Merge pull request #9 from pawelqs/develop

Develop

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: readthis
 Title: Read results from misc genomic tools
-Version: 0.5.0
+Version: 0.6.0
 Authors@R: 
     person("Paweł", "Kuś", , "[email protected]", role = c("aut", "cre"))
 Description: This package is for reading output files of: variant callers,

NAMESPACE

@@ -4,7 +4,7 @@ export(read_ascat_files)
 export(read_clip_all)
 export(read_clip_all_wide)
 export(read_clip_best_lambda)
-export(read_facets_cnvs)
+export(read_facets_cnas)
 export(read_mutect_snvs)
 export(read_strelka_somatic_snvs)
 import(dplyr)

NEWS.md

@@ -1,3 +1,6 @@
+# readthis 0.6.0
+* Naming convention changed from CNVs to CNAs
+
 # readthis 0.5.0
 * Reading ASCAT SNVs
 

R/ascat.R

@@ -1,13 +1,13 @@
 ## ------------------------------- Export --------------------------------------
 
-#' Read ASCAT CNV calls
+#' Read ASCAT CNA calls
 #'
-#' Reads the CNV variant calls and sample statistics from
-#' [ASCAT](https://github.com/VanLoo-lab/ascat) CNV caller
+#' Reads the CNA variant calls and sample statistics from
+#' [ASCAT](https://github.com/VanLoo-lab/ascat) CNA caller
 #'
 #' @param path Can be either:
-#'   1) path to a single csv file with ASCAT CNV calls
-#'   2) tibble with sample_id, cnvs, and (optionally) sample_statistics columns
+#'   1) path to a single csv file with ASCAT CNA calls
+#'   2) tibble with sample_id, cnas, and (optionally) sample_statistics columns
 #'      containing sample_ids and paths.
 #'   3) directory containing multiple ASCAT files with "*.csv" and
 #'      "*.samplestatistics.*" names.
@@ -62,32 +62,32 @@ read_ascat_files <- function(path,
     ascat <- read_ascat_files_from_dir(path, sample_id_pattern)
   }
 
-  ascat$cnvs <- use_chrom_naming_convention(ascat$cnvs, chrom_convention)
+  ascat$cnas <- use_chrom_naming_convention(ascat$cnas, chrom_convention)
   structure(ascat, class = c("cevo_ASCAT"))
 }
 
 
 ## ----------------------- Higher level functions -----------------------------
 
 read_ascat_files_single <- function(path, sample_statistics, sample_id) {
-  cnvs <- read_ascat_cnvs(path) |>
+  cnas <- read_ascat_cnas(path) |>
     mutate(sample_id = sample_id, .before = "chrom")
   if (!is.null(sample_statistics) && is_single_file(sample_statistics)) {
     stats <- read_ascat_samplestatistics(sample_statistics) |>
       mutate(sample_id = sample_id, .before = "normal_contamination")
   } else {
     stats <- empty_ascat_samplestatistics()
   }
-  lst(cnvs, sample_statistics = stats)
+  lst(cnas, sample_statistics = stats)
 }
 
 
 
 read_ascat_files_from_dataframe <- function(path) {
-  cnvs <- path |>
+  cnas <- path |>
     select("sample_id", "csv") |>
     deframe() |>
-    map(read_ascat_cnvs) |>
+    map(read_ascat_cnas) |>
     bind_rows(.id = "sample_id")
   if (is.null(path[["sample_statistics"]])) {
     stats <- empty_ascat_samplestatistics()
@@ -99,37 +99,37 @@ read_ascat_files_from_dataframe <- function(path) {
       map(read_ascat_samplestatistics) |>
       bind_rows(.id = "sample_id")
   }
-  lst(cnvs, sample_statistics = stats)
+  lst(cnas, sample_statistics = stats)
 }
 
 
 read_ascat_files_from_dir <- function(path, sample_id_pattern) {
   csv_files <- get_files(path, ".csv", sample_id_pattern)
-  cnvs <- csv_files |>
-    map(read_ascat_cnvs) |>
+  cnas <- csv_files |>
+    map(read_ascat_cnas) |>
     bind_rows(.id = "sample_id")
 
   stat_files <- get_files(path, "samplestatistics", sample_id_pattern)
   stats <- stat_files |>
     map(read_ascat_samplestatistics) |>
     bind_rows(.id = "sample_id")
-  lst(cnvs, sample_statistics = stats)
+  lst(cnas, sample_statistics = stats)
 }
 
 
 ## --------------------------- Base functions ----------------------------------
 
-read_ascat_cnvs <- function(path) {
+read_ascat_cnas <- function(path) {
   csv_cols <- c("i", "chrom", "start", "end", "normal_cn_total", "normal_cn_minor", "total_cn", "minor_cn")
-  cnvs <- read_csv(path, col_names = csv_cols, col_types = "dcdddddd") |>
+  cnas <- read_csv(path, col_names = csv_cols, col_types = "dcdddddd") |>
     mutate(major_cn = .data$total_cn - .data$minor_cn) |>
     select(
       "chrom", "start", "end",
       "total_cn", "major_cn", "minor_cn",
       normal_cn = "normal_cn_total"
     )
 
-  cnvs
+  cnas
 }
 
 

R/facets.R

@@ -1,9 +1,9 @@
 ## ------------------------------- Export --------------------------------------
 
-#' Read FACETS CNV calls
+#' Read FACETS CNA calls
 #'
 #' Reads the variant calls from [FACETS](https://github.com/mskcc/facets/tree/master)
-#' CNV caller
+#' CNA caller
 #'
 #' @param path Can be either:
 #'   1) path to a single file, sample ID can be passed using sample_id argument
@@ -17,14 +17,14 @@
 #' library(readthis)
 #'
 #' file1 <- system.file("extdata", "FACETS", "S1.csv", package = "readthis")
-#' read_facets_cnvs(file1)
+#' read_facets_cnas(file1)
 #'
 #' file2 <- system.file("extdata", "FACETS", "S2.csv", package = "readthis")
 #' files <- c(S1 = file1, S2 = file2)
-#' read_facets_cnvs(files)
+#' read_facets_cnas(files)
 #'
 #' dir <- system.file("extdata", "FACETS", package = "readthis")
-#' read_facets_cnvs(dir)
+#' read_facets_cnas(dir)
 #'
 #' @name facets
 NULL
@@ -35,14 +35,14 @@ NULL
 #' read_facets_csv() reads a single csv file. If sample_id is not provided,
 #'   file path is used
 #' @export
-read_facets_cnvs <- function(path,
+read_facets_cnas <- function(path,
                              sample_id = path,
                              chrom_convention = "UCSC") {
   if (is_single_file(path)) {
-    cnvs <- read_facets_csv(path) |>
+    cnas <- read_facets_csv(path) |>
       mutate(sample_id = sample_id, .before = "chrom")
   } else if (is_list_of_files(path)) {
-    cnvs <- map(path, read_facets_csv) |>
+    cnas <- map(path, read_facets_csv) |>
       bind_rows(.id = "sample_id")
   } else if (is_single_dir(path)) {
     files <- list.files(path, full.names = TRUE)
@@ -51,13 +51,13 @@ read_facets_cnvs <- function(path,
       map_chr(last) |>
       str_replace(".csv", "")
     names(files) <- sample_ids
-    cnvs <- files |>
+    cnas <- files |>
       set_names(sample_ids) |>
       map(read_facets_csv) |>
       bind_rows(.id = "sample_id")
   }
 
-  cnvs |>
+  cnas |>
     use_chrom_naming_convention(chrom_convention)
 }
 
@@ -66,10 +66,10 @@ read_facets_cnvs <- function(path,
 
 
 read_facets_csv <- function(file, chrom_convention = "UCSC") {
-  cnvs <- read_csv(file, col_types = "cddddddddiidiidd") |>
+  cnas <- read_csv(file, col_types = "cddddddddiidiidd") |>
     prepare_FACETS_columns()
-  class(cnvs) <- c("cevo_FACETS", class(cnvs))
-  cnvs
+  class(cnas) <- c("cevo_FACETS", class(cnas))
+  cnas
 }
 
 

README.md

@@ -26,8 +26,8 @@ devtools::install_github("pawelqs/readthis")
 
 - [Strelka2](https://github.com/Illumina/strelka) (somatic SNVs only): `read_strelka_somatic_snvs()`
 - [Mutect2](https://github.com/Illumina/strelka) SNVs: `read_mutect_snvs()`
-- [FACETS](https://github.com/mskcc/facets) CNVs: `read_facets_cnvs()`
-- [ASCAT](https://github.com/VanLoo-lab/ascat) CNVs: `read_ascat_files()` (does not work with all the files)
+- [FACETS](https://github.com/mskcc/facets) CNAs: `read_facets_cnas()`
+- [ASCAT](https://github.com/VanLoo-lab/ascat) CNAs: `read_ascat_files()` (does not work with all the files)
 
 **Other tools:**
 

tests/testthat/test-ascat.R

@@ -1,6 +1,6 @@
 test_that("read_ascat_csv() works", {
   path <- test_path("ASCAT", "S1.csv")
-  res <- read_ascat_cnvs(path)
+  res <- read_ascat_cnas(path)
   expect_s3_class(res, "tbl")
   expect_equal(dim(res), c(10, 7))
 })
@@ -17,24 +17,24 @@ test_that("read_ascat_samplestatistics() works", {
 
 
 
-test_that("read_ascat_files() works with cnvs only", {
+test_that("read_ascat_files() works with cnas only", {
   path <- test_path("ASCAT", "S1.csv")
   res <- read_ascat_files(path)
   expect_s3_class(res, "cevo_ASCAT")
-  expect_equal(dim(res$cnvs), c(10, 8))
-  expect_equal(unique(res$cnvs$sample_id), test_path("ASCAT", "S1.csv"))
+  expect_equal(dim(res$cnas), c(10, 8))
+  expect_equal(unique(res$cnas$sample_id), test_path("ASCAT", "S1.csv"))
 })
 
 
 
-test_that("read_ascat_files() works with cnvs and sample statistics", {
+test_that("read_ascat_files() works with cnas and sample statistics", {
   path <- test_path("ASCAT", "S1.csv")
   sample_statistics <- test_path("ASCAT", "S1.samplestatistics.txt")
   res <- read_ascat_files(path, sample_statistics)
   expect_s3_class(res, "cevo_ASCAT")
-  expect_equal(dim(res$cnvs), c(10, 8))
+  expect_equal(dim(res$cnas), c(10, 8))
   expect_equal(dim(res$sample_statistics), c(1, 8))
-  expect_equal(unique(res$cnvs$sample_id), test_path("ASCAT", "S1.csv"))
+  expect_equal(unique(res$cnas$sample_id), test_path("ASCAT", "S1.csv"))
   expect_equal(unique(res$sample_statistics$sample_id), test_path("ASCAT", "S1.csv"))
 })
 
@@ -50,7 +50,7 @@ test_that("read_ascat_files() works with tibble of files", {
   )
   res <- read_ascat_files(path)
   expect_s3_class(res, "cevo_ASCAT")
-  expect_equal(dim(res$cnvs), c(20, 8))
+  expect_equal(dim(res$cnas), c(20, 8))
   expect_equal(dim(res$sample_statistics), c(2, 8))
   expect_equal(unique(res$sample_statistics$sample_id), c("S1", "S2"))
 })
@@ -67,9 +67,9 @@ test_that("read_ascat_files() works with tibble of files with NAs", {
   )
   res <- read_ascat_files(path)
   expect_s3_class(res, "cevo_ASCAT")
-  expect_equal(dim(res$cnvs), c(20, 8))
+  expect_equal(dim(res$cnas), c(20, 8))
   expect_equal(dim(res$sample_statistics), c(1, 8))
-  expect_equal(unique(res$cnvs$sample_id), c("S1", "S2"))
+  expect_equal(unique(res$cnas$sample_id), c("S1", "S2"))
   expect_equal(unique(res$sample_statistics$sample_id), "S1")
 })
 
@@ -79,7 +79,7 @@ test_that("read_ascat_files() works with directory", {
   path <- test_path("ASCAT")
   res <- read_ascat_files(path)
   expect_s3_class(res, "cevo_ASCAT")
-  expect_equal(dim(res$cnvs), c(20, 8))
+  expect_equal(dim(res$cnas), c(20, 8))
   expect_equal(dim(res$sample_statistics), c(2, 8))
   expect_equal(unique(res$sample_statistics$sample_id), c("S1", "S2"))
 })

tests/testthat/test-facets.R

@@ -1,26 +1,26 @@
-test_that("read_facets_cnvs() works with single file", {
+test_that("read_facets_cnas() works with single file", {
   path <- test_path("FACETS", "S1.csv")
-  res <- read_facets_cnvs(path)
+  res <- read_facets_cnas(path)
   expect_s3_class(res, "cevo_FACETS")
   expect_equal(dim(res), c(64, 18))
   expect_equal(unique(res$sample_id), path)
 })
 
 
-test_that("read_facets_cnvs() works with dir path file", {
+test_that("read_facets_cnas() works with dir path file", {
   path <- test_path("FACETS")
-  res <- read_facets_cnvs(path)
+  res <- read_facets_cnas(path)
   expect_s3_class(res, "cevo_FACETS")
   expect_equal(dim(res), c(128, 18))
   expect_equal(unique(res$sample_id), c("S1", "S2"))
 })
 
 
-test_that("read_facets_cnvs() works with list of files", {
+test_that("read_facets_cnas() works with list of files", {
   path <- test_path("FACETS")
   path <- list.files(path, full.names = TRUE) |>
     set_names(c("S1", "S2"))
-  res <- read_facets_cnvs(path)
+  res <- read_facets_cnas(path)
   expect_s3_class(res, "cevo_FACETS")
   expect_equal(dim(res), c(128, 18))
   expect_equal(unique(res$sample_id), c("S1", "S2"))