Mercurial > repos > fubar > rgrnastar_240d
changeset 0:624238a8440f draft default tip
Uploaded
author | fubar |
---|---|
date | Mon, 29 Sep 2014 20:50:45 -0400 (2014-09-30) |
parents | |
children | |
files | rg_rnaStar.xml tool-data/rnastar_indexes.loc.sample tool_data_table_conf.xml.sample tool_dependencies.xml |
diffstat | 4 files changed, 322 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/rg_rnaStar.xml Mon Sep 29 20:50:45 2014 -0400 @@ -0,0 +1,289 @@ +<tool id="rna_star" name="rnastar" version="2.4.0d"> + <description>Gapped-read mapper for RNA-seq data</description> + <requirements> + <requirement type="package" version="2.4.0d">rnastar</requirement> + <requirement type="package" version="0.1.19">samtools</requirement> + </requirements> + <command> + ## + ## Run STAR. + ## + + STAR + ## Can adjust this as appropriate for the system. + --genomeLoad NoSharedMemory + + --genomeDir ${refGenomeSource.index.fields.path} + --readFilesIn $input1 + #if $singlePaired.sPaired == "paired" + $singlePaired.input2 + #end if + --runThreadN 4 + #if $params.settingsType == "full": + --chimSegmentMin $params.chim_segment_min + --chimScoreMin $params.chim_score_min + #end if + + ## may or may not need to generate SAM tags and handle non-canonicals for Cufflinks tools. + ${outSAMstrandField} ${outFilterIntronMotifs} ${outSAMattributes} + + ; + + ## + ## BAM conversion. + ## + + ## Convert aligned reads. + samtools view -Shb Aligned.out.sam | samtools sort - Aligned.out + + ## Convert chimeric reads. + #if $params.settingsType == "full" and $params.chim_segment_min > 0: + ; samtools view -Shb Chimeric.out.sam | samtools sort - Chimeric.out + #end if + </command> + + <stdio> + <regex match=".*" source="both" level="warning" description="Some stderr/stdout text"/> + </stdio> + + <inputs> + <param name="jobName" type="text" size="120" value="rna-star run" label="Job narrative (added to output names)" + help="Only letters, numbers and underscores (_) will be retained in this field"> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value="_" /> </valid> + </sanitizer> + </param> + <!-- FASTQ input(s) and options specifically for paired-end data. --> + <conditional name="singlePaired"> + <param name="sPaired" type="select" label="Single ended or mate-pair ended reads in this library?"> + <option value="single" selected="true">Single-end</option> + <option value="paired">Paired-end</option> + </param> + <when value="single"> + <param format="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/> + </when> + <when value="paired"> + <param format="fastqsanger,fastq,fasta" name="input1" type="data" label="RNA-Seq FASTQ file, forward reads" + help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param format="fastqsanger,fastq,fasta" name="input2" type="data" label="RNA-Seq FASTQ file, reverse reads" + help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + </when> + </conditional> + + <!-- Genome source. --> + <conditional name="refGenomeSource"> + <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"> + <option value="indexed">Use a built-in index</option> + <option value="history">Use one from the history</option> + </param> + <when value="indexed"> + <param name="index" type="select" label="Select a reference genome"> + <options from_data_table="rnastar_indexes"> + <filter type="sort_by" column="2"/> + <validator type="no_options" message="No indexes are available for the selected input dataset"/> + </options> + </param> + </when> + <when value="history"> + <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /> + </when> + </conditional> + <param name="outSAMattributes" type="select" label="Include extra sam attributes for downstream processing"> + <option value="--outSAMattributes Standard">Standard - eg for old Samtools downstream</option> + <option value="--outSAMattributes All" selected="true">All modern Samtools attributes - see below</option> + </param> + <param name="outSAMstrandField" type="select" label="Include extra sam attributes for downstream processing"> + <option value="--outSAMstrandField intronMotif" selected="true">Add XS for cufflinks</option> + <option value="">No XS added to sam output</option> + </param> + <param name="outFilterIntronMotifs" type="select" label="Canonical junction preparation for unstranded data"> + <option value="">No special handling - all non-canonical junctions passed through</option> + <option value="--outFilterIntronMotifs RemoveNoncanonical" selected="true">Remove all non-canonical junctions for eg cufflinks</option> + <option value="--outFilterIntronMotifs RemoveNoncanonicalUnannotated">Remove only unannotated non-canonical junctions for eg cufflinks</option> + </param> + <!-- Parameter settings. --> + <conditional name="params"> + <param name="settingsType" type="select" label="Settings to use" help="You can use the default settings or set custom values for any STAR parameter."> + <option value="preSet" selected="true">Use Defaults</option> + <option value="full">Full parameter list</option> + </param> + <when value="preSet" /> + <!-- Full/advanced params. --> + <when value="full"> + <param name="chim_segment_min" type="integer" min="0" value="0" label="Minimum chimeric segment length" /> + <param name="chim_score_min" type="integer" min="0" value="0" label="Minimum total (summed) score of the chimeric segments" /> + + </when> + </conditional> + </inputs> + + <outputs> + <data format="txt" name="output_log" label="${on_string}_{jobName}.log" from_work_dir="Log.final.out"/> + <data format="interval" name="chimeric_junctions" label="${on_string}_{jobName}_starchimjunc.bed" from_work_dir="Chimeric.out.junction"> + <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="star_indexes" column="1" offset="0"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="refGenomeSource.index" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> + </data> + <data format="bam" name="chimeric_reads" label="${on_string}_${jobName}_starmappedchim.bam" + from_work_dir="Chimeric.out.bam"> + <filter>(params['settingsType'] == 'full' and params['chim_segment_min'] > 0)</filter> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="star_indexes" column="1" offset="0"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="refGenomeSource.index" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> + </data> + <data format="interval" name="splice_junctions" label="${on_string}_${jobName}_starsplicejunct.bed" + from_work_dir="SJ.out.tab"> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="star_indexes" column="1" offset="0"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="refGenomeSource.index" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> + </data> + <data format="bam" name="mapped_reads" label="${on_string}_${jobName}_starmapped.bam" + from_work_dir="Aligned.out.bam"> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="star_indexes" column="1" offset="0"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="refGenomeSource.index" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> + </data> + </outputs> +<help> + +**What it does** +Runs the rna star gapped aligner. Suited to paired or single end rna-seq. + +8.2: SAM alignments + +The number of loci Nmap a read maps to (multi-mapping) is given by NH:i: field. +The mapping quality MAPQ (column 5) is 255 for uniquely mapping reads, and int(-10*log10(1-1/Nmap)) for +multi-mapping reads. This scheme is same as the one used by Tophat and is compatible with Cufflinks. + +For multi-mappers, all alignments except one are marked with 0x100 (secondary alignment) in the FLAG +column 2. The un-marked alignment is either the best one (i.e. highest scoring), or is randomly selected from +the alignments of equal quality. + +8.2.1: Standard SAM attributes +With default --outSAMattributes Standard option the following SAM attributes will be generated: + +Column 12: NH: number of loci a read (pair) maps to +Column 13: IH: alignment index for all alignments of a read +Column 14: aS: alignment score +Column 15: nM: number of mismatches (does not include indels) + +8.2.2: Extra SAM attrbiutes +If --outSAMattributes All option is used, the following additional attributes will be output: + +Column 16: jM:B:c,M1,M2,... Intron motifs for all junctions (i.e. N in CIGAR): +0: non-canonical; 1:GT/AG, 2: CT/AC, 3: GC/AG, 4: CT/GC, 5: AT/AC, 6: GT/AT. + +If splice junctions database is used, and a junction is annotated, 20 is added to its motif value. +Column 17: jI:B:I,Start1,End1,Start2,End2,... Start and End of introns for all junctions (1-based) + +Note, that samtools 0.1.18 or later have to be used with these extra attributes. + + +8.2.3: XS SAM strand attribute for Cufflinks/Cuffdiff + +If you have un-stranded RNA-seq data, and wish to run Cufflinks/Cuffdiff on STAR alignments, you will +need to run STAR with --outSAMstrandField intronMotif option, which will generate the XS +strand attribute for all alignments that contain splice junctions. The spliced alignments that have undefined +strand (i.e. containing only non-canonical junctions) will be suppressed. + +If you have stranded RNA-seq data, you do not need to use any specific STAR options. Instead, you need +to run Cufflinks with the library option --library-type options. For example, cufflinks with +library-type fr-firststrand should be used for the “standard” dUTP protocol. +This option has to be used only for Cufflinks runs and not for STAR runs. + +It is recommended to remove the non-canonical junctions for Cufflinks runs using – + +--outFilterIntronMotifs RemoveNoncanonical +filter out alignments that contain non-canonical junctions + +OR + +--outFilterIntronMotifs RemoveNoncanonicalUnannotated +filter out alignments that contain non-canonical unannotated junctions +when using annotated splice junctions database. The annotated non- +canonical junctions will be kept. + + +**Attributions** + +Note that each component has its own license. Good luck with figuring out your obligations. + +rna_star - see the web site at rna_star_ + +For details, please see the rna_starMS_ +"STAR: ultrafast universal RNA-seq aligner" +A. Dobin et al, Bioinformatics 2012; doi: 10.1093/bioinformatics/bts635 + +Galaxy_ (that's what you are using right now!) for gluing everything together + +Most of the work for this wrapper XML is Jeremy Goecks' original STAR_ wrapper + +Minor tweaks to output names to suit our downstream purposes, toolshed automated dependencies +and odds and ends of other code and documentation comprising this tool was +written by Ross Lazarus and that part is licensed_ the same way as other rgenetics artefacts + +.. _STAR: https://bitbucket.org/jgoecks/jeremys-code/raw/fa1930a689b8e2f6b59cc1706e5ba0ed8ad357be/galaxy/tool-wrappers/star.xml +.. _licensed: http://creativecommons.org/licenses/by-nc-nd/3.0/ +.. _rna_star: http://code.google.com/p/rna-star/ +.. _rna_starMS: http://bioinformatics.oxfordjournals.org/content/29/1/15.full +.. _Galaxy: http://getgalaxy.org + +</help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/rnastar_indexes.loc.sample Mon Sep 29 20:50:45 2014 -0400 @@ -0,0 +1,11 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of rna-star indexed sequences data files. You will +#need to create these data files and then create a bowtie_indices.loc +#file similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The bowtie2_indices.loc +#file has this format (longer white space characters are TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <file_base_path> +# +#hg19 hg19 hg19 full /mnt/galaxyIndices/genomes/hg19/rnastar +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Mon Sep 29 20:50:45 2014 -0400 @@ -0,0 +1,7 @@ +<!-- 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> + <table name="rnastar_indexes" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/rnastar_indexes.loc" /> + </table> +</tables>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Mon Sep 29 20:50:45 2014 -0400 @@ -0,0 +1,15 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="rnastar" version="2.4.0d"> + <repository changeset_revision="2ab1b6182b63" name="package_rnastar_240d" owner="fubar" prior_installation_required="True" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + </package> + <package name="samtools" version="0.1.19"> + <repository changeset_revision="632f1a03db92" name="package_samtools_0_1_19" owner="iuc" prior_installation_required="True" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + </package> + + <readme> +Installs the STAR wrapper and dependency packages samtools and star - see https://code.google.com/p/rna-star/ +STAR is a very fast mapper for rna-seq giving junctions if the indexes are constructed with a junction library + </readme> + +</tool_dependency>