Mercurial > repos > eiriche > bsmap

changeset 10:4f9b7eaecbd4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Deleted selected files
author eiriche
date Fri, 30 Nov 2012 05:28:16 -0500
parents 385d004f3cb1
children 413c742682f7
files bsmap.xml bsmap_fasta.loc.sample bsmap_meth_caller.sh bsmap_meth_caller.xml bsmap_wrapper.sh tool_data_table_conf.xml.sample
diffstat 6 files changed, 0 insertions(+), 494 deletions(-) [+]
line wrap: on
line diff
--- a/bsmap.xml	Fri Nov 30 05:10:53 2012 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,246 +0,0 @@
-<tool id="bsmap" name="BSMAP Mapper">
-	<requirements>
-	    <requirement type='package'>
-		bsmap
-	    </requirement>
-	</requirements>
-        <command interpreter="bash">
-              bsmap_wrapper.sh
-			##Reference genome
-			##ref="${reference.fields.path}"
-			#if $refGenomeSource.genomeSource == "history":
-				ref="${refGenomeSource.myFile.extra_files_path}/${refGenomeSource.myFile.metadata.base_name}"
-			#else
-				ref="${refGenomeSource.builtin.fields.path}"
-			#end if
-			##Output files (SAM output, BSMAP summary)
-			mapped=$mapped
-			##Temp directory
-			tempdir=$mapped.files_path
-			summary=$summary
-			#if str($singlePaired.sPaired) == "single":
-			  library="single"
-			  mate1=$singlePaired.sInput1
-			  #if str($singlePaired.sParams.sSettingsType) == "full":
-			    fullparam=true
-			    qual=$singlePaired.sParams.qual
-			    threshold=$singlePaired.sParams.threshold
-			    lowqual=$singlePaired.sParams.lowqual
-			    adapter=$singlePaired.sParams.adapter
-			    firstn=$singlePaired.sParams.firstn
-			    repeat_reads=$singlePaired.sParams.repeat_reads
-			    seed_size=$singlePaired.sParams.seed_size
-			    mismatch=$singlePaired.sParams.mismatch
-			    equal_best=$singlePaired.sParams.equal_best
-			    start=$singlePaired.sParams.start
-			    end=$singlePaired.sParams.end
-			    index_interval=$singlePaired.sParams.index_interval
-			    seed_random=$singlePaired.sParams.seed_random
-			    rrbs=$singlePaired.sParams.rrbs
-			    mode=$singlePaired.sParams.mode
-			    align_info=$singlePaired.sParams.align_info     
-			  #end if
-			#else:
-			  library="paired"
-			  mate1=$singlePaired.pInput1
-			  mate2=$singlePaired.pInput2
-			  unpaired=$unpaired
-			  #if str($singlePaired.pParams.pSettingsType) == "full":    
-			    fullparam=true
-			    qual=$singlePaired.pParams.qual
-			    threshold=$singlePaired.pParams.threshold
-			    lowqual=$singlePaired.pParams.lowqual
-			    adapter=$singlePaired.pParams.adapter
-			    firstn=$singlePaired.pParams.firstn
-			    repeat_reads=$singlePaired.pParams.repeat_reads
-			    seed_size=$singlePaired.pParams.seed_size
-			    mismatch=$singlePaired.pParams.mismatch
-			    equal_best=$singlePaired.pParams.equal_best
-			    start=$singlePaired.pParams.start
-			    end=$singlePaired.pParams.end
-			    index_interval=$singlePaired.pParams.index_interval
-			    seed_random=$singlePaired.pParams.seed_random
-			    rrbs=$singlePaired.pParams.rrbs
-			    mode=$singlePaired.pParams.mode
-			    align_info=$singlePaired.pParams.align_info     
-			    maxinsert=$singlePaired.pParams.maxinsert  
-			    mininsert=$singlePaired.pParams.mininsert  
-			  #end if
-			#end if
-        </command>
-  <inputs>
-
-  <conditional name="refGenomeSource">
-      <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in reference?">
-        <option value="builtin">Use a built-in index</option>
-        <option value="history">Use one from the history</option>
-      </param>
-      <when value="builtin">
-        <param name="index" type="select" label="Select a reference genome">
-          <options from_data_table="bsmap_fasta">
-            <filter type="sort_by" column="2" />
-            <validator type="no_options" message="No reference genomes are available" />
-          </options>
-        </param>
-      </when>
-      <when value="history">
-        <param name="myFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" />
-      </when> 
-  </conditional>
-  
-  <conditional name="singlePaired">
-      <param name="sPaired" type="select" label="Is this library mate-paired?">
-        <option value="single">Single-end</option>
-        <option value="paired">Paired-end</option>
-      </param>
-      <when value="single">
-        <param name="sInput1" type="data" format="fastq,fasta" label="FASTQ file" help="Must have ASCII encoded quality scores"/>
-        <conditional name="sParams">
-          <param name="sSettingsType" type="select" label="BSMAP settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list">
-            <option value="preSet">Commonly used</option>
-            <option value="full">Full parameter list</option>
-          </param>
-          <when value="preSet" />
-          <when value="full">
-	    <param name="qual" type="select" label="Select the type of FastQ qualities">
-		<option value="33">phred33-quals</option>
-		<option value="64">phred64-quals</option>
-	    </param>
-	    <param name="threshold" type="integer" value="0" label="Quality threshold in trimming" help="0-40, default=0 (no trim)" min="0" max="40" />
-	    <param name="lowqual" type="integer" value="5" label="Filter low-quality reads containing >n Ns" help="default=5" />
-	    <param name="adapter" type="text" value="none" label="3-end adapter sequence" help="default: none (no trim)" />
-	    <param name="firstn" type="integer" value="144" label="Map the first N nucleotides of the read" help="default:144 (map the whole read)" />
-	    
-	    <param name="repeat_reads" type="select" label="How to report repeat hits">
-	      <option value="0">none(unique hit only)</option>
-	      <option value="1">random one</option>
-	    </param>
-	    
-	    <param name="seed_size" type="integer" value="16" label="Seed size" min="8" max="16" help="default=16(WGBS mode), 12(RRBS mode)" />
-	    <param name="mismatch" type="integer" value="2" label="Maximum number of mismatches allowed on a read" max="15" />
-	    <param name="equal_best" type="integer" value="20" label="Maximum number of equal best hits to count" max="1000" />
-	    <param name="start" type="integer" value="1" label="Start from the Nth read or read pair" />
-	    <param name="end" type="integer" value="4294967295" label="End at the Nth read or read pair" />
-	    <param name="index_interval" type="integer" value="4" label="Index interval" />
-	    <param name="seed_random" type="integer" value="-1" label="Seed for random number generation used in selecting multiple hits" help="other seed values generate pseudo random number based on read index number, to allow reproducible mapping results" />
-	    <param name="rrbs" type="text" value="none" label="Activating RRBS mapping mode and set restriction enzyme digestion sites" help="digestion position marked by '-', example: -D C-CGG for MspI digestion. default: none (whole genome shotgun bisulfite mapping mode)" />
-	     <param name="mode" type="select" label="Set mapping strand information">
-		<option value="0">only map to 2 forward strands</option>
-		<option value="1">map SE or PE reads to all 4 strands</option>
-	    </param>
-	    <param name="align_info" type="text" value="none" label="Set alignment information for the additional nucleotide transition" help="is in the form of two different nucleotides N1N2,indicating N1 in the reads could be mapped to N2 in the reference sequences. default: -M TC, corresponds to C=>U(T) transition in bisulfite conversion. example: -M GA could be used to detect A=>I(G) transition in RNA editing." />
-          </when> <!-- full -->
-        </conditional> <!-- sParams -->
-      </when> <!-- single -->
-   
-      <when value="paired">
-        <param name="pInput1" type="data" format="fastq,fasta" label="Forward FASTQ file" />
-	<param name="pInput2" type="data" format="fastq,fasta" label="Reverse FASTQ file" />
-
-        <conditional name="pParams">
-          <param name="pSettingsType" type="select" label="BSMAP settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list">
-            <option value="preSet">Commonly used</option>
-            <option value="full">Full parameter list</option>
-          </param>
-         <when value="preSet" />
-          <when value="full">
-	    <param name="qual" type="select" label="Select the type of FastQ qualities">
-		<option value="33">phred33-quals</option>
-		<option value="64">phred64-quals</option>
-	    </param>
-	    
-	    <param name="mininsert" type="integer" value="28" label="Minimal insert size allowed" />
-	    <param name="maxinsert" type="integer" value="500" label="Maximal insert size allowed" />
-	    
-	    <param name="threshold" type="integer" value="0" label="Quality threshold in trimming" help="0-40, default=0 (no trim)" min="0" max="40" />
-	    <param name="lowqual" type="integer" value="5" label="Filter low-quality reads containing >n Ns" help="default=5" />
-	    <param name="adapter" type="text" value="none" label="3-end adapter sequence" help="default: none (no trim)" />
-	    <param name="firstn" type="integer" value="144" label="Map the first N nucleotides of the read" help="default:144 (map the whole read)" />
-	    
-	    <param name="repeat_reads" type="select" label="How to report repeat hits">
-	      <option value="0">none(unique hit only)</option>
-	      <option value="1">random one</option>
-	    </param>
-	    
-	    <param name="seed_size" type="integer" value="16" label="Seed size" min="8" max="16" help="default=16(WGBS mode), 12(RRBS mode)" />
-	    <param name="mismatch" type="integer" value="2" label="Maximum number of mismatches allowed on a read" max="15" />
-	    <param name="equal_best" type="integer" value="20" label="Maximum number of equal best hits to count" max="1000" />
-	    <param name="start" type="integer" value="1" label="Start from the Nth read or read pair" />
-	    <param name="end" type="integer" value="4294967295" label="End at the Nth read or read pair" />
-	    <param name="index_interval" type="integer" value="4" label="Index interval" />
-	    <param name="seed_random" type="integer" value="-1" label="Seed for random number generation used in selecting multiple hits" help="other seed values generate pseudo random number based on read index number, to allow reproducible mapping results" />
-	    <param name="rrbs" type="text" value="none" label="Activating RRBS mapping mode and set restriction enzyme digestion sites" help="digestion position marked by '-', example: -D C-CGG for MspI digestion. default: none (whole genome shotgun bisulfite mapping mode)" />
-	     <param name="mode" type="select" label="Set mapping strand information">
-		<option value="0">only map to 2 forward strands</option>
-		<option value="1">map SE or PE reads to all 4 strands</option>
-	    </param>
-	    <param name="align_info" type="text" value="none" label="Set alignment information for the additional nucleotide transition" help="is in the form of two different nucleotides N1N2,indicating N1 in the reads could be mapped to N2 in the reference sequences. default: -M TC, corresponds to C=>U(T) transition in bisulfite conversion. example: -M GA could be used to detect A=>I(G) transition in RNA editing." />
-
-	    
-          </when> <!-- full -->
-        </conditional> <!-- pParams -->
-      </when> <!-- paired -->
-    </conditional> <!-- singlePaired -->
-  
-  
- </inputs>
- <outputs>
-        <data name="mapped" format="sam" label="BSMAP Mapped Reads">
-	    <actions>
-		<action type="metadata" name="dbkey">
-		    <option type="from_data_table" name="bsmap_fasta" column="1" offset="0">
-			<filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
-			<filter type="param_value" ref="reference" column="0"/>
-		    </option>
-		</action>
-	    </actions>	  
-	</data>
-	<data name="summary" format="txt" label="BSMAP Mapping Summary" />
-	<data name="unpaired" format ="sam" label="BSMAP Unpaired Hits">
-	  <filter>(singlePaired['sPaired'] == 'paired')</filter>
-	</data>
-
- </outputs>
- <help>
-**What it does**
-
-BSMAP is a short reads mapping software for bisulfite sequencing reads. It has the following features:
-
-   - read length up to 144 nt, allow up to 15 mismatches, gap size up to 3 bp.
-
-   - support single end and pair end mapping. support multi-thread mapping.
-
-   - support both "Lister protocol" (sequence 2 forward strands only) and "Cokus protocol" (sequence all 4 bisulfite converted strands)
-
-   - reads are directly mapped to original reference genome sequence, no need to preprocess the reads and reference genome to convert C to T.
-
-   - support both whole genome bisulfite sequencing (WGBS) mode and reduced representation bisulfite sequencing (RRBS) mode, allow changing the digestion site information to support different digestion enzymes for RRBS.
-
-   - allow trimming adapter sequences and low quality nucleotides from the 3'end of reads
-
-   - allow trade off between speed/memory usage/mapping sensitivity. For human genome, the RRBS mode uses ~3GB. In WGBS mode, the typical memory usage is ~9GB, but can be as low as 5GB.
-
-   - allow alignment for other nucleotide transitions, for example, can be set to detect the A=>I(G) transition in RNA editing.
-
-.. _BSMAP: http://code.google.com/p/bsmap/
-
-**Input formats**
-
-BSMAP accepts files in FASTA/FASTQ format.
-
-**Outputs**
-
-The output contains the following files:
-
-    -  mapped reads in SAM format
-    
-    -  mapping summary
-    
-    -  unpaired hits (only for paired-end mapping)
-   
- </help>
- 
- <tests>
- </tests>
-</tool>
-
--- a/bsmap_fasta.loc.sample	Fri Nov 30 05:10:53 2012 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,16 +0,0 @@
-#This is a sample file distributed with Galaxy that enables BSMAP
-#to use a directory of reference FastA sequences data files.The bsmap_fasta.loc
-#file has this format (longer white space characters are TAB characters):
-#
-#<unique_build_id>   <dbkey>   <display_name>   <file_path>
-#
-#
-#Your bsmap_fasta.loc file should include an entry per line for each
-reference you have stored. For example:
-#
-#phiX174              phiX   phiX174          /depot/data2/galaxy/phiX/base/phiX.fasta
-#hg18canon            hg18   hg18 Canonical   /depot/data2/galaxy/hg18/base/hg18canon.fasta
-#hg18full             hg18   hg18 Full        /depot/data2/galaxy/hg18/base/hg18full.fasta
-#/orig/path/hg19.fa   hg19   hg19             /depot/data2/galaxy/hg19/base/hg19.fasta
-#...etc...
-#
--- a/bsmap_meth_caller.sh	Fri Nov 30 05:10:53 2012 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,32 +0,0 @@
-#!/bin/bash
-#
-# Galaxy wrapper for BSMAP Methylation Caller
-#
-
-set -e
-
-#get parameters
-
-until [ $# -eq 0 ]
-do
-	case $1 in
-		input=*)
-			input=${1#input=}
-			;;
-		method=*)
-			method=${1#method=}
-			;;
-		output=*)
-			output=${1#output=}
-			;;
-		tempdir=*)
-			tempdir=${1#tempdir=}
-			;;
-		ref=*)
-			ref=${1#ref=}
-			;;
-	esac
-	shift
-done
-
-methratio.py -o $output -d $ref -q $input
\ No newline at end of file
--- a/bsmap_meth_caller.xml	Fri Nov 30 05:10:53 2012 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,59 +0,0 @@
-<tool id="bsmap_meth_caller" name="BSMAP Methylation Caller">
-	<requirements>
-	    <requirement type='package'>
-		bsmap
-	    </requirement>
-	</requirements>
-	<requirements>
-	    <requirement type='package'>
-		samtools
-	    </requirement>
-	</requirements>
-        <command interpreter="bash">
-               bsmap_meth_caller.sh			
-			input=$bsmap_sam
-			unique=$unique
-			properly=$properly
-			zero_meth = $zero_meth
-			rem_dup = $rem_dup
-			combine_cpg = $combine_cpg
-			trimN = $trimN
-			depth = $depth			
-			output=$output
-			tempdir=$output.files_path
-			ref="${ filter( lambda x: str( x[1] ) == str( $bsmap_sam.metadata.dbkey ), $__app__.tool_data_tables['bsmap_fasta'].get_fields() )[0][3] }"
-        </command>
-  <inputs>
-	<param name="bsmap_sam" format="sam" type="data" label="BSMAP mapping output file" help="Must be in SAM format" />
-	<param name="unique" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Process only unique mappings/pairs" />  
-	<param name="properly" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Process only properly paired mappings" /> 
-	<param name="zero_meth" type="boolean" truevalue="true" falsevalue="false" checked="True" label="report loci with zero methylation ratios" /> 
-	<param name="rem_dup" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Remove duplicated reads" />
-	<param name="combine_cpg" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Combine CpG methylaion ratios on both strands" />
-	<param name="trimN" type="integer" value="2" label="Trim N fill-in nucleotides in DNA fragment end-repairing" help="This option is only for pair-end mapping. For RRBS, N could be detetmined by the distance between cuttings sites on forward and reverse strands. For WGBS, N is usually between 0~3" />
-	<param name="depth" type="integer" value="1" label="Minimum sequencing depth to report loci" />
-  </inputs>
-  <outputs>
-	<data name="output" format ="bed" label="BSMAP methylation output" />
-  </outputs>
-  <help>
-**What it does**
-
-This methylation caller parses the BSMAP SAM output file into bed format.
-
-
-**Output format** ::
-
-
-  Column  			Description
-  ----------------------	--------------------------------------
-  1 chr				chromosome
-  2 pos 			position
-  3 strand 			strand
-  4 context 			context (CHH,CHG,CpG)
-  5 coverage 			totally sequenced Cs at that position
-  6 methylated			methylated Cs at that position
-  7 percentage methylated	percentage of 6
-  </help>
-</tool>
-
--- a/bsmap_wrapper.sh	Fri Nov 30 05:10:53 2012 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,133 +0,0 @@
-#!/bin/bash
-#
-# Galaxy wrapper for BSMAP
-# Written by Eugen Eirich @ Institute for Molecular Biology Mainz
-#
-
-set -e
-
-#get parameters
-
-until [ $# -eq 0 ]
-do
-	case $1 in
-		ref=*)
-			ref=${1#ref=}
-			;;
-		library=*)
-			library=${1#library=}
-			;;
-		unpaired=*)
-			unpaired=${1#unpaired=}
-			;;
-		mapped=*)
-			mapped=${1#mapped=}
-			;;
-		fullparam=*)
-			fullparam=${1#fullparam=}
-			;;
-		mate1=*)
-			mate1=${1#mate1=}
-			;;
-		mate2=*)
-			mate2=${1#mate2=}
-			;;
-		qual=*)
-			qual="-z ${1#qual=}"
-			;;
-		threshold=*)
-			threshold="-q ${1#threshold=}"
-			;;
-		lowqual=*)
-			lowqual="-f ${1#lowqual=}"
-			;;
-		adapter=*)
-			adapter=${1#adapter=}
-			;;
-		firstn=*)
-			firstn="-L ${1#firstn=}"
-			;;
-		repeat_reads=*)
-			repeat_reads="-r ${1#repeat_reads=}"
-			;;
-		seed_size=*)
-			seed_size="-s ${1#seed_size=}"
-			;;
-		mismatch=*)
-			mismatch="-v ${1#mismatch=}"
-			;;
-		equal_best=*)
-			equal_best="-w ${1#equal_best=}"
-			;;
-		start=*)
-			start="-B ${1#start=}"
-			;;
-		end=*)
-			end="-E ${1#end=}"
-			;;
-		index_interval=*)
-			index_interval="-I ${1#index_interval=}"
-			;;
-		seed_random=*)
-			seed_random=${1#seed_random=}
-			;;
-		rrbs=*)
-			rrbs=${1#rrbs=}
-			;;
-		mode=*)
-			mode="-n ${1#mode=}"
-			;;
-		align_info=*)
-			align_info=${1#align_info=}
-			;;
-		maxinsert=*)
-			maxinsert="-x ${1#maxinsert=}"
-			;;
-		mininsert=*)
-			mininsert="-m ${1#mininsert=}"
-			;;
-		summary=*)
-			summary=${1#summary=}
-			;;
-	esac
-	shift
-done
-
-
-if [ "$rrbs" != "" ]
-then
-  rrbs="-D $rrbs"
-fi
-
-if [ "$align_info" != "" ]
-then
-  align_info="-M $align_info"
-fi
-
-if [ "$adapter" != "" ]
-then
-  adapter="-A $adapter"
-fi
-
-if [ "$seed_random" != "" ]
-then
-  seed_random="-S $seed_random"
-fi
-
-
-if [ "$library" == "single" ]
-then
-    if [ "$fullparam" == 'false' ]
-    then      
-      bsmap -a $mate1 -d $ref -o $mapped -R -r 0 -p 4 > $summary
-    else
-      bsmap -a $mate1 -d $ref -o $mapped -R -r 0 -p 4 $qual $threshold $lowqual $adapter $firstn $repeat_reads $seed_size $mismatch $equal_best $start $end $index_interval $mode  > $summary
-    fi
-else
-    if [ "$fullparam" == 'false' ]
-    then
-      bsmap -a $mate1 -b $mate2 -2 $unpaired -d $ref -o $mapped -R -r 0 -p 4  > $summary
-    else
-      bsmap -a $mate1 -b $mate2 -2 $unpaired -d $ref -o $mapped -R -r 0 -p 4 $qual $threshold $lowqual $adapter $firstn $repeat_reads $seed_size $mismatch $equal_best $start $end $index_interval $mode $maxinsert $mininsert   > $summary
-    fi
-fi
--- a/tool_data_table_conf.xml.sample	Fri Nov 30 05:10:53 2012 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,8 +0,0 @@
-<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc-->
-<tables>
-   <!-- Locations of FastA genomes for BSMAP -->
-     <table name="bsmap_fasta" comment_char="#">
-        <columns>value, dbkey, name, path</columns>
-        <file path="tool-data/bsmap_fasta.loc" />
-    </table>  
-</tables>