Upgrade gsc_mannwhitney_de tool (#651)

* Update .shed.yml * reorganize test and check conda upgrade * generate valid new tests * Lint R code * remove deployment on testtoolshed
ARTbio · Nov 30, 2023 · c394391 · c394391
1 parent a3dc683
commit c394391
Show file tree

Hide file tree

Showing 16 changed files with 4,272 additions and 47,107 deletions.
diff --git a/.github/workflows/pr.yaml b/.github/workflows/pr.yaml
@@ -385,14 +385,6 @@ jobs:
       with:
         path: ~/.cache/pip
         key: pip_cache_py_${{ matrix.python-version }}_gxy_${{ needs.setup.outputs.galaxy-head-sha }}
-    - name: Deploy on testtoolshed
-      uses: galaxyproject/planemo-ci-action@v1
-      with:
-        mode: deploy
-        repository-list: ${{ needs.setup.outputs.repository-list }}
-        shed-target: testtoolshed
-        shed-key: ${{ secrets.TTS_API_KEY }}
-      continue-on-error: true
     - name: Deploy on toolshed
       uses: galaxyproject/planemo-ci-action@v1
       with:

diff --git a/tools/gsc_mannwhitney_de/.shed.yml b/tools/gsc_mannwhitney_de/.shed.yml
@@ -6,6 +6,6 @@ long_description:
 categories:
   - Transcriptomics
 homepage_url: http://artbio.fr
-remote_repository_url: https://github.com/ARTbio/tools-artbio/tree/master/tools/gsc_mannwhitney_de
+remote_repository_url: https://github.com/ARTbio/tools-artbio/tree/main/tools/gsc_mannwhitney_de
 toolshed:
   - toolshed
diff --git a/tools/gsc_mannwhitney_de/MannWhitney_DE.R b/tools/gsc_mannwhitney_de/MannWhitney_DE.R
@@ -1,97 +1,102 @@
-####################
-#   Differential   #
-#     analysis     #
-####################
-
-# Perform a differential analysis between 2
-# groups of cells.
+# Perform a differential analysis between 2 groups of cells.
 
 # Example of command
 # Rscript MannWhitney_DE.R --input <input.tsv> --sep <tab> --colnames <TRUE> --metadata <signature.tsv> --column_name <rate> --fdr <0.01> --output <diff_analysis.tsv>
 
-# load packages that are provided in the conda env
-options( show.error.messages=F,
-       error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
+options(show.error.messages = FALSE,
+  error = function() {
+    cat(geterrmessage(), file = stderr())
+    q("no", 1, FALSE)
+  }
+)
+
 loc <- Sys.setlocale("LC_MESSAGES", "en_US.UTF-8")
-warnings()
-library(optparse)
 
-#Arguments
-option_list = list(
+suppressPackageStartupMessages({
+  library(optparse)
+})
+
+sessionInfo()
+
+option_list <- list(
   make_option(
     "--input",
     default = NA,
-    type = 'character',
+    type = "character",
     help = "Input file that contains log2(CPM +1) values"
   ),
   make_option(
     "--sep",
-    default = '\t',
-    type = 'character',
+    default = "\t",
+    type = "character",
     help = "File separator [default : '%default' ]"
   ),
   make_option(
     "--colnames",
     default = TRUE,
-    type = 'logical',
+    type = "logical",
     help = "Consider first line as header ? [default : '%default' ]"
-  ),  
+  ),
   make_option(
     "--comparison_factor_file",
     default = NA,
-    type = 'character',
+    type = "character",
     help = " A two column table : cell identifiers and a comparison factor that split cells in two categories (high/low, HOM/HET,...)"
   ),
   make_option(
     "--factor1",
-    type = 'character',
+    type = "character",
     help = "level associated to the control condition in the factor file"
-  ), 
+  ),
   make_option(
     "--factor2",
-    type = 'character',
+    type = "character",
     help = "level associated to the test condition in the factor file"
   ),
   make_option(
     "--fdr",
     default = 0.01,
-    type = 'numeric',
+    type = "numeric",
     help = "FDR threshold [default : '%default' ]"
   ),
   make_option(
     "--log",
-    default=FALSE,
-    action="store_true",
-    type = 'logical',
+    default = FALSE,
+    action = "store_true",
+    type = "logical",
     help = "Expression data are log-transformed [default : '%default' ]"
   ),
   make_option(
     "--output",
     default = "results.tsv",
-    type = 'character',
+    type = "character",
     help = "Output name [default : '%default' ]"
   )
 )
 
-opt = parse_args(OptionParser(option_list = option_list),
-                 args = commandArgs(trailingOnly = TRUE))
+opt <- parse_args(OptionParser(option_list = option_list),
+                  args = commandArgs(trailingOnly = TRUE))
 
-if (opt$sep == "tab") {opt$sep = "\t"}
-if (opt$sep == "comma") {opt$sep = ","}
+if (opt$sep == "tab") {
+  opt$sep <- "\t"
+}
+if (opt$sep == "comma") {
+  opt$sep <- ","
+}
 
 #Open files
 data.counts <- read.table(
   opt$input,
   h = opt$colnames,
   row.names = 1,
   sep = opt$sep,
-  check.names = F
+  check.names = FALSE
 )
 
 metadata <- read.table(
   opt$comparison_factor_file,
   header = TRUE,
-  stringsAsFactors = F,
+  stringsAsFactors = FALSE,
   sep = "\t",
   check.names = FALSE,
   row.names = 1
@@ -100,35 +105,34 @@ metadata <- read.table(
 metadata <- subset(metadata, rownames(metadata) %in% colnames(data.counts))
 
 # Create two logical named vectors for each factor level of cell signature
-factor1_cells <- setNames(metadata[,1] == opt$factor1, rownames(metadata))
-factor2_cells <- setNames(metadata[,1] == opt$factor2, rownames(metadata))
+factor1_cells <- setNames(metadata[, 1] == opt$factor1, rownames(metadata))
+factor2_cells <- setNames(metadata[, 1] == opt$factor2, rownames(metadata))
 
 ## Mann-Whitney test (Two-sample Wilcoxon test)
 MW_test <- data.frame(t(apply(data.counts, 1, function(x) {
   do.call("cbind", wilcox.test(x[names(factor1_cells)[factor1_cells]], x[names(factor2_cells)[factor2_cells]]))[, 1:2]
-})), stringsAsFactors = F)
+})), stringsAsFactors = FALSE)
 
 # Benjamini-Hochberg correction and significativity
-MW_test$p.adjust <- p.adjust(as.numeric(MW_test$p.value), method = "BH" , n = nrow(MW_test))
-# MW_test$Critical.value <- (rank(MW_test$p.value) / nrow(MW_test)) * opt$fdr
+MW_test$p.adjust <- p.adjust(as.numeric(MW_test$p.value), method = "BH", n = nrow(MW_test))
 MW_test$Significant <- MW_test$p.adjust < opt$fdr
 
 ## Descriptive Statistics Function
 descriptive_stats <- function(InputData) {
-  SummaryData = data.frame(
+  SummaryData <- data.frame(
     mean = rowMeans(InputData),
     SD = apply(InputData, 1, sd),
     Variance = apply(InputData, 1, var),
     Percentage_Detection = apply(InputData, 1, function(x, y = InputData) {
       (sum(x != 0) / ncol(y)) * 100
     }),
-    mean_condition2 = rowMeans(InputData[,factor2_cells]),
+    mean_condition2 = rowMeans(InputData[, factor2_cells]),
     mean_condition1 = rowMeans(InputData[, factor1_cells])
   )
-  if(opt$log) {
-  SummaryData$log2FC <- SummaryData$mean_condition2 - SummaryData$mean_condition1
+  if (opt$log) {
+    SummaryData$log2FC <- SummaryData$mean_condition2 - SummaryData$mean_condition1
   } else {
-  SummaryData$log2FC <- log2(SummaryData$mean_condition2 / SummaryData$mean_condition1)
+    SummaryData$log2FC <- log2(SummaryData$mean_condition2 / SummaryData$mean_condition1)
   }
   return(SummaryData)
 }
@@ -139,16 +143,16 @@ results <- merge(gene_stats, MW_test, by = "row.names")
 colnames(results)[1] <- "genes"
 
 ## Annotate Significant column
-results$Significant[results$Significant == T & !is.na(results$Significant)] <- ifelse(subset(results, Significant == T)$log2FC > 0, "UP", "DOWN")
-results$Significant[results$Significant == F & !is.na(results$Significant)] <- "NS"
+results$Significant[results$Significant == TRUE & !is.na(results$Significant)] <- ifelse(subset(results, Significant == TRUE)$log2FC > 0, "UP", "DOWN")
+results$Significant[results$Significant == FALSE & !is.na(results$Significant)] <- "NS"
 
 
 # Save files
 write.table(
-  results[order(results$p.adjust),],
+  results[order(results$p.adjust), ],
   opt$output,
   sep = "\t",
-  quote = F,
-  col.names = T,
-  row.names = F
+  quote = FALSE,
+  col.names = TRUE,
+  row.names = FALSE
 )
diff --git a/tools/gsc_mannwhitney_de/mannwhitney_de.xml b/tools/gsc_mannwhitney_de/mannwhitney_de.xml
@@ -1,7 +1,7 @@
-<tool id="mannwhitney_de" name="Perform a differential analysis" version="0.9.4">
+<tool id="mannwhitney_de" name="Perform a differential analysis" version="4.1.3+galaxy0">
     <description>using a Mann-Whitney test</description>
     <requirements>
-        <requirement type="package" version="1.3.2=r3.3.2_0">r-optparse</requirement>
+        <requirement type="package" version="1.7.1">r-optparse</requirement>
     </requirements>
     <stdio>
         <exit_code range="1:" level="fatal" description="Tool exception" />
@@ -48,37 +48,26 @@
     </outputs>
     <tests>
         <test>
-            <param name="input" value="filtered-0.05.tab" ftype="txt"/>
+            <param name="input" value="input.tsv" ftype="tabular"/>
             <param name="sep" value="tab" />
             <param name="colnames" value="TRUE"/>
-            <param name="comparison_factor_file" value="signature_2columns.tsv" ftype="tabular"/>
+            <param name="comparison_factor_file" value="factor_2col.tsv" ftype="tabular"/>
             <param name="factor1" value="LOW"/>
             <param name="factor2" value="HIGH"/>
-            <param name="fdr" value="0.01"/>
+            <param name="fdr" value="0.05"/>
             <param name="log" value="true"/>
-            <output name="output" file="geneMetadata_log.tsv" ftype="tabular"/>
+            <output name="output" file="result.tsv" ftype="tabular"/>
         </test>
         <test>
-            <param name="input" value="filtered-0.05.tab" ftype="txt"/>
-            <param name="sep" value="tab" />
+            <param name="input" value="input.csv" ftype="txt"/>
+            <param name="sep" value="comma" />
             <param name="colnames" value="TRUE"/>
-            <param name="comparison_factor_file" value="signature_3columns.tsv" ftype="tabular"/>
+            <param name="comparison_factor_file" value="factor_3col.tsv" ftype="tabular"/>
             <param name="factor1" value="LOW"/>
             <param name="factor2" value="HIGH"/>
-            <param name="fdr" value="0.01"/>
+            <param name="fdr" value="0.05"/>
             <param name="log" value="true"/>
-            <output name="output" file="geneMetadata_log.tsv" ftype="tabular"/>
-        </test>
-        <test>
-            <param name="input" value="filterCells_100.tsv" ftype="txt"/>
-            <param name="sep" value="tab" />
-            <param name="colnames" value="TRUE"/>
-            <param name="comparison_factor_file" value="signature_2columns.tsv" ftype="tabular"/>
-            <param name="factor1" value="LOW"/>
-            <param name="factor2" value="HIGH"/>
-            <param name="fdr" value="0.01"/>
-            <param name="log" value="false"/>
-            <output name="output" file="geneMetadata_nolog.tsv" ftype="tabular"/>
+            <output name="output" file="result_from_csv.tsv" ftype="tabular"/>
         </test>
     </tests>
     <help>

diff --git a/tools/gsc_mannwhitney_de/test-data/factor_2col.tsv b/tools/gsc_mannwhitney_de/test-data/factor_2col.tsv
@@ -0,0 +1,101 @@
+cell	rate
+c173.B4	LOW
+c173.A2	LOW
+c173.E2	LOW
+c173.F6	LOW
+c173.B12	LOW
+c173.H1	HIGH
+c173.E4	HIGH
+c173.C2	LOW
+c173.F4	LOW
+c173.E10	HIGH
+c173.E6	LOW
+c173.C4	HIGH
+c173.B10	LOW
+c173.A7	LOW
+c173.B8	LOW
+c173.F9	LOW
+c173.G6	HIGH
+c173.A9	LOW
+c173.D2	HIGH
+c173.F2	LOW
+c173.H9	LOW
+c173.G1	LOW
+c173.B3	LOW
+c173.D7	HIGH
+c173.A12	LOW
+c173.C1	LOW
+c173.H7	HIGH
+c173.H5	LOW
+c173.G2	LOW
+c173.A3	LOW
+c173.D3	LOW
+c173.E1	LOW
+c173.G12	HIGH
+c173.C10	HIGH
+c173.C3	LOW
+c173.A5	LOW
+c173.G4	LOW
+c173.B11	LOW
+c173.G9	HIGH
+c173.F1	LOW
+c173.D8	LOW
+c173.E12	HIGH
+c173.F11	LOW
+c173.E5	LOW
+c173.G10	LOW
+c173.B9	LOW
+c173.C7	HIGH
+c173.B2	LOW
+c173.H4	LOW
+c174.G5	LOW
+c174.H9	LOW
+c174.A10	LOW
+c174.G10	HIGH
+c174.C8	LOW
+c174.F6	LOW
+c174.B4	LOW
+c174.H7	LOW
+c174.E10	HIGH
+c174.D5	LOW
+c174.E5	LOW
+c174.B11	LOW
+c174.F10	LOW
+c174.A5	LOW
+c174.B8	LOW
+c174.F2	LOW
+c174.F9	HIGH
+c174.F4	HIGH
+c174.B6	LOW
+c174.E2	LOW
+c174.G2	LOW
+c174.D8	LOW
+c174.H6	LOW
+c174.C3	HIGH
+c174.B7	LOW
+c174.A7	LOW
+c174.H10	LOW
+c174.F7	HIGH
+c174.A2	LOW
+c174.E4	LOW
+c174.D12	LOW
+c174.H4	LOW
+c174.C5	LOW
+c174.E9	LOW
+c174.D1	LOW
+c174.G4	LOW
+c174.G9	LOW
+c174.D4	HIGH
+c174.H11	HIGH
+c174.A9	LOW
+c174.A4	HIGH
+c174.C7	LOW
+c174.D11	LOW
+c174.F5	LOW
+c174.G6	LOW
+c174.D6	LOW
+c174.H3	LOW
+c174.F12	LOW
+c174.E6	LOW
+c174.G3	LOW
+c174.A8	LOW