| Previous changeset 12:4deacfee76ef (2022-03-15) Next changeset 14:6679616d0c18 (2022-03-22) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 040e4945da00a279cb60daae799fce9489f99c50" |
|
modified:
macros.xml mqppep_anova.R mqppep_anova.xml mqppep_anova_script.Rmd |
|
added:
workflow/ppenrich_suite_wf.ga |
| b |
| diff -r 4deacfee76ef -r b41a077af3aa macros.xml --- a/macros.xml Tue Mar 15 18:17:55 2022 +0000 +++ b/macros.xml Tue Mar 22 20:47:40 2022 +0000 |
| b |
| @@ -1,5 +1,5 @@ <macros> - <token name="@TOOL_VERSION@">0.1.3</token> + <token name="@TOOL_VERSION@">0.1.4</token> <token name="@VERSION_SUFFIX@">0</token> <xml name="requirements"> <requirements> |
| b |
| diff -r 4deacfee76ef -r b41a077af3aa mqppep_anova.R --- a/mqppep_anova.R Tue Mar 15 18:17:55 2022 +0000 +++ b/mqppep_anova.R Tue Mar 22 20:47:40 2022 +0000 |
| [ |
| b'@@ -1,207 +1,243 @@\n-#!/usr/bin/env Rscript\r\n-# libraries\r\n-library(optparse)\r\n-library(data.table)\r\n-library(stringr)\r\n-# bioconductor-preprocesscore\r\n-# - libopenblas\r\n-# - r-data.table\r\n-# - r-rmarkdown\r\n-# - r-ggplot2\r\n-# - texlive-core\r\n-\r\n-# ref for parameterizing Rmd document: https://stackoverflow.com/a/37940285\r\n-\r\n-# parse options\r\n-option_list <- list(\r\n- make_option(\r\n- c("-i", "--inputFile"),\r\n- action = "store",\r\n- default = NA,\r\n- type = "character",\r\n- help = "Phosphopeptide Intensities sparse input file path"\r\n- ),\r\n- make_option(\r\n- c("-a", "--alphaFile"),\r\n- action = "store",\r\n- default = NA,\r\n- type = "character",\r\n- help = paste0("List of alpha cutoff values for significance testing;",\r\n- " path to text file having one column and no header")\r\n- ),\r\n- make_option(\r\n- c("-f", "--firstDataColumn"),\r\n- action = "store",\r\n- default = "10",\r\n- type = "character",\r\n- help = "First column of intensity values"\r\n- ),\r\n- make_option(\r\n- c("-m", "--imputationMethod"),\r\n- action = "store",\r\n- default = "group-median",\r\n- type = "character",\r\n- help = paste0("Method for missing-value imputation,",\r\n- " one of c(\'group-median\',\'median\',\'mean\',\'random\')")\r\n- ),\r\n- make_option(\r\n- c("-p", "--meanPercentile"),\r\n- action = "store",\r\n- default = 3,\r\n- type = "integer",\r\n- help = paste0("Mean percentile for randomly generated imputed values;",\r\n- ", range [1,99]")\r\n- ),\r\n- make_option(\r\n- c("-d", "--sdPercentile"),\r\n- action = "store",\r\n- default = 3,\r\n- type = "double",\r\n- help = paste0("Adjustment value for standard deviation of",\r\n- " randomly generated imputed values; real")\r\n- ),\r\n- make_option(\r\n- c("-s", "--regexSampleNames"),\r\n- action = "store",\r\n- default = "\\\\.(\\\\d+)[A-Z]$",\r\n- type = "character",\r\n- help = "Regular expression extracting sample-names"\r\n- ),\r\n- make_option(\r\n- c("-g", "--regexSampleGrouping"),\r\n- action = "store",\r\n- default = "(\\\\d+)",\r\n- type = "character",\r\n- help = paste0("Regular expression extracting sample-group",\r\n- " from an extracted sample-name")\r\n- ),\r\n- make_option(\r\n- c("-o", "--imputedDataFile"),\r\n- action = "store",\r\n- default = "output_imputed.tsv",\r\n- type = "character",\r\n- help = "Imputed Phosphopeptide Intensities output file path"\r\n- ),\r\n- make_option(\r\n- c("-r", "--reportFile"),\r\n- action = "store",\r\n- default = "QuantDataProcessingScript.html",\r\n- type = "character",\r\n- help = "HTML report file path"\r\n- )\r\n-)\r\n-args <- parse_args(OptionParser(option_list = option_list))\r\n-\r\n-# Check parameter values\r\n-\r\n-if (! file.exists(args$inputFile)) {\r\n- stop((paste("Input file", args$inputFile, "does not exist")))\r\n-}\r\n-input_file <- args$inputFile\r\n-alpha_file <- args$alphaFile\r\n-first_data_column <- args$firstDataColumn\r\n-imputation_method <- args$imputationMethod\r\n-mean_percentile <- args$meanPercentile\r\n-sd_percentile <- args$sdPercentile\r\n-\r\n-regex_sample_names <- gsub("^[ \\t\\n]*", "",\r\n- readChar(args$regexSampleNames, 1000)\r\n- )\r\n-regex_sample_names <- gsub("[ \\t\\n]*$", "",\r\n- regex_sample_names\r\n- )\r\n-cat(regex_sample_names)\r\n-cat("\\n")\r\n-\r\n-regex_sample_grouping <- gsub("^[ \\t\\n]*", "",\r\n- readChar(args$regexSampleGrouping, 1000)\r\n- )\r\n-regex_sample_grouping <- gsub("[ \\t\\n]*$", "",\r\n- regex_sample_grouping\r\n- )\r\n-cat(regex_sample_grouping)\r\n-cat("\\n")\r\n-\r\n-imputed_data_file_name <- args$imputedDataFile\r\n-report_file_name <- args$reportFile\r\n-\r\n-print("args is:")\r\n-cat(str(args))\r\n-\r\n-print("regex_sample_names is:")\r\n-cat(str(regex_sample_names))\r\n-\r\n-print("regex_sample_grouping is:")\r\n-cat(str(regex_sample_grouping))\r\n-\r\n-# from: https://github.co'..b'rgs$alphaFile\n+first_data_column <- args$firstDataColumn\n+imputation_method <- args$imputationMethod\n+print(\n+ grepl(\n+ pattern = imputation_method,\n+ x = c("group-median", "median", "mean", "random")\n+ )\n+ )\n+\n+if (\n+ sum(\n+ grepl(\n+ pattern = imputation_method,\n+ x = c("group-median", "median", "mean", "random")\n+ )\n+ ) < 1\n+ ) {\n+ print(sprintf("bad imputationMethod argument: %s", imputation_method))\n+ return(-1)\n+ }\n+\n+mean_percentile <- args$meanPercentile\n+print("mean_percentile is:")\n+cat(str(mean_percentile))\n+\n+sd_percentile <- args$sdPercentile\n+print("sd_percentile is:")\n+cat(str(mean_percentile))\n+\n+\n+regex_sample_names <- gsub("^[ \\t\\n]*", "",\n+ readChar(args$regexSampleNames, 1000)\n+ )\n+regex_sample_names <- gsub("[ \\t\\n]*$", "",\n+ regex_sample_names\n+ )\n+cat(regex_sample_names)\n+cat("\\n")\n+\n+regex_sample_grouping <- gsub("^[ \\t\\n]*", "",\n+ readChar(args$regexSampleGrouping, 1000)\n+ )\n+regex_sample_grouping <- gsub("[ \\t\\n]*$", "",\n+ regex_sample_grouping\n+ )\n+cat(regex_sample_grouping)\n+cat("\\n")\n+\n+imputed_data_file_name <- args$imputedDataFile\n+imp_qn_lt_data_filenm <- args$imputedQNLTDataFile\n+report_file_name <- args$reportFile\n+\n+print("regex_sample_names is:")\n+cat(str(regex_sample_names))\n+\n+print("regex_sample_grouping is:")\n+cat(str(regex_sample_grouping))\n+\n+# from: https://github.com/molgenis/molgenis-pipelines/wiki/\n+# How-to-source-another_file.R-from-within-your-R-script\n+# Function location_of_this_script returns the location of this .R script\n+# (may be needed to source other files in same dir)\n+location_of_this_script <- function() {\n+ this_file <- NULL\n+ # This file may be \'sourced\'\n+ for (i in - (1:sys.nframe())) {\n+ if (identical(sys.function(i), base::source)) {\n+ this_file <- (normalizePath(sys.frame(i)$ofile))\n+ }\n+ }\n+\n+ if (!is.null(this_file)) return(dirname(this_file))\n+\n+ # But it may also be called from the command line\n+ cmd_args <- commandArgs(trailingOnly = FALSE)\n+ cmd_args_trailing <- commandArgs(trailingOnly = TRUE)\n+ cmd_args <- cmd_args[\n+ seq.int(\n+ from = 1,\n+ length.out = length(cmd_args) - length(cmd_args_trailing)\n+ )\n+ ]\n+ res <- gsub("^(?:--file=(.*)|.*)$", "\\\\1", cmd_args)\n+\n+ # If multiple --file arguments are given, R uses the last one\n+ res <- tail(res[res != ""], 1)\n+ if (0 < length(res)) return(dirname(res))\n+\n+ # Both are not the case. Maybe we are in an R GUI?\n+ return(NULL)\n+}\n+\n+script_dir <- location_of_this_script()\n+\n+rmarkdown_params <- list(\n+ inputFile = input_file\n+ , alphaFile = alpha_file\n+ , firstDataColumn = first_data_column\n+ , imputationMethod = imputation_method\n+ , meanPercentile = mean_percentile\n+ , sdPercentile = sd_percentile\n+ , regexSampleNames = regex_sample_names\n+ , regexSampleGrouping = regex_sample_grouping\n+ , imputedDataFilename = imputed_data_file_name\n+ , imputedQNLTDataFile = imp_qn_lt_data_filenm\n+ )\n+\n+print("rmarkdown_params")\n+str(rmarkdown_params)\n+\n+# freeze the random number generator so the same results will be produced\n+# from run to run\n+set.seed(28571)\n+\n+# BUG (or "opportunity")\n+# To render as PDF for the time being requires installing the conda\n+# package `r-texlive` until this issue in `texlive-core` is resolved:\n+# https://github.com/conda-forge/texlive-core-feedstock/issues/19\n+# This workaround is detailed in the fourth comment of:\n+# https://github.com/conda-forge/texlive-core-feedstock/issues/61\n+\n+library(tinytex)\n+tinytex::install_tinytex()\n+rmarkdown::render(\n+ input = paste(script_dir, "mqppep_anova_script.Rmd", sep = "/")\n+, output_format = rmarkdown::pdf_document(toc = TRUE)\n+, output_file = report_file_name\n+, params = rmarkdown_params\n+)\n' |
| b |
| diff -r 4deacfee76ef -r b41a077af3aa mqppep_anova.xml --- a/mqppep_anova.xml Tue Mar 15 18:17:55 2022 +0000 +++ b/mqppep_anova.xml Tue Mar 22 20:47:40 2022 +0000 |
| [ |
| @@ -19,21 +19,24 @@ cd \$TEMP; cp '$__tool_directory__/mqppep_anova_script.Rmd' . || exit 0; cp '$__tool_directory__/mqppep_anova.R' . || exit 0; - \${CONDA_PREFIX}/bin/Rscript \$TEMP/mqppep_anova.R - --inputFile '$input_file' - --alphaFile $alpha_file - --firstDataColumn $first_data_column - --imputationMethod $imputation.imputation_method - #if '$imputation_method' == 'random': - --meanPercentile '$meanPercentile' - --sdPercentile '$sdPercentile' - #end if - --regexSampleNames $sample_names_regex_f - --regexSampleGrouping $sample_grouping_regex_f - --imputedDataFile $imputed_data_file - --reportFile $report_file; + \${CONDA_PREFIX}/bin/Rscript \$TEMP/mqppep_anova.R + --inputFile '$input_file' + --alphaFile '$alpha_file' + --firstDataColumn $first_data_column + --imputationMethod $imputation.imputation_method + #if $imputation.imputation_method == "random" + --meanPercentile '$imputation.meanPercentile' + --sdPercentile '$imputation.sdPercentile' + #end if + --regexSampleNames $sample_names_regex_f + --regexSampleGrouping $sample_grouping_regex_f + --imputedDataFile $imputed_data_file + --imputedQNLTDataFile '$imp_qn_lt_file' + --reportFile '$report_file'; + export RESULT=\$?; cd \${OLD_PWD}; - rm -rf \$HOME + rm -rf \$HOME; + exit \${RESULT} ]]></command> <configfiles> <configfile name="sample_names_regex_f"> @@ -98,7 +101,8 @@ </param> </inputs> <outputs> - <data name="imputed_data_file" format="tabular" label="${input_file.name}.${imputation.imputation_method}-imputed_QN_LT_intensities" ></data> + <data name="imputed_data_file" format="tabular" label="${input_file.name}.${imputation.imputation_method}-imputed_intensities" ></data> + <data name="imp_qn_lt_file" format="tabular" label="${input_file.name}.${imputation.imputation_method}-imputed_QN_LT_intensities" ></data> <!-- <data name="report_file" format="html" label="${input_file.name}.${imputation.imputation_method}-imputed_report (download/unzip to view)" ></data> --> @@ -112,7 +116,7 @@ <param name="imputation_method" value="group-median"/> <param name="sample_names_regex" value="\.\d+[A-Z]$"/> <param name="sample_grouping_regex" value="\d+"/> - <output name="imputed_data_file"> + <output name="imp_qn_lt_file"> <assert_contents> <has_text text="Phosphopeptide" /> <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" /> @@ -130,11 +134,11 @@ <param name="sdPercentile" value="0.2" /> <param name="sample_names_regex" value="\.\d+[A-Z]$"/> <param name="sample_grouping_regex" value="\d+"/> - <output name="imputed_data_file"> + <output name="imp_qn_lt_file"> <assert_contents> <has_text text="Phosphopeptide" /> <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" /> - <has_text text="0.82258" /> + <has_text text="8.392287" /> <has_text text="pSQKQEEENPAEETGEEK" /> </assert_contents> </output> @@ -192,11 +196,14 @@ **Outputs** -``intensities_*-imputed_QN_LT`` +``imputed_intensities`` + Phosphopeptide MS intensities where missing values have been **imputed** by the chosen method, in tabular format. + +``imputed_QN_LT_intensities`` Phosphopeptide MS intensities where missing values have been **imputed** by the chosen method, quantile-normalized (**QN**), and log10-transformed (**LT**), in tabular format. ``report_file`` - Summary report for normalization, imputation, and ANOVA, in PDF format. + Summary report for normalization, imputation, and **ANOVA**, in PDF format. **Authors** |
| b |
| diff -r 4deacfee76ef -r b41a077af3aa mqppep_anova_script.Rmd --- a/mqppep_anova_script.Rmd Tue Mar 15 18:17:55 2022 +0000 +++ b/mqppep_anova_script.Rmd Tue Mar 22 20:47:40 2022 +0000 |
| [ |
| b'@@ -1,24 +1,50 @@\n ---\n title: "MaxQuant Phospho-Proteomic Enrichment Pipeline ANOVA"\n author: "Larry Cheng; Art Eschenlauer"\n-date: "May 28, 2018; Nov 16, 2021"\n+date: "May 28, 2018; Mar 16, 2022"\n output:\n- pdf_document: default\n+ pdf_document:\n+ toc: true\n+ latex_document:\n+ toc: true\n params:\n inputFile: "test-data/test_input_for_anova.tabular"\n alphaFile: "test-data/alpha_levels.tabular"\n firstDataColumn: "Intensity"\n imputationMethod: !r c("group-median", "median", "mean", "random")[1]\n meanPercentile: 1\n- sdPercentile: 0.2\n+ sdPercentile: 1.0\n regexSampleNames: "\\\\.\\\\d+[A-Z]$"\n regexSampleGrouping: "\\\\d+"\n- imputedDataFilename: "Upstream_Map_pST_outputfile_STEP4_QN_LT.txt"\n+ imputedDataFilename: "test-data/imputedDataFilename.txt"\n+ imputedQNLTDataFile: "test-data/imputedQNLTDataFile.txt"\n+ show_toc: true\n ---\n+<!--\n+ latex_document: default\n+ inputFile: "test-data/test_input_for_anova.tabular"\n+ inputFile: "test-data/density_failure.preproc_tab.tabular"\n+ inputFile: "test-data/UT_Phospho_STY_Sites.preproc_tab"\n+date: "May 28, 2018; Mar 16, 2022"\n+-->\n ```{r setup, include = FALSE}\n # ref for parameterizing Rmd document: https://stackoverflow.com/a/37940285\n knitr::opts_chunk$set(echo = FALSE, fig.dim = c(9, 10))\n \n+# freeze the random number generator so the same results will be produced\n+# from run to run\n+set.seed(28571)\n+\n+### CONSTANTS\n+\n+const_parfin <- par("fin")\n+const_boxplot_fill <- "grey94"\n+const_stripchart_cex <- 0.5\n+const_stripsmall_cex <-\n+ sqrt(const_stripchart_cex * const_stripchart_cex / 2)\n+const_stripchart_jitter <- 0.3\n+const_write_debug_files <- FALSE\n+\n ### FUNCTIONS\n \n #ANOVA filter function\n@@ -27,9 +53,155 @@\n pvalue <- summary(x_aov)[[1]][["Pr(>F)"]][1]\n pvalue\n }\n+\n+write_debug_file <- function(s) {\n+ if (const_write_debug_files) {\n+ s_path <- sprintf("test-data/%s.txt", deparse(substitute(s)))\n+ write.table(\n+ s,\n+ file = s_path,\n+ sep = "\\t",\n+ col.names = TRUE,\n+ row.names = TRUE,\n+ quote = FALSE\n+ )\n+ }\n+}\n+\n+latex_collapsed_vector <- function(collapse_string, v) {\n+ cat(\n+ paste0(\n+ gsub("_", "\\\\\\\\_", v),\n+ collapse = collapse_string\n+ )\n+ )\n+}\n+\n+latex_itemized_collapsed <- function(collapse_string, v) {\n+ cat("\\\\begin{itemize}\\n\\\\item ")\n+ latex_collapsed_vector(collapse_string, v)\n+ cat("\\n\\\\end{itemize}\\n")\n+}\n+\n+latex_itemized_list <- function(v) {\n+ latex_itemized_collapsed("\\n\\\\item ", v)\n+}\n+\n+latex_enumerated_collapsed <- function(collapse_string, v) {\n+ cat("\\\\begin{enumerate}\\n\\\\item ")\n+ latex_collapsed_vector(collapse_string, v)\n+ cat("\\n\\\\end{enumerate}\\n")\n+}\n+\n+latex_enumerated_list <- function(v) {\n+ latex_enumerated_collapsed("\\n\\\\item ", v)\n+}\n+\n+latex_table_row <- function(v) {\n+ latex_collapsed_vector(" & ", v)\n+ cat(" \\\\\\\\\\n")\n+}\n+\n+# Use this like print.data.frame, from which it is adapted:\n+print_data_frame_latex <-\n+ function(\n+ x,\n+ ...,\n+ # digits to pass to format.data.frame\n+ digits = NULL,\n+ # TRUE -> right-justify columns; FALSE -> left-justify\n+ right = TRUE,\n+ # maximumn number of rows to print\n+ max = NULL,\n+ # string with justification of each column\n+ justification = NULL,\n+ # TRUE to center on page\n+ centered = FALSE,\n+ # optional capttion\n+ caption = NULL,\n+ # h(inline); b(bottom); t (top) or p (separate page)\n+ anchor = "h"\n+ ) {\n+ if (is.null(justification))\n+ justification <-\n+ Reduce(\n+ f = paste,\n+ x = rep_len(if (right) "r" else "l", length(colnames(x)))\n+ )\n+ n <- length(rownames(x))\n+ if (length(x) == 0L) {\n+ cat(\n+ sprintf(\n+ # if n is one, use singular \'row\', else use plural \'rows\'\n+ ngettext(\n+ n,\n+ "data frame with 0 columns and %d row",\n+ "data frame with 0 columns and %d rows"\n+ ),\n+ n\n+ ),\n+ "\\n",\n+ sep = ""\n+ )\n+ '..b',\n main = "Imputed, normalized intensities", # no line plot\n- las = 2,\n+ las = 1,\n+ col = const_boxplot_fill,\n ylab = expression(log[10](intensity))\n )\n+ # Points\n+ stripchart(\n+ filtered_data_filtered, # Data\n+ method = "jitter", # Random noise\n+ jitter = const_stripchart_jitter,\n+ pch = 19, # Pch symbols\n+ cex = const_stripchart_cex, # Size of symbols reduced\n+ col = "goldenrod", # Color of the symbol\n+ vertical = TRUE, # Vertical mode\n+ add = TRUE # Add it over\n+ )\n+ par(old_par)\n } else {\n cat(sprintf(\n- "No peptides were found to have cutoff adjusted p-value < %0.2f\\n",\n+ "%s < %0.2f\\n\\n\\n\\n\\n",\n+ "No peptides were found to have cutoff adjusted p-value <",\n cutoff\n ))\n }\n- par(old_par)\n \n if (nrow(filtered_data_filtered) > 0) {\n #Add Phosphopeptide column to anova_filtered table\n anova_filtered_merge <- merge(\n- x = connect_df\n- ,\n- y = filtered_data_filtered\n- ,\n- by.x = "Intensity"\n- ,\n+ x = connect_df,\n+ y = filtered_data_filtered,\n+ by.x = "Intensity",\n by.y = 1\n )\n anova_filtered_merge_order <- rownames(filtered_p)\n@@ -759,12 +1181,9 @@\n # Merge qualitative columns into the ANOVA data\n output_table <- data.frame(anova_filtered$Phosphopeptide)\n output_table <- merge(\n- x = output_table\n- ,\n- y = data_table_imp_qn_lt\n- ,\n- by.x = "anova_filtered.Phosphopeptide"\n- ,\n+ x = output_table,\n+ y = data_table_imp_qn_lt,\n+ by.x = "anova_filtered.Phosphopeptide",\n by.y = "Phosphopeptide"\n )\n \n@@ -777,7 +1196,7 @@\n nrow = nrow(m)\n )\n )\n- m <- m[!m_nan_rows, ]\n+ m <- m[!m_nan_rows, , drop = FALSE]\n if (nrow(m) > 0) {\n rownames_m <- rownames(m)\n rownames(m) <- sapply(\n@@ -791,11 +1210,15 @@\n )\n }\n )\n- margins <-\n- c(max(nchar(colnames(m))) * 10 / 16 # col\n- , max(nchar(rownames(m))) * 5 / 16 # row\n- )\n how_many_peptides <- min(50, nrow(m))\n+ number_of_peptides_found <- how_many_peptides\n+ if (nrow(m) > 1) {\n+ m_margin <- m[how_many_peptides:1, ]\n+ margins <-\n+ c(max(nchar(colnames(m_margin))) * 10 / 16 # col\n+ , max(nchar(rownames(m_margin))) * 5 / 16 # row\n+ )\n+ }\n \n cat("\\\\newpage\\n")\n if (nrow(m) > 50) {\n@@ -805,16 +1228,19 @@\n cutoff)\n )\n } else {\n- cat("Heatmap for peptides whose",\n- sprintf("adjusted p-value < %0.2f\\n",\n- cutoff)\n- )\n+ if (nrow(m) == 1) {\n+ cat(\n+ sprintf("Heatmap for %d usable peptides whose", nrow(m)),\n+ sprintf("adjusted p-value < %0.2f\\n", cutoff)\n+ )\n+ next\n+ }\n }\n- cat("\\\\newline\\n")\n- cat("\\\\newline\\n")\n- op <- par("cex.main")\n+ cat("\\n\\n\\n")\n+ cat("\\n\\n\\n")\n try(\n if (nrow(m) > 1) {\n+ old_oma <- par("oma")\n par(cex.main = 0.6)\n heatmap(\n m[how_many_peptides:1, ],\n@@ -823,19 +1249,19 @@\n cexRow = 0.7,\n cexCol = 0.8,\n scale = "row",\n- #ACE scale = "none",\n margins = margins,\n main =\n- "Heatmap of unimputed, unnormalized intensities",\n- xlab = ""\n+ "Unimputed, unnormalized intensities",\n+ xlab = "",\n+ las = 1 #, fin = c(9, 5.5)\n )\n }\n )\n- par(op)\n }\n }\n }\n }\n+cat("\\\\leavevmode\\n\\n\\n")\n ```\n \n <!--\n' |
| b |
| diff -r 4deacfee76ef -r b41a077af3aa workflow/ppenrich_suite_wf.ga --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/workflow/ppenrich_suite_wf.ga Tue Mar 22 20:47:40 2022 +0000 |
| [ |
| b'@@ -0,0 +1,652 @@\n+{\n+ "a_galaxy_workflow": "true",\n+ "annotation": "phoshpoproteomic enrichment data pre-processing and ANOVA",\n+ "creator": [\n+ {\n+ "class": "Person",\n+ "identifier": "0000-0002-2882-0508",\n+ "name": "Art Eschenlauer"\n+ }\n+ ],\n+ "format-version": "0.1",\n+ "license": "MIT",\n+ "name": "ppenrich_suite_wf",\n+ "steps": {\n+ "0": {\n+ "annotation": "The Phospho (STY)Sites.txt file produced by MaxQuant (found in the txt folder).",\n+ "content_id": null,\n+ "errors": null,\n+ "id": 0,\n+ "input_connections": {},\n+ "inputs": [\n+ {\n+ "description": "The Phospho (STY)Sites.txt file produced by MaxQuant (found in the txt folder).",\n+ "name": "Phospho (STY)Sites.txt"\n+ }\n+ ],\n+ "label": "Phospho (STY)Sites.txt",\n+ "name": "Input dataset",\n+ "outputs": [],\n+ "position": {\n+ "bottom": 346.3999938964844,\n+ "height": 81.89999389648438,\n+ "left": 495,\n+ "right": 695,\n+ "top": 264.5,\n+ "width": 200,\n+ "x": 495,\n+ "y": 264.5\n+ },\n+ "tool_id": null,\n+ "tool_state": "{\\"optional\\": false, \\"format\\": [\\"tabular\\"]}",\n+ "tool_version": null,\n+ "type": "data_input",\n+ "uuid": "21c3c29d-9e8c-4ece-b585-9e68fed7a93f",\n+ "workflow_outputs": []\n+ },\n+ "1": {\n+ "annotation": "FASTA file of all human canonical isoforms, derived from Swiss-Prot (e.g., merge of https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot_varsplic.fasta.gz and https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz)",\n+ "content_id": null,\n+ "errors": null,\n+ "id": 1,\n+ "input_connections": {},\n+ "inputs": [\n+ {\n+ "description": "FASTA file of all human canonical isoforms, derived from Swiss-Prot (e.g., merge of https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot_varsplic.fasta.gz and https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz)",\n+ "name": "SwissProt_Human_Canonical_Isoform.fasta"\n+ }\n+ ],\n+ "label": "SwissProt_Human_Canonical_Isoform.fasta",\n+ "name": "Input dataset",\n+ "outputs": [],\n+ "position": {\n+ "bottom": 708.8000030517578,\n+ "height": 102.30000305175781,\n+ "left": 685,\n+ "right": 885,\n+ "top": 606.5,\n+ "width": 200,\n+ "x": 685,\n+ "y": 606.5\n+ },\n+ "tool_id": null,\n+ "tool_state": "{\\"optional\\": false, \\"format\\": [\\"fasta\\"]}",\n+ "tool_version": null,\n+ "type": "data_input",\n+ "uuid": "5da7317c-4def-48f3-8eac-af95bd18b290",\n+ "workflow_outputs": []\n+ },\n+ "2": {\n+ "annotation": "Derived from https://networkin.info/download/networkin_human_predictions_3.1.tsv.xz (which is free for non-commercial use - for required citation, see https://networkin.info/)",\n+ "content_id": null,\n+ "errors": null,\n+ "id": 2,\n+ "input_connections": {},\n+ "inputs": [\n+ {\n+ "description": "Derived from https://networkin.info/download/networkin_human_predictions_3.1.tsv.xz (which is free for non-commercial use - for required citation, see https://networkin.info/)",\n+ "name": "NetworKIN_cutoffscore2.0.tab'..b'_regex\\": \\"\\\\\\\\.(\\\\\\\\d+)[A-Z]$\\", \\"__page__\\": null, \\"__rerun_remap_job_id__\\": null}",\n+ "tool_version": null,\n+ "type": "tool",\n+ "uuid": "ffa771c3-c52d-42a4-b78f-a60a39678792",\n+ "workflow_outputs": [\n+ {\n+ "label": "intensities_group-mean-imputed_QN_LT",\n+ "output_name": "imputed_data_file",\n+ "uuid": "169d677f-0acb-4c56-b057-21f4aaf2b920"\n+ },\n+ {\n+ "label": "intensities_group-mean-imputed_report",\n+ "output_name": "report_file",\n+ "uuid": "25edae88-3bb6-4ec9-8b98-686fded7ed79"\n+ }\n+ ]\n+ },\n+ "9": {\n+ "annotation": "Perform ANOVA. For imputing missing values, create random values.",\n+ "content_id": "mqppep_anova",\n+ "errors": null,\n+ "id": 9,\n+ "input_connections": {\n+ "alpha_file": {\n+ "id": 6,\n+ "output_name": "output"\n+ },\n+ "input_file": {\n+ "id": 7,\n+ "output_name": "preproc_tab"\n+ }\n+ },\n+ "inputs": [],\n+ "label": "MaxQuant Phosphopeptide ANOVA randomly imputed",\n+ "name": "MaxQuant Phosphopeptide ANOVA",\n+ "outputs": [\n+ {\n+ "name": "imputed_data_file",\n+ "type": "tabular"\n+ },\n+ {\n+ "name": "report_file",\n+ "type": "pdf"\n+ }\n+ ],\n+ "position": {\n+ "bottom": 1609.6000061035156,\n+ "height": 255.60000610351562,\n+ "left": 1617,\n+ "right": 1817,\n+ "top": 1354,\n+ "width": 200,\n+ "x": 1617,\n+ "y": 1354\n+ },\n+ "post_job_actions": {\n+ "RenameDatasetActionimputed_data_file": {\n+ "action_arguments": {\n+ "newname": "#{input_file}.intensities_randomly-imputed_QN_LT"\n+ },\n+ "action_type": "RenameDatasetAction",\n+ "output_name": "imputed_data_file"\n+ },\n+ "RenameDatasetActionreport_file": {\n+ "action_arguments": {\n+ "newname": "#{input_file}.intensities_randomly-imputed_report (download/unzip to view)"\n+ },\n+ "action_type": "RenameDatasetAction",\n+ "output_name": "report_file"\n+ }\n+ },\n+ "tool_id": "mqppep_anova",\n+ "tool_state": "{\\"alpha_file\\": {\\"__class__\\": \\"ConnectedValue\\"}, \\"first_data_column\\": \\"Intensity\\", \\"imputation\\": {\\"imputation_method\\": \\"random\\", \\"__current_case__\\": 3, \\"meanPercentile\\": \\"1\\", \\"sdPercentile\\": \\"0.2\\"}, \\"input_file\\": {\\"__class__\\": \\"ConnectedValue\\"}, \\"sample_grouping_regex\\": \\"(\\\\\\\\d+)\\", \\"sample_names_regex\\": \\"\\\\\\\\.(\\\\\\\\d+)[A-Z]$\\", \\"__page__\\": null, \\"__rerun_remap_job_id__\\": null}",\n+ "type": "tool",\n+ "uuid": "f1f2bdf9-fbc0-4205-b834-9a8af5814dc9",\n+ "workflow_outputs": [\n+ {\n+ "label": "intensities_randomly-imputed_QN_LT",\n+ "output_name": "imputed_data_file",\n+ "uuid": "d70a3476-fb42-4533-831b-4fcb2bda74fc"\n+ },\n+ {\n+ "label": "intensities_randomly-imputed_report",\n+ "output_name": "report_file",\n+ "uuid": "d6701a61-357b-4a27-8154-ca41eb16d8a6"\n+ }\n+ ]\n+ }\n+ },\n+ "tags": [\n+ "ppenrich"\n+ ],\n+ "uuid": "445a0eb0-25c7-44c0-8259-a3346b01cbf3",\n+ "version": 3\n+}\n' |