Merge branch 'unit-test'

d3b-center · Mar 9, 2021 · ae9ca90 · ae9ca90
2 parents c8aec4a + 470ee1d
commit ae9ca90
Show file tree

Hide file tree

Showing 88 changed files with 1,701 additions and 86,735 deletions.
diff --git a/.github/workflows/R-CMD-check.yaml b/.github/workflows/R-CMD-check.yaml
@@ -17,11 +17,11 @@ jobs:
       fail-fast: false
       matrix:
         config:
-          - { os: windows-latest, r: 'release', bioc: '3.11'}
-          - { os: macOS-latest, r: 'release', bioc: '3.11'}
-          - { os: macOS-latest, r: 'release', bioc: 'devel'}
+          - { os: windows-latest, r: 'devel', bioc: 'devel'}
+          - { os: macOS-latest, r: 'release', bioc: '3.12'}
+          - { os: macOS-latest, r: 'devel', bioc: 'devel', curlConfigPath: '/usr/bin/'}
           - { os: ubuntu-latest, r: 'release', image: 'bioconductor/bioconductor_docker:devel'}
-
+          
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
       CRAN: ${{ matrix.config.cran }}
@@ -66,6 +66,19 @@ jobs:
           path: ${{ env.R_LIBS_USER }}
           key: ${{ runner.os }}-r-${{ matrix.config.r }}-bioc-${{ matrix.config.bioc }}-${{ hashFiles('depends.Rds') }}
           restore-keys: ${{ runner.os }}-r-${{ matrix.config.r }}-bioc-${{ matrix.config.bioc }}-
+
+      - name: Install system dependencies (macOS)
+        if: runner.os == 'macOS'
+        run: |
+          brew install harfbuzz
+          brew install fribidi
+          
+      - name: Set up gfortran symlinks (macOS)
+        if: runner.os == 'macOS'
+        run: |
+          set -x
+          sudo ln -s /usr/local/Cellar/gcc@8/8.4.0_2/lib/gcc/8 /usr/local/gfortran/lib
+          gfortran --version
 
       - name: Install system dependencies
         if: runner.os == 'Linux'
@@ -83,6 +96,7 @@ jobs:
           deps <- remotes::dev_package_deps(dependencies = TRUE, repos = BiocManager::repositories())
           BiocManager::install(local_deps[local_deps %in% deps$package[deps$diff != 0]], Ncpu = 2L)
           remotes::install_cran('rcmdcheck', Ncpu = 2L)
+          BiocManager::install("federicomarini/annoFuseData")
         shell: Rscript {0}
 
       - name: Session info

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -20,10 +20,13 @@ License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: true
 RoxygenNote: 7.1.1
+Depends:
+    annoFuseData
 Imports: 
     reshape2,
     dplyr,
     tidyr,
+    tidyselect,
     purrr,
     ggplot2,
     qdapRegex,
@@ -49,7 +52,10 @@ Imports:
     rmarkdown,
     methods
 Suggests: 
-    knitr
+    knitr,
+    testthat
+Remotes:
+    federicomarini/annoFuseData
 VignetteBuilder: knitr
 NeedsCompilation: no
 biocViews:

diff --git a/NAMESPACE b/NAMESPACE
@@ -22,6 +22,7 @@ export(samplecount_fusion_calls)
 export(shinyFuse)
 export(theme_publication)
 export(zscored_annotation)
+import(annoFuseData)
 import(rintrojs)
 import(shiny, except = c(renderDataTable, dataTableOutput))
 import(shinydashboard)
@@ -109,9 +110,9 @@ importFrom(tibble,column_to_rownames)
 importFrom(tibble,remove_rownames)
 importFrom(tibble,rownames_to_column)
 importFrom(tidyr,gather)
-importFrom(tidyr,one_of)
 importFrom(tidyr,separate)
 importFrom(tidyr,unnest)
+importFrom(tidyselect,one_of)
 importFrom(utils,browseURL)
 importFrom(utils,head)
 importFrom(utils,read.delim)
diff --git a/R/aggregate_fusion_calls.R b/R/aggregate_fusion_calls.R
@@ -1,11 +1,11 @@
 #' Function to aggregate Caller and read support per fusions calls
 #'
-#' @param standardFusioncalls A dataframe from star fusion or arriba standardized 
+#' @param standardFusioncalls A dataframe from star fusion or arriba standardized
 #' to run through the filtering steps
-#' @param removeother TRUE to remove Fusion_Type="other" and keep only in-frame and 
+#' @param removeother TRUE to remove Fusion_Type="other" and keep only in-frame and
 #' frameshift Default: FALSE
-#' @param filterAnnots regex to remove from annots column eg. 
-#' LOCAL_REARRANGEMENT|LOCAL_INVERSION 
+#' @param filterAnnots regex to remove from annots column eg.
+#' LOCAL_REARRANGEMENT|LOCAL_INVERSION
 #' ## TODO: should this mentioned above be e.g. the default value?
 #'
 #' @export
@@ -15,33 +15,37 @@
 #' @examples
 #' # standardize
 #' fusionfileArriba <- read_arriba_calls(
-#'   system.file("extdata", "arriba_example.tsv", package = "annoFuse"))
+#'   system.file("extdata", "arriba_example.tsv", package = "annoFuseData")
+#' )
 #' fusionfileStarFusion <- read_starfusion_calls(
-#'   system.file("extdata", "starfusion_example.tsv", package = "annoFuse"))
+#'   system.file("extdata", "starfusion_example.tsv", package = "annoFuseData")
+#' )
 #' formattedArriba <- fusion_standardization(fusionfileArriba,
-#'                                           caller = "ARRIBA",
-#'                                           tumorID = "tumorID")
+#'   caller = "ARRIBA",
+#'   tumorID = "tumorID"
+#' )
 #' formattedStarFusion <- fusion_standardization(fusionfileStarFusion,
-#'                                               caller = "STARFUSION",
-#'                                               tumorID = "tumorID")
+#'   caller = "STARFUSION",
+#'   tumorID = "tumorID"
+#' )
 #' # merge standardized fusion calls
 #' standardFusioncalls <- as.data.frame(rbind(formattedStarFusion, formattedArriba))
 #' fusionQCFiltered <- fusion_filtering_QC(
-#'   standardFusioncalls = standardFusioncalls, 
+#'   standardFusioncalls = standardFusioncalls,
 #'   readingFrameFilter = "in-frame|frameshift|other",
 #'   artifactFilter = "GTEx_Recurrent|DGD_PARALOGS|Normal|BodyMap|ConjoinG",
 #'   junctionReadCountFilter = 1,
 #'   spanningFragCountFilter = 10,
-#'   readthroughFilter = TRUE)
-#' # aggregate calls 
-#' aggregate_fusion_calls(fusionQCFiltered)    
-#' 
+#'   readthroughFilter = TRUE
+#' )
+#' # aggregate calls
+#' aggregate_fusion_calls(fusionQCFiltered)
 aggregate_fusion_calls <- function(standardFusioncalls,
                                    removeother = FALSE,
                                    filterAnnots) {
   standardFusioncalls <- .check_annoFuse_calls(standardFusioncalls)
   stopifnot(is.logical(removeother))
-  
+
   if (removeother) {
     # aggregate caller per FusionName, Sample and Fusion_Type
     fusion_caller.summary <- standardFusioncalls %>%
@@ -50,20 +54,20 @@ aggregate_fusion_calls <- function(standardFusioncalls,
       group_by(.data$FusionName, .data$Sample, .data$Fusion_Type) %>%
       unique() %>%
       dplyr::mutate(CalledBy = toString(.data$Caller), caller_count = n())
-    
+
     if (!missing(filterAnnots)) {
       # remove fusion within local rearrangement if required for your project
       standardFusioncalls <- standardFusioncalls %>%
         # remove local rearrangement/adjacent genes use "LOCAL_REARRANGEMENT|LOCAL_INVERSION"
         dplyr::filter(!grepl(filterAnnots, .data$annots))
     }
-    
+
     # to add aggregated caller from fusion_caller.summary
     standardFusioncalls <- standardFusioncalls %>%
       dplyr::filter(.data$Fusion_Type != "other") %>%
       left_join(fusion_caller.summary, by = (c("Sample", "FusionName", "Fusion_Type", "Caller"))) %>%
       unique()
-    
+
     return(standardFusioncalls)
   }
   else {
@@ -73,19 +77,19 @@ aggregate_fusion_calls <- function(standardFusioncalls,
       group_by(.data$FusionName, .data$Sample, .data$Fusion_Type) %>%
       unique() %>%
       dplyr::mutate(CalledBy = toString(.data$Caller), caller_count = n())
-    
+
     if (!missing(filterAnnots)) {
       # remove fusion within local rearrangement if required for your project
       standardFusioncalls <- standardFusioncalls %>%
         # remove local rearrangement/adjacent genes use "LOCAL_REARRANGEMENT|LOCAL_INVERSION"
         dplyr::filter(!grepl(filterAnnots, .data$annots))
     }
-    
+
     # to add aggregated caller from fusion_caller.summary
     standardFusioncalls <- standardFusioncalls %>%
       left_join(fusion_caller.summary, by = (c("Sample", "FusionName", "Fusion_Type", "Caller"))) %>%
       unique()
-    
+
     return(standardFusioncalls)
   }
-}
+}
diff --git a/R/annoFuse-pkg.R b/R/annoFuse-pkg.R
@@ -19,16 +19,18 @@
 #' @importFrom reshape2 colsplit dcast melt
 #' @importFrom stats na.omit
 #' @importFrom stringr str_detect str_replace
-#' @importFrom tibble add_column column_to_rownames remove_rownames 
+#' @importFrom tibble add_column column_to_rownames remove_rownames
 #' rownames_to_column
-#' @importFrom tidyr gather separate unnest one_of
+#' @importFrom tidyr gather separate unnest
+#' @importFrom tidyselect one_of
 #' @importFrom utils head read.delim browseURL
 #' @importFrom EnsDb.Hsapiens.v86 EnsDb.Hsapiens.v86
 #' @importFrom ensembldb genes
 #' @importFrom purrr is_empty
 #' @importFrom rmarkdown render
 #' @importFrom methods is
 #' @importFrom shinycssloaders withSpinner
+#' @import annoFuseData
 #'
 #' @name annoFuse-pkg
 #' @docType package
@@ -40,7 +42,7 @@ globalVariables(c(
   "gene_biotype", "Type.ct", "NAME", "Sample", "Domain",
   "Gene1A_DOMAIN_RETAINED_IN_FUSION", "Gene1B_DOMAIN_RETAINED_IN_FUSION",
   "Gene1A_anno", "Gene1B_anno", "Annot", "Annot.ct", "Annotation",
-  "JunctionReadCount", "PROT_FUSION_TYPE" ,"SpanningFragCount",
+  "JunctionReadCount", "PROT_FUSION_TYPE", "SpanningFragCount",
   "pfam_id", "LeftBreakpoint", "LeftBreakpointChr", "RightBreakpoint",
   "RightBreakpointChr"
 ))
diff --git a/R/annoFuse-utils.R b/R/annoFuse-utils.R
@@ -3,18 +3,20 @@
 
 .check_annoFuse_calls <- function(standardFusioncalls) {
   stopifnot(is(standardFusioncalls, "data.frame"))
-  
+
   # with a minimal set of columns to be there...
-  cols_fusioncalls <- c("Sample", "LeftBreakpoint", "RightBreakpoint", "FusionName",
-                        "Gene1A", "Gene1B")
-
+  cols_fusioncalls <- c(
+    "Sample", "LeftBreakpoint", "RightBreakpoint", "FusionName",
+    "Gene1A", "Gene1B"
+  )
+
   stopifnot(all(cols_fusioncalls %in% colnames(standardFusioncalls)))
-  
+
   invisible(standardFusioncalls)
 }
 
 
-#' Read in fusion calls from  Arriba v1.1.0 
+#' Read in fusion calls from  Arriba v1.1.0
 #'
 #' @param arriba_calls Please refer to software documenation [fusions.tsv](https://arriba.readthedocs.io/en/latest/output-files/)
 #'
@@ -23,12 +25,11 @@
 #'
 #' @examples
 #' fusionfileArriba <- read_arriba_calls(
-#'                         system.file("extdata", "arriba_example.tsv", package = "annoFuse"))
-#'                         
-
-read_arriba_calls <- function(arriba_calls){
+#'   system.file("extdata", "arriba_example.tsv", package = "annoFuseData")
+#' )
+read_arriba_calls <- function(arriba_calls) {
   # set col types
-  col_types = readr::cols(
+  col_types <- readr::cols(
     `#gene1` = readr::col_character(),
     gene2 = readr::col_character(),
     `strand1(gene/fusion)` = readr::col_character(),
@@ -54,8 +55,8 @@ read_arriba_calls <- function(arriba_calls){
     peptide_sequence = readr::col_character(),
     read_identifiers = readr::col_character()
   )
-  
-  arriba_calls<-read_tsv(arriba_calls, col_types = col_types)
+
+  arriba_calls <- read_tsv(arriba_calls, col_types = col_types)
   return(arriba_calls)
 }
 
@@ -68,11 +69,11 @@ read_arriba_calls <- function(arriba_calls){
 #'
 #' @examples
 #' fusionfileStarFusion <- read_starfusion_calls(
-#'                            system.file("extdata", "starfusion_example.tsv", package = "annoFuse"))
-#'                            
+#'   system.file("extdata", "starfusion_example.tsv", package = "annoFuseData")
+#' )
 read_starfusion_calls <- function(starfusion_calls) {
   # set col types
-  col_types = readr::cols(
+  col_types <- readr::cols(
     `#FusionName` = readr::col_character(),
     JunctionReadCount = readr::col_integer(),
     SpanningFragCount = readr::col_integer(),
@@ -99,8 +100,8 @@ read_starfusion_calls <- function(starfusion_calls) {
     PFAM_LEFT = readr::col_character(),
     PFAM_RIGHT = readr::col_character()
   )
-  
-  starfusion_calls<- read_tsv(starfusion_calls,col_types = col_types)
+
+  starfusion_calls <- read_tsv(starfusion_calls, col_types = col_types)
   return(starfusion_calls)
 }