From 0c38992747199886806475ed097c24dc9d8aa305 Mon Sep 17 00:00:00 2001
From: Habib Rehman <harehman@iu.edu>
Date: Mon, 23 Feb 2026 07:33:05 -0600
Subject: [PATCH 1/3] denoist, but transcripts aren't working yet

---
 .../denoist_correction/config.vsh.yaml        | 68 +++++++++++++++++
 .../denoist_correction/script.R               | 73 +++++++++++++++++++
 2 files changed, 141 insertions(+)
 create mode 100644 src/methods_expression_correction/denoist_correction/config.vsh.yaml
 create mode 100644 src/methods_expression_correction/denoist_correction/script.R

diff --git a/src/methods_expression_correction/denoist_correction/config.vsh.yaml b/src/methods_expression_correction/denoist_correction/config.vsh.yaml
new file mode 100644
index 00000000..76e88194
--- /dev/null
+++ b/src/methods_expression_correction/denoist_correction/config.vsh.yaml
@@ -0,0 +1,68 @@
+__merge__: /src/api/comp_method_expression_correction.yaml
+
+name: denoist_correction
+label: "denoist_correction"
+summary: "Correct counts / remove contamination using the DenoIST methods"
+description: >-
+  DenoIST is a package for denoising image-based spatial transcriptomics data. It takes a IST count matrix and returns a adjusted count matrix with contamination removed.
+links:
+  documentation: "https://github.com/aaronkwc/DenoIST"
+  repository: "https://github.com/aaronkwc/DenoIST"
+references:
+  doi: "10.1101/2025.11.13.688387"
+
+arguments:
+  - name: --celltype_key
+    required: false
+    direction: input
+    type: string
+    default: cell_type
+
+  - name: --nbins
+    required: false
+    direction: input
+    type: integer
+    default: 200
+
+  - name: --distance
+    required: false
+    direction: input
+    type: integer
+    default: 50
+
+
+resources:
+  - type: r_script
+    path: script.R
+
+engines:
+  - type: docker
+    image: openproblems/base_r:1
+    setup:
+      #- type: docker
+      #  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')"
+
+      # 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
+
+  - type: native
+
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [ hightime, highcpu, highmem ]
\ No newline at end of file
diff --git a/src/methods_expression_correction/denoist_correction/script.R b/src/methods_expression_correction/denoist_correction/script.R
new file mode 100644
index 00000000..423a6bba
--- /dev/null
+++ b/src/methods_expression_correction/denoist_correction/script.R
@@ -0,0 +1,73 @@
+library(Matrix)
+library(DenoIST)
+library(SpatialExperiment)
+library(SingleCellExperiment)
+library(anndataR)
+library(scuttle)
+
+## 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",
+#   "keep_all_cells" = FALSE,
+  "distance" = 50,
+  "nbins" = 200,
+)
+
+meta <- list(
+  'cpus': 4,
+)
+
+## VIASH END
+
+# Read the input h5ad file and convert to SingleCellExperiment and Seurat
+sce <- read_h5ad(par$input_spatial_with_cell_types, as = "SingleCellExperiment")
+spe <- SpatialExperiment(
+    assay = counts(sce),
+    colData = colData(sce),
+    spatialCoordsNames = c("centroid_x", "centroid_y"))
+
+tx <- read.csv(par$input_tx)
+
+# filter out 0 cells
+# if (!par$keep_all_cells) {
+#   cat("Filtering cells with 0 counts\n")
+#   sce <- sce[, colSums(counts(sce)) > 0]
+#   xe <- subset(xe, subset = nCount_RNA > 0)
+# }
+
+
+# check cores
+cores <- 1
+if ("cpus" %in% names(meta) && !is.null(meta$cpus)) cores <- meta$cpus
+cat(sprintf("Number of cores: %s\n", cores))
+
+# Run the algorithm
+
+res <- denoist(mat = spe,
+              tx = tx,
+              feature_label = "feature_name",
+              coords = NULL,
+              distance = par$distance, nbins = par$nbins, cl = cores) #TODO add in params
+
+# format name
+corrected_counts <- res$adjusted_counts
+
+# create corrected counts layer in original SingleCell object
+cat("Normalizing counts\n")
+
+# First copy in counts
+assay(sce, "corrected_counts") <- assay(sce, "counts")
+
+# Then, replace only the updated cells
+assay(sce, "corrected_counts")[rownames(corrected_counts), colnames(corrected_counts)] <- corrected_counts
+
+# Library size normalization - see note in resolVI
+size_factors <- librarySizeFactors(assay(sce, "corrected_counts"))
+assay(sce, "normalized") <- assay(logNormCounts(sce, size_factors=size_factors, assay.type = "corrected_counts"),"logcounts")
+
+# Write the final object to h5ad format
+cat("Writing to h5ad\n")
+dir.create(dirname(par$output), showWarnings = FALSE, recursive = TRUE)
+write_h5ad(sce, par$output, mode = "w")
\ No newline at end of file

From e34165ecda36b66b5d5bb0c02350930a95b0a06a Mon Sep 17 00:00:00 2001
From: Habib Rehman <harehman@iu.edu>
Date: Thu, 26 Feb 2026 15:21:38 -0500
Subject: [PATCH 2/3] Adding denoist method

---
 .../denoist_correction/config.vsh.yaml        | 33 ++++++++++++++-----
 .../denoist_correction/script.R               | 29 ++++++++++------
 2 files changed, 43 insertions(+), 19 deletions(-)

diff --git a/src/methods_expression_correction/denoist_correction/config.vsh.yaml b/src/methods_expression_correction/denoist_correction/config.vsh.yaml
index 76e88194..d451d915 100644
--- a/src/methods_expression_correction/denoist_correction/config.vsh.yaml
+++ b/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
 
diff --git a/src/methods_expression_correction/denoist_correction/script.R b/src/methods_expression_correction/denoist_correction/script.R
index 423a6bba..68e09c97 100644
--- a/src/methods_expression_correction/denoist_correction/script.R
+++ b/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

From fbbdcb23470ff8a2d34c78ca81ee1d719bbc2790 Mon Sep 17 00:00:00 2001
From: Habib Rehman <harehman@iu.edu>
Date: Fri, 27 Feb 2026 15:59:21 -0500
Subject: [PATCH 3/3] Adding to API file for exp correction and fixing comments

---
 src/api/comp_method_expression_correction.yaml              | 4 ++++
 .../denoist_correction/config.vsh.yaml                      | 5 -----
 .../denoist_correction/script.R                             | 6 +++---
 3 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/src/api/comp_method_expression_correction.yaml b/src/api/comp_method_expression_correction.yaml
index ff726d55..fbe8cb3f 100644
--- a/src/api/comp_method_expression_correction.yaml
+++ b/src/api/comp_method_expression_correction.yaml
@@ -15,6 +15,10 @@ arguments:
     required: false
     direction: input
     __merge__: /src/api/file_scrnaseq_reference.yaml
+  - name: --input_ist
+    direction: input
+    required: false
+    __merge__: /src/api/file_transcript_assignments.yaml
   - name: --output
     required: true
     direction: output
diff --git a/src/methods_expression_correction/denoist_correction/config.vsh.yaml b/src/methods_expression_correction/denoist_correction/config.vsh.yaml
index d451d915..3443db90 100644
--- a/src/methods_expression_correction/denoist_correction/config.vsh.yaml
+++ b/src/methods_expression_correction/denoist_correction/config.vsh.yaml
@@ -12,11 +12,6 @@ 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
diff --git a/src/methods_expression_correction/denoist_correction/script.R b/src/methods_expression_correction/denoist_correction/script.R
index 68e09c97..9939f365 100644
--- a/src/methods_expression_correction/denoist_correction/script.R
+++ b/src/methods_expression_correction/denoist_correction/script.R
@@ -11,7 +11,7 @@ par <- list(
   "input_spatial_with_cell_types" = "task_ist_preprocessing/resources_test/task_ist_preprocessing/mouse_brain_combined/spatial_aggregated_counts.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,
+  "keep_all_cells" = FALSE,
   "distance" = 50,
   "nbins" = 200,
 )
@@ -22,7 +22,7 @@ meta <- list(
 
 ## VIASH END
 
-# Read the input h5ad file and convert to SingleCellExperiment and Seurat
+# Read the input h5ad file and convert to SingleCellExperiment -> SpatialExperiment
 cat("Reading input files\n")
 sce <- read_h5ad(par$input_spatial_with_cell_types, as = "SingleCellExperiment")
 
@@ -58,7 +58,7 @@ res <- denoist(mat = spe,
               tx = tx,
               feature_label = "feature_name",
               coords = NULL,
-              distance = par$distance, nbins = par$nbins, cl = cores) #TODO add in params
+              distance = par$distance, nbins = par$nbins, cl = cores)
 
 # format name
 corrected_counts <- res$adjusted_counts