| Previous changeset 0:fec313f5c889 (2021-04-12) |
|
Commit message:
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/main/tools/pathifier commit f7363f7c391bd501fc4d1c10aaf372ec2bd82732 |
|
modified:
pathifier.R pathifier.xml |
| b |
| diff -r fec313f5c889 -r 0960bd1161fa pathifier.R --- a/pathifier.R Mon Apr 12 09:55:24 2021 +0000 +++ b/pathifier.R Mon Feb 12 23:57:01 2024 +0000 |
| [ |
| b'@@ -4,10 +4,10 @@\n ##################################################################################################\n \n \n-options(show.error.messages = F, error = function() {\n- cat(geterrmessage(), file = stderr()); q("no", 1, F)\n- }\n-)\n+options(show.error.messages = FALSE, error = function() {\n+ cat(geterrmessage(), file = stderr())\n+ q("no", 1, FALSE)\n+})\n # we need that to not crash galaxy with an UTF8 error on German LC settings.\n loc <- Sys.setlocale("LC_MESSAGES", "en_US.UTF-8")\n \n@@ -18,106 +18,112 @@\n library(circlize)\n \n option_list <- list(\n- make_option(\n- "--exp",\n- type = "character",\n- help = "Expression matrix"),\n- make_option(\n- "--sep",\n- type = "character",\n- default = "\\t",\n- help = "File separator [default : \'%default\']"\n- ),\n- make_option(\n- "--genes",\n- type = "character",\n- help = "Gene sets Pathways : gmt format (one pathway per line : Name, description, genes (one by column), tab separated)"),\n- make_option(\n- "--is_normal",\n- default = F,\n- type = "logical",\n- help = "Define normals cells in your data"),\n- make_option(\n- "--normals",\n- type = "character",\n- help = "A vector of sample status : 1 = Healthy, 0 = Tumor. Must be in the same order as in expression data"),\n- make_option(\n- "--logfile",\n- type = "character",\n- default = "log.txt",\n- help = "Log file name [default : \'%default\']"\n- ),\n- make_option(\n- "--max_stability",\n- type = "logical",\n- default = T,\n- help = "If true, throw away components leading to low stability of sampling noise [default : \'%default\']"\n- ),\n- make_option(\n- "--attempts",\n- type = "integer",\n- default = 10,\n- help = "Number of runs to determine stability. [default : \'%default\']"\n- ),\n- make_option(\n- "--min_std",\n- type = "character",\n- default = "0.4",\n- help = "Minimum of standard deviation to filter out low variable genes.\n+ make_option(\n+ "--exp",\n+ type = "character",\n+ help = "Expression matrix"\n+ ),\n+ make_option(\n+ "--sep",\n+ type = "character",\n+ default = "\\t",\n+ help = "File separator [default : \'%default\']"\n+ ),\n+ make_option(\n+ "--genes",\n+ type = "character",\n+ help = "Gene sets Pathways : gmt format (one pathway per line : Name, description, genes (one by column), tab separated)"\n+ ),\n+ make_option(\n+ "--is_normal",\n+ default = FALSE,\n+ type = "logical",\n+ help = "Define normals cells in your data"\n+ ),\n+ make_option(\n+ "--normals",\n+ type = "character",\n+ help = "A vector of sample status : 1 = Healthy, 0 = Tumor. Must be in the same order as in expression data"\n+ ),\n+ make_option(\n+ "--logfile",\n+ type = "character",\n+ default = "log.txt",\n+ help = "Log file name [default : \'%default\']"\n+ ),\n+ make_option(\n+ "--max_stability",\n+ type = "logical",\n+ default = TRUE,\n+ help = "If true, throw away components leading to low stability of sampling noise [default : \'%default\']"\n+ ),\n+ make_option(\n+ "--attempts",\n+ type = "integer",\n+ default = 10,\n+ help = "Number of runs to determine stability. [default : \'%default\']"\n+ ),\n+ make_option(\n+ "--min_std",\n+ type = "character",\n+ default = "0.4",\n+ help = "Minimum of standard deviation to filter out low variable genes.\n Use --min.std data, to use the minimum std of your data [default : \'%default\']"\n- ),\n- make_option(\n- "--min_exp",\n- type = "character",\n- default = "4",\n- help = "Minimum of gene expression to filter out low expressed genes.\n+ ),\n+ make_option(\n+ "--min_exp",\n+ type = "character",\n+ default = "4",\n+ help = "Minimum of gene expression to filter out low expressed genes.\n Use --min.exp data, to use the minimum expression of your data [default : \'%d'..b'(exp_matrix_filtered)\n+ color_status_heatmap <- list(Status = c(normal = "blue", tumor = "red"))\n+ }\n+} else {\n+ pds <- quantify_pathways_deregulation(exp_matrix_filtered,\n+ allgenes,\n+ gs,\n+ pathwaynames,\n+ maximize_stability = args$max_stability,\n+ attempts = args$attempts,\n+ logfile = args$logfile,\n+ min_std = args$min_std,\n+ min_exp = args$min_exp\n+ )\n+ for (i in pathwaynames) {\n+ df <- data.frame(pds$curves[[i]][, 1:3],\n+ PDS = as.numeric(pds$scores[[i]]),\n+ curve_order = as.vector(pds$curves_order[[i]])\n+ )\n+ ordered <- df[df$curve_order, ]\n \n- layout(cbind(1:2, 1:2), heights = c(7, 1))\n- sc3 <- scatterplot3d(ordered[, 1:3],\n- main = paste("Principal curve of", i),\n- box = F, pch = 19, type = "l")\n- sc3$points3d(ordered[, 1:3], box = F, pch = 19,\n- col = col_score_fun(ordered$PDS))\n+ layout(cbind(1:2, 1:2), heights = c(7, 1))\n+ sc3 <- scatterplot3d(ordered[, 1:3],\n+ main = paste("Principal curve of", i),\n+ box = FALSE, pch = 19, type = "l"\n+ )\n+ sc3$points3d(ordered[, 1:3],\n+ box = FALSE, pch = 19,\n+ col = col_score_fun(ordered$PDS)\n+ )\n \n- # Plot color scale legend\n- par(mar = c(5, 3, 0, 3))\n- plot(seq(min(ordered$PDS), max(ordered$PDS), length = 100), rep(0, 100), pch = 15,\n- axes = TRUE, yaxt = "n", xlab = "Color scale of PDS", ylab = "", bty = "n",\n- col = col_score_fun(seq(min(ordered$PDS), max(ordered$PDS), length = 100)))\n+ # Plot color scale legend\n+ par(mar = c(5, 3, 0, 3))\n+ plot(seq(min(ordered$PDS), max(ordered$PDS), length = 100), rep(0, 100),\n+ pch = 15,\n+ axes = TRUE, yaxt = "n", xlab = "Color scale of PDS", ylab = "", bty = "n",\n+ col = col_score_fun(seq(min(ordered$PDS), max(ordered$PDS), length = 100))\n+ )\n \n \n- ## annotation for heatmap (for the moment none for this situation)\n- sample_status <- NA\n- color_status_heatmap <- NA\n- }\n+ ## annotation for heatmap (for the moment none for this situation)\n+ sample_status <- NA\n+ color_status_heatmap <- NA\n+ }\n }\n \n ## Create dataframe from Pathifier list and round score to 4 digits\n@@ -283,29 +318,31 @@\n ## plot heatmap\n if (ncol(pds_scores) > 1) {\n pheatmap(t(pds_scores),\n- main = "Heatmap of Pathway Deregulation Score", # heat map title\n- cluster_rows = args$heatmap_cluster_pathways, # apply clustering method\n- cluster_cols = args$heatmap_cluster_cells, # apply clustering method\n+ main = "Heatmap of Pathway Deregulation Score", # heat map title\n+ cluster_rows = args$heatmap_cluster_pathways, # apply clustering method\n+ cluster_cols = args$heatmap_cluster_cells, # apply clustering method\n \n- #Additional Options\n- ## Color labeled columns\n- annotation_col = sample_status,\n- annotation_colors = color_status_heatmap,\n- show_rownames = args$heatmap_show_pathway_labels,\n- show_colnames = args$heatmap_show_cell_labels,\n- border_color = NA,\n- legend = TRUE)\n+ # Additional Options\n+ ## Color labeled columns\n+ annotation_col = sample_status,\n+ annotation_colors = color_status_heatmap,\n+ show_rownames = args$heatmap_show_pathway_labels,\n+ show_colnames = args$heatmap_show_cell_labels,\n+ border_color = NA,\n+ legend = TRUE\n+ )\n }\n dev.off()\n \n \n ## write table\n write.table(pds_scores,\n- args$pds,\n- row.names = T,\n- col.names = T,\n- quote = F,\n- sep = "\\t")\n+ args$pds,\n+ row.names = TRUE,\n+ col.names = TRUE,\n+ quote = FALSE,\n+ sep = "\\t"\n+)\n \n ## write S4 pathifier object\n save(pds, file = args$rdata)\n' |
| b |
| diff -r fec313f5c889 -r 0960bd1161fa pathifier.xml --- a/pathifier.xml Mon Apr 12 09:55:24 2021 +0000 +++ b/pathifier.xml Mon Feb 12 23:57:01 2024 +0000 |
| [ |
| @@ -1,23 +1,28 @@ -<tool id="pathifier" name="Pathifier" version="1.0.1"> +<tool id="pathifier" name="Pathifier" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> <description>: Quantify deregulation of pathways in cancer</description> + <macros> + <token name="@TOOL_VERSION@">1.40.0</token> + <token name="@VERSION_SUFFIX@">0</token> + <token name="@PROFILE@">23.0</token> + </macros> <requirements> - <requirement type="package" version="1.6.2=r35h6115d3f_0">r-optparse</requirement> - <requirement type="package" version="1.22.0=r351_0">bioconductor-pathifier</requirement> - <requirement type="package" version="1.0.12=r351h6115d3f_0">r-pheatmap</requirement> - <requirement type="package" version="0.3_41=r351h6115d3f_0">r-scatterplot3d</requirement> - <requirement type="package" version="0.4.7=r35h6115d3f_0">r-circlize</requirement> + <requirement type="package" version="@TOOL_VERSION@">bioconductor-pathifier</requirement> + <requirement type="package" version="1.7.4">r-optparse</requirement> + <requirement type="package" version="1.0.12">r-pheatmap</requirement> + <requirement type="package" version="0.3_44">r-scatterplot3d</requirement> + <requirement type="package" version="0.4.15">r-circlize</requirement> </requirements> <stdio> <exit_code range="1:" level="fatal" description="Tool exception" /> </stdio> <command detect_errors="exit_code"><![CDATA[ - Rscript $__tool_directory__/pathifier.R + Rscript '$__tool_directory__/pathifier.R' --exp '$input' --sep '$input_sep' --genes '$genes' - #if $reference.is_normal == "Yes": - --is_normal 'TRUE' + #if str($reference.reference_selector) == 'TRUE': + --is_normal '$reference.reference_selector' --normals '$reference.normals' #end if @@ -35,7 +40,6 @@ --logfile '$logfile' --plot '$plot' --rdata '$rdatafile' - ]]></command> <inputs> <param name="input" type="data" format="txt,tabular" label="expression data"/> @@ -46,9 +50,13 @@ <param name="genes" type="data" format="txt" label="Gene sets Pathways" help="Must be in gmt format (one pathway per line : Name, description, genes (one by column), tab separated)" /> <conditional name="reference"> - <param name="is_normal" label="Do you have non cancer transcriptomes in your data set ?" type="boolean" truevalue="Yes" falsevalue="" checked="false" - help="If set the starting curve depends on the matrix of points with in a certain row order (first 'normal' then 'cancer' samples), otherwise the first principal component is used. See help for more informations"/> - <when value="Yes"> + <param name="reference_selector" label="Do you have non cancer transcriptomes in your data set ?" type="select" + help="Yes, if the starting curve depends on the matrix of points with in a certain row order + (first 'normal' then 'cancer' samples), otherwise (No) the first principal component is used. See help section for more informations"> + <option selected="True" value="TRUE">Yes</option> + <option value="">No</option> + </param> + <when value="TRUE"> <param name="normals" type="data" format="tabular" label="Sample status" help="A two-column data frame, first column contains data labels, second column the levels of sample status : 1 = Healthy, 0 = Tumor (no header)" /> </when> @@ -74,7 +82,6 @@ <option value="no" selected="True">No</option> <option value="yes">Yes</option> </param> - </inputs> <outputs> <data name="pds" format="tabular" label="Pathifier Deregulation Score (PDS) of ${on_string}" /> @@ -83,14 +90,14 @@ </data> <data name="plot" format="pdf" label="Pathifier vizualization of ${on_string}" /> <data name="rdatafile" format="rdata" label="Pathifier S4 object of ${on_string}" > - <filter>rds == 'yes'</filter> + <filter>rdata == 'yes'</filter> </data> </outputs> <tests> - <test> + <test expect_num_outputs="3"> <param name="input" value="sheffer.tsv" ftype="tabular"/> <param name="genes" value="kegg_pathways.gmt" ftype="txt" /> - <param name="is_normal" value="True" /> + <param name="reference_selector" value="TRUE" /> <param name="normals" value="normals.tsv" ftype="tabular" /> <param name="log" value="yes" /> <param name="attempts" value="100" /> @@ -98,10 +105,10 @@ <output name="pds" file="sheffer.kegg.tsv" ftype="tabular"/> <output name="plot" file="plot.pdf" ftype="pdf" compare="sim_size" /> </test> - <test> + <test expect_num_outputs="3"> <param name="input" value="sheffer_noref.tsv" ftype="tabular"/> <param name="genes" value="kegg_pathways.gmt" ftype="txt" /> - <param name="is_normal" value="" /> + <param name="reference_selector" value="" /> <param name="log" value="no" /> <param name="rdata" value="yes" /> <param name="attempts" value="50" /> |