annotate size_histogram.xml @ 3:31782dbb7d85 draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_sr_size_histograms commit 4813e8efaadd5755956bbea2069098bf6ec63e38

<tool id="Size_histogram" name="Generate size histograms from alignment files" version="0.9.9">
    <description>from sRbowtie aligment</description>
    <requirements>
        <requirement type="package" version="0.12.7">bowtie</requirement>
        <requirement type="package" version="0.7.7">pysam</requirement>
        <requirement type="package" version="3.1.2">R</requirement>
        <requirement type="package" version="2.14">biocbasics</requirement>
        <requirement type="package" version="1.9">numpy</requirement>
    </requirements>
    <command interpreter="python">
        size_histogram.py
        #if $refGenomeSource.genomeSource == "history":
            --reference_fasta  ## sys.argv[2]
            $refGenomeSource.ownFile ## index source
        #else:
            #silent reference= filter( lambda x: str( x[0] ) == str( $refGenomeSource.series[0].input.dbkey ), $__app__.tool_data_tables[ 'bowtie_indexes' ].get_fields() )[0][-1]
            --reference_bowtie_index
            $reference
        #end if
        --rcode
        $plotCode
        --output_size_distribution
        $size_distribution_dataframe
        --minquery
        $minquery
        --maxquery
        $maxquery
        --input
        #for $i in $refGenomeSource.series
            $i.input
        #end for
        --ext
        #for $i in $refGenomeSource.series
            $i.input.ext
        #end for
        --label
        #for $i in $refGenomeSource.series
            "$i.input.element_identifier"
        #end for
        --normalization_factor
        #for $i in $refGenomeSource.series
            $i.norm
        #end for
        #if $gff:
            --gff $gff
        #end if
        #if $global.value == 'yes':
            --global_size
        #end if
        #if $collapsestrands.value == 'yes':
            --collapse
        #end if

    </command>
    <inputs>
        <conditional name="refGenomeSource">
            <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
                <option value="indexed">Use a built-in index</option>
                <option value="history">Use one from the history</option>
            </param>
            <when value="indexed">
                <repeat name="series" title="Add alignment files">
                    <param name="input" type="data" label="Select multiple alignments to parse" format="tabular,sam,bam">
                        <validator type="dataset_metadata_in_data_table" table_name="bowtie_indexes" metadata_name="dbkey" metadata_column="0" message="database not set for this bowtie output. Select the database(=genome used for matching) manually, or select a reference fasta from your history."/>
                    </param>
                    <param name="norm" type="float" value="1" label="Indicate a normalization factor to compare multiple aligments"/>
                </repeat>
            </when>
            <when value="history">
                <param name="ownFile" type="data" format="fasta" label="Select a fasta file, to serve as index reference" />
                <repeat name="series" title="Add alignment files">
                    <param name="input" type="data" label="Select multiple alignments to parse" format="tabular,sam,bam"/>
                    <param name="norm" type="float" value="1" label="Indicate a normalization factor to compare multiple aligments"/>
                </repeat>
            </when>
        </conditional>
        <param name="gff" type="data" format="gff,gff3" optional="true" label="Optional: select a GFF to investigate regions of interest" help="GFF must match genome build"/>
        <!-- <validator type="dataset_metadata_in_data_table" table_name="bowtie_indexes" metadata_name="dbkey" metadata_column="0" message="GFF database and alignment file databse do not match!"/> -->
        <param name="global" type="select" label="Generate size distribution for each item, or generate a global alignment">
            <option value="no">for each item</option>
            <option value="yes">global</option>
        </param>
        <param name="collapsestrands" type="select" label="Whether + and - reads should be collapsed or not">
            <option value="no">Do not collapse</option>
            <option value="yes">Collapse + and - reads</option>
        </param>
        <param name="minquery" type="integer" size="3" value="18" label="Min size of reads to plot" help="'15' = 15 nucleotides"/>
        <param name="maxquery" type="integer" size="3" value="28" label="Max size of reads to plot" help="'30' = 30 nucleotides"/>
        <param name="title" type="text" size="15" value="Size distribution" label="Main Titles"/>
        <param name="xlabel" type="text" size="15" value="Size in nucleotides" label="x axis label"/>
        <param name="ylabel" type="text" size="15" value="Number of reads" label="y axis label"/>
        <param name="yrange" type="integer" size="3" value="0" label="y axis range for size distributions. 0 means auto-scaling."/>
        <param name="rows_per_page" type="text" size="9" value="8" label="How many items to display per page?">
            <validator type="in_range" min="6" max="20" message="Select between 6 and 20 rows, as the readability will suffer otherwise."/>
        </param>
    </inputs>
   <configfiles>
     <configfile name="plotCode">
      ## Setup R error handling to go to stderr
      options( show.error.messages=F,
               error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
      library(RColorBrewer)
      library(lattice)
      library(latticeExtra)
      library(grid)
      library(gridExtra)

      ##cheetahtemplate data frame implementation
      size=read.delim("${size_distribution_dataframe}", header=T, row.names=NULL)
      n_samples = length(unique (size\$sample))
      n_genes = length (unique (levels(size\$gene)))

      if (${yrange} != 0) {
         # This is used for specifying the y-axis limits
         ylim=c(-${yrange}, ${yrange})
      } else { ylim="" }

      par.settings.size=list(layout.heights=list(top.padding=1, bottom.padding=1),
                             strip.background = list(col = c("lightblue", "lightgreen"))
                             )

      smR.prepanel=function(x,y,...){; yscale=c(-max(abs(y)), max(abs(y)));list(ylim=yscale);} # use if one want y axis in the middle of the plot

      plot_size_distribution= function(df, ...) {
         bc= barchart(count~as.factor(size)|factor(sample, levels=unique(sample))+gene, data = df, origin = 0,
                      horizontal=FALSE,
	              group=polarity,
	              stack=TRUE,
                      col=c('red', 'blue'),
                      cex=0.75,
                      scales=list(y=list(tick.number=4, rot=90, relation="free", cex=0.5, alternating=T), x=list(cex=.6 ) ),
                      xlab = "readsize in nucleotides",
                      ylab = "${ylabel}",
                      main="${title}" ,
                      par.strip.text = list(cex=0.75),
                      as.table=TRUE,
                      newpage = T,
                      ...)

          combineLimits(update(useOuterStrips(bc,
                                              strip.left = strip.custom(par.strip.text = list(cex=0.5))
                                              ),
                        layout=c(n_samples,${rows_per_page})),
                        margin.x=F, margin.y=1)
          }

      # per_gene_size=lapply(genes, function(x) subset(size, gene==x)) # no object in this script

      global = "no"
      #if $global.value == 'yes':
        global = "yes"
      #end if

      if (global=="no") {
      width = 8.2677*n_samples/4
      } else { width = 8.2677 }

      options(warn=-1)
      pdf(file="${size_PDF}", paper="special", height=11.69, width=width)

      if (ylim == "" &amp;&amp; global=="no") {
          plot_size_distribution(size, par.settings=par.settings.size)
         }
      if (ylim != "" &amp;&amp; global=="no") { plot_size_distribution(size, par.settings=par.settings.size, ylim=ylim)
         }
      if (ylim == "" &amp;&amp; global=="yes") {  bc= barchart(count~as.factor(size)|factor(sample, levels=unique(sample)), data = size, origin = 0,
              horizontal=FALSE,
              group=polarity,
              stack=TRUE,
              col=c('red', 'blue'),
              scales=list(y=list(tick.number=4, rot=90, relation="same"), cex=1),
              xlab = "readsize in nucleotides",
              ylab = "${ylabel}",
              main="${title}" , as.table=TRUE, newpage = T,
              aspect=0.5,
              strip = strip.custom(par.strip.text = list(cex = 1), which.given=1, bg="lightblue")
              )
         bc
         }
      if (ylim != "" &amp;&amp; global=="yes") {  bc= barchart(count~as.factor(size)|factor(sample, levels=unique(sample)), data = size, origin = 0,
              horizontal=FALSE,
              group=polarity,
              stack=TRUE,
              col=c('red', 'blue'),
              scales=list(y=list(tick.number=4, rot=90, relation="same"), cex=1),
              xlab = "readsize in nucleotides",
              ylab = "${ylabel}",
              ylim = ylim,
              main="${title}" , as.table=TRUE, newpage = T,
              aspect=0.5,
              strip = strip.custom(par.strip.text = list(cex = 1), which.given=1, bg="lightblue")
              )
         bc
         }

      devname=dev.off()

     </configfile>
   </configfiles>
    <outputs>
        <data format="tabular" name="size_distribution_dataframe" label="Size_distribution_dataframe.tab"/>
        <data format="pdf" name="size_PDF" label="Size_distribution.pdf"/>
    </outputs>
<help>

**What it does**

Takes one or more alignment files (BAM, SAM or tabular bowtie output) as input and produces a histogram of read sizes,
where by default for each "chromosome" a histogram of read sizes is drawn.
Reads that map in sense are on the top (red), reads that map antisense are on the bottom (blue).


.. class:: warningmark

'''TIP''' The input data can be produced using the sRbowtie tool.

----

'''Example'''

Query sequence::
For a SAM file as the following:

  5	16	2L_79	24393	255	17M	*	0	0	CCTTCATCTTTTTTTTT	IIIIIIIIIIIIIIIII	XA:i:0	MD:Z:17	NM:i:0

  11	0	2R_1	12675	255	21M	*	0	0	AAAAAAAACGCGTCCTTGTGC	IIIIIIIIIIIIIIIIIIIII	XA:i:0	MD:Z:21	NM:i:0

  2	16	2L_5	669	255	23M	*	0	0	TGTTGCTGCATTTCTTTTTTTTT	IIIIIIIIIIIIIIIIIIIIIII	XA:i:0	MD:Z:23	NM:i:0

produce a plot like this:

----

.. image:: static/images/size_histogram.png
    :height: 800
    :width: 500

</help>
    <tests>
        <test>
            <param name="genomeSource" value="history" />
            <param name="ownFile" value="transposons.fasta" ftype="fasta" />
            <param name="series_0|input" value="sample1.srbowtie_out" ftype="tabular"/>
            <param name="series_0|norm" value="1" />
            <param name="series_1|input" value="sample2.srbowtie_out" ftype="tabular"/>
            <param name="series_1|norm" value="1" />
            <param name="series_2|input" value="sample3.srbowtie_out" ftype="tabular"/>
            <param name="series_2|norm" value="1" />
            <param name="global" value="no" />
            <param name="collapsestrands" value="no" />
            <param name="minquery" value="18"/>
            <param name="maxquery" value="30"/>
            <param name="title" value="Size distribution"/>
            <param name="xlabel" value="Size in nucleotides"/>
            <param name="ylabel" value="Number of reads"/>
            <param name="rows_per_page" value="10"/>
            <output name="size_distribution_dataframe" ftype="tabular" file="Size_distribution_dataframe.tab" />
            <output name="size_PDF" ftype="pdf" file="Size_distribution.pdf" />
        </test>
    </tests>
</tool>