or bigBed file in the UCSC genome browser </description>
-  <command interpreter="bash"> 
-	make_ucsc_track.sh -i $input -t ${input.ext} -n '$name' -o $assembly > $output
-  </command>
-  <inputs>
-    <param name="input" type="data" format="bigwig,bigbed" label="Input file" help="bigWig or bigBEd format." />
-    <param name="name" type="text" label="Track name" help="Type the track name you want to appear when you import the file in the UCSC browser." >
-         <validator type="empty_field" />
-    </param>
-
-    <param name="assembly" type="text" label="Orgamism assembly" help="E.g. hg19" >
-	<validator type="empty_field" />
-    </param>
-
-<!--    <param name="visibility" type="select" label="Track visibility">
-	<option value="3">Full</option>
-        <option value="2">Pack</option>
-        <option value="1">Dense</option>
-    </param>
--->
-  </inputs>
-  
-  <outputs>
-    <data format="txt" name="output"/> 
-  </outputs>
-  <help>
-This tool creates a UCSC track line for a bigWig or bigBed dataset in Galaxy. The text output can be pasted in the "Paste URLs or data" form in the `Add Custom Tracks`_ section of the UCSC Genome Browser.
-
-.. _Add Custom Tracks: http://genome.ucsc.edu/cgi-bin/hgCustom 
-
-  </help>
-</tool>
-