test: add Visualization Unit Tests

..Rcheck/00check.log

@@ -0,0 +1,13 @@
+* using log directory ‘/Users/bianjh/Documents/Projects/Development/SCOT/..Rcheck’
+* using R version 4.5.1 (2025-06-13)
+* using platform: aarch64-apple-darwin20
+* R was compiled by
+    Apple clang version 16.0.0 (clang-1600.0.26.6)
+    GNU Fortran (GCC) 14.2.0
+* running under: macOS Tahoe 26.4.1
+* using session charset: UTF-8
+* checking for file ‘./DESCRIPTION’ ... ERROR
+Required fields missing or empty:
+  ‘Author’ ‘Maintainer’
+* DONE
+Status: 1 ERROR

DESCRIPTION

@@ -72,4 +72,4 @@ Config/testthat/edition: 3
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.3
+Config/roxygen2/version: 8.0.0

R/convert_human_gene_list.R

@@ -8,29 +8,44 @@
 #' @export
 #'
 #' @return Character vector of mapped mouse genes
-convert_human_gene_list <- function(genes) {
-  # data variables must be initialized to silence the R CMD check note:
-  #    'no visible binding for global variable'
-  gns <- NULL
+convert_human_gene_list <- function(genes = NULL) {
+  result <- character(0)
 
-  # TODO: make this function generic enough to convert any genome to any other
-  egs <- AnnotationDbi::mapIds(
-    org.Hs.eg.db::org.Hs.eg.db,
-    gns,
-    "ENTREZID",
-    "SYMBOL"
-  )
-  mapped <- AnnotationDbi::select(
-    Orthology.eg.db::Orthology.eg.db,
-    egs,
-    "Mus.musculus",
-    "Homo.sapiens"
-  )
-  mapped$MUS <- AnnotationDbi::mapIds(
-    org.Mm.eg.db::org.Mm.eg.db,
-    as.character(mapped$Mus.musculus),
-    "SYMBOL",
-    "ENTREZID"
-  )
-  return(as.character(unlist(mapped$MUS)))
+  # Validate input: must be character vector
+  if (!is.character(genes)) {
+    stop(paste0(
+      "Input 'genes' must be a character vector, not ",
+      paste(class(genes), collapse = " ")
+    ))
+  } else if (length(genes) == 0L) {
+    warning("Input 'genes' is empty; returning character(0)")
+  } else {
+    # Map human SYMBOL to ENTREZID
+    egs <- AnnotationDbi::mapIds(
+      org.Hs.eg.db::org.Hs.eg.db,
+      genes,
+      "ENTREZID",
+      "SYMBOL"
+    )
+
+    # Map human ENTREZID to mouse ENTREZID
+    mapped <- AnnotationDbi::select(
+      Orthology.eg.db::Orthology.eg.db,
+      as.character(egs),
+      "Mus.musculus",
+      "Homo.sapiens"
+    )
+
+    # Map mouse ENTREZID to SYMBOL
+    mapped$MUS <- AnnotationDbi::mapIds(
+      org.Mm.eg.db::org.Mm.eg.db,
+      as.character(mapped$Mus.musculus),
+      "SYMBOL",
+      "ENTREZID"
+    )
+
+    result <- as.character(unlist(mapped$MUS))
+  }
+
+  return(result)
 }

R/make_volcano_plot.R

@@ -5,7 +5,7 @@
 #' differential expression table generated by Seurat
 #'
 #' @param de_table Differential expression table generated by Seurat containing
-#' p_val, pct.1, pct.2 avg_log2FC and p_val_adj
+#' p_val, pct.1, pct.2 avg_log_2_fc and p_val_adj
 #' @param logfc Boolean to color genes meeting logfc threshold of 1.5
 #' @param pval Boolean to color genes meeting p-value threshold of 0.05
 #' @param significant Boolean to color genes that meet both logfc and p-value
@@ -26,33 +26,36 @@ make_volcano_plot <- function(
 ) {
   log10_p <- -log10(de_table$p_val_adj)
   log10_p[which(de_table$p_val_adj == 0)] <- 500
-  avg_log2FC <- de_table$avg_log2FC
+  avg_log_2_fc <- de_table$avg_log_2_fc
   gene <- rownames(de_table)
   significance <- vector(length = length(log10_p))
   significance[] <- "NotSignificant"
   if (logfc == TRUE) {
-    significance[which(abs(de_table$avg_log2FC) > 1.5)] <- "avg_log2FC > 1.5"
+    significance[which(
+      abs(de_table$avg_log_2_fc) > 1.5
+    )] <- "avg_log_2_fc > 1.5"
   }
   if (isTRUE(pval)) {
     significance[which(de_table$p_val_adj < 0.05)] <- "p_val_adj < 0.05"
   }
   if (isTRUE(significant)) {
     significance[which(
-      abs(de_table$avg_log2FC) > 1.5 &
+      abs(de_table$avg_log_2_fc) > 1.5 &
         de_table$p_val_adj < 0.05
-    )] <- "p_val_adj < 0.05 & avg_log2FC > 1.5"
+    )] <- "p_val_adj < 0.05 & avg_log_2_fc > 1.5"
   }
-  df <- as.data.frame(cbind(avg_log2FC, log10_p, significance, gene))
+  df <- as.data.frame(cbind(avg_log_2_fc, log10_p, significance, gene))
+  colnames(df) <- c("avg_log_2_fc", "log10_p", "significance", "gene")
   rownames(df) <- rownames(de_table)
   df[, 1] <- as.numeric(df[, 1])
   df[, 2] <- as.numeric(df[, 2])
   df[, 3] <- factor(
     df[, 3],
     levels = c(
       "NotSignificant",
-      "avg_log2FC > 1.5",
+      "avg_log_2_fc > 1.5",
       "p_val_adj < 0.05",
-      "p_val_adj < 0.05 & avg_log2FC > 1.5"
+      "p_val_adj < 0.05 & avg_log_2_fc > 1.5"
     )
   )
   data_subset <- NULL
@@ -68,13 +71,13 @@ make_volcano_plot <- function(
 
   volcano <- ggplot2::ggplot(
     df,
-    ggplot2::aes(x = avg_log2FC, y = log10_p, col = significance)
+    ggplot2::aes(x = avg_log_2_fc, y = log10_p, col = significance)
   ) +
     ggplot2::geom_point() +
     #      geom_vline(xintercept = 0, color = "black", linewidth = 1.5)+
     ggplot2::xlim(
-      -ceiling(max(abs(df$avg_log2FC))),
-      ceiling(max(abs(df$avg_log2FC)))
+      -ceiling(max(abs(df$avg_log_2_fc))),
+      ceiling(max(abs(df$avg_log_2_fc)))
     )
 
   if (!is.null(data_subset)) {

R/seurat_clustering.R

@@ -15,6 +15,25 @@
 #' @return The updated Seurat single cell object with recalculated PCA,
 #' neighbors, UMAP and clusters
 seurat_clustering <- function(so_in, npcs_in, resolution = 0.8, algorithm = 3) {
+  # Validate npcs_in: must be a positive integer >= 3 (for UMAP n.components)
+  if (!is.numeric(npcs_in) || npcs_in != as.integer(npcs_in) || npcs_in <= 0) {
+    rlang::abort("npcs_in must be a positive integer")
+  }
+
+  if (npcs_in < 3) {
+    rlang::abort("npcs_in must be at least 3 for UMAP computation")
+  }
+
+  # Validate resolution: must be positive
+  if (!is.numeric(resolution) || resolution <= 0) {
+    rlang::abort("resolution must be a positive numeric value")
+  }
+
+  # Validate algorithm: must be 1, 2, or 3
+  if (!is.numeric(algorithm) || !(algorithm %in% c(1, 2, 3))) {
+    rlang::abort("algorithm must be 1 (Louvain), 2 (Leiden), or 3 (SLM)")
+  }
+
   so <- Seurat::RunPCA(
     object = so_in,
     features = Seurat::VariableFeatures(object = so_in),
@@ -24,8 +43,8 @@ seurat_clustering <- function(so_in, npcs_in, resolution = 0.8, algorithm = 3) {
   so <- Seurat::FindNeighbors(so, dims = 1:npcs_in)
   so <- Seurat::FindClusters(
     so,
-    resolution = 0.8,
-    algorithm = 3,
+    resolution = resolution,
+    algorithm = algorithm,
     verbose = TRUE
   )
   so <- Seurat::RunUMAP(so, dims = 1:npcs_in, n.components = 3)

R/split_featurePlot.R

@@ -42,11 +42,6 @@ split_featurePlot <- function(
 ) {
   plot_list <- list()
   plot_output <- list()
-  if (is.null(reduction)) {
-    embed <- so@reductions[[SeuratObject::DefaultDimReduc(so)]]@cell.embeddings
-  } else {
-    embed <- Seurat::Embeddings(so, reduction = reduction)
-  }
 
   # TODO refactor with map or lapply
   for (feature in features) {
@@ -61,8 +56,6 @@ split_featurePlot <- function(
         order = order,
         reduction = reduction
       ) +
-        ggplot2::xlim(range(embed[, 1])) +
-        ggplot2::ylim(range(embed[, 2])) +
         ggplot2::ggtitle(ident)
     }
   }