Merge pull request #44 from alephnull7/master

Updates to tabular stats and paper figures
michaelgruenstaeudl · May 25, 2024 · 3d70111 · 3d70111
2 parents 3cac42c + 1689c2d
commit 3d70111
Show file tree

Hide file tree

Showing 26 changed files with 218 additions and 146 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,7 +1,17 @@
 CHANGELOG
 ---------
 
-#### Version 1.1.1 (2024.05.20)
+#### Version 1.1.2 (2024.05.24)
+* Updates to summary tabular statistics files
+  * Inclusion of unpartitioned statistics for coding and noncoding regions summaries
+  * Standardize name of summary groups to `Chromosome`
+  * Update WRSD metric to in terms of kilobases
+* Updates to `scripts_for_figures_tables`
+  * `Figure1` updated to use manual jittering for boxplot with outlier labels
+  * Include `Figure1b` in output file
+  * Changes to value exactness in some tables
+
+#### Version 1.1.1 (2024.05.21)
 * Minor fixes to tabular statistics file creation
 * A coverage of 0 for a window is always labeled as low coverage
 

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: PACVr
-Version: 1.1.1
-Date: 2024-05-20
+Version: 1.1.2
+Date: 2024-05-24
 Title: Plastome Assembly Coverage Visualization
 Authors@R: c(person("Gregory", "Smith", role=c("ctb")),
              person("Nils", "Jenke", role=c("ctb")),

diff --git a/R/AnalysisSpecs.R b/R/AnalysisSpecs.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 AnalysisSpecs <- R6Class("AnalysisSpecs",
   public = list(
@@ -10,9 +10,9 @@ AnalysisSpecs <- R6Class("AnalysisSpecs",
     isIRCheck = FALSE,
     windowSize = 250,
     isSyntenyLine = FALSE,
-    regions_name = "Source",
-    regions_start = "srcStart",
-    regions_end = "srcEnd",
+    regions_name = "Chromosome",
+    regions_start = "chromStart",
+    regions_end = "chromEnd",
 
     # constructor
     initialize = function(IRCheck = NA,
@@ -26,7 +26,6 @@ AnalysisSpecs <- R6Class("AnalysisSpecs",
       private$setSyntenyLineType(IRCheck)
       private$setIsIRCheck(IRCheck)
       private$setIsSyntenyLine()
-      private$setCovFields()
     }
   ),
 
@@ -59,19 +58,6 @@ AnalysisSpecs <- R6Class("AnalysisSpecs",
     # precondition: `syntenyLineType` is set
     setIsSyntenyLine = function() {
       self$isSyntenyLine <- !is.null(self$syntenyLineType)
-    },
-
-    # precondition: `isIRCheck` is set
-    setCovFields = function() {
-      if (self$isIRCheck) {
-        self$regions_name <- "Chromosome"
-        self$regions_start <- "chromStart"
-        self$regions_end <- "chromEnd"
-      } else {
-        self$regions_name <- "Source"
-        self$regions_start <- "srcStart"
-        self$regions_end <- "srcEnd"
-      }
     }
   )
 )

diff --git a/R/GBKData.R b/R/GBKData.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 GBKData <- R6Class("GBKData",
   public = list(

diff --git a/R/IROps.R b/R/IROps.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 checkIREquality <- function(gbkData,
                             analysisSpecs) {

diff --git a/R/OutputSpecs.R b/R/OutputSpecs.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 OutputSpecs <- R6Class("OutputSpecs",
   public = list(

diff --git a/R/PACVr.R b/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="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 PACVr.read.gb <- function(gbkFile) {
   gbkRaw <- getGbkRaw(gbkFile)

diff --git a/R/RCircosOps.R b/R/RCircosOps.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 
 # The following R functions were taken from the R package RCircos and then modified.

diff --git a/R/compileStats.R b/R/compileStats.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 PACVr.compileCovStats <- function(gbkData,
                                   coverageRaw,

diff --git a/R/coverageCalcOps.R b/R/coverageCalcOps.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 CovCalc <- function(coverageRaw,
                     windowSize = 250,
@@ -159,41 +159,58 @@ setLowCoverage <- function(covDataField, regions_name = NULL) {
 # adapted from `nilsj9/PlastidSequenceCoverage`
 getCovSummaries <- function(covData,
                             analysisSpecs) {
-  regions_name <- analysisSpecs$regions_name
-
   covData <- filterCovData(covData,
                            analysisSpecs)
   covSummaries <- getCovDepths(covData,
-                               regions_name)
-  covSummaries <- updateRegionsSummary(covSummaries,
-                                       covData$ir_regions,
-                                       regions_name)
+                               analysisSpecs$regions_name)
+  covSummaries <- updateSummaries(covSummaries,
+                                  covData,
+                                  analysisSpecs)
+  return(covSummaries)
+}
+
+updateSummaries <- function(covSummaries,
+                            covData,
+                            analysisSpecs) {
+  covSummaries$regions_summary <- updateCovSummary(covSummaries$regions_summary,
+                                                   covData$ir_regions,
+                                                   analysisSpecs,
+                                                   TRUE)
+  covSummaries$genes_summary <- updateCovSummary(covSummaries$genes_summary,
+                                                 covData$ir_genes,
+                                                 analysisSpecs)
+  covSummaries$noncoding_summary <- updateCovSummary(covSummaries$noncoding_summary,
+                                                     covData$ir_noncoding,
+                                                     analysisSpecs)
   return(covSummaries)
 }
 
-updateRegionsSummary <- function(covSummaries,
-                                 covDataRegions,
-                                 regions_name) {
-  covSumRegions <- covSummaries$regions_summary
-  regions_evenness <- getCovEvenness(covDataRegions,
-                                     regions_name)
-  if (regions_name == "Source") {
-    covSumRegions[regions_name] <- "Complete_genome"
-    regions_evenness[regions_name] <- "Complete_genome"
+updateCovSummary <- function(covSummary,
+                             covDataField,
+                             analysisSpecs,
+                             isRegions = FALSE) {
+  regions_name <- analysisSpecs$regions_name
+  isIRCheck <- analysisSpecs$isIRCheck
+
+  cov_evenness <- getCovEvenness(covDataField,
+                                 regions_name)
+  if (!isIRCheck) {
+    unpartName <- ifelse(isRegions, "Complete_genome", "Unpartitioned")
+    covSummary[regions_name] <- unpartName
+    cov_evenness[regions_name] <- unpartName
   }
-  covSumRegions <- dplyr::full_join(covSumRegions,
-                                    regions_evenness,
-                                    regions_name)
-
-  if (regions_name != "Source") {
-    genome_summary <- getGenomeSummary(covDataRegions,
-                                       regions_name)
-    covSumRegions <- dplyr::bind_rows(covSumRegions,
-                                      genome_summary)
+  covSummary <- dplyr::full_join(covSummary,
+                                 cov_evenness,
+                                 regions_name)
+
+  if (isIRCheck) {
+    genome_summary <- getGenomeSummary(covDataField,
+                                       regions_name,
+                                       isRegions)
+    covSummary <- dplyr::bind_rows(covSummary,
+                                   genome_summary)
   }
-
-  covSummaries$regions_summary <- covSumRegions
-  return(covSummaries)
+  return(covSummary)
 }
 
 filterCovData <- function(covData,
@@ -256,7 +273,7 @@ getCovDepth <- function(covDataField, regions_name = NULL) {
   }
   covDepth <- covDataField %>%
     calcCovDepth()
-  if (!is.null(regions_name) && regions_name == "Source") {
+  if (nrow(covDepth) == 1) {
     covDepth[regions_name] <- "Unpartitioned"
   }
   return(covDepth)
@@ -275,19 +292,19 @@ calcCovDepth <- function(df) {
       lowCovWin_abs = sum(lowCoverage == "*", na.rm = TRUE),
       regionLen = sum(length, na.rm = TRUE),
       .groups = "drop") %>%
-    addLowCovWin_relToRegionLen()
+    addLowCovWin_perKilobase()
   )
 }
 
-addLowCovWin_relToRegionLen <- function(df) {
+addLowCovWin_perKilobase <- function(df) {
   lowCovWin_abs <-
-    lowCovWin_relToRegionLen <-
+    lowCovWin_perKilobase <-
     regionLen <-
     NULL
 
   return (
     df %>%
-    dplyr::mutate(lowCovWin_relToRegionLen = lowCovWin_abs / regionLen)
+    dplyr::mutate(lowCovWin_perKilobase = lowCovWin_abs / regionLen * 1000)
   )
 }
 
@@ -326,13 +343,17 @@ evennessScore <- function(coverage) {
   return(E)
 }
 
-getGenomeSummary <- function(covDataField, regions_name) {
+getGenomeSummary <- function(covDataField, regions_name, isRegions) {
   genome_depth <- getCovDepth(covDataField)
   genome_evenness <- getCovEvenness(covDataField)
 
   genome_summary <- genome_depth %>%
     dplyr::bind_cols(genome_evenness)
-  genome_summary[regions_name] <- "Complete_genome"
+  if (isRegions) {
+    genome_summary[regions_name] <- "Complete_genome"
+  } else {
+    genome_summary[regions_name] <- "Unpartitioned"
+  }
   return(genome_summary)
 }
 
diff --git a/R/customRead.gb.R b/R/customRead.gb.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 read.gbWithHandling <- function(gbkRaw, count=0) {
   gbkData <- tryCatch({

diff --git a/R/helpers.R b/R/helpers.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 HistCol <- function(cov, threshold, relative, logScale) {
   # Function to generate color vector for histogram data

diff --git a/R/parsingOps.R b/R/parsingOps.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 PACVr.parseGenes <- function (gbkSeqFeatures) {
   # Function to extract gene information from Genbank flatfile data

diff --git a/R/quadripOps.R b/R/quadripOps.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 FilterByKeywords <- function(allRegions, where) {
   # Function to filter list based on genomic keywords

diff --git a/R/readingOps.R b/R/readingOps.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 read.gbSeqFeaturesAdapt <- function(gbkData, analysisSpecs) {
   gbkSeqFeatures <- read.gbSeqFeatures(gbkData,

diff --git a/R/visualisationOps.R b/R/visualisationOps.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 vizWithRCircos <- function(gbkData,
                                  coverage,

diff --git a/R/writingOps.R b/R/writingOps.R
@@ -1,7 +1,7 @@
 #!/usr/bin/env RScript
 #contributors=c("Gregory Smith", "Nils Jenke", "Michael Gruenstaeudl")
 #email="m_gruenstaeudl@fhsu.edu"
-#version="2024.05.20.2131"
+#version="2024.05.24.2053"
 
 writeCovTables <- function(covData, sample_name, dir) {
   writeStatsTable(covData$ir_genes, sample_name, dir, "coverage.genes")