Version 1.0.8

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

@@ -5,11 +5,6 @@ on:
     workflows: [document]
     types:
       - completed
-  push:
-    branches: [main, master]
-    paths: ["tests/**"]
-  pull_request:
-    branches: [main, master]
 
 name: R-CMD-check
 

.github/workflows/dos2unix.yaml

@@ -2,7 +2,7 @@
 # Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
 on:
   push:
-    paths: ["R/**"]
+    paths: ["R/**", "tests/**"]
 
 name: dos2unix
 
@@ -18,13 +18,16 @@ jobs:
         run: sudo apt-get install dos2unix
 
       - name: Run dos2unix
-        run: find ./R -type f -name "*.R" -exec dos2unix {} \;
+        run: |
+          find ./R -type f -name "*.R" -exec dos2unix {} \;
+          find ./tests/testthat -type f -name "*.R" -exec dos2unix {} \;
 
       - name: Commit and push changes
         run: |
           git config --local user.name "$GITHUB_ACTOR"
           git config --local user.email "$GITHUB_ACTOR@users.noreply.github.com"
           git add ./R/*.R
+          git add ./tests/testthat/*.R
           git commit -m "Conversion of R files from CRLF to LF" || echo "No changes to commit"
           git pull --ff-only
           git push origin

CHANGELOG.md

@@ -1,5 +1,13 @@
 CHANGELOG
 ---------
+#### Version 1.0.8 (2024.02.22)
+* Handling of GenBank features with multiple qualifiers of the same name
+* Coverage summaries added to `verbose` output files
+* Parameters `syntenyLineType` and `regionsCheck` for `PACVr.complete()` have been combined into `IRCheck`
+* Support for PNG `output`
+* Samples without `note` can be used for standard coverage analysis
+* Sample name in BAM file can match either `VERSION` or `ACCESSION` of GenBank file for `verbose` analysis
+* Analysis continues without regions when IR presence test unsuccessful 
 
 #### Version 1.0.7 (2024.02.01)
 * More robust parsing of feature sequence locations using INSDC standards

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: PACVr
-Version: 1.0.7
-Date: 2024-02-01
+Version: 1.0.8
+Date: 2024-02-22
 Title: Plastome Assembly Coverage Visualization
 Authors@R: c(person("Gregory", "Smith", role=c("ctb")),
              person("Nils", "Jenke", role=c("ctb")),
@@ -19,7 +19,8 @@ Imports:
     RCircos (>= 1.2.0),
     grDevices,
     stats,
-    utils
+    utils,
+    tidyr
 Description: Visualizes the coverage depth of a complete plastid genome as well as the equality of its inverted repeat regions in relation to the circular, quadripartite genome structure and the location of individual genes. For more information, please see Gruenstaeudl and Jenke (2020) <doi:10.1186/s12859-020-3475-0>.
 License: BSD 3-clause License + file LICENSE
 RoxygenNote: 7.3.1

NAMESPACE

@@ -7,6 +7,7 @@ importFrom(dplyr,"%>%")
 importFrom(grDevices,colors)
 importFrom(grDevices,dev.off)
 importFrom(grDevices,pdf)
+importFrom(grDevices,png)
 importFrom(stats,aggregate)
 importFrom(stats,cov)
 importFrom(stats,sd)

R/IRoperations.R

@@ -1,10 +1,9 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.02.01.1736"
+#version="2024.02.22.2236"
 
-checkIREquality <- function(gbkData, regions, dir, sample_name) {
-  gbkSeq <- read.gbSeq(gbkData)
+checkIREquality <- function(gbkSeq, regions, dir, sample_name) {
   if ("IRb" %in% regions[, 4] && "IRa" %in% regions[, 4]) {
     repeatB <- as.numeric(regions[which(regions[, 4] == "IRb"), 2:3])
     repeatA <-

R/PACVr-package.R

@@ -2,16 +2,17 @@
 "_PACKAGE"
 
 ## usethis namespace: start
+#' @export RCircos.Env 
 #' @importFrom dplyr %>%
 #' @importFrom grDevices colors
 #' @importFrom grDevices dev.off
 #' @importFrom grDevices pdf
+#' @importFrom grDevices png
+#' @importFrom RCircos RCircos.Env
 #' @importFrom stats aggregate
 #' @importFrom stats cov
 #' @importFrom stats sd
 #' @importFrom utils write.csv
 #' @importFrom utils write.table
-#' @importFrom RCircos RCircos.Env
-#' @export RCircos.Env 
 ## usethis namespace: end
 NULL

R/PACVr.R

@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.02.01.1736"
+#version="2024.02.22.2236"
 
 PACVr.read.gb <- function(gbkFile) {
   gbkRaw <- getGbkRaw(gbkFile)
@@ -12,121 +12,50 @@ PACVr.read.gb <- function(gbkFile) {
   return(gbkData)
 }
 
-PACVr.parseName <- function (gbkData) {
-  return(read.gbSampleName(gbkData))
-}
-
-PACVr.parseQuadripRegions <- function (gbkData, gbkDataDF) {
-  raw_quadripRegions <- ParseQuadripartiteStructure(gbkDataDF)
-  quadripRegions <- fillDataFrame(gbkData, raw_quadripRegions)
-  return(quadripRegions)
-}
-
-PACVr.parseSource <- function(gbkDataDF) {
-  return(parseSource(gbkDataDF))
-}
-
-PACVr.parseGenes <- function (gbkDataDF) {
-  # This function parses the genes of a GenBank file
-  logger::log_info('Parsing the different genes')
-  genes <- ExtractAllGenes(gbkDataDF)
-  return(genes)
-}
-
-PACVr.calcCoverage <-
-  function (bamFile, windowSize=250) {
-    logger::log_info('Calculating the sequencing coverage')
-    coverage <- CovCalc(bamFile, windowSize)
-    return(coverage)
-  }
-
-PACVr.generateIRGeneData <- function(genes, quadripRegions,
-                                     syntenyLineType) {
-  # Parse GenBank file
-  if ("IRb" %in% quadripRegions[, 4] &&
-      "IRa" %in% quadripRegions[, 4]) {
-    linkData <- GenerateIRSynteny(genes, syntenyLineType)
-    return(linkData)
-  }
-  return(-1)
-}
-
 PACVr.verboseInformation <- function(gbkData,
-                                     bamFile,
-                                     genes,
-                                     quadripRegions,
+                                     coverageRaw,
                                      analysisSpecs,
-                                     output) {
-  sampleName <- PACVr.parseName(gbkData)
-  verbosePath <- getVerbosePath(sampleName, output)
-  printCovStats(bamFile,
-                genes,
-                quadripRegions,
+                                     plotSpecs) {
+  sampleName <- gbkData$sampleName
+  verbosePath <- getVerbosePath(sampleName,
+                                plotSpecs)
+  printCovStats(coverageRaw,
+                gbkData$genes,
+                gbkData$quadripRegions,
                 sampleName,
                 analysisSpecs,
                 verbosePath)
-  if (!is.null(analysisSpecs$syntenyLineType)) {
-    checkIREquality(gbkData,
-                    quadripRegions,
+  if (analysisSpecs$isSyntenyLine) {
+    checkIREquality(gbkData$seq,
+                    gbkData$quadripRegions,
                     verbosePath,
                     sampleName)
   }
   logger::log_info('Verbose output saved in `{verbosePath}`')
 }
 
 PACVr.visualizeWithRCircos <- function(gbkData,
-                                       genes,
-                                       quadripRegions,
                                        coverage,
-                                       windowSize,
-                                       logScale,
-                                       threshold,
-                                       relative,
-                                       linkData,
-                                       syntenyLineType,
-                                       textSize) {
-  # Step 1. Generate plot title
-  plotTitle <- read.gbPlotTitle(gbkData)
-  # Step 2. Visualize
+                                       analysisSpecs,
+                                       plotSpecs) {
+  logger::log_info('Generating a visualization of the sequencing coverage')
+  isOutput <- plotSpecs$isOutput
+
+  if (isOutput) {
+    createVizFile(plotSpecs)
+  }
+
   visualizeWithRCircos(
-    plotTitle,
-    genes,
-    quadripRegions,
+    gbkData,
     coverage,
-    windowSize,
-    threshold,
-    logScale,
-    relative,
-    linkData,
-    syntenyLineType,
-    textSize
+    analysisSpecs,
+    plotSpecs
   )
-}
-
-PACVr.quadripRegions <- function(gbkData,
-                                 gbkDataDF,
-                                 isIRCheck) {
-  if (isIRCheck) {
-    logger::log_info('Parsing the quadripartite genome structure')
-    quadripRegions <- PACVr.parseQuadripRegions(gbkData,
-                                                gbkDataDF)
-  } else {
-    quadripRegions <- PACVr.parseSource(gbkDataDF)
-  }
-  return(quadripRegions)
-}
 
-PACVr.linkData <- function(genes,
-                           quadripRegions,
-                           syntenyLineType) {
-  linkData <- NULL
-  if (!is.null(syntenyLineType)) {
-    logger::log_info('Inferring the IR regions and the genes within the IRs')
-    linkData <- PACVr.generateIRGeneData(genes,
-                                         quadripRegions,
-                                         syntenyLineType)
+  if (isOutput) {
+    dev.off()
+    logger::log_info('Visualization saved as `{plotSpecs$output}`')
   }
-  return(linkData)
 }
 
 #' @title Execute the complete pipeline of \pkg{PACVr}
@@ -191,79 +120,44 @@ PACVr.complete <- function(gbkFile,
                            verbose=FALSE,
                            output=NA) {
   ######################################################################
-  gbkData <- PACVr.read.gb(gbkFile)
-  analysisSpecs <- getAnalysisSpecs(IRCheck)
-  gbkDataDF <- read.gb2DF(gbkData,
-                          analysisSpecs)
-  if (is.null(gbkDataDF)) {
-    logger::log_error(paste("No usable data to perform specified analysis"))
-    return(NULL)
+  read.gbData <- PACVr.read.gb(gbkFile)
+  analysisSpecs <- getAnalysisSpecs(IRCheck,
+                                    windowSize)
+  gbkData <- PACVr.gbkData(read.gbData,
+                           analysisSpecs)
+  rm(read.gbData)
+  gc()
+  if (is.null(gbkData)) {
+    logger::log_fatal('Unsuccessful.')
+    return(-1)
   }
-
-  ###################################
-  quadripRegions <- PACVr.quadripRegions(gbkData,
-                                         gbkDataDF,
-                                         analysisSpecs$isIRCheck)
 
   ###################################
-  genes <- PACVr.parseGenes(gbkDataDF)
+  plotSpecs <- getPlotSpecs(logScale,
+                            threshold,
+                            relative,
+                            textSize,
+                            output)
 
   ###################################
   coverage <- PACVr.calcCoverage(bamFile,
-                                 windowSize)
-
-  ###################################
-  linkData <- PACVr.linkData(genes,
-                             quadripRegions,
-                             analysisSpecs$syntenyLineType)
+                                 analysisSpecs$windowSize,
+                                 plotSpecs$logScale)
 
   ###################################
   if (verbose) {
     PACVr.verboseInformation(gbkData,
-                             bamFile,
-                             genes,
-                             quadripRegions,
+                             coverage$raw,
                              analysisSpecs,
-                             output)
+                             plotSpecs)
   }
 
   ###################################
-  if (!is.na(output)) {
-    logger::log_info('Generating a visualization of the sequencing coverage')
-    pdf(output, width=10, height=10)
-    PACVr.visualizeWithRCircos(
-      gbkData,
-      genes,
-      quadripRegions,
-      coverage,
-      windowSize,
-      threshold,
-      logScale,
-      relative,
-      linkData,
-      IRCheck,
-      textSize
-    )
-    dev.off()
-    logger::log_info('Visualization (including coverage) saved as `{output}`')
-  } else {
-    logger::log_info('No coverage data inferred; generating empty visualization')
-    PACVr.visualizeWithRCircos(
-      gbkData,
-      genes,
-      quadripRegions,
-      coverage,
-      windowSize,
-      threshold,
-      logScale,
-      relative,
-      linkData,
-      IRCheck,
-      textSize
-    )
-    dev.off()
-    logger::log_info('Visualization (excluding coverage) saved as `{output}`')
-  }
+  PACVr.visualizeWithRCircos(gbkData,
+                             coverage$plot,
+                             analysisSpecs,
+                             plotSpecs)
+
   ######################################################################
   logger::log_success('Done.')
   ######################################################################

R/customizedRCircos.R

@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.02.01.1736"
+#version="2024.02.22.2236"
 
 
 # The following R functions were taken from the R package RCircos and then modified.