Mercurial > repos > devteam > tophat
changeset 1:af089ca8b4ee draft
planemo upload commit 33927a87ba2eee9bf0ecdd376a66241b17b3d734
| author | devteam |
|---|---|
| date | Tue, 13 Oct 2015 12:33:25 -0400 |
| parents | 51c6602b46b9 |
| children | cc37e3dcc680 |
| files | tool_dependencies.xml tophat_wrapper.xml |
| diffstat | 2 files changed, 30 insertions(+), 38 deletions(-) [+] |
line wrap: on
line diff
--- a/tool_dependencies.xml Thu Jan 23 12:30:49 2014 -0500 +++ b/tool_dependencies.xml Tue Oct 13 12:33:25 2015 -0400 @@ -1,12 +1,12 @@ <?xml version="1.0"?> <tool_dependency> <package name="bowtie" version="0.12.7"> - <repository changeset_revision="f54826948b0b" name="package_bowtie_0_12_7" owner="devteam" prior_installation_required="False" toolshed="http://testtoolshed.g2.bx.psu.edu" /> + <repository changeset_revision="f0faa5eea2eb" name="package_bowtie_0_12_7" owner="devteam" toolshed="https://testtoolshed.g2.bx.psu.edu" /> </package> <package name="samtools" version="0.1.18"> - <repository changeset_revision="c0f72bdba484" name="package_samtools_0_1_18" owner="devteam" prior_installation_required="False" toolshed="http://testtoolshed.g2.bx.psu.edu" /> + <repository changeset_revision="c0f72bdba484" name="package_samtools_0_1_18" owner="devteam" toolshed="https://testtoolshed.g2.bx.psu.edu" /> </package> <package name="tophat" version="1.4.0"> - <repository changeset_revision="765982facf05" name="package_tophat_1_4_0" owner="devteam" prior_installation_required="False" toolshed="http://testtoolshed.g2.bx.psu.edu" /> + <repository changeset_revision="765982facf05" name="package_tophat_1_4_0" owner="devteam" toolshed="https://testtoolshed.g2.bx.psu.edu" /> </package> </tool_dependency>
--- a/tophat_wrapper.xml Thu Jan 23 12:30:49 2014 -0500 +++ b/tophat_wrapper.xml Tue Oct 13 12:33:25 2015 -0400 @@ -1,5 +1,5 @@ -<tool id="tophat" name="Tophat for Illumina" version="1.5.0"> - <!-- Wrapper compatible with Tophat versions 1.3.0 to 1.4.1 --> +<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> @@ -43,7 +43,7 @@ --seg-mismatches=$singlePaired.sParams.seg_mismatches --seg-length=$singlePaired.sParams.seg_length --library-type=$singlePaired.sParams.library_type - + ## Indel search. #if $singlePaired.sParams.indel_search.allow_indel_search == "Yes": ## --allow-indels @@ -104,7 +104,7 @@ --seg-mismatches=$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 @@ -181,25 +181,14 @@ <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)" /> + <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"> @@ -234,7 +223,7 @@ </when> <when value="No" /> </conditional> <!-- /own_junctions --> - + <!-- Closure search. --> <conditional name="closure_search"> <param name="use_search" type="select" label="Use Closure Search"> @@ -402,7 +391,7 @@ </test> <!-- Test base-space single-end reads with user-supplied reference fasta and full parameters --> <test> - <!-- Tophat commands: + <!-- 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 @@ -481,12 +470,12 @@ </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, 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_ 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://tophat.cbcb.umd.edu/ - +.. _TopHat: http://ccb.jhu.edu/software/tophat/ + ------ **Know what you are doing** @@ -495,19 +484,19 @@ 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 +.. __: 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. +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. @@ -519,27 +508,27 @@ ------- -**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 + -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 + -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 + -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. @@ -560,4 +549,7 @@ --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>