Mercurial > repos > yhoogstrate > fuma
changeset 3:f06461883f7b draft
updated to version 2.7.1 and extended wrapper with additional output type and a help section
author | yhoogstrate |
---|---|
date | Thu, 02 Apr 2015 08:06:04 -0400 |
parents | 76293f7745ff |
children | c9b1bbe7bdac |
files | fuma.xml tool_dependencies.xml |
diffstat | 2 files changed, 80 insertions(+), 15 deletions(-) [+] |
line wrap: on
line diff
--- a/fuma.xml Sun Mar 29 05:28:17 2015 -0400 +++ b/fuma.xml Thu Apr 02 08:06:04 2015 -0400 @@ -1,9 +1,9 @@ <?xml version="1.0" encoding="UTF-8"?> -<tool id="fuma" name="FuMa" version="2.6.6.b"> +<tool id="fuma" name="FuMa" version="2.7.1.a"> <description>FuMa (FusionMatcher) matches detected fusion genes based on gene name subset matching (designed in particular for RNA-Seq).</description> <requirements> - <requirement type="package" version="2.6.6">fuma</requirement> + <requirement type="package" version="2.7.1">fuma</requirement> </requirements> <version_command>fuma --version</version_command><!-- -V also works, but is not GNU standard --> @@ -36,8 +36,19 @@ $samples_str -l $links_str + #if $output_format == "list_boolean" + -f list + #else -f $output_format - -o $fuma_overview + #end if + -o $fuma_overview ; + + + + #if $output_format == "list_boolean" + fuma-list-to-boolean-list -o tmp.txt $fuma_overview && + mv tmp.txt $fuma_overview + #end if </command> <inputs> @@ -46,21 +57,22 @@ <param name="format" type="select" label="Format of dataset"> <option value="chimerascan">ChimeraScan</option> <option value="defuse">DeFuse</option> - <option value="completegenomics">Complete Genomics</option> - <option value="tophatfusionpostpotentialfusion">Tophat Fusion Post (potential fusion file)</option> - <option value="tophatfusionpostresult">Tophat Fusion Post (result file)</option> - <option value="tophatfusionpre">Tophat Fusion Pre (final list file)</option> - <option value="fusioncatcherfinal">FusionCatcher (final-list file)</option> + <option value="complete-genomics">Complete Genomics</option> + <option value="fusion-catcher_final">Fusion Catcher (final-list file)</option> <option value="fusionmap">FusionMap</option> - <option value="rnastarchimeric">STAR (chimeric file)</option> - <option value="oncofuse">Oncofuse</option> - <option value="trinitygmap">GMAP (As step after Trinity)</option> + <option value="trinity-gmap">GMAP (As step after Trinity)</option> + <option value="oncofuse">OncoFuse</option> + <option value="rna-star_chimeric">STAR (chimeric file)</option> + <option value="tophat-fusion_pre">Tophat Fusion Pre (fusions.out)</option> + <option value="tophat-fusion_post_potential_fusion">Tophat Fusion Post (potential_fusion.txt)</option> + <option value="tophat-fusion_post_result">Tophat Fusion Post (result.txt)</option> </param> <param name="gene_annotation" type="data" format="bed" label="Corresponding gene-name annotation file (BED format)" help="Make use of persistent gene annotations! Gene annotations should only be different if different reference genome builds were used." /> </repeat> <param name="output_format" type="select" label="Output format"> - <option value="list" selected="true">List</option> + <option value="list_boolean" selected="true">List (Boolean)</option> + <option value="list">List</option> <option value="summary">Count summary</option> </param> </inputs> @@ -98,6 +110,59 @@ </test> </tests> - <help> + <help>============ +Introduction +============ + +FuMa (Fusion Matcher) matches predicted fusion events (both genomic and transcriptomic) according to chromosomal location or assocatiated gene annotation(s) where the latter should be genome build inspecific. + +Because RNA-Sequencing deals with samples that may have undergrond splicing, reads may split up because of biological processes. If a fusion event takes place, the same thing may happen. Therefore we hypothesize that using spanning read distances may be unreliable, because there are known introns of > 100kb. Therefore, FuMa translates the breakpoint to gene names, and only overlaps breakpoints with the same genename(s). + +===== +Usage +===== + +After you have uploaded the results of your Fusion Gene detection experiment, and selected the format to be *tabular*, you can start the FuMa wrapper. For each dataset you simply have to add another repeat. Then you have to select a corresponding format: + +******* +Formats +******* + ++-------------------+-----------------------+-------------------------------------+ +|Tools | File | Format string | ++===================+=======================+=====================================+ +|ChimeraScan | chimeras.bedpe | chimerascan | ++-------------------+-----------------------+-------------------------------------+ +|Complete Genomics | highConfidenceJu*.tsv | complete-genomics | ++-------------------+-----------------------+-------------------------------------+ +|Complete Genomics | allJunctionsBeta*.tsv | complete-genomics | ++-------------------+-----------------------+-------------------------------------+ +|DeFuse | results.txt | defuse | ++-------------------+-----------------------+-------------------------------------+ +|DeFuse | results.classify.txt | defuse | ++-------------------+-----------------------+-------------------------------------+ +|DeFuse | results.filtered.txt | defuse | ++-------------------+-----------------------+-------------------------------------+ +|Fusion Catcher | final-list_cand*.txt | fusion-catcher_final | ++-------------------+-----------------------+-------------------------------------+ +|FusionMap | | fusionmap | ++-------------------+-----------------------+-------------------------------------+ +|Trinity + GMAP | | trinity-gmap | ++-------------------+-----------------------+-------------------------------------+ +|OncoFuse | | oncofuse | ++-------------------+-----------------------+-------------------------------------+ +|RNA STAR | Chimeric.out.junction | rna-star_chimeric | ++-------------------+-----------------------+-------------------------------------+ +|TopHat Fusion pre | fusions.out | tophat-fusion_pre | ++-------------------+-----------------------+-------------------------------------+ +|TopHat Fusion post | potential_fusion.txt | tophat-fusion_post_potential_fusion | ++-------------------+-----------------------+-------------------------------------+ +|TopHat Fusion post | result.txt | tophat-fusion_post_result | ++-------------------+-----------------------+-------------------------------------+ + +To annotate genes upon the breakpoints you must provide a BED file that contains gene annotations for the user genome build. Make sure **your BED file contains one gene per line**. You should use BED files that contain one exon per line only if you want restrict your analysis to fusion genes detected within exons. + +UCSC genome browser provides a very simple way of obtaining BED files with one gene per line by selecting their *RefSeq Genes*-track and *knownGene*-table and putting the export format to BED. Galaxy should have a built-in UCSC table browser. + </help> </tool>
--- a/tool_dependencies.xml Sun Mar 29 05:28:17 2015 -0400 +++ b/tool_dependencies.xml Thu Apr 02 08:06:04 2015 -0400 @@ -1,6 +1,6 @@ <?xml version="1.0"?> <tool_dependency> - <package name="fuma" version="2.6.6"> + <package name="fuma" version="2.7.1"> <install version="1.0"> <actions> <action type="make_directory">$INSTALL_DIR/lib/python</action> @@ -9,7 +9,7 @@ <action type="shell_command"> git clone https://github.com/yhoogstrate/fuma.git fuma && cd fuma && - git reset --hard 433d68af9a1b113bd0ae09c2b80279c589ac2d5a && + git reset --hard 3d9a0532209d4ad10283cac324788b4fecfd2675 && export PYTHONPATH=$PYTHONPATH:$INSTALL_DIR/lib/python:$INSTALL_DIR/lib64/python && python setup.py build &&