Merge pull request #710 from ARTbio/gsc_scran_normalize

update Gsc_scran_normalize

tools/gsc_scran_normalize/.shed.yml

@@ -6,6 +6,7 @@ long_description: |
   Normalizes raw counts expression matrix using deconvolution size factors
 categories:
   - Transcriptomics
+  - Single Cell
 homepage_url: http://artbio.fr
 remote_repository_url: https://github.com/ARTbio/tools-artbio/tree/main/tools/gsc_scran_normalize
 toolshed:

tools/gsc_scran_normalize/scran-normalize.R

@@ -1,8 +1,9 @@
-options(show.error.messages = FALSE,
-  error = function() {
-    cat(geterrmessage(), file = stderr())
-    q("no", 1, FALSE)
-  }
+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()
@@ -13,63 +14,63 @@ library(dynamicTreeCut)
 
 # Arguments
 option_list <- list(
-  make_option(
-    c("-d", "--data"),
-    default = NA,
-    type = "character",
-    help = "Input file that contains count values to transform"
-  ),
-  make_option(
-    "--cluster",
-    default = FALSE,
-    action = "store_true",
-    type = "logical",
-    help = "Whether to calculate the size factor per cluster or on all cell"
-  ),
-  make_option(
-    c("-m", "--method"),
-    default = "hclust",
-    type = "character",
-    help = "The clustering method to use for grouping cells into cluster : hclust or igraph [default : '%default' ]"
-  ),
-  make_option(
-    "--size",
-    default = 100,
-    type = "integer",
-    help = "Minimal number of cells in each cluster : hclust or igraph [default : '%default' ]"
-  ),
-  make_option(
-    c("-o", "--out"),
-    default = "res.tab",
-    type = "character",
-    help = "Output name [default : '%default' ]"
-  )
+    make_option(
+        c("-d", "--data"),
+        default = NA,
+        type = "character",
+        help = "Input file that contains count values to transform"
+    ),
+    make_option(
+        "--cluster",
+        default = FALSE,
+        action = "store_true",
+        type = "logical",
+        help = "Whether to calculate the size factor per cluster or on all cell"
+    ),
+    make_option(
+        c("-m", "--method"),
+        default = "hclust",
+        type = "character",
+        help = "The clustering method to use for grouping cells into cluster : hclust or igraph [default : '%default' ]"
+    ),
+    make_option(
+        "--size",
+        default = 100,
+        type = "integer",
+        help = "Minimal number of cells in each cluster : hclust or igraph [default : '%default' ]"
+    ),
+    make_option(
+        c("-o", "--out"),
+        default = "res.tab",
+        type = "character",
+        help = "Output name [default : '%default' ]"
+    )
 )
 
 opt <- parse_args(OptionParser(option_list = option_list),
-                  args = commandArgs(trailingOnly = TRUE))
+    args = commandArgs(trailingOnly = TRUE)
+)
 
 
 data <- read.table(
-  opt$data,
-  check.names = FALSE,
-  header = TRUE,
-  row.names = 1,
-  sep = "\t"
+    opt$data,
+    check.names = FALSE,
+    header = TRUE,
+    row.names = 1,
+    sep = "\t"
 )
 
 ## Import data as a SingleCellExperiment object
 sce <- SingleCellExperiment(list(counts = as.matrix(data)))
 
 if (opt$cluster) {
-  clusters <- quickCluster(sce, min.size = opt$size, method = opt$method)
+    clusters <- quickCluster(sce, min.size = opt$size, method = opt$method)
 
-  ## Compute sum factors
-  sce <- computeSumFactors(sce, cluster = clusters)
+    ## Compute sum factors
+    sce <- computeSumFactors(sce, cluster = clusters)
 } else {
-
-  ## Compute sum factors
-  sce <- computeSumFactors(sce)
+    ## Compute sum factors
+    sce <- computeSumFactors(sce)
 }
 
 sce <- logNormCounts(sce)
@@ -78,10 +79,10 @@ logcounts <- data.frame(genes = rownames(sce), round(logcounts(sce), digits = 5)
 
 
 write.table(
-  logcounts,
-  opt$out,
-  col.names = TRUE,
-  row.names = FALSE,
-  quote = FALSE,
-  sep = "\t"
+    logcounts,
+    opt$out,
+    col.names = TRUE,
+    row.names = FALSE,
+    quote = FALSE,
+    sep = "\t"
 )

tools/gsc_scran_normalize/scran_normalize.xml

@@ -1,5 +1,8 @@
-<tool id="scran_normalize" name="scran_normalize" version="1.28.1+galaxy0">
+<tool id="scran_normalize" name="scran_normalize" version="1.28.1+galaxy1">
     <description>Normalize raw counts expression values using deconvolution size factors</description>
+    <xrefs>
+        <xref type="bio.tools">galaxy_single_cell_suite</xref>
+    </xrefs>
     <requirements>
         <requirement type="package" version="1.28.1">bioconductor-scran</requirement>
         <requirement type="package" version="1.63_1">r-dynamictreecut</requirement>
@@ -71,18 +74,19 @@ expression across the majority of genes represents some technical bias that shou
 
 Cell-specific biases are normalized using the computeSumFactors method, which implements the
 deconvolution strategy for scaling normalization (A. T. Lun, Bach, and Marioni 2016). It creates a reference : 
-  - if no clustering step : the average count of all transcriptomes 
-  - if you choose to cluster your cells : the average count of each cluster. 
+
+- if no clustering step : the average count of all transcriptomes 
+- if you choose to cluster your cells : the average count of each cluster.
+
 Then it pools cells and then sum their expression profiles. The size factor is described as the median ration
 between the count sums and the average across all genes. Finally it constructs a linear distribution (deconvolution method)
 of size factors by taking multiple pools of cells.
 
 You can apply this method on cell cluster instead of your all set of cells by using quickCluster.
 It defines cluster using distances based on Spearman correlation on counts between cells, there is two available methods : 
 
-  - *hclust* : hierarchical clustering on the distance matrix and dynamic tree cut.
-  - *igraph* : constructs a Shared Nearest Neighbor graph (SNN) on the distance matrix and identifies highly connected communities.
-
+- *hclust* : hierarchical clustering on the distance matrix and dynamic tree cut.
+- *igraph* : constructs a Shared Nearest Neighbor graph (SNN) on the distance matrix and identifies highly connected communities.
 
 Note: First header row must NOT start with a '#' comment character