comparison tophat_wrapper.xml @ 1:af089ca8b4ee draft

planemo upload commit 33927a87ba2eee9bf0ecdd376a66241b17b3d734

0:51c6602b46b9

<tool id="tophat" name="Tophat for Illumina" version="1.5.0">
    <!-- Wrapper compatible with Tophat versions 1.3.0 to 1.4.1 -->
    <description>Find splice junctions using RNA-seq data</description>
    <version_command>tophat --version</version_command>
    <requirements>
        <requirement type="package" version="0.1.18">samtools</requirement>
        <requirement type="package" version="0.12.7">bowtie</requirement>

                    --max-segment-intron $singlePaired.sParams.max_segment_intron
                    --initial-read-mismatches=$singlePaired.sParams.initial_read_mismatches
                    --seg-mismatches=$singlePaired.sParams.seg_mismatches
                    --seg-length=$singlePaired.sParams.seg_length
                    --library-type=$singlePaired.sParams.library_type
                    
                    ## Indel search.
                    #if $singlePaired.sParams.indel_search.allow_indel_search == "Yes":
                        ## --allow-indels
                        --max-insertion-length $singlePaired.sParams.indel_search.max_insertion_length
                        --max-deletion-length $singlePaired.sParams.indel_search.max_deletion_length

                    --max-segment-intron $singlePaired.pParams.max_segment_intron
                    --initial-read-mismatches=$singlePaired.pParams.initial_read_mismatches
                    --seg-mismatches=$singlePaired.pParams.seg_mismatches
                    --seg-length=$singlePaired.pParams.seg_length
                    --library-type=$singlePaired.pParams.library_type
                    
                    ## Indel search.
                    #if $singlePaired.pParams.indel_search.allow_indel_search == "Yes":
                        ## --allow-indels
                        --max-insertion-length $singlePaired.pParams.indel_search.max_insertion_length
                        --max-deletion-length $singlePaired.pParams.indel_search.max_deletion_length

                  </param>
                  <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." />
                  <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" />
                  <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." />
                  <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="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." />
                  <conditional name="indel_search">
                      <param name="allow_indel_search" type="select" label="Allow indel search">
                          <option value="Yes">Yes</option>
                          <option value="No">No</option>
                      </param>
                      <when value="No"/>
                      <when value="Yes">
                         <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." />
                         <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." />
                      </when>
                  </conditional>
alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" />
                  <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" />
                  <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" />
                  <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" />
                  <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" />
                  <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" />
                  <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" />
                  
                  <!-- Options for supplying own junctions. -->
                  <conditional name="own_junctions">
                      <param name="use_junctions" type="select" label="Use Own Junctions">
                        <option value="No">No</option>
                        <option value="Yes">Yes</option>

                            <option value="Yes">Yes</option>
                          </param>
                      </when>
                      <when value="No" />
                  </conditional> <!-- /own_junctions -->
                  
                  <!-- Closure search. -->
                  <conditional name="closure_search">
                    <param name="use_search" type="select" label="Use Closure Search">
                      <option value="No">No</option>
                      <option value="Yes">Yes</option>

            <output name="junctions" file="tophat_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:
            bowtie-build -f test-data/tophat_in1.fasta tophat_in1
            tophat -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 +closure-search +min-closure-exon 50 +min-closure-intron 50 +max-closure-intro 5000 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger
            Replace the + with double-dash
            Rename the files in tmp_dir appropriately
            -->

            <output name="accepted_hits" file="tophat_out4h.bam" compare="sim_size" />
        </test>
    </tests>

    <help>
**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, and then analyzes the mapping results to identify splice junctions between exons. Please cite: Trapnell, C., Pachter, L. and Salzberg, S.L. TopHat: discovering splice junctions with RNA-Seq. Bioinformatics 25, 1105-1111 (2009).        

.. _Tophat: http://tophat.cbcb.umd.edu/
        
------

**Know what you are doing**

.. class:: warningmark

There is no such thing (yet) as an automated gearshift in splice junction identification. It is all like stick-shift driving in San Francisco. In other words, running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.

.. __: http://tophat.cbcb.umd.edu/manual.html

------

**Input formats**

Tophat accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.

------

**Outputs**

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**

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**

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-closure-search               Disables the mate pair closure-based search for junctions. Currently, has no effect - closure search is off by default.

  --min-coverage-intron             The minimum intron length that may be found during coverage search. The default is 50.
  --max-coverage-intron             The maximum intron length that may be found during coverage search. The default is 20000.
  --min-segment-intron              The minimum intron length that may be found during split-segment search. The default is 50.
  --max-segment-intron              The maximum intron length that may be found during split-segment search. The default is 500000.
    </help>
</tool>

1:af089ca8b4ee

<tool id="tophat" name="TopHat for Illumina" version="1.5.0">
    <!-- Wrapper compatible with TopHat versions 1.3.0 to 1.4.1 -->
    <description>Find splice junctions using RNA-seq data</description>
    <version_command>tophat --version</version_command>
    <requirements>
        <requirement type="package" version="0.1.18">samtools</requirement>
        <requirement type="package" version="0.12.7">bowtie</requirement>

                    --max-segment-intron $singlePaired.sParams.max_segment_intron
                    --initial-read-mismatches=$singlePaired.sParams.initial_read_mismatches
                    --seg-mismatches=$singlePaired.sParams.seg_mismatches
                    --seg-length=$singlePaired.sParams.seg_length
                    --library-type=$singlePaired.sParams.library_type

                    ## Indel search.
                    #if $singlePaired.sParams.indel_search.allow_indel_search == "Yes":
                        ## --allow-indels
                        --max-insertion-length $singlePaired.sParams.indel_search.max_insertion_length
                        --max-deletion-length $singlePaired.sParams.indel_search.max_deletion_length

                    --max-segment-intron $singlePaired.pParams.max_segment_intron
                    --initial-read-mismatches=$singlePaired.pParams.initial_read_mismatches
                    --seg-mismatches=$singlePaired.pParams.seg_mismatches
                    --seg-length=$singlePaired.pParams.seg_length
                    --library-type=$singlePaired.pParams.library_type

                    ## Indel search.
                    #if $singlePaired.pParams.indel_search.allow_indel_search == "Yes":
                        ## --allow-indels
                        --max-insertion-length $singlePaired.pParams.indel_search.max_insertion_length
                        --max-deletion-length $singlePaired.pParams.indel_search.max_deletion_length

                  </param>
                  <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." />
                  <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" />
                  <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." />
                  <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="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." />
                  <expand macro="indel_searchConditional" />
                  <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" />
                  <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" />
                  <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" />
                  <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" />
                  <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" />
                  <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" />

                  <!-- Options for supplying own junctions. -->
                  <conditional name="own_junctions">
                      <param name="use_junctions" type="select" label="Use Own Junctions">
                        <option value="No">No</option>
                        <option value="Yes">Yes</option>

                            <option value="Yes">Yes</option>
                          </param>
                      </when>
                      <when value="No" />
                  </conditional> <!-- /own_junctions -->

                  <!-- Closure search. -->
                  <conditional name="closure_search">
                    <param name="use_search" type="select" label="Use Closure Search">
                      <option value="No">No</option>
                      <option value="Yes">Yes</option>

            <output name="junctions" file="tophat_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:
            bowtie-build -f test-data/tophat_in1.fasta tophat_in1
            tophat -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 +closure-search +min-closure-exon 50 +min-closure-intron 50 +max-closure-intro 5000 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger
            Replace the + with double-dash
            Rename the files in tmp_dir appropriately
            -->

            <output name="accepted_hits" file="tophat_out4h.bam" compare="sim_size" />
        </test>
    </tests>

    <help>
**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, and then analyzes the mapping results to identify splice junctions between exons.

.. _TopHat: http://ccb.jhu.edu/software/tophat/

------

**Know what you are doing**

.. class:: warningmark

There is no such thing (yet) as an automated gearshift in splice junction identification. It is all like stick-shift driving in San Francisco. In other words, running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.

.. __: http://ccb.jhu.edu/software/tophat/manual.shtml

------

**Input formats**

TopHat accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.

------

**Outputs**

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**

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**

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-closure-search               Disables the mate pair closure-based search for junctions. Currently, has no effect - closure search is off by default.

  --min-coverage-intron             The minimum intron length that may be found during coverage search. The default is 50.
  --max-coverage-intron             The maximum intron length that may be found during coverage search. The default is 20000.
  --min-segment-intron              The minimum intron length that may be found during split-segment search. The default is 50.
  --max-segment-intron              The maximum intron length that may be found during split-segment search. The default is 500000.
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btp120</citation>
    </citations>
</tool>