Adding denoist method

Author: Habib Rehman

src/methods_expression_correction/denoist_correction/config.vsh.yaml

@@ -12,6 +12,11 @@ references:
   doi: "10.1101/2025.11.13.688387"
 
 arguments:
+  - name: --input_ist
+    direction: input
+    required: true
+    type: file
+
   - name: --celltype_key
     required: false
     direction: input
@@ -23,12 +28,21 @@ arguments:
     direction: input
     type: integer
     default: 200
+    description: Number of bins to use for hexagonal binning, which is used for calculating background transcript contamination
 
   - name: --distance
     required: false
     direction: input
     type: integer
     default: 50
+    description: Maximum distance to consider for local background estimation
+
+  - name: --keep_all_cells
+    required: false
+    direction: input
+    type: boolean
+    default: false
+    description: Whether to keep cells with 0 counts (may cause errors if set to TRUE)
 
 
 resources:
@@ -43,21 +57,22 @@ engines:
       #  run: |
       #    apt-get update && apt-get install -y wget
       - type: r
-        bioc: [anndataR, rhdf5, scuttle, DenoIST, devtools]
-      #- type: r
-      #  bioc: [SummarizedExperiment,SingleCellExperiment,SpatialExperiment]
-      #  bioc_force_install: true
-      # - type: docker
-      #   run: |
-      #     Rscript -e "BiocManager::install('SingleCellExperiment', type = 'source', force = TRUE, ask = FALSE); devtools::install_github('aaronkwc/DenoIST')"
+        bioc: [anndataR, rhdf5, scuttle, devtools, DelayedMatrixStats]
+        cran: [arrow]
+      - type: r
+        bioc: [SummarizedExperiment,SingleCellExperiment,SpatialExperiment]
+        # bioc_force_install: true
+      - type: docker
+        run: |
+          Rscript -e "BiocManager::install('SingleCellExperiment', type = 'source', force = TRUE, ask = FALSE); devtools::install_github('aaronkwc/DenoIST')"
 
       # SingleCellExperiment part can probably be left out again in the future. It currently fixes a bug described in these issues:
       # https://github.com/drighelli/SpatialExperiment/issues/171
       # https://github.com/satijalab/seurat/issues/9889
       # The reinstall of SingleCellExperiment triggers the correct re-install of SpatialExperiment.
 
-      # Is there a better way to install an r package from github?
-      # The 6 million timeout thing stops it from breaking
+      # DenoIST is not available for bioconductor 3.22, only 3.23 :/
+      # if bioconductor is updated, it should make things easier
 
   - type: native
 

src/methods_expression_correction/denoist_correction/script.R

@@ -4,12 +4,13 @@ library(SpatialExperiment)
 library(SingleCellExperiment)
 library(anndataR)
 library(scuttle)
+library(arrow)
 
 ## VIASH START
 par <- list(
   "input_spatial_with_cell_types" = "task_ist_preprocessing/resources_test/task_ist_preprocessing/mouse_brain_combined/spatial_aggregated_counts.h5ad",
-  "input_tx" = "mouse_combined_transcripts.csv",
-  "output" = "task_ist_preprocessing/tmp/split_corrected.h5ad",
+  "input_ist" = "task_ist_preprocessing/resources_test/task_ist_preprocessing/mouse_brain_combined/raw_ist.zarr",
+  "output" = "task_ist_preprocessing/tmp/denoist_corrected.h5ad",
 #   "keep_all_cells" = FALSE,
   "distance" = 50,
   "nbins" = 200,
@@ -22,21 +23,29 @@ meta <- list(
 ## VIASH END
 
 # Read the input h5ad file and convert to SingleCellExperiment and Seurat
+cat("Reading input files\n")
 sce <- read_h5ad(par$input_spatial_with_cell_types, as = "SingleCellExperiment")
+
+# filter out 0 cells
+if (!par$keep_all_cells) {
+  cat("Filtering cells with 0 counts\n")
+  sce <- sce[, colSums(counts(sce)) > 0]
+}
+
 spe <- SpatialExperiment(
     assay = counts(sce),
     colData = colData(sce),
     spatialCoordsNames = c("centroid_x", "centroid_y"))
 
-tx <- read.csv(par$input_tx)
-
-# filter out 0 cells
-# if (!par$keep_all_cells) {
-#   cat("Filtering cells with 0 counts\n")
-#   sce <- sce[, colSums(counts(sce)) > 0]
-#   xe <- subset(xe, subset = nCount_RNA > 0)
-# }
+# Read in transcripts
+tx_dataset <- arrow::open_dataset(file.path(par$input_ist, "points/transcripts/points.parquet"))
+tx <- as.data.frame((tx_dataset))
 
+#If no QV column
+if(!("qv" %in% names(tx))) {
+  cat("QV column not found, adding dummy column of 20 (should be unecessary in future updates?)")
+  tx["qv"] <- 20
+}
 
 # check cores
 cores <- 1