view nastiseq.xml @ 0:0a0bba8e1823 draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/rna_tools/nastiseq commit 8b472e8680bb0ae5d11ee48b642ab305f9333a48

<tool id="nastiseq" name="NASTIseq" version="1.0">
  <description>Identify cis-NATs using ssRNA-seq</description>

  <requirements>
    <requirement type="package" version="1.0">r-nastiseq</requirement>
  </requirements>
  <stdio>
        <regex match="Execution halted"
           source="both"
           level="fatal"
           description="Execution halted." />
        <regex match="Error in"
           source="both"
           level="fatal"
           description="An undefined error occured, please check your intput carefully and contact your administrator." />
  </stdio>
  <command>
<![CDATA[
      Rscript '$script_file'
]]>
  </command>
  <configfiles>
    <configfile name="script_file">
          library(NASTIseq)

          genepos = read.delim("${annotation}", header=FALSE, comment.char="#")
          colnames(genepos) = c("seqname", "source", "feature", "start", "end", "score", "strand", "frame", "attributes")
          genepos = subset(genepos, feature=="gene")

          get_id = function(attri){
              gene_info = strsplit(attri, ";")[[1]][1]
              gene_id = strsplit(gene_info, " ")[[1]][2]
              gene_id = gsub('\"', '', gene_id)
              return(gene_id)
           }

          genepos\$attributes = as.character(lapply(as.character(genepos\$attributes), get_id))

          pospairs = read.table("${positive_pair}", sep = "\t", as.is = TRUE)

          smat = as.matrix(read.table("${count_smt}",  sep = "\t",  row.names = 1))

          asmat = as.matrix(read.table("${count_asmt}",  sep = "\t",  row.names = 1))

          WRscore = getNASTIscore(smat, asmat)

          negpairs = getnegativepairs(genepos)

          WRpred = NASTIpredict(smat,asmat, pospairs, negpairs)

          WRpred_rocr = prediction(WRpred\$predictions,WRpred\$labels)

          thr = defineFDR(WRpred_rocr,0.05)

          WR_names = FindNATs(WRscore, thr, pospairs, genepos)

          write.table(WR_names\$newpairs, file = "output_newpairs.tsv", row.names = FALSE, col.names = FALSE, sep = "\t", quote = FALSE)

          write.table(WR_names\$neworphan, file = "output_neworphan.tsv", row.names = FALSE, col.names = FALSE, sep = "\t", quote = FALSE)

    </configfile>
  </configfiles>
  <inputs>
    <param name="annotation" type="data" format="gtf" label="Annotation file"
        help="The gene ids should be in agreement in the files of annotation, known pairs and read count.">
    </param>
    <param name="positive_pair" type="data" format="tabular" label="Known pairs"
        help="A known pair of cis-natural antisense transcripts">
    </param>
    <param name="count_smt" type="data" format="tabular" label="Read count of sense strand"
        help="">
    </param>
    <param name="count_asmt" type="data" format="tabular" label="Read count of antisense strand"
        help="">
    </param>
  </inputs>
  <outputs>
      <data name="newpairs" format="tabular"
      from_work_dir="output_newpairs.tsv"
      label="${tool.name} on ${on_string}: New pairs">
      </data>
      <data name="neworphan" format="tabular"
      from_work_dir="output_neworphan.tsv"
      label="${tool.name} on ${on_string}: New orphans">
      </data>
  </outputs>
  <tests>
    <test>
        <param name="annotation" value="input_TAIR10_annotation.gtf" ftype="gtf" />
        <param name="positive_pair" value="input_positive_pair.tsv" ftype="tabular" />
        <param name="count_smt" value="input_read_count_smt.tsv" ftype="tabular" />
        <param name="count_asmt" value="input_read_count_asmt.tsv" ftype="tabular" />
        <output name="newpairs" file="output_newpairs.tsv" ftype="tabular"/>
        <output name="neworphan" file="output_neworphan.tsv" ftype="tabular"/>
    </test>
  </tests>
<help>
<![CDATA[
.. class:: infomark

**What it does**

  Pairs of RNA molecules transcribed from partially or entirely complementary loci
  are called cis-natural antisense transcripts (cis-NATs),
  and they play key roles in the regulation of gene expression in many organisms.
  A promising experimental tool for profiling sense and antisense transcription
  is strand-specific RNA sequencing (ssRNA-seq). `NASTIseq`_  is to identify
  cis-NATs using ssRNA-seq. `NASTIseq`_  is based on model comparison that incorporates
  the inherent variable efficiency of generating perfectly strand-specific libraries.
  Applying the method to the ssRNA-seq data from whole root and
  cell-type specific Arabidopsis libraries confirmed most of
  the known cis-NAT pairs and identified hundreds of additional cis-NAT pairs.

.. _NASTIseq: https://ohlerlab.mdc-berlin.de/software/NASTIseq_104/

.. class:: infomark

**Inputs**

  ``Annotation file``:  the annotation in `gtf`_ format

  .. _gtf: http://www.ensembl.org/info/website/upload/gff.html

  ``Known pairs``: a table of two  column  matrix,  with  each  row  contains  the
  names of a known pair of cis-natural antisense transcripts. Example as following::

          AT2G46910       AT2G46915
          AT3G12250       AT3G12260
          AT5G50315       AT5G50320

  ``Read count of sense strand``: a table of N by M matrix of read count for reads that mapped
  to  the  sense  strand.   N  is  the  number  of  gene  loci.   M  is  the
  number of biological replicates in the sample.  Each
  rowname must be a unique locus name. Example as following::

          AT1G38440       0       2       0
          AT1G43171       2       8       1
          AT1G67670       3       7       0

  ``Read count of antisense strand``: a table of N by M matrix of read count for reads that mapped
  to  the  antisense  strand.    N  is  the  number  of  gene  loci.   M  is  the
  number of biological replicates in the sample.  Each
  rowname must be a unique locus name. Example as following::

          AT1G38440       0       0       0
          AT1G43171       0       0       0
          AT1G67670       0       0       2

  Read counts can be obtained using popular software such as `RSamtools`_.

.. _RSamtools: http://bioconductor.org/packages/release/bioc/html/Rsamtools.html

.. class:: infomark

**Outputs**

  ``New pairs``: a table of two  column  matrix,  with  each  row  contains  the
  names of a new pair of cis-natural antisense transcripts. Example as following::

        AT1G76630       AT1G76640
        AT2G06045       AT2G06050
        AT4G30100       AT4G30110


  ``New orphans``: a list of new orphan transcripts. Example as following::

        ATMG00030
        AT5G49440
        AT2G11240
]]>
</help>
<citations>
    <citation type="doi">10.1101/gr.149310.112</citation>
</citations>
</tool>