manhattanly function replacement

.Rbuildignore

@@ -15,6 +15,7 @@
 ^pkgdown$
 ^data-raw$
 ^\.bumpversion\.toml$
+^Makefile$
 
 ^CODE_OF_CONDUCT\.md$
 ^inst/rmd/rnasum.html$

.pre-commit-config.yaml

@@ -1,16 +1,13 @@
 # All available hooks: https://pre-commit.com/hooks.html
 # R specific hooks: https://github.com/lorenzwalthert/precommit
 repos:
--   repo: https://github.com/lorenzwalthert/precommit
-    rev: v0.4.3.9017
-    hooks:
-    -   id: use-tidy-description
-    -   id: readme-rmd-rendered
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v6.0.0
     hooks:
     -   id: check-added-large-files
         args: ['--maxkb=200']
+    - id: file-contents-sorter
+      files: '^\.Rbuildignore$'
 -   repo: local
     hooks:
     -   id: forbid-to-commit

DESCRIPTION

@@ -20,8 +20,7 @@ License: MIT + file LICENSE
 Depends: 
     R (>= 4.1.0)
 Remotes:
-    umccr/RNAsum.data,
-    sahirbhatnagar/manhattanly
+    umccr/RNAsum.data
 biocViews: Software, RNASeq, Workflow
 Imports:
     assertthat,
@@ -38,7 +37,6 @@ Imports:
     htmlwidgets,
     knitr,
     limma,
-    manhattanly,
     matrixStats,
     optparse,
     pdftools,

LICENSE

@@ -0,0 +1,2 @@
+YEAR: 2026
+COPYRIGHT HOLDER: RNAsum authors

Makefile

@@ -0,0 +1,14 @@
+.PHONY: all pkgdown
+
+check:
+	@R -e "devtools::check()" --quiet --no-restore --no-save
+
+pkgdown:
+	@R -e "pkgdown::build_site()" --quiet --no-restore --no-save
+
+roxydoc:
+	@R -e "devtools::document()" --quiet --no-restore --no-save
+
+build:
+	@R -e "pak::local_install(upgrade = FALSE, dependencies = FALSE)" --quiet --no-restore --no-save
+

NAMESPACE

@@ -38,6 +38,7 @@ export(pca)
 export(pcgr_expr)
 export(pcgr_tiers_tsv_read)
 export(perc_rank)
+export(plot_cnv_manhattan)
 export(ppl_cnv_som_gene_read)
 export(prepare2write)
 export(purple_cnv_summary)

R/exprTable.R

@@ -22,6 +22,7 @@
 #' @param type Type.
 #' @param civic_clin_evid civic_clin_evid tibble from reference genes.
 #' @param scaling Scaling
+#' @param batch_rm Remove batch-associated effects between datasets.
 #'
 #' @importFrom dplyr %>%
 #' @return Table with coloured cells indicating expression values for selected genes

R/kallisto.R

@@ -6,11 +6,11 @@
 #' @return Tibble with the counts per gene transcript, or NULL if any of the
 #'         input params are NULL.
 #' @examples
-#' x <- system.file("rawdata/test_data/quant/abundance.tsv", package = "RNAsum")
+#' x <- system.file("rawdata/test_data/kallisto/abundance.tsv", package = "RNAsum")
 #' tx2gene <- NULL
 #' (kc <- kallisto_counts(x, tx2gene)) # NULL since no tx2gene specified
 #' @testexamples
-#' expect_null(sc)
+#' expect_null(kc)
 #' @export
 kallisto_counts <- function(x, tx2gene = NULL) {
   if (is.null(x) || is.null(tx2gene)) {
@@ -29,7 +29,7 @@ kallisto_counts <- function(x, tx2gene = NULL) {
   txi_kallisto <- tximport::tximport(files = x, type = "kallisto", tx2gene = tx2gene)
   counts <- txi_kallisto[["counts"]] |>
     tibble::as_tibble(rownames = "rowname", .name_repair = make.names) |>
-    dplyr::rename(count = X) |>
+    dplyr::rename(count = .data$X) |>
     dplyr::filter(!grepl("PAR_Y", .data$rowname))
 
   counts <- counts |>

R/manhattan.R

@@ -0,0 +1,253 @@
+#' Manhattan Plot for Copynumber Data
+#'
+#' @param cnv_data CN data frame including Gene, P, Diff_Perc, Diff_Z_score,
+#' Alterations, GENEBIOTYPE, ENSEMBL, SEQNAME, GENESEQSTART, GENESEQEND,
+#' Immunic_Cycle_Role.
+#' @param genes_to_highlight Atomic vector of gene names to highlight.
+#' @param title Plot title.
+#' @param show_legend Show legend.
+#' @param point_size Point size.
+#' @param highlight_size Highlight size.
+#' @param cn_top Top CN threshold.
+#' @param cn_bottom Bottom CN threshold.
+#'
+#' @returns Plotly object.
+#'
+#' @examples
+#' \dontrun{
+#' cnv_data <- data.annot
+#' genes_to_highlight <- unique(data.sub$Gene)
+#' }
+#' @export
+plot_cnv_manhattan <- function(
+  cnv_data,
+  genes_to_highlight = NULL,
+  title = "",
+  show_legend = TRUE,
+  point_size = 3,
+  highlight_size = 8,
+  cn_top = NULL,
+  cn_bottom = NULL
+) {
+  chr_lengths <- cnv_data |>
+    dplyr::group_by(.data$SEQNAME) |>
+    dplyr::summarize(max_pos = max(.data$GENESEQSTART), .groups = "drop") |>
+    dplyr::arrange(.data$SEQNAME) |>
+    dplyr::mutate(offset = cumsum(c(0, utils::head(.data$max_pos, -1))))
+
+  plot_data <- cnv_data |>
+    dplyr::left_join(chr_lengths, by = "SEQNAME") |>
+    dplyr::mutate(
+      pos_cum = .data$GENESEQSTART + .data$offset,
+      is_highlighted = .data$Gene %in% genes_to_highlight
+    )
+
+  data_normal <- plot_data |>
+    dplyr::filter(!.data$is_highlighted)
+  data_highlight <- plot_data |>
+    dplyr::filter(.data$is_highlighted)
+
+  chr_centers <- plot_data |>
+    dplyr::group_by(.data$SEQNAME) |>
+    dplyr::summarize(
+      center = (min(.data$pos_cum) + max(.data$pos_cum)) / 2,
+      .groups = "drop"
+    ) |>
+    dplyr::arrange(.data$SEQNAME)
+
+  chr_bands <- plot_data |>
+    dplyr::group_by(.data$SEQNAME) |>
+    dplyr::summarize(
+      xmin = min(.data$pos_cum),
+      xmax = max(.data$pos_cum),
+      .groups = "drop"
+    ) |>
+    dplyr::arrange(.data$SEQNAME) |>
+    dplyr::mutate(
+      color = ifelse(
+        seq_len(dplyr::n()) %% 2 == 0,
+        "rgba(220, 220, 220, 0.3)",
+        "rgba(180, 180, 180, 0.3)"
+      )
+    )
+
+  y_max <- max(plot_data$P, cn_top, na.rm = TRUE) * 1.05
+  y_min <- min(plot_data$P, cn_bottom, na.rm = TRUE)
+  x_min <- min(plot_data$pos_cum, na.rm = TRUE)
+  x_max <- max(plot_data$pos_cum, na.rm = TRUE)
+
+  chr_label <- function(chr) {
+    dplyr::case_when(
+      chr == 23L ~ "X",
+      chr == 24L ~ "Y",
+      chr == 25L ~ "MT",
+      .default = as.character(chr)
+    )
+  }
+
+  p <- plotly::plot_ly()
+
+  for (i in seq_len(nrow(chr_bands))) {
+    p <- p |>
+      plotly::add_ribbons(
+        x = c(chr_bands$xmin[i], chr_bands$xmax[i]),
+        ymin = rep(y_min, 2),
+        ymax = rep(y_max, 2),
+        fillcolor = chr_bands$color[i],
+        line = list(width = 0),
+        showlegend = FALSE,
+        hoverinfo = "skip"
+      )
+  }
+
+  for (chr in sort(unique(data_normal$SEQNAME))) {
+    chr_data <- data_normal |>
+      dplyr::filter(.data$SEQNAME == chr)
+    color <- ifelse(chr %% 2 == 0, "#404040", "#808080")
+
+    p <- p |>
+      plotly::add_trace(
+        data = chr_data,
+        x = ~pos_cum,
+        y = ~P,
+        type = "scatter",
+        mode = "markers",
+        marker = list(size = point_size, color = color, opacity = 0.6),
+        text = ~ paste0(
+          "<b>",
+          Gene,
+          "</b><br>",
+          "(",
+          format(GENESEQSTART, big.mark = ","),
+          ", ",
+          round(P, 2),
+          ") chr",
+          chr_label(SEQNAME),
+          "<br>",
+          "Gene: ",
+          Gene,
+          "<br>",
+          "Diff_Z_score: ",
+          round(Diff_Z_score, 2),
+          "<br>",
+          "Diff_Perc: ",
+          round(Diff_Perc, 1),
+          "<br>",
+          "Alterations: ",
+          Alterations
+        ),
+        hoverinfo = "text",
+        showlegend = FALSE,
+        name = paste("Chr", chr_label(chr))
+      )
+  }
+
+  if (nrow(data_highlight) > 0) {
+    unique_genes <- unique(data_highlight$Gene)
+    for (gene_name in unique_genes) {
+      gene_data <- data_highlight |>
+        dplyr::filter(.data$Gene == gene_name)
+      p <- p |>
+        plotly::add_trace(
+          data = gene_data,
+          x = ~pos_cum,
+          y = ~P,
+          type = "scatter",
+          mode = "markers",
+          marker = list(
+            size = highlight_size,
+            color = "#E74C3C",
+            line = list(color = "#C0392B", width = 1),
+            opacity = 0.9
+          ),
+          text = ~ paste0(
+            "<b>",
+            Gene,
+            "</b><br>",
+            "(",
+            format(GENESEQSTART, big.mark = ","),
+            ", ",
+            round(P, 2),
+            ") chr",
+            chr_label(SEQNAME),
+            "<br>",
+            "Gene: ",
+            Gene,
+            "<br>",
+            "Diff_Z_score: ",
+            round(Diff_Z_score, 2),
+            "<br>",
+            "Diff_Perc: ",
+            round(Diff_Perc, 1),
+            "<br>",
+            "Alterations: ",
+            Alterations
+          ),
+          hoverinfo = "text",
+          name = gene_name,
+          showlegend = show_legend
+        )
+    }
+  }
+
+  if (!is.null(cn_top)) {
+    p <- p |>
+      plotly::add_segments(
+        x = x_min,
+        xend = x_max,
+        y = cn_top,
+        yend = cn_top,
+        line = list(color = "gray", width = 1, dash = "dash"),
+        inherit = FALSE,
+        showlegend = FALSE,
+        hoverinfo = "skip"
+      )
+  }
+  if (!is.null(cn_bottom)) {
+    p <- p |>
+      plotly::add_segments(
+        x = x_min,
+        xend = x_max,
+        y = cn_bottom,
+        yend = cn_bottom,
+        line = list(color = "gray", width = 1, dash = "dash"),
+        inherit = FALSE,
+        showlegend = FALSE,
+        hoverinfo = "skip"
+      )
+  }
+
+  p1 <- p |>
+    plotly::layout(
+      title = list(text = title, x = 0.5, xanchor = "center"),
+      xaxis = list(
+        title = list(text = "Chromosome"),
+        tickmode = "array",
+        tickvals = chr_centers$center,
+        ticktext = vapply(chr_centers$SEQNAME, chr_label, character(1)),
+        showgrid = FALSE,
+        zeroline = FALSE
+      ),
+      yaxis = list(
+        title = list(text = "CN value"),
+        showgrid = TRUE,
+        gridcolor = "rgba(200, 200, 200, 0.5)",
+        zeroline = TRUE
+      ),
+      hovermode = "closest",
+      plot_bgcolor = "white",
+      paper_bgcolor = "white",
+      legend = list(
+        orientation = "v",
+        yanchor = "top",
+        y = 1,
+        xanchor = "left",
+        x = 1.02,
+        bgcolor = "rgba(255, 255, 255, 0.8)",
+        bordercolor = "rgba(0, 0, 0, 0.2)",
+        borderwidth = 1
+      ),
+      margin = list(r = 150)
+    )
+  p1
+}

R/refdata.R

@@ -3,14 +3,15 @@
 #' Get a list of paths to internal and external reference data, based on a
 #' selected dataset name.
 #' @param dataset Reference RNAsum dataset of interest.
+#' @param batch_rm Remove batch-associated effects between datasets.
 #'
 #' @return List with paths to internal and external reference datasets
 #'         (Counts, Targets and Name).
 #'
 #' @examples
 #' x <- get_refdata(dataset = "TEST")
 #' @export
-get_refdata <- function(dataset, batch_rm) {
+get_refdata <- function(dataset, batch_rm = FALSE) {
   assertthat::assert_that(dataset %in% names(RNAsum::REFERENCE_DATASETS))
   refdata_dir <- system.file("extdata", package = "RNAsum.data")
   d_clean <- base::strsplit(dataset, split = "-", fixed = TRUE)[[1]][1]

R/utils_shortcuts.R

@@ -19,7 +19,6 @@ dummy1 <- function() {
   ggforce::geom_sina
   ggplot2::ggplot
   limma::removeBatchEffect
-  manhattanly::manhattanly
   optparse::make_option
   preprocessCore::normalize.quantiles
   ragg::agg_png