Dev

.Rbuildignore

@@ -4,3 +4,7 @@
 ^LICENSE\.md$
 ^\.github$
 ^data-raw$
+^vignettes/prerender_figures\.R$
+^_pkgdown\.yml$
+^docs$
+^pkgdown$

.github/workflows/R-CMD-check.yaml

@@ -4,7 +4,7 @@ on:
   push:
     branches: [main, master]
   pull_request:
-    branches: [main, master]
+    branches: [main, master, dev]
 
 name: R-CMD-check.yaml
 

.gitignore

@@ -51,3 +51,5 @@ rsconnect/
 .Rdata
 .DS_Store
 .quarto
+inst/doc
+docs

DESCRIPTION

@@ -16,11 +16,13 @@ Authors@R: c(
 Description: This package contains functions that help in manipulating tables and generating plots for multi-omics analysis including genomics, transcriptomics, proteomics, methylomics and immunoinformatics.
 License: CC BY-NC-SA 4.0
 Encoding: UTF-8
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 Imports:
     dplyr,
     ggplot2,
     tsne,
+    cowplot,
+    graphics,
     magrittr,
     rlang,
     stats,
@@ -32,20 +34,33 @@ Imports:
     patchwork
 Suggests: 
     biomaRt,
-    cowplot,
+    circlize,
+    cluster,
+    ComplexHeatmap,
     dbscan,
+    knitr,
+    rmarkdown,
+    DESeq2,
     ggnewscale,
+    ggraph,
     ggrepel,
+    igraph,
     grDevices,
     matrixStats,
     openxlsx,
     pheatmap,
     readr,
     survival,
     survminer,
+    tidygraph,
     tidyr,
-    tidyselect
+    tidyselect,
+    tm
 Roxygen: list(markdown = TRUE)
 Depends: 
     R (>= 3.5)
 LazyData: true
+LazyDataCompression: xz
+VignetteBuilder: knitr
+URL: https://bigmindlab.github.io/OmicsKit
+

NAMESPACE

@@ -1,24 +1,36 @@
 # Generated by roxygen2: do not edit by hand
 
 export(add_annotations)
-export(barplot_GSEA)
+export(addgenesPA)
 export(detect_filter)
+export(do_clust)
+export(geneset_similarity)
 export(get_annotations)
+export(get_network_communities)
 export(get_stars)
-export(heatmap_GSEA)
-export(merge_GSEA)
+export(get_superterm)
+export(getgenesPA)
+export(heatmap_PA)
+export(heatmap_path_PA)
+export(list_gmts)
+export(merge_PA)
+export(multiplot_PA)
+export(network_clust)
+export(network_clust_gg)
 export(nice_KM)
 export(nice_PCA)
 export(nice_UMAP)
 export(nice_VSB)
+export(nice_VSB_DEseq2)
 export(nice_Volcano)
 export(nice_tSNE)
-export(plot_GSEA)
 export(power_analysis)
 export(save_results)
 export(split_cases)
+export(splot_PA)
 export(tpm)
 import(ggplot2)
 importFrom(magrittr,"%>%")
 importFrom(patchwork,plot_layout)
 importFrom(rlang,.data)
+importFrom(utils,modifyList)

R/add_annotations.R

@@ -8,6 +8,42 @@
 #' @param reference A reference table with the annotations including a column named "geneID".
 #' @param variables Character vector of columns in `reference` to add. If NULL (default), all columns except geneID are used.
 #' @param data_frame Logical; if TRUE, coerce `object` to a data.frame first. Default: FALSE.
+#'
+#' @return The input `object` as a data frame with additional columns from
+#'   `reference` joined by Ensembl gene ID. A `geneID` column is added
+#'   containing the row names of the original object.
+#'
+#' @examples
+#' \dontrun{
+#' data(norm_counts)
+#'
+#' # Requires a reference table with a "geneID" column.
+#' # Use get_annotations() to generate it:
+#' annotations <- get_annotations(
+#'   ensembl_ids = rownames(norm_counts),
+#'   mode        = "genes"
+#' )
+#'
+#' # Add gene symbol and biotype columns to the counts matrix
+#' norm_counts_annot <- add_annotations(
+#'   object    = norm_counts,
+#'   reference = annotations,
+#'   variables = c("symbol", "biotype")
+#' )
+#'
+#' # Inspect result
+#' head(norm_counts_annot[, c("geneID", "symbol", "biotype")])
+#'
+#' # Add all annotation columns (variables = NULL uses everything)
+#' norm_counts_full <- add_annotations(
+#'   object    = norm_counts,
+#'   reference = annotations
+#' )
+#' }
+#'
+#' @seealso [get_annotations()] to generate the `reference` table;
+#'   [norm_counts] for an example input matrix.
+#'
 #' @export
 
 add_annotations <- function(object, reference, variables = NULL, data_frame = FALSE){

R/dataclust_PA.R

@@ -0,0 +1,71 @@
+####################
+# Example datasets #
+####################
+
+#' Example gene set list for pathway analysis clustering
+#'
+#' A named list of 40 curated gene sets spanning four biological themes:
+#' apoptosis & cell death, cell cycle & DNA damage, immune response &
+#' inflammation, and metabolism. Gene set names follow standard database
+#' conventions (`KEGG_`, `HALLMARK_`, `GO_`) and gene symbols are real human
+#' genes. Designed to be used as input to [geneset_similarity()].
+#'
+#' @format A named list of 40 elements. Each element is a character vector of
+#'   human gene symbols (HGNC) belonging to that gene set. Gene set sizes range
+#'   from 11 to 20 genes.
+#'
+#' @source Curated manually for OmicsKit examples, based on KEGG, MSigDB
+#'   Hallmark, and Gene Ontology gene set collections.
+#'
+#' @examples
+#' data(geneset_list)
+#'
+#' # How many gene sets?
+#' length(geneset_list)
+#'
+#' # Inspect one gene set
+#' geneset_list[["KEGG_APOPTOSIS"]]
+#'
+#' # Use with geneset_similarity()
+#' data(camera_results)
+#' jac <- geneset_similarity(geneset_list, camera_results, fdr_th = 0.05)
+#'
+#' @seealso [geneset_similarity()], [camera_results]
+"geneset_list"
+
+
+#' Example CAMERA enrichment results for pathway analysis clustering
+#'
+#' A data frame simulating the output of a CAMERA differential expression
+#' analysis, containing significance values for the 40 gene sets in
+#' [geneset_list]. Approximately 60% of gene sets have FDR < 0.05, providing
+#' enough significant sets for meaningful clustering. Designed to be used
+#' alongside [geneset_list] as input to [geneset_similarity()].
+#'
+#' @format A data frame with 40 rows and 4 columns:
+#'   \describe{
+#'     \item{GeneSet}{Character. Gene set name, matching the names in
+#'       [geneset_list].}
+#'     \item{Direction}{Character. Enrichment direction: `"Up"` or `"Down"`.}
+#'     \item{PValue}{Numeric. Raw p-value from the simulated CAMERA test.}
+#'     \item{FDR}{Numeric. Benjamini-Hochberg adjusted p-value.}
+#'   }
+#'
+#' @source Simulated with `set.seed(1905)` in `data-raw/example_PA.R` for
+#'   OmicsKit examples.
+#'
+#' @examples
+#' data(camera_results)
+#'
+#' # Overview
+#' head(camera_results)
+#'
+#' # How many gene sets are significant?
+#' sum(camera_results$FDR < 0.05)
+#'
+#' # Use with geneset_similarity()
+#' data(geneset_list)
+#' jac <- geneset_similarity(geneset_list, camera_results, fdr_th = 0.05)
+#'
+#' @seealso [geneset_similarity()], [geneset_list]
+"camera_results"