Previous changeset 9:385d004f3cb1 (2012-11-30) Next changeset 11:413c742682f7 (2012-11-30) |
Commit message:
Deleted selected files |
removed:
bsmap.xml bsmap_fasta.loc.sample bsmap_meth_caller.sh bsmap_meth_caller.xml bsmap_wrapper.sh tool_data_table_conf.xml.sample |
b |
diff -r 385d004f3cb1 -r 4f9b7eaecbd4 bsmap.xml --- a/bsmap.xml Fri Nov 30 05:10:53 2012 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
[ |
b'@@ -1,246 +0,0 @@\n-<tool id="bsmap" name="BSMAP Mapper">\n-\t<requirements>\n-\t <requirement type=\'package\'>\n-\t\tbsmap\n-\t </requirement>\n-\t</requirements>\n- <command interpreter="bash">\n- bsmap_wrapper.sh\n-\t\t\t##Reference genome\n-\t\t\t##ref="${reference.fields.path}"\n-\t\t\t#if $refGenomeSource.genomeSource == "history":\n-\t\t\t\tref="${refGenomeSource.myFile.extra_files_path}/${refGenomeSource.myFile.metadata.base_name}"\n-\t\t\t#else\n-\t\t\t\tref="${refGenomeSource.builtin.fields.path}"\n-\t\t\t#end if\n-\t\t\t##Output files (SAM output, BSMAP summary)\n-\t\t\tmapped=$mapped\n-\t\t\t##Temp directory\n-\t\t\ttempdir=$mapped.files_path\n-\t\t\tsummary=$summary\n-\t\t\t#if str($singlePaired.sPaired) == "single":\n-\t\t\t library="single"\n-\t\t\t mate1=$singlePaired.sInput1\n-\t\t\t #if str($singlePaired.sParams.sSettingsType) == "full":\n-\t\t\t fullparam=true\n-\t\t\t qual=$singlePaired.sParams.qual\n-\t\t\t threshold=$singlePaired.sParams.threshold\n-\t\t\t lowqual=$singlePaired.sParams.lowqual\n-\t\t\t adapter=$singlePaired.sParams.adapter\n-\t\t\t firstn=$singlePaired.sParams.firstn\n-\t\t\t repeat_reads=$singlePaired.sParams.repeat_reads\n-\t\t\t seed_size=$singlePaired.sParams.seed_size\n-\t\t\t mismatch=$singlePaired.sParams.mismatch\n-\t\t\t equal_best=$singlePaired.sParams.equal_best\n-\t\t\t start=$singlePaired.sParams.start\n-\t\t\t end=$singlePaired.sParams.end\n-\t\t\t index_interval=$singlePaired.sParams.index_interval\n-\t\t\t seed_random=$singlePaired.sParams.seed_random\n-\t\t\t rrbs=$singlePaired.sParams.rrbs\n-\t\t\t mode=$singlePaired.sParams.mode\n-\t\t\t align_info=$singlePaired.sParams.align_info \n-\t\t\t #end if\n-\t\t\t#else:\n-\t\t\t library="paired"\n-\t\t\t mate1=$singlePaired.pInput1\n-\t\t\t mate2=$singlePaired.pInput2\n-\t\t\t unpaired=$unpaired\n-\t\t\t #if str($singlePaired.pParams.pSettingsType) == "full": \n-\t\t\t fullparam=true\n-\t\t\t qual=$singlePaired.pParams.qual\n-\t\t\t threshold=$singlePaired.pParams.threshold\n-\t\t\t lowqual=$singlePaired.pParams.lowqual\n-\t\t\t adapter=$singlePaired.pParams.adapter\n-\t\t\t firstn=$singlePaired.pParams.firstn\n-\t\t\t repeat_reads=$singlePaired.pParams.repeat_reads\n-\t\t\t seed_size=$singlePaired.pParams.seed_size\n-\t\t\t mismatch=$singlePaired.pParams.mismatch\n-\t\t\t equal_best=$singlePaired.pParams.equal_best\n-\t\t\t start=$singlePaired.pParams.start\n-\t\t\t end=$singlePaired.pParams.end\n-\t\t\t index_interval=$singlePaired.pParams.index_interval\n-\t\t\t seed_random=$singlePaired.pParams.seed_random\n-\t\t\t rrbs=$singlePaired.pParams.rrbs\n-\t\t\t mode=$singlePaired.pParams.mode\n-\t\t\t align_info=$singlePaired.pParams.align_info \n-\t\t\t maxinsert=$singlePaired.pParams.maxinsert \n-\t\t\t mininsert=$singlePaired.pParams.mininsert \n-\t\t\t #end if\n-\t\t\t#end if\n- </command>\n- <inputs>\n-\n- <conditional name="refGenomeSource">\n- <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in reference?">\n- <option value="builtin">Use a built-in index</option>\n- <option value="history">Use one from the history</option>\n- </param>\n- <when value="builtin">\n- <param name="index" type="select" label="Select a reference genome">\n- <options from_data_table="bsmap_fasta">\n- <filter type="sort_by" column="2" />\n- <validator type="no_options" message="No reference genomes are available" />\n- </options>\n- </param>\n- </when>\n- <when value="history">\n- <param name="myFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" />\n- </when> \n- </conditional>\n- \n- <conditional name="singlePaired">\n- <param name="sPaired" type="select" label="Is this library mate-paired?">\n- <option value="single">Single-end</option>\n- <option value="paired">Paired-end</option>\n- </param>\n- <when value="single">\n- <param name="sInput1" type="data" format="fastq,fasta" label="FASTQ file" help="Must have ASCII enc'..b'ismatches allowed on a read" max="15" />\n-\t <param name="equal_best" type="integer" value="20" label="Maximum number of equal best hits to count" max="1000" />\n-\t <param name="start" type="integer" value="1" label="Start from the Nth read or read pair" />\n-\t <param name="end" type="integer" value="4294967295" label="End at the Nth read or read pair" />\n-\t <param name="index_interval" type="integer" value="4" label="Index interval" />\n-\t <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" />\n-\t <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)" />\n-\t <param name="mode" type="select" label="Set mapping strand information">\n-\t\t<option value="0">only map to 2 forward strands</option>\n-\t\t<option value="1">map SE or PE reads to all 4 strands</option>\n-\t </param>\n-\t <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." />\n-\n-\t \n- </when> <!-- full -->\n- </conditional> <!-- pParams -->\n- </when> <!-- paired -->\n- </conditional> <!-- singlePaired -->\n- \n- \n- </inputs>\n- <outputs>\n- <data name="mapped" format="sam" label="BSMAP Mapped Reads">\n-\t <actions>\n-\t\t<action type="metadata" name="dbkey">\n-\t\t <option type="from_data_table" name="bsmap_fasta" column="1" offset="0">\n-\t\t\t<filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>\n-\t\t\t<filter type="param_value" ref="reference" column="0"/>\n-\t\t </option>\n-\t\t</action>\n-\t </actions>\t \n-\t</data>\n-\t<data name="summary" format="txt" label="BSMAP Mapping Summary" />\n-\t<data name="unpaired" format ="sam" label="BSMAP Unpaired Hits">\n-\t <filter>(singlePaired[\'sPaired\'] == \'paired\')</filter>\n-\t</data>\n-\n- </outputs>\n- <help>\n-**What it does**\n-\n-BSMAP is a short reads mapping software for bisulfite sequencing reads. It has the following features:\n-\n- - read length up to 144 nt, allow up to 15 mismatches, gap size up to 3 bp.\n-\n- - support single end and pair end mapping. support multi-thread mapping.\n-\n- - support both "Lister protocol" (sequence 2 forward strands only) and "Cokus protocol" (sequence all 4 bisulfite converted strands)\n-\n- - reads are directly mapped to original reference genome sequence, no need to preprocess the reads and reference genome to convert C to T.\n-\n- - 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.\n-\n- - allow trimming adapter sequences and low quality nucleotides from the 3\'end of reads\n-\n- - 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.\n-\n- - allow alignment for other nucleotide transitions, for example, can be set to detect the A=>I(G) transition in RNA editing.\n-\n-.. _BSMAP: http://code.google.com/p/bsmap/\n-\n-**Input formats**\n-\n-BSMAP accepts files in FASTA/FASTQ format.\n-\n-**Outputs**\n-\n-The output contains the following files:\n-\n- - mapped reads in SAM format\n- \n- - mapping summary\n- \n- - unpaired hits (only for paired-end mapping)\n- \n- </help>\n- \n- <tests>\n- </tests>\n-</tool>\n-\n' |
b |
diff -r 385d004f3cb1 -r 4f9b7eaecbd4 bsmap_fasta.loc.sample --- a/bsmap_fasta.loc.sample Fri Nov 30 05:10:53 2012 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
@@ -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... -# |
b |
diff -r 385d004f3cb1 -r 4f9b7eaecbd4 bsmap_meth_caller.sh --- 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 $input \ No newline at end of file |
b |
diff -r 385d004f3cb1 -r 4f9b7eaecbd4 bsmap_meth_caller.xml --- a/bsmap_meth_caller.xml Fri Nov 30 05:10:53 2012 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
[ |
@@ -1,59 +0,0 @@ -<tool id="bsmap_meth_caller" name="BSMAP Methylation Caller"> - <requirements> - <requirement type='package'> - bsmap - </requirement> - </requirements> - <requirements> - <requirement type='package'> - samtools - </requirement> - </requirements> - <command interpreter="bash"> - bsmap_meth_caller.sh - input=$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> - |
b |
diff -r 385d004f3cb1 -r 4f9b7eaecbd4 bsmap_wrapper.sh --- 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 |
b |
diff -r 385d004f3cb1 -r 4f9b7eaecbd4 tool_data_table_conf.xml.sample --- 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 |
b |
@@ -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> |