update with fixed GChecks

.gitignore

@@ -16,4 +16,14 @@ README.md
 pipeline_store
 pipeline_store.R
 R_scripts
+.R
+.RDataTmp
+.RDataTmp1
+.github
+Pipeline_benchmarking_script.R
+fibrosis_data
+.R
+.RDataTmp
+.RDataTmp1
+.github
 

DESCRIPTION

@@ -18,22 +18,16 @@ Imports:
   tarchetypes,
   crew,
   crew.cluster,
-  qs,
   tidybulk,
   tidySummarizedExperiment,
   tidySingleCellExperiment,
   SummarizedExperiment, 
   edgeR,
-  sctransform (>= 0.3.3),
   Seurat (>= 5.0.0),
   Matrix (>= 1.6),
-  irlba (>= 2.3.5.1),
-  glmGamPoi,
   dplyr, 
   tidyr, 
-  ggplot2,
   glue,
-  here,
   stringr,
   tidyseurat,
   purrr,
@@ -47,47 +41,27 @@ Imports:
   celldex,
   scuttle,
   CellChat,
-  tidyHeatmap,
   gridGraphics,
-  sccomp,
   scDblFinder,
-  ggupset,
   magrittr,
   rlang, 
   S4Vectors, 
   BiocGenerics, 
   AnnotationDbi, 
-  broom,
-  lifecycle,
-  SingleCellExperiment,
-  knitr, 
-  scRNAseq, 
-  digest, 
-  cowplot, 
-  igraph, 
-  callr, 
   circlize, 
-  future, 
   future.apply, 
   ids, 
-  methods, 
-  pbapply, 
-  scales, 
   RColorBrewer,
-  knitr,
   digest, 
   cowplot, 
   igraph, 
-  RColorBrewer,
   callr,
-  circlize,
   future,
-  future.apply,
-  ids,
   methods,
   pbapply,
   reshape2,
   scales,
+  data.table
 Encoding: UTF-8
 LazyData: true
 RoxygenNote: 7.3.1
@@ -107,6 +81,9 @@ biocViews:
 LazyDataCompression: xz
 Config/testthat/edition: 3
 Suggests: 
-    testthat (>= 3.0.0), 
-    knitr, 
-    scRNAseq
+    testthat, 
+    scRNAseq,
+    ggplot2,
+    irlba,
+    sctransform, 
+    knitr

NAMESPACE

@@ -19,8 +19,12 @@ export(pseudobulk_merge)
 export(run_targets_pipeline)
 export(seurat_to_ligand_receptor_count)
 export(test_differential_abundance_hpc)
+import(crew)
+import(crew.cluster)
+import(dplyr)
 import(future.apply)
 import(scDblFinder)
+import(tarchetypes)
 import(targets)
 import(tidySingleCellExperiment)
 import(tidySummarizedExperiment)
@@ -51,6 +55,7 @@ importFrom(RColorBrewer,brewer.pal)
 importFrom(S4Vectors,cbind)
 importFrom(S4Vectors,metadata)
 importFrom(Seurat,CellCycleScoring)
+importFrom(Seurat,CreateAssayObject)
 importFrom(Seurat,CreateSeuratObject)
 importFrom(Seurat,DefaultAssay)
 importFrom(Seurat,FindClusters)
@@ -70,13 +75,15 @@ importFrom(Seurat,as.SingleCellExperiment)
 importFrom(SingleR,SingleR)
 importFrom(SummarizedExperiment,SummarizedExperiment)
 importFrom(SummarizedExperiment,assays)
+importFrom(SummarizedExperiment,colData)
 importFrom(SummarizedExperiment,rowData)
 importFrom(callr,r)
 importFrom(celldex,BlueprintEncodeData)
 importFrom(celldex,MonacoImmuneData)
 importFrom(circlize,colorRamp2)
 importFrom(cowplot,as_grob)
 importFrom(crew,crew_controller_local)
+importFrom(data.table,":=")
 importFrom(digest,digest)
 importFrom(dplyr,"%>%")
 importFrom(dplyr,across)
@@ -106,6 +113,7 @@ importFrom(grid,grid.grab)
 importFrom(gridGraphics,grid.echo)
 importFrom(ids,random_id)
 importFrom(igraph,graph_from_adjacency_matrix)
+importFrom(igraph,in_circle)
 importFrom(igraph,layout_)
 importFrom(magrittr,extract2)
 importFrom(methods,slot)
@@ -115,6 +123,7 @@ importFrom(purrr,map)
 importFrom(purrr,map2)
 importFrom(purrr,map2_dbl)
 importFrom(purrr,map_chr)
+importFrom(purrr,map_int)
 importFrom(purrr,when)
 importFrom(readr,read_csv)
 importFrom(readr,write_lines)

R/CellChat.R

@@ -407,6 +407,7 @@ computeCommunProb = function (object, type = c("triMean", "truncatedMean", "thre
 #' @importFrom future nbrOfWorkers
 #' @importFrom methods slot
 #' @importFrom pbapply pbsapply
+#' @importFrom CellChat computeCentralityLocal
 #' @import future.apply
 netAnalysis_computeCentrality = function (object = NULL, slot.name = "netP", net = NULL, net.name = NULL,
                                           thresh = 0.05)
@@ -431,11 +432,11 @@ netAnalysis_computeCentrality = function (object = NULL, slot.name = "netP", net
       # ADDED BY STEFANO
       net0[net0<0] = 0
 
-      return(CellChat:::computeCentralityLocal(net0))
+      return(computeCentralityLocal(net0))
     }, simplify = FALSE)
   }
   else {
-    centr.all <- as.list(CellChat:::computeCentralityLocal(net))
+    centr.all <- as.list(computeCentralityLocal(net))
   }
   names(centr.all) <- net.name
   if (is.null(object)) {
@@ -493,6 +494,7 @@ cellchat_diff_for_circle = function(pathway, x, y){
 #' @importFrom circlize colorRamp2
 #' @importFrom RColorBrewer brewer.pal
 #' @importFrom scales rescale
+#' @importFrom igraph in_circle 
 draw_cellchat_circle_plot = function (net, color.use = NULL, title.name = NULL, sources.use = NULL,
                                       targets.use = NULL, remove.isolate = FALSE, top = 1, top_absolute = NULL, weight.scale = T,
                                       vertex.weight = 20, vertex.weight.max = NULL, vertex.size.max = 15,

R/execute_pipeline.R

@@ -19,8 +19,11 @@
 #'
 #' @importFrom glue glue
 #' @importFrom targets tar_script
+#' @import tarchetypes
 #' @import targets
 #' @importFrom future tweak
+#' @import crew 
+#' @import crew.cluster
 #' @export
 run_targets_pipeline <- function(
     input_data, 
@@ -81,10 +84,10 @@ run_targets_pipeline <- function(
   # Write pipeline to a file
   tar_script({
 
-    library(targets)
-    library(tarchetypes)
-    library(crew)
-    library(crew.cluster)
+    # library(targets)
+    # library(tarchetypes)
+    # library(crew)
+    # library(crew.cluster)
 
     computing_resources = readRDS("temp_computing_resources.rds")
     #-----------------------#

R/functions.R

@@ -17,6 +17,7 @@ if(getRversion() >= "2.15.1")  utils::globalVariables(c("."))
 #' @return A tibble with cell type annotation data.
 #'
 #' @importFrom celldex BlueprintEncodeData
+#' @importFrom Seurat CreateAssayObject
 #' @importFrom celldex MonacoImmuneData
 #' @importFrom scuttle logNormCounts
 #' @importFrom SingleR SingleR
@@ -456,6 +457,7 @@ alive_identification <- function(input_read_RNA_assay,
 #' @importFrom dplyr left_join
 #' @importFrom dplyr filter
 #' @importFrom Matrix Matrix 
+#' @importFrom SummarizedExperiment colData
 #' @importFrom Seurat as.SingleCellExperiment
 #' @import scDblFinder
 #' @export
@@ -466,6 +468,12 @@ doublet_identification <- function(input_read_RNA_assay,
                                    reference_label_fine,
                                    assay = NULL){
 
+  # Fix GChecks 
+  .cell = NULL 
+  empty_droplet = NULL 
+  high_mitochondrion = NULL 
+  high_ribosome = NULL 
+
   # Get assay
   if(is.null(assay)) assay = input_read_RNA_assay@assays |> names() |> extract2(1)
 
@@ -740,6 +748,12 @@ preprocessing_output <- function(tissue,
 
 # Create pseudobulk for each sample 
 create_pseudobulk <- function(preprocessing_output_S , assays ,x ,...) {
+  #Fix GChecks 
+  .sample = NULL 
+  .feature = NULL 
+  data_source = NULL 
+  symbol = NULL 
+
   #browser()
   x = enquo(x)
 
@@ -768,9 +782,10 @@ create_pseudobulk <- function(preprocessing_output_S , assays ,x ,...) {
 #' @description
 #' Merge pseudobulk from all samples. Ensures that missing genes are accounted 
 #' for and aligns data across multiple samples.
-#' @param `create_pseudobulk_sample`: A list pseudobulk samples generated by `create_pseudobulk`
-#' @param assays: Default is set of `RNA` 
-#' @param x: User specified character vector for the column from which we subset the samples for pseudobulk analysis 
+#' @param create_pseudobulk_sample A list pseudobulk samples generated by `create_pseudobulk`
+#' @param assays Default is set of `RNA` 
+#' @param x User specified character vector for the column from which we subset the samples for pseudobulk analysis 
+#' @param ... Additional arguments 
 #' 
 #' @importFrom purrr map
 #' @importFrom dplyr select
@@ -1040,9 +1055,15 @@ seurat_to_ligand_receptor_count = function(counts, .cell_group, assay, sample_fo
 #' @importFrom dplyr left_join
 #' @importFrom tibble enframe
 #' @importFrom purrr map2
+#' @import dplyr 
+#' @importFrom data.table :=
 #' @export
 map_add_dispersion_to_se = function(se_df, .col, abundance = NULL){
 
+  # Fix GitChecks 
+  assay_name = NULL 
+
+
   .col = enquo(.col)
 
   if(abundance |> length() > 1) stop("HPCell says: for now only one feature abundance measure can be selected")
@@ -1090,6 +1111,7 @@ map_add_dispersion_to_se = function(se_df, .col, abundance = NULL){
 #' @return Data frame with test results.
 #'
 #' @importFrom rlang enquo
+#' @import dplyr 
 #' @export
 map_test_differential_abundance = function(
 
@@ -1141,6 +1163,7 @@ map_test_differential_abundance = function(
 #' @return Data frame with SummarizedExperiment objects split into chunks.
 #'
 #' @importFrom dplyr n
+#' @import dplyr 
 #' @importFrom dplyr mutate
 #' @importFrom tidyr unnest
 #' @importFrom dplyr select
@@ -1172,8 +1195,10 @@ map_split_se_by_gene = function(se_df, .col, .number_of_chunks){
     mutate(se_md5 = ids::random_id(n()))
 }
 
+#' Split SummarizedExperiment Object by number of genes
 #' @importFrom rlang enquo 
 #' @importFrom dplyr tibble
+#' @import dplyr 
 #' 
 #' @param se_df A `SingleCellExperiment` DataFrame that contains gene expression or other related data.
 #' @param .col A symbol or string indicating the column in `se_df` which should be dynamically split into multiple chunks based on gene count.
@@ -1207,10 +1232,12 @@ map_split_se_by_number_of_genes = function(se_df, .col, chunk_size = 100){
     mutate(se_md5 = ids::random_id(n()))
 }
 
-
+#' Split SingleCellExperiment Object by genes
 #' @importFrom digest digest
 #' @importFrom rlang enquo
 #' @importFrom purrr map_chr
+#' @importFrom data.table :=
+#' @import dplyr 
 #' 
 #' @param sce_df A dataframe (or tibble) where one of the columns contains
 #' SingleCellExperiment objects 
@@ -1248,8 +1275,8 @@ map_split_sce_by_gene = function(sce_df, .col, how_many_chunks_base = 10, max_ce
 #' @param empty_droplet Single dataframe containing empty droplet filtering information 
 #' @return A vector of variable gene names
 #' 
-#' @importFrom Seurat VariableFeatures, FindVariableFeatures
-#' 
+#' @importFrom Seurat VariableFeatures
+#' @importFrom Seurat FindVariableFeatures
 #' 
 #' @export
 # Find set of variable genes 
@@ -1298,6 +1325,7 @@ find_variable_genes <- function(input_seurat, empty_droplet){
 #' @importFrom readr read_csv
 #' @importFrom dplyr bind_rows
 #' @importFrom dplyr join_by
+#' @importFrom data.table :=
 #'
 #'
 #' @export
@@ -1368,7 +1396,7 @@ annotation_consensus = function(single_cell_data, .sample_column, .cell_type, .a
     # Clean cell types
     mutate(cell_type_clean = cell_type |> clean_cell_types()) |> 
     left_join(read_csv("~/PostDoc/CuratedAtlasQueryR/dev/metadata_cell_type.csv"),  by = "cell_type") |> 
-    HPCell::clean_cell_types_deeper() |>
+    clean_cell_types_deeper() |>
 
     # Reference annotation link
     left_join(reference_annotation )