update testthat tests, params and version bump

DESCRIPTION

@@ -1,16 +1,16 @@
 Package: svaNUMT
 Type: Package
 Title: NUMT detection from structural variant calls
-Version: 1.1.1
-Date: 2021-03-09
+Version: 1.1.2
+Date: 2022-03-07
 Authors@R: c(
 	person("Ruining", "Dong", email="lnyidrn@gmail.com", role=c("aut", "cre"), comment=c(ORCID = "0000-0003-1433-0484")))
 Description: svaNUMT contains functions for detecting NUMT events from structural variant calls. 
     It takes structural variant calls in GRanges of breakend notation and identifies NUMTs by 
     nuclear-mitochondrial breakend junctions. The main function reports candidate NUMTs if there is a pair of valid insertion 
     sites found on the nuclear genome within a certain distance threshold.
     The candidate NUMTs are reported by events.
-License: GPL-3
+License: GPL-3 + file LICENSE
 Depends:
 	GenomicRanges,
 	rtracklayer,
@@ -21,7 +21,6 @@ Depends:
     R (>= 4.0)
 Imports:
     assertthat,
-    Biostrings,
     stringr,
     dplyr,
     methods,
@@ -40,7 +39,6 @@ Suggests:
     readr,
     plyranges,
     circlize,
-    tictoc,
     IRanges,
     SummarizedExperiment,
     rmarkdown

R/eventDetection.R

@@ -6,15 +6,18 @@
 #' nuclear chromosome and mitochondrial genome. Only BND notations are supported at the current stage.
 #' Possible linked nuclear insertion sites are reported by chromosome in GRanges format.
 #' @param gr A GRanges object
-#' @param max_ins_dist The maximum distance allowed on the reference genome between the paired insertion sites.
-#' Only intra-chromosomal NUMT events are supported. Default value is 10.
+#' @inheritParams numtDetect_MT
+#' @inheritParams numtDetect_insseq
+#' @inheritParams numtDetect_known
 #' @return A nested list of GRanges objects of candidate NUMTs.
 #' @examples
 #' vcf.file <- system.file("extdata", "MT.vcf", package = "svaNUMT")
 #' vcf <- VariantAnnotation::readVcf(vcf.file, "hg19")
 #' gr <- breakpointRanges(vcf, nominalPosition=TRUE)
-#' library(BSgenome.Hsapiens.UCSC.hg19)
-#' genome <- BSgenome.Hsapiens.UCSC.hg19
+#' numtS <- readr::read_table(system.file("extdata", "numtS.txt", package = "svaNUMT"), col_names = FALSE)
+#' colnames(numtS) <- c("bin", "seqnames", "start", "end", "name", "score", "strand")
+#' numtS <- `seqlevelsStyle<-`(GRanges(numtS), "NCBI")
+#' genome <- BSgenome.Hsapiens.UCSC.hg19::BSgenome.Hsapiens.UCSC.hg19
 #' genomeMT <- genome$chrMT
 #' numt.gr <- numtDetect(gr, numtS, genomeMT, max_ins_dist=20)
 #' @export

R/insSeq.R

@@ -13,7 +13,6 @@
 #' @return A nested list of GRanges objects of candidate NUMTs.
 numtDetect_insseq <- function(gr, genomeMT, min_len=20, min.Align=0.8){
     assertthat::assert_that(is(gr, "GRanges"), msg = "gr should be a GRanges object")
-    assertthat::assert_that(is(numtS, "GRanges"), msg = "numtS should be a GRanges object")
     assertthat::assert_that(!isEmpty(gr), msg = "gr can't be empty")
     gr <- gr[seqnames(gr) %in% standardChromosomes(gr) & 
                  seqnames(partner(gr)) %in% standardChromosomes(gr)]

R/numtS.R

@@ -6,7 +6,7 @@
 #' @param numtS A GRanges object of known NUMT sites.
 #' @param max_ins_dist The maximum distance allowed on the reference genome between the paired insertion sites.
 #' Only intra-chromosomal NUMT events are supported. Default value is 10.
-#' @param gaxgap_numtS The maximum distance allowed betweeen the insertion sequence loci and known NUMTs.
+#' @param maxgap_numtS The maximum distance allowed betweeen the insertion sequence loci and known NUMTs.
 #' @keywords internal
 #' @return A nested list of GRanges objects of candidate NUMTs.
 numtDetect_known <- function(gr, numtS, max_ins_dist=10, maxgap_numtS=10){

tests/testthat.R

@@ -1,4 +1,5 @@
 library(testthat)
 library(svaNUMT)
 
+
 test_check("svaNUMT")

tests/testthat/test-eventDetection.R

@@ -1,30 +1,72 @@
 context('event detection functions')
+library(readr)
+library(BSgenome.Hsapiens.UCSC.hg19)
 na12878 <- readVcf(system.file("extdata", "gridss-na12878.vcf", package = "svaNUMT"))
 numt <- readVcf(system.file("extdata", "MT.vcf", package = "svaNUMT"))
+#known NUMTs as GRanges
+numtS <- read_table(system.file("extdata", "numtS.txt", package = "svaNUMT"), col_names = FALSE)
+colnames(numtS) <- c("bin", "seqnames", "start", "end", "name", "score", "strand")
+numtS <- `seqlevelsStyle<-`(GRanges(numtS), "NCBI")
+#mitochondria reference genome
+genomeMT <- BSgenome.Hsapiens.UCSC.hg19$chrMT
+#default numtDetect() parameters
+max_ins_dist=10
+maxgap_numtS=10 
+min_len=20
+min.Align=0.8
 
 #NUMT detection
-test_that("numtDetect returns nothing with no nu-mt fusion", {
+test_that("numtDetect returns an empty list and messages with no nu-mt fusion", {
     gr <- suppressWarnings(breakpointRanges(na12878))
-    expect_equal(NULL,numtDetect(gr))
-    expect_message(numtDetect(gr), 
+    expect_equal(list(MT=NULL, known=NULL, insSeq=NULL),
+                 numtDetect(gr, numtS, genomeMT, 
+                                 max_ins_dist = 10, maxgap_numtS=maxgap_numtS, 
+                                 min_len=min_len, min.Align=min.Align))
+    expect_message(numtDetect(gr, numtS, genomeMT, 
+                              max_ins_dist = 10, maxgap_numtS=maxgap_numtS, 
+                              min_len=min_len, min.Align=min.Align), 
                    "There is no NUMT event detected. Check whether 'chrM' or 'MT' is present in the VCF.")
+    expect_message(numtDetect(gr, numtS, genomeMT, 
+                              max_ins_dist = 10, maxgap_numtS=maxgap_numtS, 
+                              min_len=min_len, min.Align=min.Align), 
+                   "There is no MT sequence from known NUMT events detected.")
+    expect_message(numtDetect(gr, numtS, genomeMT, 
+                              max_ins_dist = 10, maxgap_numtS=maxgap_numtS, 
+                              min_len=min_len, min.Align=min.Align), 
+                   "There is no NUMT event detected by insertion sequences.")
 })
 
-test_that("numtDetect returns nothing but message when no paired candidate insertion site is found within the given threshold", {
+test_that("numtDetect returns an empty and message when no paired candidate insertion site is found within the given threshold", {
     gr <- suppressWarnings(breakpointRanges(numt))
-    expect_equal(NULL, numtDetect(gr, 10))
-    expect_message(numtDetect(gr, 10), 
+    expect_equal(list(MT=NULL, known=NULL, insSeq=NULL), 
+                 numtDetect(gr, numtS, genomeMT, 
+                                  max_ins_dist = 10, maxgap_numtS=maxgap_numtS, 
+                                  min_len=min_len, min.Align=min.Align))
+    expect_message(numtDetect(gr, numtS, genomeMT, 
+                              max_ins_dist = 10, maxgap_numtS=maxgap_numtS, 
+                              min_len=min_len, min.Align=min.Align), 
                    "There is no NUMT event detected. Paired candidate insertion site not found.")
-
+    expect_message(numtDetect(gr, numtS, genomeMT, 
+                              max_ins_dist = 10, maxgap_numtS=maxgap_numtS, 
+                              min_len=min_len, min.Align=min.Align), 
+                   "There is no MT sequence from known NUMT events detected.")
+    expect_message(numtDetect(gr, numtS, genomeMT, 
+                              max_ins_dist = 10, maxgap_numtS=maxgap_numtS, 
+                              min_len=min_len, min.Align=min.Align), 
+                   "There is no NUMT event detected by insertion sequences.")
     # expect_equal(c("11", "11", "MT", "MT"), as.character(seqnames(gr)))
     # expect_equal(c(49883572, 49883585, 16093, 16493), start(gr))
     # expect_equal(c(49883572, 49883585, 16093, 16493), end(gr))
     # expect_equal(c("+", "-", "-", "+"), as.character(strand(gr)))
     # expect_equal(CharacterList("gridss9h", "gridss39h", "gridss9h", "gridss39h"), gr$candidatePartnerId)
 })
 
-test_that("numtDetect returns a list of 2 when candidate NUMTs are found", {
+test_that("numtDetect returns a list element MT which consists of 2 lists when 
+          candidate NUMTs by MT breakpoints are found", {
     gr <- suppressWarnings(breakpointRanges(numt))
-    expect_equal(2, length(numtDetect(gr, 20)))
+    NUMT <- numtDetect(gr, numtS, genomeMT, 
+               max_ins_dist = 20, maxgap_numtS=maxgap_numtS, 
+               min_len=min_len, min.Align=min.Align)
+    expect_equal(2, length(NUMT$MT))
 })