Catching up iss169 to main: New branch to include containerized packages

bin/seurat_preprocess_init.Rmd

@@ -0,0 +1,114 @@
+---
+title: "scRNA Sample Processing"
+output:
+  html_document:
+    toc: yes
+editor_options:
+  chunk_output_type: console
+params:
+  species: "hg38"
+  sampleid: "WB_Lysis_1"
+  h5: "./tests/test_dir/cellranger_counts/sample1/outs/filtered_feature_bc_matrix.h5"
+  qc_filtering: "miQC"
+  nCount_RNA_max: 500000
+  nCount_RNA_min: 1000
+  nFeature_RNA_max: 5000
+  nFeature_RNA_min: 200
+  percent_mt_max: 10
+  percent_mt_min: 0
+  doublet_finder: "DoubletFinder"
+  npcs: 30
+---
+
+```{r, prep_args, message=FALSE}
+# set up params
+species <- params$species
+sample_id <- params$sampleid
+h5 <- params$h5
+
+qc_filtering <- params$qc_filtering # manual, miqc, mads
+nCount_RNA_max <- as.numeric(params$nCount_RNA_max)
+nCount_RNA_min <- as.numeric(params$nCount_RNA_min)
+nFeature_RNA_max <- as.numeric(params$nFeature_RNA_max)
+nFeature_RNA_min <- as.numeric(params$nFeature_RNA_min)
+percent_mt_max <- as.numeric(params$percent_mt_max)
+percent_mt_min <- as.numeric(params$percent_mt_min)
+doublet_finder <- params$doublet_finder
+npcs_val <- as.numeric(params$npcs)
+```
+
+```{r, handle_pkg, message=FALSE}
+if (!("SCOT" %in% installed.packages())){
+  devtools::install_github("CCBR/SCOT", ref = "main" )
+}
+library("SCOT")
+```
+
+```{r, pre-processing, message = FALSE, echo=FALSE, include =FALSE}
+# read in data
+rnaCounts <- Seurat::Read10X_h5(h5)
+
+#REMOVED CONDITION FOR TESTING, WHICH IS NOW IN NEXTFLOW ARGUMENTS
+so_pre <- Seurat::CreateSeuratObject(counts = rnaCounts)
+
+so_pre <- SCOT::calc_prelim_stats(so = so_pre, sampleID = sample_id)
+
+#Violin plots to be moved to secondary visualization
+
+```
+
+```{r QC}
+#Use SCOT function for filtering conditions
+so_pre
+so_filt <- subset(so_pre, subset = nFeature_RNA > 200)
+
+so_filt <- SCOT::filter_cells(so_filt, method = qc_filtering)
+
+so_pre$keep <- "low_genes"
+so_pre$keep[colnames(so_filt)] <- so_filt$keep
+
+so_filt <- subset(so_filt, subset = keep == "keep")
+```
+
+```{r normalization_and_clustering}
+#Calculate s.genes and g2m.genes
+#Normalize RNA
+#Scale RNA
+#Cell cycle scoring
+#SCTransform
+#PCA, UMAP, and initial clustering
+so_filt <- SCOT::preprocess_sample(
+  so_in = so_filt, species = species, npcs_in = npcs_val
+)
+```
+
+```{r cell_type_annotation}
+so_filt <- SCOT::run_singleR_db(so_in = so_filt, species = species)
+```
+
+```{r doublet_finding}
+if (doublet_finder %in% c("DoubletFinder", "scDblFinder","consensus","union")){
+  so_filt <- SCOT::filter_doublets(
+    so_in = so_filt, doublet_finder_method = doublet_finder
+  )
+}
+
+so_pre$keep[setdiff(colnames(so_pre)[which(so_pre$keep=="keep")], colnames(so_filt))] <- "doublet_removed"
+```
+
+```{r process_unfiltered}
+so_pre <- SCOT::preprocess_sample(
+  so_in = so_pre, species = species, npcs_in = npcs_val
+)
+```
+
+```{r save_objects}
+fpath_process <- paste0(sample_id, "_seurat_preprocess.rds")
+saveRDS(so_filt, fpath_process)
+fpath_prefilt <- paste0(sample_id, "_seurat_prefilter.rds")
+saveRDS(so_pre, fpath_prefilt)
+```
+
+```{r print_session}
+sessionInfo()
+```

bin/seurat_preprocess_report.Rmd

@@ -0,0 +1,104 @@
+---
+title: "scRNA Sample Report"
+output:
+  html_document:
+    toc: yes
+editor_options:
+  chunk_output_type: console
+params:
+  species: "hg38"
+  sampleid: "WB_Lysis_1"
+  h5: "./tests/test_dir/cellranger_counts/sample1/outs/filtered_feature_bc_matrix.h5"
+  preprocess_rds: "./tests/test_dir/process_sample/WB_Lysis_1_seurat_preprocess.rds"
+  prefilter_rds: "./tests/test_dir/process_sample/WB_Lysis_1_seurat_prefilter.rds"
+  qc_filtering: "miQC"
+  nCount_RNA_max: 500000
+  nCount_RNA_min: 1000
+  nFeature_RNA_max: 5000
+  nFeature_RNA_min: 200
+  percent_mt_max: 10
+  percent_mt_min: 0
+  doublet_finder: "DoubletFinder"
+  npcs: 30
+---
+
+
+```{r, prep_args, message=FALSE}
+# set up params
+species <- params$species
+sample_id <- params$sampleid
+h5 <- params$h5
+processed <- params$preprocess_rds
+prefilter <- params$prefilter_rds
+qc_filtering <- params$qc_filtering # manual, miqc, mads
+nCount_RNA_max <- as.numeric(params$nCount_RNA_max)
+nCount_RNA_min <- as.numeric(params$nCount_RNA_min)
+nFeature_RNA_max <- as.numeric(params$nFeature_RNA_max)
+nFeature_RNA_min <- as.numeric(params$nFeature_RNA_min)
+percent_mt_max <- as.numeric(params$percent_mt_max)
+percent_mt_min <- as.numeric(params$percent_mt_min)
+doublet_finder <- params$doublet_finder
+npcs_val <- as.numeric(params$npcs)
+```
+
+```{r, handle_pkg, message=FALSE}
+if (!("SCOT" %in% installed.packages())){
+  devtools::install_github("CCBR/SCOT", ref = "main" )
+}
+library("SCOT")
+if (!requireNamespace("Seurat", quietly = TRUE)) {
+  install.packages("Seurat")
+}
+
+```
+
+```{r load_objects, echo=FALSE, message=FALSE, warning=FALSE}
+so_prefilter <- Seurat::readRDS(prefilter)
+so_processed <- Seurat::readRDS(processed)
+
+n_prefilter <- ncol(so_prefilter)
+n_processed <- ncol(so_processed)
+```
+
+## Filtering Summary
+```{r summary_table}
+#UPDATE TO INDICATE
+summary_table <- data.frame(
+  Stage = c("Prefilter", "Processed"),
+  Cells = c(n_prefilter, n_processed)
+)
+
+knitr::kable(summary_table, caption = "Cell counts before and after filtering")
+```
+
+## UMAP of Filtered Cells
+
+## Violin plots for QC metrics
+
+```{r violin_plots, echo=FALSE, message=FALSE, warning=FALSE}
+qc_features <- c("nFeature_RNA", "nCount_RNA", "percent.mt")
+
+p_prefilter <- Seurat::VlnPlot(
+  so_prefilter,
+  features = qc_features,
+  ncol = 3,
+  pt.size = 0.1,
+  log = 10
+) + ggplot2::ggtitle("QC metrics before filtering")
+
+p_processed <- Seurat::VlnPlot(
+  so_processed,
+  features = qc_features,
+  ncol = 3,
+  pt.size = 0.1,
+  log = 10
+) + ggplot2::ggtitle("QC metrics after filtering")
+
+p_prefilter
+p_processed
+```
+
+
+```{r print_session}
+sessionInfo()
+```

codemeta.json

@@ -59,10 +59,10 @@
     }
   ],
   "codeRepository": "https://github.com/CCBR/SINCLAIR",
-  "datePublished": "2026-05-12",
+  "datePublished": "2026-05-13",
   "identifier": "https://doi.org/10.5281/zenodo.15283503",
   "license": "https://spdx.org/licenses/MIT",
   "name": "SINCLAIR: SINgle CelL AnalysIs Resource",
   "url": "https://ccbr.github.io/SINCLAIR",
-  "version": "v0.3.7"
+  "version": "v0.4.0"
 }

conf/test_pbmc.config

@@ -18,7 +18,7 @@ params {
     nFeature_RNA_min            = 200
     percent_mt_max              = 30
     percent_mt_min              = 0
-    run_doublet_finder          = "Y"
+    doublet_finder              = "DoubletFinder"
 
      // GEX
     seurat_resolution           = "0.1,0.2,0.3,0.5,0.6,0.8,1"

docs/params.md

@@ -26,7 +26,7 @@ Define where the pipeline should find input data and save output data.
 | `nFeature_RNA_min`            |                                                                                         | `integer` | 200                       |          |        |
 | `percent_mt_max`              |                                                                                         | `integer` | 10                        |          |        |
 | `percent_mt_min`              |                                                                                         | `integer` | 0                         |          |        |
-| `run_doublet_finder`          | (accepted: `Y`\|`N`)                                                                    | `string`  | Y                         |          |        |
+| `doublet_finder`              | (accepted: `scDblFinder`\|`union`\|`consensus`)                                         | `string`  | DoubletFinder             |          |        |
 | `seurat_resolution`           |                                                                                         | `string`  | 0.1,0.2,0.3,0.5,0.6,0.8,1 |          |        |
 | `npcs`                        |                                                                                         | `integer` | 50                        |          |        |
 | `resolution_list`             |                                                                                         | `string`  | 0.1,0.2,0.3,0.5,0.6,0.8,1 |          |        |

modules/local/seurat_preprocess.nf

@@ -14,14 +14,15 @@ process SEURAT_PREPROCESS {
     val(nFeature_RNA_min)
     val(percent_mt_max)
     val(percent_mt_min)
-    val(run_doublet_finder)
+    val(doublet_finder)
     val(npcs)
     path(rmd)
-    path(scRNA_functions)
 
     output:
-    tuple val(id), path ("*.rds")                 , emit:rds
-    tuple val(id), path ("*.html")                 , emit:logs
+    tuple val(id), path ("*.seurat_preprocess.rds"), emit:rds
+    tuple val(id), path ("*_seurat_prefilter.rds"), emit:prefilter
+    tuple val(id), path ("*seurat_preprocess.html"), emit:logs
+ //   tuple val(id), path ("*seurat_preprocess_report.html"), emit:report
 
     script:
     def args = task.ext.args ?: ''
@@ -33,23 +34,24 @@ process SEURAT_PREPROCESS {
             sampleid="$id",
             h5="$h5",
             qc_filtering="$qc_filtering",
-            nCount_RNA_max=$nCount_RNA_max,
-            nCount_RNA_min=$nCount_RNA_min,
-            nFeature_RNA_max=$nFeature_RNA_max,
-            nFeature_RNA_min=$nFeature_RNA_min,
-            percent_mt_max=$percent_mt_max,
-            percent_mt_min=$percent_mt_min,
-            run_doublet_finder="$run_doublet_finder",
-            npcs=$npcs,
-            scRNA_functions="$scRNA_functions",
+
+            nCount_RNA_max="$nCount_RNA_max",
+            nCount_RNA_min="$nCount_RNA_min",
+            nFeature_RNA_max="$nFeature_RNA_max",
+            nFeature_RNA_min="$nFeature_RNA_min",
+            percent_mt_max="$percent_mt_max",
+            percent_mt_min="$percent_mt_min",
+            doublet_finder="$doublet_finder",
+            npcs="$npcs",
             celldex_cache="$celldex_path"
             ),
-        output_file = "${id}_seurat_preprocess.html"
-    )
+        output_file = "${id}_seurat_preprocess.html")'
+
     """
 
     stub:
     """
+    touch ${id}_seurat_prefilter.rds
     touch ${id}_seurat_preprocess.rds
     touch ${id}_seurat_preprocess.html
     """

nextflow.config

@@ -17,14 +17,14 @@ params {
     vars_to_regress             = null // other options include "percent.mt,nFeature_RNA,S.Score,G2M.Score,nCount_RNA"
 
     // seurat_preprocess.nf
-    qc_filtering                = "miqc" //other options include "manual" (uses subsequent thresholds), "mads" (3 median absolute deviations)
+    qc_filtering                = "miQC" //other options include "manual" (uses subsequent thresholds), "mads" (3 median absolute deviations)
     nCount_RNA_max              = 500000
     nCount_RNA_min              = 1000
     nFeature_RNA_max            = 5000
     nFeature_RNA_min            = 200
     percent_mt_max              = 10
     percent_mt_min              = 0
-    run_doublet_finder          = "Y"
+    doublet_finder              = "DoubletFinder" //other options are "scDblFinder", "union", and "consensus"
 
      // GEX
     seurat_resolution           = "0.1,0.2,0.3,0.5,0.6,0.8,1"
@@ -42,7 +42,8 @@ params {
 
     // Scripts
     script_functions            = "${projectDir}/bin/scRNA_functions.R"
-    script_preprocess           = "${projectDir}/bin/seurat_preprocess.Rmd"
+    script_preprocess           = "${projectDir}/bin/seurat_preprocess_init.Rmd"
+    script_preprocess_report    = "${projectDir}/bin/seurat_preprocess_report.Rmd"
     script_merge                = "${projectDir}/bin/seurat_merge.Rmd"
     script_bc_harmony           = "${projectDir}/bin/batch_correction_harmony.Rmd"
     script_bc_rpca              = "${projectDir}/bin/batch_correction_rpca.Rmd"

nextflow_schema.json

@@ -89,10 +89,10 @@
           "type": "integer",
           "default": 0
         },
-        "run_doublet_finder": {
+        "doublet_finder": {
           "type": "string",
-          "default": "Y",
-          "enum": ["Y", "N"]
+          "default": "DoubletFinder",
+          "enum": ["scDblFinder", "union", "consensus"]
         },
         "seurat_resolution": {
           "type": "string",