tophat2: tophat2_wrapper.xml comparison

comparison tophat2_wrapper.xml @ 7:4eb3c3beb9c7 draft

planemo upload commit 4ec9eb1570ea116d83f5464a786af6e14fb5b57d

author	devteam
date	Fri, 09 Oct 2015 15:48:52 -0400
parents	5c5517d2a9e9
children	758594ed0364

comparison

equal deleted inserted replaced

-:6202ec8aab61
+:4eb3c3beb9c7
-<tool id="tophat2" name="Tophat" version="0.9">
+<tool id="tophat2" name="TopHat" version="0.9">
 <!-- Wrapper compatible with Tophat version 2.0.0+ -->
 <description>Gapped-read mapper for RNA-seq data</description>
 <version_command>tophat2 --version</version_command>
 <requirements>
 <requirement type="package" version="2.2.5">bowtie2</requirement>
 ##
 ## Run tophat.
 ##
 tophat2
 ## Change this to accommodate the number of threads you have available.
 --num-threads \${GALAXY_SLOTS:-4}
 ## Set params.
 #if $params.settingsType == "full":
 --read-mismatches $params.read_mismatches
 #if str($params.bowtie_n) == "Yes":
 --bowtie-n
 #end if
 --read-edit-dist $params.read_edit_dist
 --read-realign-edit-dist $params.read_realign_edit_dist
 -a $params.anchor_length
 -m $params.splice_mismatches
 -i $params.min_intron_length
 --min-segment-intron $params.min_segment_intron
 --max-segment-intron $params.max_segment_intron
 --segment-mismatches $params.seg_mismatches
 --segment-length $params.seg_length
 --library-type $params.library_type
 ## Indel search.
 #if $params.indel_search.allow_indel_search == "Yes":
 ## --allow-indels
 --max-insertion-length $params.indel_search.max_insertion_length
 --max-deletion-length $params.indel_search.max_deletion_length
 --min-coverage-intron $params.coverage_search.min_coverage_intron
 --max-coverage-intron $params.coverage_search.max_coverage_intron
 #else:
 --no-coverage-search
 #end if
 #if str($params.microexon_search) == "Yes":
 --microexon-search
 #end if
 #if $params.fusion_search.do_search == "Yes":
 --fusion-search
 --fusion-anchor-length $params.fusion_search.anchor_len
 --fusion-min-dist $params.fusion_search.min_dist
 --fusion-read-mismatches $params.fusion_search.read_mismatches
 --fusion-multireads $params.fusion_search.multireads
 --fusion-multipairs $params.fusion_search.multipairs
 --fusion-ignore-chromosomes "$params.fusion_search.ignore_chromosomes"
 #end if
 #if $params.bowtie2_settings.b2_settings == "Yes":
 #if $params.bowtie2_settings.preset.b2_preset == "Yes":
 --b2-$params.bowtie2_settings.preset.b2_preset_select
 #end if
 #end if
 #end if
 ## Read group information.
 #if $readGroup.specReadGroup == "yes"
 --rg-id "$readGroup.rgid"
 ## Set index path, inputs and parameters specific to paired data.
 #if $singlePaired.sPaired != "single"
 -r $singlePaired.mate_inner_distance
 --mate-std-dev=$singlePaired.mate_std_dev
 #if str($singlePaired.report_discordant_pairs) == "No":
 --no-discordant
 #end if
 #if $singlePaired.sPaired == "paired"
 #end if
 #else
 ${index_path} "$singlePaired.input1"
 #end if
 </command>
 <inputs>
 <conditional name="singlePaired">
 <param name="sPaired" type="select" label="Is this single-end or paired-end data?">
 <option value="single">Single-end</option>
 <option value="paired">Paired-end (as individual datasets)</option>
 <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" help="--min-coverage-intron; The minimum intron length that may be found during coverage search. The default is 50."/>
 <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" help="--max-coverage-intron; The maximum intron length that may be found during coverage search. The default is 20000."/>
 </when>
 <when value="No" />
 </conditional>
 <!-- Microexon search params -->
 <param name="microexon_search" type="select" label="Use Microexon Search" help="--microexon-search; With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.">
 <option value="No">No</option>
 <option value="Yes">Yes</option>
 </param>
 <!-- Fusion mapping. -->
 <conditional name="fusion_search">
 <param name="do_search" type="select" label="Do Fusion Search" help="Reads can be aligned to potential fusion transcripts if the --fusion-search option is specified. The fusion alignments are reported in SAM format using custom fields XF and XP (see the output format) and some additional information about fusions will be reported (see fusions.out). Once mapping is done, you can run tophat-fusion-post to filter out fusion transcripts (see the TopHat-Fusion website for more details).">
 <option selected="true" value="No">No</option>
 <option value="Yes">Yes</option>
 <param name="multireads" type="integer" value="2" label="Multireads" help="--fusion-multireads; Reads that map to more than this many places will be ignored. It may be possible that a fusion is supported by reads (or pairs) that map to multiple places. The default is 2."/>
 <param name="multipairs" type="integer" value="2" label="Multipairs" help="--fusion-multipairs; Pairs that map to more than this many places will be ignored. The default is 2."/>
 <param name="ignore_chromosomes" type="text" value='' label="--fusion-ignore-chromosomes; Ignore some chromosomes such as chrM when detecting fusion break points"/>
 </when>
 </conditional>
 <!-- Bowtie2 settings. -->
 <conditional name="bowtie2_settings">
 <param name="b2_settings" type="select" label="Set Bowtie2 settings">
 <option selected="true" value="No">No</option>
 <option value="Yes">Yes</option>
 <param name="specReadGroup" type="select" label="Specify read group?">
 <option value="yes">Yes</option>
 <option value="no" selected="True">No</option>
 </param>
 <when value="yes">
-<param name="rgid" type="text" size="25" label="Read group identiﬁer (ID). Each @RG line must have a unique ID. The value of ID is used in the RG tags of alignment records. Must be unique among all read groups in header section." help="Required if RG specified. Read group IDs may be modiﬁed when merging SAM ﬁles in order to handle collisions." />
+<param name="rgid" type="text" label="Read group identiﬁer (ID). Each @RG line must have a unique ID. The value of ID is used in the RG tags of alignment records. Must be unique among all read groups in header section." help="Required if RG specified. Read group IDs may be modiﬁed when merging SAM ﬁles in order to handle collisions." />
-<param name="rglb" type="text" size="25" label="Library name (LB)" help="Required if RG specified" />
+<param name="rglb" type="text" label="Library name (LB)" help="Required if RG specified" />
-<param name="rgpl" type="text" size="25" label="Platform/technology used to produce the reads (PL)" help="Required if RG specified. Valid values : CAPILLARY, LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO" />
+<param name="rgpl" type="text" label="Platform/technology used to produce the reads (PL)" help="Required if RG specified. Valid values : CAPILLARY, LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO" />
-<param name="rgsm" type="text" size="25" label="Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" />
+<param name="rgsm" type="text" label="Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" />
 </when>
 <when value="no" />
 </conditional> <!-- readGroup -->
 </inputs>
 <output name="junctions" file="tophat2_out2j.bed" />
 <output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" />
 </test>
 <!-- Test base-space single-end reads with user-supplied reference fasta and full parameters -->
 <test>
-<!-- Tophat commands:
+<!-- TopHat commands:
 bowtie2-build -f test-data/tophat_in1.fasta tophat_in1
 tophat2 -o tmp_dir -p 1 -a 8 -m 0 -i 70 -I 500000 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger
 Replace the + with double-dash
 Rename the files in tmp_dir appropriately
 -->
 <!-- TopHat commands:
 tophat2 -o tmp_dir -r 20 -p 1 -a 8 -m 0 -i 70 -I 500000 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search +report_discordant_pairs tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger
 Replace the + with double-dash
 Rename the files in tmp_dir appropriately
 -->
 <conditional name="singlePaired">
 <param name="sPaired" value="paired"/>
 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/>
 <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/>
 <param name="mate_inner_distance" value="20"/>
 <param name="report_discordant_pairs" value="Yes" />
 <conditional name="bowtie2_settings">
 <param name="b2_settings" value="No" />
 </conditional>
 <!-- Fusion search params -->
 <conditional name="fusion_search">
 <param name="do_search" value="Yes" />
 <param name="anchor_len" value="21" />
 <param name="min_dist" value="10000021" />
 <param name="read_mismatches" value="3" />
 <param name="multireads" value="4" />
 <param name="multipairs" value="5" />
 <output name="junctions" file="tophat2_out4j.bed" />
 <output name="accepted_hits" file="tophat_out4h.bam" compare="sim_size" />
 </test>
 </tests>
 <help>
-**Tophat Overview**
+**TopHat Overview**
-TopHat_ is a fast splice junction mapper for RNA-Seq reads. It aligns RNA-Seq reads to mammalian-sized genomes using the ultra high-throughput short read aligner Bowtie(2), and then analyzes the mapping results to identify splice junctions between exons. Please cite: Kim D, Pertea G, Trapnell C, Pimentel H, Kelley R, and Salzberg SL. TopHat2: accurate alignment
+TopHat_ is a fast splice junction mapper for RNA-Seq reads. It aligns RNA-Seq reads to mammalian-sized genomes using the ultra high-throughput short read aligner Bowtie(2), and then analyzes the mapping results to identify splice junctions between exons.
-of transcriptomes in the presence of insertions, deletions and gene fusions. Genome Biol 14:R36, 2013.
+.. _TopHat: http://ccb.jhu.edu/software/tophat/
-.. _Tophat: http://ccb.jhu.edu/software/tophat/
 ------
 **Know what you are doing**
 .. class:: warningmark
 ------
 **Input formats**
-Tophat accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.
+TopHat accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.
 ------
 **Outputs**
-Tophat produces two output files:
+TopHat produces two output files:
 - junctions -- A UCSC BED_ track of junctions reported by TopHat. Each junction consists of two connected BED blocks, where each block is as long as the maximal overhang of any read spanning the junction. The score is the number of alignments spanning the junction.
 - accepted_hits -- A list of read alignments in BAM_ format.
 .. _BED: http://genome.ucsc.edu/FAQ/FAQformat.html#format1
 Two other possible outputs, depending on the options you choose, are insertions and deletions, both of which are in BED format.
 -------
-**Tophat settings**
+**TopHat settings**
-All of the options have a default value. You can change any of them. Some of the options in Tophat have been implemented here.
+All of the options have a default value. You can change any of them. Some of the options in TopHat have been implemented here.
 ------
-**Tophat parameter list**
+**TopHat parameter list**
-This is a list of implemented Tophat options::
+This is a list of implemented TopHat options::
 -r                                This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments
 selected at 300bp, where each end is 50bp, you should set -r to be 200. There is no default, and this parameter
 is required for paired end runs.
 --mate-std-dev INT                The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp.
 -a/--min-anchor-length INT        The "anchor length". TopHat will report junctions spanned by reads with at least this many bases on each side of the junction. Note that individual spliced
 alignments may span a junction with fewer than this many bases on one side. However, every junction involved in spliced alignments is supported by at least one
 read with this many bases on each side. This must be at least 3 and the default is 8.
 -m/--splice-mismatches INT        The maximum number of mismatches that may appear in the "anchor" region of a spliced alignment. The default is 0.
 -i/--min-intron-length INT        The minimum intron length. TopHat will ignore donor/acceptor pairs closer than this many bases apart. The default is 70.
 -I/--max-intron-length INT        The maximum intron length. When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read. The default is 500000.
 -g/--max-multihits INT            Instructs TopHat to allow up to this many alignments to the reference for a given read, and suppresses all alignments for reads with more than this many
 alignments. The default is 40.
 -G/--GTF [GTF 2.2 file]           Supply TopHat with a list of gene model annotations. TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping.
 -j/--raw-juncs [juncs file]       Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-], left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive.
 -no-novel-juncs                   Only look for junctions indicated in the supplied GFF file. (ignored without -G)
 --no-coverage-search              Disables the coverage based search for junctions.

Mercurial > repos > devteam > tophat2

comparison tophat2_wrapper.xml @ 7:4eb3c3beb9c7 draft