| Previous changeset 6:922d309640db (2022-03-11) Next changeset 8:2cdb2280771c (2022-03-15) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 9a0fa6d0f9aadc069a5551a54da6daf307885637" |
|
modified:
MaxQuantProcessingScript.R PhosphoPeptide_Upstream_Kinase_Mapping.pl macros.xml mqppep_anova.R mqppep_anova.xml mqppep_anova_script.Rmd repository_dependencies.xml workflow/ppenrich_suite_wf.ga |
| b |
| diff -r 922d309640db -r d728198f1ba5 MaxQuantProcessingScript.R --- a/MaxQuantProcessingScript.R Fri Mar 11 20:04:05 2022 +0000 +++ b/MaxQuantProcessingScript.R Tue Mar 15 00:35:16 2022 +0000 |
| [ |
| @@ -695,7 +695,6 @@ # Write phosphopeptides filtered by enrichment # -- -#ACE colnames(quant_data_qc_enrichment)[1] <- "Phosphopeptide" write.table( quant_data_qc_enrichment, file = output_filename, |
| b |
| diff -r 922d309640db -r d728198f1ba5 PhosphoPeptide_Upstream_Kinase_Mapping.pl --- a/PhosphoPeptide_Upstream_Kinase_Mapping.pl Fri Mar 11 20:04:05 2022 +0000 +++ b/PhosphoPeptide_Upstream_Kinase_Mapping.pl Tue Mar 15 00:35:16 2022 +0000 |
| [ |
| b'@@ -25,7 +25,6 @@\n ###############################################################################################################################\r\n \r\n use strict;\r\n-#ACE use warnings;\r\n use warnings \'FATAL\' => \'all\';\r\n \r\n use Getopt::Std;\r\n@@ -67,7 +66,6 @@\n my (@kinases_PhosphoSite, $kinases_PhosphoSite);\r\n my ($p_sequence_kinase_PhosphoSite, $p_sequence_PhosphoSite, $kinase_PhosphoSite);\r\n my (%regulatory_sites_PhosphoSite_hash);\r\n-#ACE my %psp_regsite_protein;\r\n my (%domain, %ON_FUNCTION, %ON_PROCESS, %ON_PROT_INTERACT, %ON_OTHER_INTERACT, %notes, %organism);\r\n my (%unique_motifs);\r\n my ($kinase_substrate_NetworKIN_matches, $kinase_motif_matches, $kinase_substrate_PhosphoSite_matches);\r\n@@ -196,8 +194,6 @@\n \r\n getopts(\'i:f:s:n:m:p:r:P:F:o:O:D:hva\', \\%opts) ;\r\n \r\n-#ACE print %opts; #ACE\r\n-#ACE print "\\n"; #ACE\r\n \r\n if (exists($opts{\'h\'})) {\r\n usage();\r\n@@ -221,15 +217,6 @@\n $fasta_in = $opts{\'f\'};\r\n $use_sqlite = 0;\r\n }\r\n-#ACE if (exists($opts{\'s\'}) && -e $opts{\'s\'}) {\r\n-#ACE $use_sqlite = 1;\r\n-#ACE $dbfile = $opts{\'s\'};\r\n-#ACE } elsif (!exists($opts{\'f\'}) || !-e $opts{\'f\'}) {\r\n-#ACE die(\'Neither input FASTA file nor input SQLite file was found\');\r\n-#ACE } else {\r\n-#ACE $use_sqlite = 0;\r\n-#ACE $fasta_in = $opts{\'f\'};\r\n-#ACE }\r\n my $species;\r\n if ((!exists($opts{\'s\'})) || ($opts{\'s\'} eq \'\')) {\r\n $species = \'human\';\r\n@@ -426,8 +413,6 @@\n push (@databases, $x[0]);\r\n push (@accessions, $x[1]);\r\n push (@names, $x[2]);\r\n- #ACE print "names $x[2]\\n";\r\n- #ACE print "--- $_\\n";\r\n pseudo_sed();\r\n s/$/\\t/;\r\n push (@parsed_fasta, $_);\r\n@@ -439,7 +424,6 @@\n }\r\n $parsed_fasta[$#accessions] = $parsed_fasta[$#accessions].$x[0];\r\n }\r\n- #ACE print "... \'$parsed_fasta[$#accessions]\'\\n";\r\n }\r\n close IN1;\r\n print "Done Reading FASTA file $fasta_in\\n";\r\n@@ -614,7 +598,6 @@\n $i = system("\\$CONDA_PREFIX/bin/python $dirname/search_ppep.py -u $db_out -p $file_in --verbose");\r\n } else {\r\n $i = system("\\$CONDA_PREFIX/bin/python $dirname/search_ppep.py -u $db_out -p $file_in");\r\n- #ACE DELETEME $i = system("\\$CONDA_PREFIX/bin/python $dirname/search_ppep.py -u $db_out -p $file_in --verbose");\r\n }\r\n if ($i) {\r\n print "python $dirname/search_ppep.py -u $db_out -p $file_in\\n exited with exit code $i\\n";\r\n@@ -634,7 +617,6 @@\n #\r\n ###############################################################################################################################\r\n \r\n-#ACE print OUT "$headers\\tFormatted Motifs\\tUnique Motifs\\tPhospho-site(s)\\tAccessions(s)\\tName(s)\\n";\r\n \r\n print "--- Match the non_p_peptides to the \\@sequences array:\\n";\r\n \r\n@@ -750,7 +732,6 @@\n }\r\n \r\n # Prepare counter and phosphopeptide tracker for next row\r\n- #ACE print "counter: $counter; phosphpepetide: $current_ppep\\n";\r\n $former_ppep = $current_ppep;\r\n $counter -= 1;\r\n \r\n@@ -822,15 +803,11 @@\n my @matches = @{$matched_sequences{$peptide_to_match}};\r\n @tmp_motifs_array = ();\r\n for my $i (0 .. $#matches) {\r\n- #ACE print "Matching $peptide_to_match to match $i\\n";\r\n- #ACE print "\\$sites{\\$peptide_to_match}[\\$i] $sites{$peptide_to_match}[$i]\\n";\r\n \r\n # Find the location of the phospo-site in the sequence(s)\r\n $tmp_site = 0; my $offset = 0;\r\n my $tmp_p_peptide = $peptide_to_match;\r\n- #ACE print "peptide_to_match: $peptide_to_match at position $sites{$peptide_to_match}[$i] in sequence $matched_sequences{$peptide_to_match}[$i]\\n";\r\n $tmp_p_peptide =~ s/#//g; $tmp_p_peptide =~ s/\\d//g; $tmp_p_peptide =~ s/\\_//g; $tmp_p_peptide =~ s/\\.//g;\r\n- #ACE print "tmp_p_peptide: $tmp_p_peptide\\n";\r\n \r\n # Find all phosphorylated residues in the p_peptide\r\n @p_sites = ();\r\n@@ -870,9 +847,7 @@\n my $arg1 = $matched_sequences{$peptide_to_match}[$i];\r\n \r\n if (($total_length > 0) && (length($arg1) > $arg2 + $total_length - 1)) {\r\n- #ACE print "\\$tmp_'..b'- #ACE }\r\n- #ACE elsif ($psp_regsite_protein{$seq_plus7aa} eq "") {\r\n- #ACE # do nothing\r\n- #ACE }\r\n- #ACE else {\r\n- #ACE $psp_regsite_protein_2{$peptide} = $psp_regsite_protein_2{$peptide}." / ".$psp_regsite_protein{$seq_plus7aa};\r\n- #ACE }\r\n \r\n # $ON_FUNCTION_2\r\n if ($ON_FUNCTION_2{$peptide} eq "") {\r\n@@ -1682,7 +1610,6 @@\n }\r\n $organism_2{$peptide} = $organism{$seq_plus7aa};\r\n } else {\r\n- #ACE print "d not found \\$regulatory_sites_PhosphoSite_hash{{$seq_plus7aa}}\\n";\r\n } # if (exists($regulatory_sites_PhosphoSite -> {$seq_plus7aa}))\r\n } # for my $k (0 .. $#formatted_sequences) \r\n } # if/else number of phosphosites\r\n@@ -1716,7 +1643,6 @@\n \r\n foreach my $peptide (keys %data) {\r\n if (exists($domain_2{$peptide}) and (defined $domain_2{$peptide}) and (not $domain_2{$peptide} eq "") ) {\r\n- #ACE print "writing domain $domain_2{$peptide} for regulatory site(s) $seq_plus7aa_2{$peptide}\\n"; #ACE\r\n $psp_regulatory_site_stmth->bind_param(1, $domain_2{$peptide});\r\n $psp_regulatory_site_stmth->bind_param(2, $ON_FUNCTION_2{$peptide});\r\n $psp_regulatory_site_stmth->bind_param(3, $ON_PROCESS_2{$peptide});\r\n@@ -1728,7 +1654,6 @@\n if (not $psp_regulatory_site_stmth->execute()) {\r\n print "Error writing PSP_Regulatory_site for one regulatory site with peptide \'$domain_2{$peptide}\': $psp_regulatory_site_stmth->errstr\\n";\r\n } else {\r\n- #ACE print "added domain for $domain_2{$peptide}\\n";\r\n }\r\n } elsif (exists($domain_2{$peptide}) and (not defined $domain_2{$peptide})) {\r\n print "\\$domain_2{$peptide} is undefined\\n"; #ACE\r\n@@ -1989,7 +1914,6 @@\n my $tmp_site_for_printing = $p_residues{$peptide}{$i}[$j] + 1; # added 12.05.2012 for Justin\'s data\r\n print OUT "$foobar";\r\n print OUT "$tmp_site_for_printing\\t";\r\n- #ACE print OUT "p$residues{$peptide}{$i}[$j]$tmp_site_for_printing\\t";\r\n $tmp_for_insert .= "p$residues{$peptide}{$i}[$j]$tmp_site_for_printing";\r\n $there_were_sites = 1;\r\n }\r\n@@ -2049,7 +1973,6 @@\n # begin store-to-SQLite "ppep_metadata" table\r\n # ---\r\n for $i (1..14) {\r\n- #ACE print "\\$ppep_metadata_stmth->bind_param($i, " . $ppep_metadata[$i-1] . ")\\n";\r\n $ppep_metadata_stmth->bind_param($i, $ppep_metadata[$i-1]);\r\n }\r\n if (not $ppep_metadata_stmth->execute()) {\r\n@@ -2074,7 +1997,6 @@\n $ppep_intensity_stmth->bind_param( 1, $ppep_id );\r\n $ppep_intensity_stmth->bind_param( 2, $sample_id_lut{$samples[$i]} );\r\n $ppep_intensity_stmth->bind_param( 3, $intense );\r\n- #ACE print "insert ($peptide, $samples[$i], $intense)\\n";\r\n if (not $ppep_intensity_stmth->execute()) {\r\n print "Error writing tuple ($peptide,$samples[$i],$intense): $ppep_intensity_stmth->errstr\\n";\r\n }\r\n@@ -2103,13 +2025,11 @@\n }\r\n else { print OUT "\\t";}\r\n }\r\n- #ACE my %wrote_motif = {};\r\n my %wrote_motif;\r\n my $motif_parts_0;\r\n for my $i (0 .. $#motif_sequence) {\r\n if (exists($kinase_motif_matches{$peptide}{$motif_sequence[$i]})) {\r\n print OUT "X\\t";\r\n- #ACE my @motif_parts = split(/ motif /, $motif_type{$motif_sequence[$i]});\r\n $motif_parts_0 = $motif_type{$motif_sequence[$i]}." ".$motif_sequence[$i];\r\n my $key = "$peptide\\t$gene_names\\t$motif_parts_0";\r\n if (!exists($wrote_motif{$key})) {\r\n' |
| b |
| diff -r 922d309640db -r d728198f1ba5 macros.xml --- a/macros.xml Fri Mar 11 20:04:05 2022 +0000 +++ b/macros.xml Tue Mar 15 00:35:16 2022 +0000 |
| b |
| @@ -1,4 +1,30 @@ <macros> - <token name="@TOOL_VERSION@">0.1.0</token> + <token name="@TOOL_VERSION@">0.1.1</token> <token name="@VERSION_SUFFIX@">0</token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="0.3.3" >openblas</requirement> + <requirement type="package" version="0.4.0" >r-sass</requirement> + <requirement type="package" version="1.14.2" >r-data.table</requirement> + <requirement type="package" version="1.22.2" >numpy</requirement> + <requirement type="package" version="1.4.0" >pyahocorasick</requirement> + <requirement type="package" version="1.4.0" >r-stringr</requirement> + <requirement type="package" version="1.4.1" >pandas</requirement> + <requirement type="package" version="1.56.0" >bioconductor-preprocesscore</requirement> + <requirement type="package" version="1.64" >perl-dbd-sqlite</requirement> + <requirement type="package" version="1.7.1" >r-optparse</requirement> + <requirement type="package" version="1.7.1" >r-optparse</requirement> + <requirement type="package" version="2.11" >r-rmarkdown</requirement> + <!-- + It would be nice to use conda-forge/texlive-core, but issue 23 blocked PDF-creation. + Also, I got pango font errors (output had missing symbols replaced with boxes) unless + I specified the build as well as the version, i.e. + texlive-core=20210325=h97429d4_0 + --> + <requirement type="package" >r-tinytex</requirement> + <requirement type="package" version="3.3.5" >r-ggplot2</requirement> + <requirement type="package" version="3.9.10" >python</requirement> + <requirement type="package" version="5.26.2" >perl</requirement> + </requirements> + </xml> </macros> |
| b |
| diff -r 922d309640db -r d728198f1ba5 mqppep_anova.R --- a/mqppep_anova.R Fri Mar 11 20:04:05 2022 +0000 +++ b/mqppep_anova.R Tue Mar 15 00:35:16 2022 +0000 |
| b |
| @@ -196,9 +196,12 @@ # from run to run set.seed(28571) + +library(tinytex) +tinytex::install_tinytex() rmarkdown::render( input = paste(script_dir, "mqppep_anova_script.Rmd", sep = "/") -, output_format = rmarkdown::html_document(pandoc_args = "--self-contained") +, output_format = rmarkdown::pdf_document() , output_file = report_file_name , params = rmarkdown_params ) |
| b |
| diff -r 922d309640db -r d728198f1ba5 mqppep_anova.xml --- a/mqppep_anova.xml Fri Mar 11 20:04:05 2022 +0000 +++ b/mqppep_anova.xml Tue Mar 15 00:35:16 2022 +0000 |
| [ |
| @@ -3,24 +3,23 @@ <macros> <import>macros.xml</import> </macros> - <requirements> - <requirement type="package" version="1.7.1" >r-optparse</requirement> - <requirement type="package" version="1.4.0" >r-stringr</requirement> - <requirement type="package" version="1.14.2" >r-data.table</requirement> - <requirement type="package" version="3.3.5" >r-ggplot2</requirement> - <requirement type="package" version="1.56.0" >bioconductor-preprocesscore</requirement> - <requirement type="package" version="0.3.3" >openblas</requirement> - <requirement type="package" version="2.11" >r-rmarkdown</requirement> - <requirement type="package" version="0.4.0" >r-sass</requirement> - <requirement type="package" version="20210325">texlive-core</requirement> - - </requirements> - <!-- Rscript -e 'rmarkdown::render("QuantDataProcessingScript.Rmd")' --> + <expand macro="requirements"/> + <!-- + The weird invocation used here is because knitr and install_tinytex + both need access to a writeable directory, but most directories in a + biocontainer are read-only, so this builds a pseudo-home under /tmp + --> <command detect_errors="exit_code"><![CDATA[ - cd /tmp; + export OLD_PWD=\$(dirname \$(pwd)); + export HOME=/tmp\${OLD_PWD}; + mkdir -p \$HOME/bin; + mkdir -p \$HOME/tmp; + export TEMP=\$HOME/tmp; + export TMPDIR=\$TEMP; + cd \$TEMP; cp '$__tool_directory__/mqppep_anova_script.Rmd' . || exit 0; cp '$__tool_directory__/mqppep_anova.R' . || exit 0; - \${CONDA_PREFIX}/bin/Rscript /tmp/mqppep_anova.R + \${CONDA_PREFIX}/bin/Rscript \$TEMP/mqppep_anova.R --inputFile '$input_file' --alphaFile $alpha_file --firstDataColumn $first_data_column @@ -33,8 +32,8 @@ --regexSampleGrouping $sample_grouping_regex_f --imputedDataFile $imputed_data_file --reportFile $report_file; - rm mqppep_anova_script.Rmd; - rm mqppep_anova.R + cd \${OLD_PWD}; + rm -rf \$HOME ]]></command> <configfiles> <configfile name="sample_names_regex_f"> @@ -99,8 +98,11 @@ </param> </inputs> <outputs> - <data name="imputed_data_file" format="tabular" label="${input_file.name}.intensities_${imputation.imputation_method}-imputed_QN_LT" ></data> - <data name="report_file" format="html" label="${input_file.name}.report (download/unzip to view)" ></data> + <data name="imputed_data_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> + --> + <data name="report_file" format="pdf" label="${input_file.name}.${imputation.imputation_method}-imputed_report" ></data> </outputs> <tests> <test> @@ -124,6 +126,8 @@ <param name="alpha_file" ftype="tabular" value="alpha_levels.tabular"/> <param name="first_data_column" value="10"/> <param name="imputation_method" value="random"/> + <param name="meanPercentile" value="1" /> + <param name="sdPercentile" value="0.2" /> <param name="sample_names_regex" value="\.\d+[A-Z]$"/> <param name="sample_grouping_regex" value="\d+"/> <output name="imputed_data_file"> @@ -192,14 +196,7 @@ Phosphopeptide MS intensities where missing values have been **imputed** by the chosen method, quantile-normalized (**QN**), and log10-transformed (**LT**), in tabular format. ``report_file`` - (download/unzip to view) Summary report for normalization, imputation, and ANOVA. - This dataset is displayed in Galaxy as having a datatype of ``html`` in Galaxy, - but it is in fact a zipfile; the zip file contains - an HTML file. Please download and unzip it locally to view the report. - Ideally this report would be a PDF, but there is an issue - `(linked here) - <https://github.com/conda-forge/texlive-core-feedstock/issues/19>`_. - that needs to be resolved first. + Summary report for normalization, imputation, and ANOVA, in PDF format. **Authors** |
| b |
| diff -r 922d309640db -r d728198f1ba5 mqppep_anova_script.Rmd --- a/mqppep_anova_script.Rmd Fri Mar 11 20:04:05 2022 +0000 +++ b/mqppep_anova_script.Rmd Tue Mar 15 00:35:16 2022 +0000 |
| [ |
| b'@@ -1,24 +1,32 @@\n ---\n-title: "Quant Data Processing Script"\n+title: "MaxQuant Phospho-Proteomic Enrichment Pipeline ANOVA"\n author: "Larry Cheng; Art Eschenlauer"\n date: "May 28, 2018; Nov 16, 2021"\n output:\n- html_document: default\n pdf_document: default\n params:\n- inputFile: "Upstream_Map_pST_outputfile_STEP4.txt"\n- alphaFile: "alpha_levels.txt"\n+ inputFile: "test-data/test_input_for_anova.tabular"\n+ alphaFile: "test-data/alpha_levels.tabular"\n firstDataColumn: "Intensity"\n- imputationMethod: !r c("group-median","median","mean","random")[4]\n+ imputationMethod: !r c("group-median", "median", "mean", "random")[1]\n meanPercentile: 1\n sdPercentile: 0.2\n regexSampleNames: "\\\\.(\\\\d+)[A-Z]$"\n regexSampleGrouping: "(\\\\d+)"\n imputedDataFilename: "Upstream_Map_pST_outputfile_STEP4_QN_LT.txt"\n ---\n-```{r setup, include=FALSE}\n+```{r setup, include = FALSE}\n # ref for parameterizing Rmd document: https://stackoverflow.com/a/37940285\n-knitr::opts_chunk$set(echo = FALSE, fig.dim=c(9,10))\n+knitr::opts_chunk$set(echo = FALSE, fig.dim = c(9, 10))\n+\n+### FUNCTIONS\n+\n+#ANOVA filter function\n+anova_func <- function(x, grouping_factor) {\n+ x_aov <- aov(as.numeric(x) ~ grouping_factor)\n+ pvalue <- summary(x_aov)[[1]][["Pr(>F)"]][1]\n+ pvalue\n+}\n ```\n \n ## Purpose:\n@@ -28,156 +36,175 @@\n ## Variables to change for each input file\n -->\n ```{r include = FALSE}\n-#Input Filename\n-inputFile <- params$inputFile\n+# Input Filename\n+input_file <- params$inputFile\n \n-#First data column - ideally, this could be detected via regexSampleNames, but for now leave it as is.\n-firstDataColumn <- params$firstDataColumn\n-FDC_is_integer <- TRUE\n-firstDataColumn <- withCallingHandlers(\n- as.integer(firstDataColumn)\n- , warning = function(w) FDC_is_integer <<- FALSE\n+# First data column - ideally, this could be detected via regexSampleNames,\n+# but for now leave it as is.\n+first_data_column <- params$firstDataColumn\n+fdc_is_integer <- TRUE\n+first_data_column <- withCallingHandlers(\n+ as.integer(first_data_column)\n+ , warning = function(w) fdc_is_integer <<- FALSE\n )\n-if (FALSE == FDC_is_integer) {\n- firstDataColumn <- params$firstDataColumn\n+if (FALSE == fdc_is_integer) {\n+ first_data_column <- params$firstDataColumn\n }\n \n-#False discovery rate adjustment for ANOVA (Since pY abundance is low, set to 0.10 and 0.20 in addition to 0.05)\n-valFDR <- read.table(file = params$alphaFile, sep = "\\t", header=F, quote="")[,1]\n+# False discovery rate adjustment for ANOVA\n+# Since pY abundance is low, set to 0.10 and 0.20 in addition to 0.05\n+val_fdr <-\n+ read.table(file = params$alphaFile, sep = "\\t", header = F, quote = "")[, 1]\n \n #Imputed Data filename\n-imputedDataFilename <- params$imputedDataFilename\n+imputed_data_filename <- params$imputedDataFilename\n \n #ANOVA data filename\n ```\n \n-```{r include = FALSE}\n-#Imputation method, should be one of c("random","group-median","median","mean")\n-imputationMethod <- params$imputationMethod\n+```{r echo = FALSE}\n+# Imputation method, should be one of\n+# "random", "group-median", "median", or "mean"\n+imputation_method <- params$imputationMethod\n \n-#Selection of percentile of logvalue data to set the mean for random number generation when using random imputation\n-meanPercentile <- params$meanPercentile / 100.0\n+# Selection of percentile of logvalue data to set the mean for random number\n+# generation when using random imputation\n+mean_percentile <- params$meanPercentile / 100.0\n \n-#deviation adjustment-factor for random values; real number.\n-sdPercentile <- params$sdPercentile\n+# deviation adjustment-factor for random values; real number.\n+sd_percentile <- params$sdPercentile\n+\n+# Regular expression of Sample Names, e.g., "\\\\.(\\\\d+)[A-Z]$"\n+regex_sample_names <- params$regexSampleNames\n \n-#Regular expression of Sample Names, e.g., "\\\\.(\\\\d+)[A-Z]$"\n-regexSampleNames <- params$regexSampleNames\n-\n-#Regular expression to extract Sample Grouping from Sample Name (if error occurs, compare sampleNumbe'..b'(m)\n- rownames(m) <- sapply(\n- X = 1:nrow(m)\n- , FUN = function(i) {\n+\n+\n+ anova_filtered <- data.table(\n+ anova_filtered_merge$Phosphopeptide\n+ ,\n+ anova_filtered_merge$Intensity\n+ ,\n+ anova_filtered_merge[, 2:number_of_samples + 1]\n+ )\n+ colnames(anova_filtered) <-\n+ c("Phosphopeptide", colnames(filtered_data_filtered))\n+\n+ # merge qualitative columns into the ANOVA data\n+ output_table <- data.frame(anova_filtered$Phosphopeptide)\n+ output_table <- merge(\n+ x = output_table\n+ ,\n+ y = data_table_imp_qn_lt\n+ ,\n+ by.x = "anova_filtered.Phosphopeptide"\n+ ,\n+ by.y = "Phosphopeptide"\n+ )\n+\n+ #Produce heatmap to visualize significance and the effect of imputation\n+ m <-\n+ as.matrix(unimputed_quant_data_log[anova_filtered_merge_order, ])\n+ if (nrow(m) > 0) {\n+ rownames_m <- rownames(m)\n+ rownames(m) <- sapply(\n+ X = seq_len(nrow(m))\n+ ,\n+ FUN = function(i) {\n sprintf(\n- ANOVA.filtered_merge.format[i]\n- , filtered_p$FDRadjustedANOVAp[i]\n- , rownames_m[i]\n+ anova_filtered_merge_format[i]\n+ ,\n+ filtered_p$fdr_adjusted_anova_p[i]\n+ ,\n+ rownames_m[i]\n )\n }\n )\n- margins <- c(\n- max(nchar(colnames(m))) * 10 / 16 # col\n- , max(nchar(rownames(m))) * 5 / 16 # row\n- )\n- how_many_peptides <- min(50, nrow(m))\n+ margins <- c(max(nchar(colnames(m))) * 10 / 16 # col\n+ , max(nchar(rownames(m))) * 5 / 16 # row\n+ )\n+ how_many_peptides <- min(50, nrow(m))\n \n- op <- par("cex.main")\n- try(\n- if (nrow(m) > 1) {\n- par(cex.main=0.6)\n- heatmap(\n- m[how_many_peptides:1,]\n- , Rowv = NA\n- , Colv = NA\n- , cexRow = 0.7\n- , cexCol = 0.8\n- , scale="row"\n- , margins = margins\n- , main = "Heatmap of unimputed, unnormalized intensities"\n- , xlab = ""\n- # , main = bquote(\n- # .( how_many_peptides )\n- # ~ " peptides with adjusted p-value <"\n- # ~ .(sprintf("%0.2f", cutoff))\n- # )\n- )\n- } \n- )\n- #ACE fig_dim knitr::opts_chunk$set(fig.dim = fig_dim)\n- par(op)\n+ cat("\\\\newpage\\n")\n+ if (nrow(m) > 50) {\n+ cat("Heatmap for the 50 most-significant peptides",\n+ sprintf(\n+ "whose adjusted p-value < %0.2f\\n",\n+ cutoff)\n+ )\n+ } else {\n+ cat("Heatmap for peptides whose",\n+ sprintf("adjusted p-value < %0.2f\\n",\n+ cutoff)\n+ )\n+ }\n+ cat("\\\\newline\\n")\n+ cat("\\\\newline\\n")\n+ op <- par("cex.main")\n+ try(\n+ if (nrow(m) > 1) {\n+ par(cex.main = 0.6)\n+ heatmap(\n+ m[how_many_peptides:1, ],\n+ Rowv = NA,\n+ Colv = NA,\n+ cexRow = 0.7,\n+ cexCol = 0.8,\n+ scale = "row",\n+ margins = margins,\n+ main =\n+ "Heatmap of unimputed, unnormalized intensities",\n+ xlab = ""\n+ )\n+ }\n+ )\n+ par(op)\n+ }\n }\n- \n }\n }\n ```\n \n+<!--\n ## Peptide IDs, etc.\n \n See output files.\n+-->\n' |
| b |
| diff -r 922d309640db -r d728198f1ba5 repository_dependencies.xml --- a/repository_dependencies.xml Fri Mar 11 20:04:05 2022 +0000 +++ b/repository_dependencies.xml Tue Mar 15 00:35:16 2022 +0000 |
| b |
| @@ -1,5 +1,5 @@ <?xml version="1.0" ?> <repositories description="Suite for preprocessing and ANOVA of MaxQuant results using LC-MS proteomics data from phosphoproteomic enrichment."> - <repository name="mqppep_preproc" owner="eschen42" toolshed="https://testtoolshed.g2.bx.psu.edu" changeset_revision="b91809a18dbe"/> - <repository name="mqppep_anova" owner="eschen42" toolshed="https://testtoolshed.g2.bx.psu.edu" changeset_revision="d4d531006735"/> + <repository name="mqppep_preproc" owner="eschen42" toolshed="https://testtoolshed.g2.bx.psu.edu" changeset_revision="42daf70d4ed4"/> + <repository name="mqppep_anova" owner="eschen42" toolshed="https://testtoolshed.g2.bx.psu.edu" changeset_revision="922d309640db"/> </repositories> \ No newline at end of file |
| b |
| diff -r 922d309640db -r d728198f1ba5 workflow/ppenrich_suite_wf.ga --- a/workflow/ppenrich_suite_wf.ga Fri Mar 11 20:04:05 2022 +0000 +++ b/workflow/ppenrich_suite_wf.ga Tue Mar 15 00:35:16 2022 +0000 |
| [ |
| b'@@ -28,20 +28,20 @@\n "name": "Input dataset",\n "outputs": [],\n "position": {\n- "bottom": 257.06666564941406,\n- "height": 81.39999389648438,\n- "left": 339.95001220703125,\n- "right": 539.9500122070312,\n- "top": 175.6666717529297,\n+ "bottom": -36.30000305175781,\n+ "height": 82.19999694824219,\n+ "left": 150,\n+ "right": 350,\n+ "top": -118.5,\n "width": 200,\n- "x": 339.95001220703125,\n- "y": 175.6666717529297\n+ "x": 150,\n+ "y": -118.5\n },\n "tool_id": null,\n- "tool_state": "{\\"optional\\": false, \\"format\\": [\\"tabular\\"], \\"tag\\": null}",\n+ "tool_state": "{\\"optional\\": false, \\"format\\": [\\"tabular\\"]}",\n "tool_version": null,\n "type": "data_input",\n- "uuid": "002d55e6-29a5-426d-9248-70ec33424b15",\n+ "uuid": "f4273d40-f2b8-4ad0-8bcc-91e72bd25fe1",\n "workflow_outputs": []\n },\n "1": {\n@@ -60,20 +60,20 @@\n "name": "Input dataset",\n "outputs": [],\n "position": {\n- "bottom": 411.4666748046875,\n- "height": 101.79998779296875,\n- "left": 379.95001220703125,\n- "right": 579.9500122070312,\n- "top": 309.66668701171875,\n+ "bottom": 278.1000061035156,\n+ "height": 102.60000610351562,\n+ "left": 376,\n+ "right": 576,\n+ "top": 175.5,\n "width": 200,\n- "x": 379.95001220703125,\n- "y": 309.66668701171875\n+ "x": 376,\n+ "y": 175.5\n },\n "tool_id": null,\n- "tool_state": "{\\"optional\\": false, \\"format\\": [\\"fasta\\"], \\"tag\\": null}",\n+ "tool_state": "{\\"optional\\": false, \\"format\\": [\\"fasta\\"]}",\n "tool_version": null,\n "type": "data_input",\n- "uuid": "8f079dcc-1843-47cd-b4dc-1830e4466430",\n+ "uuid": "cb31b0ac-cacc-42ee-bd42-f42d0bdae128",\n "workflow_outputs": []\n },\n "2": {\n@@ -92,20 +92,20 @@\n "name": "Input dataset",\n "outputs": [],\n "position": {\n- "bottom": 573.4666748046875,\n- "height": 101.79998779296875,\n- "left": 418.95001220703125,\n- "right": 618.9500122070312,\n- "top": 471.66668701171875,\n+ "bottom": 423.1000061035156,\n+ "height": 102.60000610351562,\n+ "left": 387,\n+ "right": 587,\n+ "top": 320.5,\n "width": 200,\n- "x": 418.95001220703125,\n- "y": 471.66668701171875\n+ "x": 387,\n+ "y": 320.5\n },\n "tool_id": null,\n- "tool_state": "{\\"optional\\": false, \\"format\\": [\\"tabular\\"], \\"tag\\": null}",\n+ "tool_state": "{\\"optional\\": false, \\"format\\": [\\"tabular\\"]}",\n "tool_version": null,\n "type": "data_input",\n- "uuid": "dc894a94-97a3-40ff-811e-01b30d498478",\n+ "uuid": "e6ec01b8-ff1a-4c90-a064-b40c5cad75bb",\n "workflow_outputs": []\n },\n "3": {\n@@ -124,20 +124,20 @@\n "name": "Input dataset",\n "outputs": [],\n "position": {\n- "bottom": 726.0666809082031,\n- "height": 81.39999389648438,\n- "left": 459.95001220703125,\n- "right": 659.9500122070312,\n- "top": 644.6666870117188,\n+ "bottom": 546.6999969482422,\n+ "height": 82.19999694824219,\n+ "left": 399,\n+ "right": 599,\n+ '..b'x": 1202.949951171875,\n- "y": 1233.1666259765625\n+ "x": 1058,\n+ "y": 1093\n },\n "post_job_actions": {\n "RenameDatasetActionimputed_data_file": {\n@@ -556,19 +581,19 @@\n },\n "tool_id": "mqppep_anova",\n "tool_state": "{\\"alpha_file\\": {\\"__class__\\": \\"ConnectedValue\\"}, \\"first_data_column\\": \\"Intensity\\", \\"imputation\\": {\\"imputation_method\\": \\"group-median\\", \\"__current_case__\\": 0}, \\"input_file\\": {\\"__class__\\": \\"ConnectedValue\\"}, \\"sample_grouping_regex\\": \\"(\\\\\\\\d+)\\", \\"sample_names_regex\\": \\"\\\\\\\\.(\\\\\\\\d+)[A-Z]$\\", \\"__page__\\": null, \\"__rerun_remap_job_id__\\": null}",\n- "tool_version": "0.1.0+galaxy0",\n+ "tool_version": null,\n "type": "tool",\n- "uuid": "2257286b-6f9a-45c1-90a3-bf5b972959d5",\n+ "uuid": "a3cb902d-8ef6-4f84-bed3-80b2b20d1916",\n "workflow_outputs": [\n {\n "label": "intensities_group-mean-imputed_QN_LT",\n "output_name": "imputed_data_file",\n- "uuid": "8e7317c6-95e9-4454-b4d7-31b4de6167a8"\n+ "uuid": "ef19dcd3-8f3e-4fc4-829e-dae6719ff1cc"\n },\n {\n "label": "intensities_group-mean-imputed_report",\n "output_name": "report_file",\n- "uuid": "dfe9b34e-1f3e-4971-8382-41178104e253"\n+ "uuid": "26bb93b0-bc11-4455-a280-241253b21981"\n }\n ]\n },\n@@ -601,14 +626,14 @@\n }\n ],\n "position": {\n- "bottom": 1325.0999603271484,\n- "height": 254.93333435058594,\n- "left": 1452.949951171875,\n- "right": 1652.949951171875,\n- "top": 1070.1666259765625,\n+ "bottom": 1186,\n+ "height": 256,\n+ "left": 1308,\n+ "right": 1508,\n+ "top": 930,\n "width": 200,\n- "x": 1452.949951171875,\n- "y": 1070.1666259765625\n+ "x": 1308,\n+ "y": 930\n },\n "post_job_actions": {\n "RenameDatasetActionimputed_data_file": {\n@@ -628,19 +653,19 @@\n },\n "tool_id": "mqppep_anova",\n "tool_state": "{\\"alpha_file\\": {\\"__class__\\": \\"ConnectedValue\\"}, \\"first_data_column\\": \\"Intensity\\", \\"imputation\\": {\\"imputation_method\\": \\"random\\", \\"__current_case__\\": 3, \\"meanPercentile\\": \\"1\\", \\"sdPercentile\\": \\"0.2\\"}, \\"input_file\\": {\\"__class__\\": \\"ConnectedValue\\"}, \\"sample_grouping_regex\\": \\"(\\\\\\\\d+)\\", \\"sample_names_regex\\": \\"\\\\\\\\.(\\\\\\\\d+)[A-Z]$\\", \\"__page__\\": null, \\"__rerun_remap_job_id__\\": null}",\n- "tool_version": "0.1.0+galaxy0",\n+ "tool_version": null,\n "type": "tool",\n- "uuid": "9516971c-8532-4797-8bf9-4655ff104dbd",\n+ "uuid": "217d92af-f6d6-4fd3-a78a-090d8afd3ae0",\n "workflow_outputs": [\n {\n "label": "intensities_randomly-imputed_QN_LT",\n "output_name": "imputed_data_file",\n- "uuid": "8ceda029-d5fd-4d75-a2b3-ac582bb137c3"\n+ "uuid": "925d734f-f9d8-49e8-aebb-c8d7598d45b2"\n },\n {\n "label": "intensities_randomly-imputed_report",\n "output_name": "report_file",\n- "uuid": "84bedf25-c15b-4cc7-97e0-92f746e89f9c"\n+ "uuid": "4ab5f1b1-d04e-4634-8765-265122bc1064"\n }\n ]\n }\n@@ -648,6 +673,6 @@\n "tags": [\n "ppenrich"\n ],\n- "uuid": "ac7bf2d1-89fe-4bf6-920a-d5508842d3f9",\n- "version": 7\n+ "uuid": "c54c2b2e-8080-445c-bc3e-43950c89d4e4",\n+ "version": 3\n }\n\\ No newline at end of file\n' |