comparison pyprophet_export.xml @ 4:3cf580bf28e2 draft default tip

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/pyprophet commit 8b9f6963836c6ccb227343ce952e7b9a015d0483"

3:ece83e6b5328

<tool id="pyprophet_export" name="PyProphet export" version="@VERSION@.0">
    <description>
    Export tabular files, optional swath2stats export
    </description>
    <macros>
        <import>macros.xml</import>

########################### QC plots and tabular files #########################

## remove decoys when generating plots
data.annotated.nodecoy <- subset(data.annotated, decoy==FALSE)

pdf("summary.pdf", fonts = "Times", pointsize = 12)
plot(0,type='n',axes=FALSE,ann=FALSE)
title(main="Summarized plots and tables from pyprophet export file")

## Look at Numbers of peptides and proteins per run
grid.table(count_analytes(data.annotated.nodecoy), rows= NULL)

## Correlation of the intensities
correlation_int <- plot_correlation_between_samples(data.annotated.nodecoy, column.values = 'Intensity')

## Plot the correlation of the delta_rt, which is the deviation of the retention time from the expected retention time

    </configfiles>
    <inputs>
        <param name="input" type="data" format="osw" label="Input file" help="This file needs to be in OSW format (--in)" />
        <conditional name="conditional_output">
        <param argument="format" type="select" label="Export format, either matrix, legacy_split, legacy_merged (mProphet/PyProphet) or score_plots format" >
            <option value="legacy_split" selected="True">legaxy_split</option>
            <option value="legacy_merged">legacy_merged</option>
            <option value="matrix">matrix</option>
            <option value="score_plots">score_plots</option>
        </param>
            <when value="legacy_split">

<![CDATA[
**What it does**

PyProphet: Semi-supervised learning and scoring of OpenSWATH results.

Export tabular (tsv) tables. 

Optional SWATH2stats output. SWATH2stats is intended to transform SWATH data from the OpenSWATH software into a format readable by other statistics packages while performing filtering, annotation and FDR estimation.

**Study desing file for SWATH2stats**

    - Tabular file with columns that are named: Filename, Condition, BioReplicate, Run. 
    - The Filename should be part or the same as the original filenames used in OpenSWATH workflow
    - The Condition should be a 
    - The BioReplicate is corresponds to the biological replicate
    - The Run is the number of the run in which the sample was measured

        ::

                      Filename       Condition    BioReplicate     Run
                    healthy1.mzml     healthy         1             1
                    healthy2.mzml     healthy         2             2
                    diseased1.mzml    diseased        3             3
                        ...
                        ...


PyProphet is a Python re-implementation of the mProphet algorithm (Reiter 2010 Nature Methods) optimized for SWATH-MS data acquired by data-independent acquisition (DIA). The algorithm was originally published in (Telemann 2014 Bioinformatics) and has since been extended to support new data types and analysis modes (Rosenberger 2017, Nature biotechnology and Nature methods).

For more information, visit @link@

4:3cf580bf28e2

<tool id="pyprophet_export" name="PyProphet export" version="@VERSION@.1">
    <description>
    Export tabular files, optional swath2stats export
    </description>
    <macros>
        <import>macros.xml</import>

########################### QC plots and tabular files #########################

## remove decoys when generating plots
data.annotated.nodecoy <- subset(data.annotated, decoy==FALSE)

pdf("summary.pdf", fonts = "Times", pointsize = 8)
plot(0,type='n',axes=FALSE,ann=FALSE)
title(main="Summarized plots and tables from pyprophet export file")

## Look at Numbers of peptides and proteins per run
## for many runs table needs to be split over several pages
number_samples = nrow(count_analytes(data.annotated.nodecoy))

    ### for more than 20 annotation groups print only 20 samples per page:
    if (number_samples <= 20){
        grid.table(count_analytes(data.annotated.nodecoy), rows= NULL)
    }else{
        grid.table(count_analytes(data.annotated.nodecoy)[1:20,], rows= NULL)
        mincount = 21
        maxcount = 40
        for (count15 in 1:(ceiling(number_samples/20)-1)){
            plot(0,type='n',axes=FALSE,ann=FALSE)
            if (maxcount <= number_samples){
                grid.table(count_analytes(data.annotated.nodecoy)[mincount:maxcount,], rows= NULL)
                mincount = mincount+20
                maxcount = maxcount+20
            }else{### stop last page with last sample otherwise NA in table
                grid.table(count_analytes(data.annotated.nodecoy)[mincount:number_samples,], rows= NULL)} 
        }
    }


## Correlation of the intensities
correlation_int <- plot_correlation_between_samples(data.annotated.nodecoy, column.values = 'Intensity')

## Plot the correlation of the delta_rt, which is the deviation of the retention time from the expected retention time

    </configfiles>
    <inputs>
        <param name="input" type="data" format="osw" label="Input file" help="This file needs to be in OSW format (--in)" />
        <conditional name="conditional_output">
        <param argument="format" type="select" label="Export format, either matrix, legacy_split, legacy_merged (mProphet/PyProphet) or score_plots format" >
            <option value="legacy_split" selected="True">legacy_split</option>
            <option value="legacy_merged">legacy_merged</option>
            <option value="matrix">matrix</option>
            <option value="score_plots">score_plots</option>
        </param>
            <when value="legacy_split">

<![CDATA[
**What it does**

PyProphet: Semi-supervised learning and scoring of OpenSWATH results.

Export tabular (tsv) tables. By default, both peptide- and transition-level quantification is reported, which is necessary for requantification or SWATH2stats. If peptide and protein inference in the global context was conducted, the results will be filtered to 1% FDR by default.

Optional SWATH2stats output. SWATH2stats is intended to transform SWATH data from the OpenSWATH software into a format readable by other statistics packages while performing filtering, annotation and FDR estimation.

**Study desing file for SWATH2stats**

    - Tabular file with columns that are named: Filename, Condition, BioReplicate, Run. 
    - The Filename should be part or the same as the original filenames used in OpenSWATH workflow
    - The Condition will be used for statistical analysis. In case multiple conditions are of interest for statistical analysis (e.g. diagnosis and age), this tool has to be run multiple times as SWATH2stats can only handle one condition at a time
    - The BioReplicate is corresponds to the biological replicate
    - The Run is the number of the MS run in which the sample was measured

    - **Example for one replicate per patient**

        ::

                      Filename       Condition    BioReplicate     Run
                    healthy1.mzml     healthy         1             1
                    healthy2.mzml     healthy         2             2
                    diseased1.mzml    diseased        3             3
                    diseased2.mzml    diseased        4             4
                        ...
                        ...


    - **Example for two replicates per patient**

        ::

                      Filename       Condition    BioReplicate     Run
                    healthy1.mzml     healthy         1             1
                    healthy2.mzml     healthy         1             2
                    diseased1.mzml    diseased        2             3
                    diseased2.mzml    diseased        2             4
                        ...
                        ...

PyProphet is a Python re-implementation of the mProphet algorithm (Reiter 2010 Nature Methods) optimized for SWATH-MS data acquired by data-independent acquisition (DIA). The algorithm was originally published in (Telemann 2014 Bioinformatics) and has since been extended to support new data types and analysis modes (Rosenberger 2017, Nature biotechnology and Nature methods).

For more information, visit @link@