Mercurial > repos > galaxyp > msstatstmt
view msstatstmt.xml @ 6:bd1535813cfe draft default tip
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msstatstmt commit 86de2cd327423c44d042f98108dc93a8f83982d0
author | galaxyp |
---|---|
date | Tue, 31 Jan 2023 18:15:05 +0000 |
parents | a5e394b36d87 |
children |
line wrap: on
line source
<tool id="msstatstmt" name="MSstatsTMT" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"> <description>protein significance analysis in shotgun mass spectrometry-based proteomic experiments with tandem mass tag (TMT) labeling</description> <macros> <token name="@TOOL_VERSION@">2.0.0</token> <token name="@VERSION_SUFFIX@">1</token> <xml name="input_options_shared"> <param name="useUniquePeptide" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Use unique peptide" help="Yes (default) removes peptides that are assigned for more than one protein. We assume to use unique peptide for each protein." /> <param name="rmPSM_withMissing_withinRun" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Remove PSM with missing value within run" help="Yes will remove PSM with any missing value within each run. Default is No." /> <param name="rmPSM_withfewMea_withinRun" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove PSM with few measurements within run" help="Only for 'Remove PSM with missing value within run = No'. Yes (default) will remove the features that have 1 or 2 measurements within each run." /> <param name="rmProtein_with1Feature" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Remove proteins with one feature" help="Yes will remove the proteins which have only 1 peptide and charge. Default is No." /> </xml> </macros> <requirements> <requirement type="package" version="@TOOL_VERSION@">bioconductor-msstatstmt</requirement> </requirements> <command detect_errors="exit_code"><![CDATA[ cat '$msstatstmt_script' > '$out_r_script' && Rscript '$msstatstmt_script' && cat MSstatsTMT_summarization_log*.log > '$out_msstatstmt_sum_log' && cat MSstatsTMT_summarization_MSstats*.log > '$out_msstatstmt_sum_ms' #if $input.input_src != 'MSstatsTMT': && cat MSstatsTMT_converter_log*.log > '$out_msstatstmt_conv_log' #else: && echo "MSstatsTMT input. No conversion needed." > '$out_msstatstmt_conv_log' #end if #if $group.group_comparison == 'true': && cat MSstatsTMT_log_groupComparison*.log > '$out_msstatstmt_group_log' && cat MSstats_log*.log > '$out_msstats_gc_log' #else: && echo "No groupComparison was performed." > '$out_msstatstmt_group_log' && echo "No groupComparison was performed." > '$out_msstats_gc_log' #end if ]]></command> <configfiles> <configfile name="msstatstmt_script"><![CDATA[ library(MSstatsTMT, warn.conflicts = F, quietly = T, verbose = F) library(MSstats) #if $input.input_src == 'MSstatsTMT' input <- read.table("$input.msstatstmt_input", sep="\t", header=TRUE) #elif $input.input_src == 'MaxQuant' proteinGroups.mq <- read.table("$input.proteinGroups", sep="\t", header=TRUE) evidence.mq <- read.table("$input.evidence", sep="\t", header=TRUE) annotation.mq <- read.table("$input.annotation", sep="\t", header=TRUE) input <- MaxQtoMSstatsTMTFormat(evidence = evidence.mq, proteinGroups = proteinGroups.mq, annotation = annotation.mq, which.proteinid = "$input.proteinID", rmProt_Only.identified.by.site = $input.input_options.rmProt_Onlyidentifiedbysite, useUniquePeptide = $input.input_options.useUniquePeptide, rmPSM_withMissing_withinRun = $input.input_options.rmPSM_withMissing_withinRun, rmPSM_withfewMea_withinRun = $input.input_options.rmPSM_withfewMea_withinRun, rmProtein_with1Feature = $input.input_options.rmProtein_with1Feature, summaryforMultipleRows = $input.input_options.summaryforMultipleRows) #elif $input.input_src == 'OpenMS' input.oms <- read.table("$input.oms_input", sep="\t", header=TRUE) input <- OpenMStoMSstatsTMTFormat(input.oms, useUniquePeptide = $input.input_options.useUniquePeptide, rmPSM_withMissing_withinRun = $input.input_options.rmPSM_withMissing_withinRun, rmPSM_withfewMea_withinRun = $input.input_options.rmPSM_withfewMea_withinRun, rmProtein_with1Feature = $input.input_options.rmProtein_with1Feature, summaryforMultiplePSMs = $input.input_options.summaryforMultiplePSMs) #elif $input.input_src == 'PD' PSM.pd <- read.table("$input.PSM", sep="\t", header=TRUE) annotation.pd <- read.table("$input.annotation", sep="\t", header=TRUE) input <- PDtoMSstatsTMTFormat(PSM.pd, annotation = annotation.pd, which.proteinid = "$input.proteinID", useNumProteinsColumn = $input.input_options.useNumProteinsColumn, useUniquePeptide = $input.input_options.useUniquePeptide, rmPSM_withMissing_withinRun = $input.input_options.rmPSM_withMissing_withinRun, rmPSM_withfewMea_withinRun = $input.input_options.rmPSM_withfewMea_withinRun, rmProtein_with1Feature = $input.input_options.rmProtein_with1Feature, summaryforMultipleRows = $input.input_options.summaryforMultipleRows) #end if quant <- proteinSummarization(input, method = "$proteinSummarization.method", global_norm = $proteinSummarization.global_norm, reference_norm = $proteinSummarization.reference_norm, remove_norm_channel = $proteinSummarization.remove_norm_channel, remove_empty_channel = $proteinSummarization.remove_empty_channel, MBimpute = $proteinSummarization.MBimpute, #if $proteinSummarization.maxQuantileforCensored == '' maxQuantileforCensored = NULL) #else maxQuantileforCensored = $proteinSummarization.maxQuantileforCensored) #end if #for $plot_type in $selected_outputs #if $plot_type[-4:] == "Plot" dataProcessPlotsTMT(quant, type = '$plot_type', ylimUp = $out_plots_opt.adv.ylimUp, ylimDown = $out_plots_opt.adv.ylimDown, x.axis.size = $out_plots_opt.adv.x_axis_size, y.axis.size = $out_plots_opt.adv.y_axis_size, text.size = $out_plots_opt.adv.text_size, text.angle = $out_plots_opt.adv.text_angle, legend.size = $out_plots_opt.adv.legend_size, dot.size.profile = $out_plots_opt.adv.dot_size_profile, ncol.guide = $out_plots_opt.adv.ncol_guide, width = $out_plots_opt.width, height = $out_plots_opt.height, #if $out_plots_opt.which_Protein.select != 'list' #if $out_plots_opt.which_Protein.select == "allonly" and $plot_type == "ProfilePlot" which.Protein = "all", #else which.Protein = "$out_plots_opt.which_Protein.select", #end if #else which.Protein = unlist(read.table("$out_plots_opt.which_Protein.protein_list", sep = "\n", header = FALSE), use.names = FALSE), #end if originalPlot = $out_plots_opt.adv.originalPlot, summaryPlot = $out_plots_opt.adv.summaryPlot) #elif $plot_type == "quant" write.table(quant\$ProteinLevelData, "Quant.tsv", sep = "\t", quote = F, row.names = F, dec = ".") #end if #end for #if $group.group_comparison == 'true' #if $group.use_comp_matrix.select == 'true' comp_matrix <- read.table("$group.use_comp_matrix.comparison_matrix", sep="\t", header=TRUE, check.names=FALSE) comparison <- comp_matrix[,-1] row.names(comparison) <- as.character(comp_matrix[,1]) comparison <- as.matrix(comparison[levels(quant\$ProteinLevelData\$Condition)]) #end if comparisons <- groupComparisonTMT(data = quant, #if $group.use_comp_matrix.select == 'true' contrast.matrix = comparison, #end if moderated = $group.moderated, adj.method = "$group.adj_method", remove_norm_channel = $group.remove_norm_channel, remove_empty_channel = $group.remove_empty_channel) write.table(comparisons\$ComparisonResult, "ComparisonResult.tsv", sep = "\t", quote = F, row.names = F, dec = ".") #for $plot_type in $group.selected_group_outputs #if $plot_type == "VolcanoPlot" or $plot_type == "Heatmap" or $plot_type == "ComparisonPlot" ## Workaround for missing option "MSstatsLog" (getOption("MSstatsLog") returns NULL) MSstatsConvert::MSstatsLogsSettings() ############################################# groupComparisonPlots(data = comparisons\$ComparisonResult, type = "$plot_type", sig = $group.comparison_plots_opt.sig, #if $group.comparison_plots_opt.FCcutoff: FCcutoff = $group.comparison_plots_opt.FCcutoff, #end if logBase.pvalue = $group.comparison_plots_opt.logBase_pvalue, #if $group.comparison_plots_opt.ylimUp: ylimUp = $group.comparison_plots_opt.ylimUp, #end if #if $group.comparison_plots_opt.ylimDown: ylimDown = $group.comparison_plots_opt.ylimDown, #end if x.axis.size = $group.comparison_plots_opt.x_axis_size, y.axis.size = $group.comparison_plots_opt.y_axis_size, dot.size = $group.comparison_plots_opt.dot_size, text.size = $group.comparison_plots_opt.text_size, text.angle = $group.comparison_plots_opt.text_angle, legend.size = $group.comparison_plots_opt.legend_size, ProteinName = $group.comparison_plots_opt.ProteinName, colorkey = $group.comparison_plots_opt.colorkey, numProtein = $group.comparison_plots_opt.numProtein, clustering = "$group.comparison_plots_opt.clustering", width = $group.comparison_plots_opt.width, height = $group.comparison_plots_opt.height, #if $group.comparison_plots_opt.which_Protein.select != 'list' which.Protein = "$group.comparison_plots_opt.which_Protein.select", #else which.Protein = unlist(read.table("$group.comparison_plots_opt.which_Protein.protein_list", sep = "\n", header = FALSE), use.names = FALSE), #end if #if $group.comparison_plots_opt.which_Comparison.select != 'list' which.Comparison = "$group.comparison_plots_opt.which_Comparison.select", #else which.Comparison = unlist(read.table("$group.comparison_plots_opt.which_Comparison.comparison_list", sep = "\n", header = FALSE), use.names = FALSE), #end if address="MSstats_group_") #end if #end for #end if ]]></configfile> </configfiles> <inputs> <conditional name="input"> <param name="input_src" type="select" label="Input Source"> <option value="MSstatsTMT">MSstatsTMT (11 column format)</option> <option value="MaxQuant">MaxQuant</option> <option value="OpenMS">OpenMS</option> <option value="PD">Proteome Discoverer</option> </param> <when value="MSstatsTMT"> <param name="msstatstmt_input" type="data" format="tabular" label="MSstatsTMT (11 column format)"/> </when> <when value="MaxQuant"> <param name="evidence" type="data" format="tabular" label="evidence.txt - feature-level data"/> <param name="proteinGroups" type="data" format="tabular" label="proteinGroups.txt" help="It needs to matching protein group ID. If proteinGroups=NULL, use 'Proteins' column in 'evidence.txt'"/> <param name="annotation" type="data" format="tabular" label="annotation.txt" help="Data frame which contains column Run, Fraction, TechRepMixture, Channel, Condition, BioReplicate, Mixture." /> <param name="proteinID" type="select" label="Select Protein ID in evidence.txt"> <option value="Proteins">Protein column</option> <option value="Leading.razor.protein">Leading razor protein column</option> </param> <section name="input_options" title="MaxQtoMSstatsTMTFormat Options" expanded="false"> <param name="rmProt_Onlyidentifiedbysite" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Remove proteins only identified by site" help="Yes will remove proteins with ’+’ in ’Only.identified.by.site’ column from proteinGroups.txt, which was identified only by a modification site. No is the default." /> <expand macro="input_options_shared"/> <param name="summaryforMultipleRows" type="select" label="Summary for multiple rows" help="When there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value."> <option value="max">max</option> <option value="sum" selected="true">sum</option> </param> </section> </when> <when value="OpenMS"> <param name="oms_input" type="data" format="tabular" label="OpenMS input"/> <section name="input_options" title="OpenMStoMSstatsTMTFormat Options" expanded="false"> <expand macro="input_options_shared"/> <param name="summaryforMultiplePSMs" type="select" label="Summary for multiple PSMs" help="When there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value."> <option value="max">max</option> <option value="sum" selected="true">sum</option> </param> </section> </when> <when value="PD"> <param name="PSM" type="data" format="tabular" label="PSM output" help=""/> <param name="annotation" type="data" format="tabular" label="annotation" help="Data frame contains column Run, Fraction, TechRepMixture, Mixture, Channel, BioReplicate, Condition." /> <param name="proteinID" type="select" label="Select Protein ID"> <option value="Protein.Accessions">Protein.Accessions column</option> <option value="Master.Protein.Accessions">Master.Protein.Accessions</option> </param> <section name="input_options" title="PDtoMSstatsTMTFormat Options" expanded="false"> <param name="useNumProteinsColumn" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove shared peptides by information of # Proteins column in PSM sheet." help="" /> <expand macro="input_options_shared"/> <param name="summaryforMultipleRows" type="select" label="Summary for multiple rows" help="When there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value."> <option value="max">max</option> <option value="sum" selected="true">sum</option> </param> </section> </when> </conditional> <section name="proteinSummarization" title="Summarize peptides into proteins" expanded="false"> <param name="method" type="select" multiple="false" label="Select method"> <option value="msstats" selected="true">msstats</option> <option value="MedianPolish">MedianPolish</option> <option value="Median">Median</option> <option value="LogSum">LogSum</option> </param> <param name="global_norm" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Global median normalization" help="Global median normalization on peptide level data (equalizing the medians across all the channels and MS runs). Default is Yes. It will be performed before protein-level summarization."/> <param name="reference_norm" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Reference channel based normalization" help="Reference channel based normalization between MS runs on protein level data. Yes (default) needs at least one reference channel in each MS run, annotated by ’Norm’ in condition column. It will be performed after protein-level summarization. No will not perform this normalization step. If data only has one run, then use No"/> <param name="remove_norm_channel" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove ’Norm’ channels from protein level data."/> <param name="remove_empty_channel" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove ’Empty’ channels from protein level data"/> <param name="MBimpute" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="MBimpute" help="Only for 'method = msstats'. Yes (default) imputes missing values by accelerated failure time (AFT) model. No uses minimum value to impute the missing value for each peptide precursor ion."/> <param name="maxQuantileforCensored" type="float" optional="true" min="0" max="0.999" value="" label="Maximum quantile for deciding censored missing value" help="We assume missing values are censored. maxQuantileforCensored is maximum quantile for deciding censored missing value, for instance, 0.999. Default is empty"/> </section> <section name="out_plots_opt" title="Plot Output Options" expanded="false"> <conditional name="which_Protein"> <param name="select" type="select" label="Select protein IDs to draw plots"> <option value="all" selected="true">generate all plots for each protein</option> <option value="allonly">Option for QC plot: "allonly" will generate one QC plot with all proteins</option> <option value="list">Protein IDs as tabular input</option> </param> <when value="all"/> <when value="allonly"/> <when value="list"> <param name="protein_list" type="data" format="tabular" label="List of proteins"/> </when> </conditional> <param name="width" type="integer" min="1" value="10" label="Width of the saved pdf file"/> <param name="height" type="integer" min="1" value="10" label="Height of the saved pdf file"/> <section name="adv" title="Advanced options" expanded="false"> <param name="ylimUp" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Upper limit for y-axis in the log scale" help="No (Default) for Profile Plot and QC Plot uses the upper limit as rounded off maximum of log2(intensities) after normalization + 3."/> <param name="ylimDown" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Lower limit for y-axis in the log scale" help="No (Default) for Profile Plot and QCPlot uses 0."/> <param name="x_axis_size" type="integer" min="1" value="10" label="Size of x-axis labeling"/> <param name="y_axis_size" type="integer" min="1" value="10" label="Size of y-axis labeling"/> <param name="text_size" type="integer" min="1" value="4" label="Size of labels represented each condition at the top"/> <param name="text_angle" type="integer" min="0" max="360" value="90" label="Angle of labels represented each condition at the top"/> <param name="legend_size" type="integer" min="1" value="7" label="Size of legend above Profile plot"/> <param name="dot_size_profile" type="integer" min="1" value="2" label="Size of dots in Profile plot"/> <param name="ncol_guide" type="integer" min="1" value="5" label="Number of columns for legends at the top of plot"/> <param name="originalPlot" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Draw original profile plots without normalization"/> <param name="summaryPlot" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Draw profile plots with protein summarization for each channel and MS run"/> </section> </section> <conditional name="group"> <param name="group_comparison" type="select" label="Compare Groups"> <option value="false">No</option> <option value="true">Yes</option> </param> <when value="false"/> <when value="true"> <conditional name="use_comp_matrix"> <param name="select" type="select" label="Use comparison matrix?"> <option value="false">No</option> <option value="true">Yes</option> </param> <when value="false"/> <when value="true"> <param name="comparison_matrix" type="data" format="tabular" label="Comparison Matrix"/> </when> </conditional> <param name="moderated" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="false" label="Moderate t statistic" help="No (default) uses ordinary t statistic"/> <param name="adj_method" type="select" label="Adjusted p value method for multiple comparison"> <option value="holm">holm</option> <option value="hochberg">hochberg</option> <option value="hommel">hommel</option> <option value="bonferroni">bonferroni</option> <option value="BH" selected="true">BH</option> <option value="BY">BY</option> <option value="fdr">fdr</option> <option value="none">none</option> </param> <param name="remove_norm_channel" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove ’Norm’ channels from protein level data"/> <param name="remove_empty_channel" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove ’Empty’ channels from protein level data"/> <param name="selected_group_outputs" type="select" multiple="true" label="Select outputs"> <help>Heatmap requires more than one comparison</help> <option value="comparison_result" selected="true">Group Comparison</option> <option value="VolcanoPlot" selected="true">MSstats Volcano Plot</option> <option value="Heatmap" selected="false">MSstats Heatmap</option> <option value="ComparisonPlot" selected="true">MSstats Comparison Plot</option> </param> <section name="comparison_plots_opt" title="Comparison Plot Options" expanded="false"> <param name="sig" type="float" min="0" max="1" value="0.05" label="FDR cutoff for the adjusted p-values in heatmap and volcano plot" help="Level of significance for comparison plot. 100(1-sig)% confidence interval will be drawn."/> <param name="FCcutoff" type="float" optional="true" label="Involve fold change cutoff or not for volcano plot or heatmap." help="Empty (default) means no fold change cutoff is applied for significance analysis. Specific value means specific fold change cutoff is applied"/> <param name="logBase_pvalue" type="select" label="For volcano plot or heatmap, logarithm transformation of adjusted p-valuewith base 2 or 10"> <option value="2">2</option> <option value="10" selected="true">10</option> </param> <param name="ylimUp" type="float" optional="true" label="For all three plots, upper limit for y-axis." help="Empty (default) for volcano plot/heatmap use maximum of -log2 (adjusted p-value) or -log10 (adjusted p-value), for comparison plot uses maximum of log-fold change + CI. Alternatively, insert specific value of y-axis limit. "/> <param name="ylimDown" type="float" optional="true" label="For all tree plots, lower limit for y-axis in the log scale" help="Empty (default) for volcano plot/heatmap use minimum of -log2 (adjusted p-value) or -log10 (adjusted p-value), for comparison plot uses minimum of log-fold change - CI. Alternatively, insert specific value of y-axis limit. "/> <param name="xlimUp" type="float" optional="true" label="For Volcano plot, the limit for x-axis" help="Empty (default) for use maximum for absolute value of log-fold change or 3 as default if maximum for absolute value of log-fold change is less than 3. Alternatively, insert specific value of y-axis limit."/> <param name="axis_size" type="integer" min="1" value="10" label="Size of axes labels for Residual and QQ Plots"/> <param name="x_axis_size" type="integer" min="1" value="10" label="Size of x-axis labeling"/> <param name="y_axis_size" type="integer" min="1" value="10" label="Size of y-axis labeling"/> <param name="dot_size" type="integer" min="1" value="3" label="Size of dots in residual plots, QQPlots, volcano plot and comparison plot."/> <param name="text_size" type="integer" min="1" value="4" label="Size of Protein Name label in the graph for Volcano Plot."/> <param name="text_angle" type="integer" min="0" max="360" value="90" label="Angle of x-axis labels represented each comparison at the bottom of graph incomparison plot."/> <param name="legend_size" type="integer" min="1" value="7" label="Size of legend for color at the bottom of volcano plot. "/> <param name="ProteinName" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Display protein names in Volcano Plot." help="Yes (default) means protein names, which are significant, are displayed next to the points. No means no protein names are displayed."/> <param name="colorkey" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Show colour key"/> <param name="numProtein" type="integer" min="1" value="100" max="180" label="Number of proteins which will be presented in each heatmap."/> <param name="clustering" type="select" label="Determines how to order proteins and comparisons. Hierarchical cluster analysis with Ward method(minimum variance) is performed."> <help>’protein’ means that protein dendrogram is computed and reordered based on protein means (the order of row is changed). ’comparison’ means comparison dendrogram is computed and reordered based on comparison means (the order of comparison is changed). ’both’ means to reorder both protein and comparison.</help> <option value="protein" selected="true">protein</option> <option value="comparison">comparison</option> <option value="both">both</option> </param> <param name="width" type="integer" min="1" value="8" label="Width of the saved pdf file"/> <param name="height" type="integer" min="1" value="5" label="Height of the saved pdf file"/> <conditional name="which_Protein"> <param name="select" type="select" label="Select protein IDs to draw plots"> <option value="all" selected="true">generate all plots for each protein</option> <option value="list">Protein IDs as tabular input</option> </param> <when value="all"/> <when value="list"> <param name="protein_list" type="data" format="tabular" label="List of proteins"/> </when> </conditional> <conditional name="which_Comparison"> <param name="select" type="select" label="Select comparisons to draw plots"> <option value="all" selected="true">Generate all plots for each comparison</option> <option value="list">Comparison names as tabular input</option> </param> <when value="all"/> <when value="list"> <param name="comparison_list" type="data" format="tabular" label="List of comparisons"/> </when> </conditional> </section> </when> </conditional> <param name="selected_outputs" type="select" multiple="true" optional="false" label="Select Outputs"> <option value="msstatstmt_conv_log" selected="false">MSstatsTMT converter log</option> <option value="msstatstmt_sum_log" selected="true">MSstatsTMT summarization log</option> <option value="msstatstmt_sum_ms" selected="true">MSstatsTMT summarization MSstats</option> <option value="msstatstmt_group_log" selected="false">MSstatsTMT groupComparison log</option> <option value="msstats_gc_log" selected="false">MSstats log (groupComparison)</option> <option value="r_script" selected="false">MSstats Rscript</option> <option value="quant" selected="true">Protein abundance</option> <option value="ProfilePlot" selected="false">Profile Plot</option> <option value="QCPlot" selected="false">QC Plot</option> </param> </inputs> <outputs> <data name="out_msstatstmt_conv_log" from_work_dir="MSstatsTMT_converter_log.log" format="txt" label="${tool.name} on ${on_string}: MSstatsTMT converter log"> <filter>'msstatstmt_conv_log' in selected_outputs</filter> </data> <data name="out_msstatstmt_sum_log" from_work_dir="MSstatsTMT_summarization_log.log" format="txt" label="${tool.name} on ${on_string}: MSstatsTMT summarization log"> <filter>'msstatstmt_sum_log' in selected_outputs</filter> </data> <data name="out_msstatstmt_sum_ms" from_work_dir="MSstatsTMT_summarization_MSstats.log" format="txt" label="${tool.name} on ${on_string}: MSstatsTMT summarization MSstats"> <filter>'msstatstmt_sum_ms' in selected_outputs</filter> </data> <data name="out_msstatstmt_group_log" from_work_dir="MSstatsTMT_log_groupComparison.log" format="txt" label="${tool.name} on ${on_string}: MSstatsTMT groupComparison log"> <filter>'msstatstmt_group_log' in selected_outputs</filter> </data> <data name="out_msstats_gc_log" from_work_dir="MSstats_log.log" format="txt" label="${tool.name} on ${on_string}: MSstats log (groupComparison)"> <filter>'msstats_gc_log' in selected_outputs</filter> </data> <data name="out_r_script" format="txt" label="${tool.name} on ${on_string}: Rscript"> <filter>'r_script' in selected_outputs</filter> </data> <data name="out_quant" from_work_dir="Quant.tsv" format="tabular" label="${tool.name} on ${on_string}: Protein abundance"> <filter>'quant' in selected_outputs</filter> </data> <data name="out_profile_plot" from_work_dir="ProfilePlot.pdf" format="pdf" label="${tool.name} on ${on_string}: Profile Plot"> <filter>'ProfilePlot' in selected_outputs</filter> </data> <data name="out_qc_plot" from_work_dir="QCPlot.pdf" format="pdf" label="${tool.name} on ${on_string}: QC Plot"> <filter>'QCPlot' in selected_outputs</filter> </data> <data name="out_group_comp" from_work_dir="ComparisonResult.tsv" format="tabular" label="${tool.name} on ${on_string}: Group Comparison"> <filter>group['group_comparison'] == 'true' and 'comparison_result' in group['selected_group_outputs']</filter> </data> <data name="out_group_volcano_plot" from_work_dir="MSstats_group_VolcanoPlot.pdf" format="pdf" label="${tool.name} on ${on_string}: Group Comparison - Volcano Plot"> <filter>group['group_comparison'] == 'true' and 'VolcanoPlot' in group['selected_group_outputs']</filter> </data> <data name="out_group_heatmap" from_work_dir="MSstats_group_Heatmap.pdf" format="pdf" label="${tool.name} on ${on_string}: Group Comparison - Heatmap"> <filter>group['group_comparison'] == 'true' and 'Heatmap' in group['selected_group_outputs']</filter> </data> <data name="out_group_comp_plot" from_work_dir="MSstats_group_ComparisonPlot.pdf" format="pdf" label="${tool.name} on ${on_string}: Group Comparison - Comparison Plot"> <filter>group['group_comparison'] == 'true' and 'ComparisonPlot' in group['selected_group_outputs']</filter> </data> </outputs> <tests> <test expect_num_outputs="6"> <conditional name="input"> <param name="input_src" value="MSstatsTMT"/> <param name="msstatstmt_input" ftype="tabular" value="input.msstatstmt.txt"/> </conditional> <param name="selected_outputs" value="msstatstmt_conv_log,msstatstmt_sum_ms,msstatstmt_sum_log,r_script,ProfilePlot,QCPlot"/> <output name="out_msstatstmt_sum_ms"> <assert_contents> <has_text text="MSstats - dataProcess function" /> </assert_contents> </output> <output name="out_msstatstmt_sum_log"> <assert_contents> <has_text text="MSstatsTMT - proteinSummarization function" /> </assert_contents> </output> <output name="out_r_script"> <assert_contents> <has_n_lines n="50" /> </assert_contents> </output> <output name="out_profile_plot" file="ProfilePlot.pdf" compare="sim_size"/> <output name="out_qc_plot" file="QCPlot.pdf" compare="sim_size"/> </test> <test expect_num_outputs="6"> <conditional name="input"> <param name="input_src" value="MaxQuant"/> <param name="evidence" ftype="tabular" value="evidence.txt"/> <param name="annotation" ftype="tabular" value="annotation.txt"/> <param name="proteinGroups" ftype="tabular" value="proteinGroups.txt"/> </conditional> <conditional name="group"> <param name="group_comparison" value="true"/> <conditional name="use_comp_matrix"> <param name="select" value="true"/> <param name="comparison_matrix" ftype="tabular" value="comparison_matrix.txt"/> </conditional> <param name="selected_group_outputs" value="comparison_result,VolcanoPlot,ComparisonPlot"/> </conditional> <param name="selected_outputs" value="ProfilePlot,msstatstmt_group_log,msstats_gc_log"/> <conditional name="which_Protein"> <param name="select" value="list"/> <param name="protein_list" ftype="tabular" value="proteinIDs.txt"/> </conditional> <output name="out_group_comp"> <assert_contents> <has_n_lines n="21" /> <has_n_columns n="8" /> <has_text text="A0AVT1" /> <has_text text="A0AVT1" /> <has_text text="O43324" /> </assert_contents> </output> <output name="out_profile_plot" file="ProfilePlot_list.pdf" compare="sim_size"/> <output name="out_group_volcano_plot" file="MSstats_group_VolcanoPlot.pdf" compare="sim_size"/> <output name="out_group_comp_plot" file="MSstats_group_ComparisonPlot.pdf" compare="sim_size"/> </test> <test expect_num_outputs="3"> <conditional name="input"> <param name="input_src" value="OpenMS"/> <param name="oms_input" ftype="tabular" value="input.oms.txt"/> </conditional> <conditional name="group"> <param name="group_comparison" value="true"/> <param name="selected_group_outputs" value="comparison_result,Heatmap"/> </conditional> <param name="selected_outputs" value="r_script"/> <output name="out_r_script"> <assert_contents> <has_n_lines n="61" /> </assert_contents> </output> <output name="out_group_comp"> <assert_contents> <has_n_lines n="51" /> <has_n_columns n="8" /> <has_text text="Long_LF vs Short_HF" /> <has_text text="sp|O35226|PSMD4_MOUSE" /> </assert_contents> </output> <output name="out_group_heatmap" file="MSstats_group_Heatmap.pdf" compare="sim_size"/> </test> <test expect_num_outputs="1"> <conditional name="input"> <param name="input_src" value="PD"/> <param name="PSM" ftype="tabular" value="input.pd.txt"/> <param name="annotation" ftype="tabular" value="annotation.pd.txt"/> </conditional> <param name="selected_outputs" value="quant"/> <output name="out_quant"> <assert_contents> <has_n_lines n="1575" /> <has_n_columns n="8" /> <has_text text="PAMI-176_Mouse_A-J_1" /> <has_text text="Long_LF" /> </assert_contents> </output> </test> <test expect_num_outputs="1"> <conditional name="input"> <param name="input_src" value="MaxQuant"/> <param name="evidence" ftype="tabular" value="evidence.txt"/> <param name="annotation" ftype="tabular" value="annotation.txt"/> <param name="proteinGroups" ftype="tabular" value="proteinGroups.txt"/> </conditional> <param name="selected_outputs" value="ProfilePlot"/> <conditional name="which_Protein"> <param name="select" value="allonly"/> </conditional> <output name="out_profile_plot" file="ProfilePlot_allonly.pdf" compare="sim_size"/> </test> </tests> <help><![CDATA[ MSstatsTMT is an R-based package for detecting differentially abundant proteins in shotgun mass spectrometry-based proteomic experiments with tandem mass tag (TMT) labeling. It is applicable to isobaric labeling quantitative proteomics, including iTRAQ and TMT data. MSstatsTMT provides functionalities for two types of analysis: 1) Protein summarization based on peptide quantification data and visualization; 2) Model-based group comparison to detect significant changes in abundance. **Notes** - MSstatsTMT 11 column format: For TMT datasets an additional 'Channel' column is required, which has to be in the format 'channel.X' with X being the channel number.. :: #> ProteinName PeptideSequence #> 1 sp|Q60854|SPB6_MOUSE .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR #> 2 sp|Q60854|SPB6_MOUSE .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR #> 3 sp|Q60854|SPB6_MOUSE .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR #> 4 sp|Q60854|SPB6_MOUSE .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR #> 5 sp|Q60854|SPB6_MOUSE .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR #> 6 sp|Q60854|SPB6_MOUSE .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR #> Charge PSM Mixture #> 1 3 .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR_3 3 #> 2 3 .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR_3 3 #> 3 3 .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR_3 3 #> 4 3 .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR_3 3 #> 5 3 .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR_3 3 #> 6 3 .(TMT6plex)AFVEVNEEGTEAAAATAGMM(Oxidation)TVR_3 3 #> TechRepMixture Run Channel BioReplicate Condition Intensity #> 1 3_3 3_3_3 channel.1 21 Long_HF NA #> 2 3_3 3_3_3 channel.2 22 Norm 1068.580 #> 3 3_3 3_3_3 channel.3 23 Long_M 1508.330 #> 4 3_3 3_3_3 channel.4 24 Long_HF NA #> 5 3_3 3_3_3 channel.5 25 Long_LF 1580.951 #> 6 3_3 3_3_3 channel.6 26 Long_HF 1820.072 For more information please visit the `MSstatsConvert documentation <https://bioconductor.org/packages/devel/bioc/vignettes/MSstatsConvert/inst/doc/msstats_data_format.html>`_ - Comparison matrix as tabular file - 1st column: name of comparison - additionally one column for each condition that is present in the tabular file. Use 1 and -1 to indicate the conditions to compare and 0 for conditions that are not compared. Multiple groups can be combined by using 0.5. - first row contains the names of the groups, they must exactly match the condition name used in the annotation file - each additional row represents one comparison - Example for a two group comparison :: names groupA groupB groupA-groupB 1 -1 - Example for an experiment with 5 groups and 4 different comparisons :: names G1 G2 G3 G4 G5 G2-G1 -1 1 0 0 0 G4-G5 0 0 0 1 -1 G3-G5 0 0 -1 0 1 G1+G2-G5 0.5 0.5 0 0 -1 For additional help please visit the `MSstatsTMT documentation <https://msstats.org/msstatstmt/>`_ ]]> </help> <citations> <citation type="doi">10.1074/mcp.ra120.002105</citation> <citation type="doi">10.1021/acs.jproteome.2c00051</citation> </citations> </tool>