Mercurial > repos > jjohnson > snpeff_cds_report

view snpEff_cds_report.xml @ 7:fbb6510186df default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
when codon has ambiguous nucleotide translate to X
author Jim Johnson <jj@umn.edu>
date Mon, 15 Sep 2014 06:13:47 -0500
parents 85b933b7d231
children
line wrap: on
line source

<tool id="SnpEff-cds-report" name="SnpEff Ensembl CDS" version="1.2">
  <description>Report Variant coding sequence changes for SnpEffects</description>
  <command interpreter="python">
   snpEff_cds_report.py --in $snp_effect_vcf 
   #if len($ensembl_host.__str__.strip) > 0:
     --ensembl_host ${ensembl_host}.archive.ensembl.org
   #end if
   #if len($ensembl_dataset.__str__.strip) > 0:
     --ensembl_dataset $ensembl_dataset
   #end if
   #if len($polya.__str__.strip) > 0:
     --polyA_limit $polya
   #end if
   #if $effects_filter
     --effects_filter=$effects_filter
   #end if
   $all_effects
   $with_ccds
   $snpeff_aa_change
   #if $report_format.__str__.find('html') >= 0:
     --html_report $html_report
     --html_dir $html_report.extra_files_path
   #end if
   #if $report_format.__str__.find('tsv') >= 0:
     --tsv_file $tsv_report
   #end if
   #if $report_format.__str__.find('detailed') >= 0:
     --out $text_report
   #end if
  </command>
  <inputs>
    <param name="snp_effect_vcf" type="data" format="vcf" label="SnpEffect VCF report" help="VCF output from SnpEffect or SnpSift"/>
    <param name="ensembl_host" type="text" value="" label="Biomart Server (defaults to www.biomart.org, for an archive server enter the archive date)" help="feb2012 - would access ensembl server: feb2012.archive.ensembl.org">
      <validator type="regex" message="format: mmmYYYY">^([jfmajsond][aepuco][nbrynlgptvc]20[0-9][0-9])?$</validator>
    </param>
    <param name="ensembl_dataset" type="select" label="Oragnism" help="">
      <option value="hsapiens_gene_ensembl" selected="true">Homo sapiens</option>
      <option value="mmusculus_gene_ensembl">Mus musculus</option>
      <option value="rnorvegicus_gene_ensembl">Rattus norvegicus</option>
      <option value="drerio_gene_ensembl">Danio rerio</option>
      <option value="ggallus_gene_ensembl">Gallus gallus</option>
      <option value="amelanoleuca_gene_ensembl">Ailuropoda melanoleuca</option>
      <option value="acarolinensis_gene_ensembl">Anolis carolinensis</option>
      <option value="btaurus_gene_ensembl">Bos taurus</option>
      <option value="celegans_gene_ensembl">Caenorhabditis elegans</option>
      <option value="cjacchus_gene_ensembl">Callithrix jacchus</option>
      <option value="cfamiliaris_gene_ensembl">Canis familiaris</option>                        
      <option value="cporcellus_gene_ensembl">Cavia porcellus</option>
      <option value="choffmanni_gene_ensembl">Choloepus hoffmanni</option>
      <option value="cintestinalis_gene_ensembl">Ciona intestinalis</option>
      <option value="csavignyi_gene_ensembl">Ciona savignyi</option>
      <option value="dnovemcinctus_gene_ensembl">Dasypus novemcinctus</option>
      <option value="dordii_gene_ensembl">Dipodomys ordii</option>
      <option value="dmelanogaster_gene_ensembl">Drosophila melanogaster</option>  
      <option value="etelfairi_gene_ensembl">Echinops telfairi</option>    
      <option value="ecaballus_gene_ensembl">Equus caballus</option>                       
      <option value="eeuropaeus_gene_ensembl">Erinaceus europaeus</option>
      <option value="fcatus_gene_ensembl">Felis catus</option>
      <option value="gmorhua_gene_ensembl">Gadus morhua</option>
      <option value="gaculeatus_gene_ensembl">Gasterosteus aculeatus</option>
      <option value="ggorilla_gene_ensembl">Gorilla gorilla</option>
      <option value="itridecemlineatus_gene_ensembl">Ictidomys tridecemlineatus</option> 
      <option value="lchalumnae_gene_ensembl">Latimeria chalumnae</option>                                
      <option value="lafricana_gene_ensembl">Loxodonta africana</option>
      <option value="mmulatta_gene_ensembl">Macaca mulatta</option>
      <option value="meugenii_gene_ensembl">Macropus eugenii</option>
      <option value="mgallopavo_gene_ensembl">Meleagris gallopavo</option>
      <option value="mmurinus_gene_ensembl">Microcebus murinus</option>
      <option value="mdomestica_gene_ensembl">Monodelphis domestica</option>
      <option value="mlucifugus_gene_ensembl">Myotis lucifugus</option>
      <option value="nleucogenys_gene_ensembl">Nomascus leucogenys</option>
      <option value="oprinceps_gene_ensembl">Ochotona princeps</option>
      <option value="oniloticus_gene_ensembl">Oreochromis niloticus</option>
      <option value="oanatinus_gene_ensembl">Ornithorhynchus anatinus</option> 
      <option value="ocuniculus_gene_ensembl">Oryctolagus cuniculus</option>
      <option value="olatipes_gene_ensembl">Oryzias latipes</option>
      <option value="ogarnettii_gene_ensembl">Otolemur garnettii</option>
      <option value="ptroglodytes_gene_ensembl">Pan troglodytes</option>
      <option value="psinensis_gene_ensembl">Pelodiscus sinensis</option>
      <option value="pmarinus_gene_ensembl">Petromyzon marinus</option>
      <option value="pabelii_gene_ensembl">Pongo abelii</option>
      <option value="pcapensis_gene_ensembl">Procavia capensis</option>
      <option value="pvampyrus_gene_ensembl">Pteropus vampyrus</option>
      <option value="scerevisiae_gene_ensembl">Saccharomyces cerevisiae</option>
      <option value="sharrisii_gene_ensembl">Sarcophilus harrisii</option>
      <option value="saraneus_gene_ensembl">Sorex araneus</option>
      <option value="sscrofa_gene_ensembl">Sus scrofa</option>
      <option value="tguttata_gene_ensembl">Taeniopygia guttata</option>
      <option value="trubripes_gene_ensembl">Takifugu rubripes</option>
      <option value="tsyrichta_gene_ensembl">Tarsius syrichta</option>
      <option value="tnigroviridis_gene_ensembl">Tetraodon nigroviridis</option>
      <option value="tbelangeri_gene_ensembl">Tupaia belangeri</option>
      <option value="ttruncatus_gene_ensembl">Tursiops truncatus</option>
      <option value="vpacos_gene_ensembl">Vicugna pacos</option>
      <option value="xtropicalis_gene_ensembl">Xenopus tropicalis</option>
    </param>
    <param name="effects_filter" type="select" optional="true" multiple="true" label="Filter SnpEffect" help="Report coding changes for selected effects">
      <!-- http://snpeff.sourceforge.net/faq.html#What_effects_are_predicted? -->
      <option value="FRAME_SHIFT">FRAME_SHIFT</option>
      <option value="NON_SYNONYMOUS_CODING">NON_SYNONYMOUS_CODING</option>
      <option value="SPLICE_SITE_ACCEPTOR">SPLICE_SITE_ACCEPTOR</option>
      <option value="SPLICE_SITE_DONOR">SPLICE_SITE_DONOR</option>
      <option value="START_LOST">START_LOST</option>
      <option value="EXON_DELETED">EXON_DELETED</option>
      <option value="STOP_GAINED">STOP_GAINED</option>
      <option value="STOP_LOST">STOP_LOST</option>
      <option value="RARE_AMINO_ACID">RARE_AMINO_ACID</option>
      <option value="CODON_CHANGE">CODON_CHANGE</option>
      <option value="CODON_INSERTION">CODON_INSERTION</option>
      <option value="CODON_CHANGE_PLUS_CODON_INSERTION">CODON_CHANGE_PLUS_CODON_INSERTION</option>
      <option value="CODON_DELETION">CODON_DELETION</option>
      <option value="CODON_CHANGE_PLUS_CODON_DELETION">CODON_CHANGE_PLUS_CODON_DELETION</option>
      <option value="UTR_5_DELETED">UTR_5_DELETED</option>
      <option value="UTR_3_DELETED">UTR_3_DELETED</option>
      <option value="SYNONYMOUS_START">SYNONYMOUS_START</option>
      <option value="NON_SYNONYMOUS_START">NON_SYNONYMOUS_START</option>
      <option value="START_GAINED">START_GAINED</option>
      <option value="SYNONYMOUS_CODING">SYNONYMOUS_CODING</option>
      <option value="SYNONYMOUS_STOP">SYNONYMOUS_STOP</option>
      <option value="UTR_5_PRIME">UTR_5_PRIME</option>
      <option value="UTR_3_PRIME">UTR_3_PRIME</option>
      <option value="REGULATION">REGULATION</option>
      <option value="UPSTREAM">UPSTREAM</option>
      <option value="DOWNSTREAM">DOWNSTREAM</option>
      <option value="GENE">GENE</option>
      <option value="TRANSCRIPT">TRANSCRIPT</option>
      <option value="EXON">EXON</option>
      <option value="INTRON_CONSERVED">INTRON_CONSERVED</option>
      <option value="INTRON">INTRON</option>
      <option value="INTRAGENIC">INTRAGENIC</option>
      <option value="INTERGENIC">INTERGENIC</option>
      <option value="INTERGENIC_CONSERVED">INTERGENIC_CONSERVED</option>
      <option value="NONE">NONE</option>
      <option value="CHROMOSOME">CHROMOSOME</option>
      <option value="CUSTOM">CUSTOM</option>
      <option value="CDS">CDS</option>
    </param>
    <param name="all_effects" type="boolean" truevalue="--all_effects" falsevalue="" checked="false" label="Report the variant coding for each Ensembl Transcript at the variant position" help="Default is to report only the first Transcript that has a cDNA change"/>
    <param name="with_ccds" type="boolean" truevalue="--with_ccds" falsevalue="" checked="false" label="Report the variant coding only for Ensembl Transcripts with a CCDS ID" help=""/>
    <param name="snpeff_aa_change" type="boolean" truevalue="--snpeff_aa_change" falsevalue="" checked="false" label="Report the Amino_Acid_change from SnpEff" help="Otherwise, report the first changed Animo Acid as: AposA (ref_AA pos_from_Nterminus alt_AA)"/>
    <param name="polya" type="integer" value="5" optional="true" label="Ignore variants that are part of a Poly-A of at least this length" help="Leave blank to turn off poly A filtering">
      <validator type="in_range" message="poly A between 2 and 100 bases" min="2" max="100"/>
    </param>
    <param name="report_format" type="select" force_select="true" multiple="true" display="checkboxes" label="Report formats" help="">
      <option value="html" selected="true">Detailed HTML report</option>
      <option value="tsv" selected="true">TAB-delimited report</option>
      <option value="detailed">Detailed Text report</option>
    </param>
  </inputs>
  <outputs>
    <data format="html" name="html_report" label="Variant Detection Report (html) on ${on_string}">
      <filter>'html' in report_format</filter>
    </data>
    <data format="tabular" name="tsv_report" label="Variant Detection Report (tsv) on ${on_string}">
      <filter>'tsv' in report_format</filter>
    </data>
    <data format="text" name="text_report" label="Variant Detection Report (text) on ${on_string}">
      <filter>'detailed' in report_format</filter>
    </data>
  </outputs>
  <tests>
    <test>
      <param name="snp_effect_vcf" ftype="vcf" value="snpeff.vcf"/>
      <param name="ensembl_host" value="feb2012"/>
      <param name="ensembl_dataset" value="hsapiens_gene_ensembl"/>
      <param name="effects_filter" value="FRAME_SHIFT"/>
      <param name="effects_filter" value="FRAME_SHIFT"/>
      <param name="all_effects" value="false"/>
      <param name="with_ccds" value="true"/>
      <param name="polya" value="5"/>
      <param name="report_format" value="tsv"/>
      <output name="tsv_report">
        <assert_contents>
            <has_text text="46871931" />
            <has_text text="109461327" />
            <not_has_text text="54291558" />
        </assert_contents>
      </output>
    </test>
  </tests>
 <help>
**SnpEff Variant Detection Ensembl Report**

Generates the variant sequence and its translation for the variations reported by SnpEffect_. 
The SnpEffect_ output must be in the VCF format, and must include Ensembl Transcript IDs. SnpSift_ can be used to filter the SnpEffect_ VCF output.

The sequences are retrieved from a biomart server using the xml query interface with the Ensembl Transcript ID as the query key.   

.. _SnpEffect: http://snpeff.sourceforge.net/
.. _SnpSift: http://snpeff.sourceforge.net/SnpSift.html

 </help>
</tool>