annotate colocalization.xml @ 0:d3ca64dafdef draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit badc51fcd74ba0c14cd1ae64d5f524291fa11441"

<tool id="cardinal_colocalization" name="MSI colocalization" version="@VERSION@.0">
    <description>mass spectrometry imaging colocalization</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="2.3">r-gridextra</requirement>
      </expand>
    <command detect_errors="exit_code">
    <![CDATA[

        @INPUT_LINKING@
        cat '${MSI_colocalization}' &&
        Rscript '${MSI_colocalization}'

    ]]>
    </command>
    <configfiles>
        <configfile name="MSI_colocalization"><![CDATA[

################################# load libraries and read file #################

library(Cardinal)
library(gridExtra)

@READING_MSIDATA_FULLY_COMPATIBLE@

#if str($reference_type.reference) == "roi_ref":
    ## read and extract x,y,annotation information
    input_tabular <- read.delim("$reference_type.annotation_file", header = $reference_type.tabular_header, stringsAsFactors = FALSE)
    annotation_input <- input_tabular[,c($reference_type.column_x, $reference_type.column_y, $reference_type.column_names)]
    annotation_name <- colnames(annotation_input)[3] ##extract header for annotations to later export tabular with same name
    colnames(annotation_input) <- c("x", "y", "annotation") ## rename annotations header to default name "annotation"

    ## merge with coordinate information of msidata
    msidata_coordinates <- data.frame(coord(msidata)\$x, coord(msidata)\$y, c(1:ncol(msidata)))
    colnames(msidata_coordinates) <- c("x", "y", "pixel_index")
    merged_annotation <- merge(msidata_coordinates, annotation_input, by=c("x", "y"), all.x=TRUE)
    merged_annotation[is.na(merged_annotation)] <- "NA"
    merged_annotation <- merged_annotation[order(merged_annotation\$pixel_index),]
    msidata\$annotation <- as.character(merged_annotation[,4])
    reference_group <- msidata\$annotation == "$reference_type.ref_name"
#end if

## remove duplicated coordinates
msidata <- msidata[,!duplicated(coord(msidata))]


@DATA_PROPERTIES_INRAM@


######################################## PDF ###################################
################################################################################
################################################################################


pdf("colocalization.pdf", fonts = "Times", pointsize = 12)
plot(0,type='n',axes=FALSE,ann=FALSE)

title(main=paste0("Colocalization for file: \n\n", "$infile.display_name"))

grid.table(property_df, rows= NULL)


if (npeaks > 0 && sum(is.na(spectra(msidata)))==0)
{

    ## colocalization analysis
    col_results <- colocalized(msidata, 
             #if str($reference_type.reference) == "mz_ref":
                mz = $reference_type.mz_value,
            #else
                ref = reference_group,
            #end if
            n = $n_tophits,
            sort.by = "$sort_by",
            threshold = median)

    ## Summary results table
    col_results_df <- as.data.frame(col_results)

    write.table(col_results_df, file="$coloc_results", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
    
    ## visualize top 10 m/z features

    if (nrow(col_results_df) <= 10)
    {
        for (mass in col_results_df\$mz){
	    par(oma=c(0,0,0,1))## margin for image legend
	    print(image(msidata, mz=mass, plusminus=0.25,
	    main= paste0(round(mass, digits = 2)),
	    contrast.enhance = "histogram", strip=FALSE, ylim= c(maximumy,minimumy)))
        }
    }else{
	for (mass in col_results_df\$mz[1:10]){
	    par(oma=c(0,0,0,1))## margin for image legend
	    print(image(msidata, mz=mass, plusminus=0.25,
	    main= paste0(round(mass, digits = 2)),
	    contrast.enhance = "histogram", strip=FALSE, ylim= c(maximumy,minimumy)))
	}    
    }
    

    dev.off()
    
}else{
    print("Inputfile has no intensities > 0")
}

    ]]></configfile>
    </configfiles>
    <inputs>
        <expand macro="reading_msidata"/>
        <conditional name="reference_type">
            <param name="reference" type="select" label="Reference type" help="Region of interest (selected spectra) or m/z feature.">
                    <option value="mz_ref" selected="True">m/z feature</option>
                    <option value="roi_ref">Region of interest (spectra)</option>
                </param>
                <when value="mz_ref">
                    <param name="mz_value" type="float" value="1000" label="m/z feature" help="The m/z closest to this m/z value will be used as a reference."/>    
                </when>      
                <when value="roi_ref">
                    <expand macro="reading_pixel_annotations"/>
                    <param name="ref_name" type="text" value="reference" label="Reference name" help="Name has to match exactly on of the annotation names in the annotation file"/>    
                </when>
        </conditional>
            <param name="n_tophits" type="integer" value="10" label="Top hits" help="The number of top-ranked colocalized features to return in the tabular file." />
	    <param name="sort_by" type="select" display="radio"
                   label="sort.by" help="The colocalization measure used to rank colocalized features. Possible options
include Pearson’s correlation and Manders’ colocalization coefficients.">
                    <option value="correlation" selected="True">Pearson's correlation</option>
                    <option value="M1">Manders' colocalization coefficient 1</option>
                    <option value="M2">Manders' colocalization coefficient 2</option>
            </param>
    </inputs>
    <outputs>
        <data format="pdf" name="coloc_pdf" from_work_dir="colocalization.pdf" label = "${tool.name} on ${on_string}: results"/>
        <data format="tabular" name="coloc_results" label="${tool.name} on ${on_string}: summary"/>
    </outputs>
    <tests>
        <test>
	    <param name="infile" value="" ftype="imzml">
	        <composite_data value="spatial_DGMM_input.imzML"/>
	        <composite_data value="spatial_DGMM_input.ibd"/>
	    </param>
	    <conditional name="reference_type">
	        <param name="reference" value="mz_ref"/>
	        <param name="mz_value" value="1000"/>
	    </conditional>
	    <output name="coloc_pdf" file="coloc1.pdf" compare="sim_size" delta="2000"/>
            <output name="coloc_results" file="coloc_table1.tabular"/>
        </test>
        <test>
        <param name="infile" value="" ftype="imzml">
            <composite_data value="spatial_DGMM_input.imzML"/>
            <composite_data value="spatial_DGMM_input.ibd"/>
        </param>
	<conditional name="reference_type">
            <param name="reference" value="roi_ref"/>
            <param name="annotation_file" value="DGMM_annotations.tabular"/>
            <param name="column_x" value="1"/>
            <param name="column_y" value="2"/>
            <param name="column_names" value="3"/>
            <param name="tabular_header" value="True"/>
            <param name="ref_name" value="circle"/>    
        </conditional>
            <param name="n_tophits" value="5"/>
            <param name="sort_by" value="M2"/>
	    <output name="coloc_pdf" file="coloc2.pdf" compare="sim_size" delta="2000"/>
            <output name="coloc_results" file="coloc_table2.tabular"/>
        </test>
        <test>
	    <param name="infile" value="123_combined.RData" ftype="rdata"/>
	    <conditional name="reference_type">
	        <param name="reference" value="mz_ref"/>
	        <param name="mz_value" value="102.0"/>
	    </conditional> 
	        <param name="n_tophits" value="50"/>
	        <param name="sort_by" value="correlation"/>
	        <output name="coloc_pdf" file="coloc3.pdf" compare="sim_size" delta="2000"/>
	        <output name="coloc_results" file="coloc_table3.tabular"/>
        </test>        
    </tests>
    <help>
        <![CDATA[

@CARDINAL_DESCRIPTION@

-----

This tool finds colocalized features in an imaging dataset. Use it to find m/z features that are colocalized with another m/z feature or regions of interests. 

@MSIDATA_INPUT_DESCRIPTION@

    - NA intensities are not allowed
    - duplicated coordinates will be removed
    - it is highly recommended to use a dataset that is reduced for the number of m/z features e.g. pre-processed and optionally filtered for m/z of interest in order to keep computational times reasonable.


**Options**

- The reference can be either a single m/z feature or a region of interest provided via the annotation file. 

	- For single m/z features the closest m/z to the m/z value that is used as reference is used
	- For regions of interest as a reference the name of the region that should be used as a reference has to be written exactly in the way in which it appears in the annotation file input. 
	    @SPECTRA_TABULAR_INPUT_DESCRIPTION@
	
- By default, pearson correlation is used to rank the colocalized features. Manders’ colocalization coefficients (M1 and M2) are also provided.

**Output**

- Pdf with file info and the ion images of the top 10 m/z features (to plot the ion images for more m/z features use the MSI mz images tool)
- Tabular file with the top m/z features and their correlation values (pearson, Manders 1 and Manders 2) with the reference


        ]]>
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv146</citation>
    </citations>

</tool>