Merge branch 'master' of github.com:lindsayrutter/bigPint

Version 1.0.3 rebase

.github/workflows/no-response.yml

@@ -0,0 +1,13 @@
+# Configuration for probot-no-response - https://github.com/probot/no-response
+
+# Number of days of inactivity before an Issue is closed for lack of response
+daysUntilClose: 14
+# Label requiring a response
+responseRequiredLabel: more-information-needed
+# Comment to post when closing an Issue for lack of response. Set to `false` to disable
+closeComment: >
+  This issue has been automatically closed because there has been no response
+  to our request for more information from the original author. With only the
+  information that is currently in the issue, we don't have enough information
+  to take action. Please reach out if you have or find the answers we need so
+  that we can investigate further.

DESCRIPTION

@@ -1,31 +1,56 @@
 Package: bigPint
-Version: 1.3.1
-Title: Big multivariate data plotted interactively
-Description: Methods for visualizing large multivariate datasets using static and interactive scatterplot matrices, parallel coordinate plots, volcano plots, and litre plots. Includes examples for visualizing RNA-sequencing datasets and differentially expressed genes.
-Authors@R: c(person("Lindsay", "Rutter", email = "lindsayannerutter@gmail.com", role = c("aut","cre")),
+Version: 1.19.1
+Title: BIG multivariate data Plotted INTeractively
+Description: Make big data pint-sized. Methods for visualizing large multivariate datasets using static and interactive scatterplot matrices, parallel coordinate plots, volcano plots, and litre plots. Includes examples for visualizing RNA-sequencing datasets and differentially expressed genes.
+Authors@R: c(person("Lindsay", "Rutter", email = "bigpintpackage@gmail.com", role = c("aut","cre")),
   person("Dianne", "Cook", email = "dicook@monash.edu", role = c("aut")))
 License: GPL-3
 Depends: R (>= 3.6.0)
-Imports: DelayedArray (>= 0.12.2), dplyr (>= 0.7.2), GGally (>= 1.3.2),
-        ggplot2 (>= 2.2.1), graphics (>= 3.5.0), grDevices (>= 3.5.0),
-        grid (>= 3.5.0), gridExtra (>= 2.3), hexbin (>= 1.27.1),
-        Hmisc (>= 4.0.3), htmlwidgets (>= 0.9), methods (>= 3.5.2),
-        plotly (>= 4.7.1), plyr (>= 1.8.4), RColorBrewer (>= 1.1.2),
-        reshape (>= 0.8.7), shiny (>= 1.0.5), shinycssloaders (>= 0.2.0),
-        shinydashboard (>= 0.6.1), stats (>= 3.5.0), stringr (>= 1.3.1),
-        SummarizedExperiment (>= 1.16.1), tidyr (>= 0.7.0), utils (>= 3.5.0)
+biocViews:
+Imports:
+    DelayedArray (>= 0.12.2),
+    dplyr (>= 0.7.2),
+    GGally (>= 1.3.2),
+    ggplot2 (>= 2.2.1),
+    graphics (>= 3.5.0),
+    grDevices (>= 3.5.0),
+    grid (>= 3.5.0),
+    gridExtra (>= 2.3),
+    hexbin (>= 1.27.1),
+    Hmisc (>= 4.0.3),
+    htmlwidgets (>= 0.9),
+    methods (>= 3.5.2),
+    plotly (>= 4.7.1),
+    plyr (>= 1.8.4),
+    RColorBrewer (>= 1.1.2),
+    reshape (>= 0.8.7),
+    shiny (>= 1.0.5),
+    shinycssloaders (>= 0.2.0),
+    shinydashboard (>= 0.6.1),
+    stats (>= 3.5.0),
+    stringr (>= 1.3.1),
+    SummarizedExperiment (>= 1.16.1),
+    tidyr (>= 0.7.0),
+    utils (>= 3.5.0)
 VignetteBuilder: knitr
-Suggests: BiocGenerics (>= 0.29.1), data.table (>= 1.11.8), EDASeq (>=
-        2.14.0), edgeR (>= 3.22.2), gtools (>= 3.5.0), knitr (>= 1.13),
-        matrixStats (>= 0.53.1), rmarkdown (>= 1.10), roxygen2 (>=
-        3.0.0), RUnit (>= 0.4.32), tibble (>= 1.4.2),
-biocViews: Clustering, DataImport, DifferentialExpression,
-        GeneExpression, MultipleComparison, Normalization,
-        Preprocessing, QualityControl, RNASeq, Sequencing, Software,
-        Transcription, Visualization
-RoxygenNote: 7.0.2
+Suggests:
+    BiocStyle (>= 3.18),
+    BiocGenerics (>= 0.29.1),
+    data.table (>= 1.11.8),
+    EDASeq (>= 2.14.0),
+    edgeR (>= 3.22.2),
+    gtools (>= 3.5.0),
+    knitr (>= 1.13),
+    matrixStats (>= 0.53.1),
+    rmarkdown (>= 1.10),
+    roxygen2 (>= 3.0.0),
+    RUnit (>= 0.4.32),
+    tibble (>= 1.4.2)
+RoxygenNote: 7.2.3
 BugReports: https://github.com/lindsayrutter/bigPint/issues
 URL: https://github.com/lindsayrutter/bigPint
 NeedsCompilation: no
 Packaged: 2018-11-30 04:06:13 UTC; suzu
+LazyData: true
 Encoding: UTF-8
+PackageStatus: Deprecated

NEWS.md

@@ -1,3 +1,12 @@
+## bigPint 1.5.1 (2020-08-23)
+plotClusters() function now has option for superimposing pairs or whole data using the showPairs parameter.
+
+## bigPint 1.3.3 (2020-06-15)
+[Our software paper](https://doi.org/10.1371/journal.pcbi.1007912) was published in PLoS Computational Biology. In this paper, we describe how our package created independent layers of interactivity using Plotly in R. Pseudocode and source code are provided. Computational scientists can leverage our open-source code to expand upon our layered interactive technology and apply it in new ways toward other computational biology tasks.
+
+## bigPint 1.3.2 (2020-03-04)
+Users can now input SummarizedExperiment data type to create any bigPint plot.
+
 ## bigPint 1.3.2 (2020-03-04)
 Users can now input SummarizedExperiment data type to create any bigPint plot.
 

R/convertSEPair.R

@@ -34,7 +34,7 @@ convertSEPair <- function(dataSE, group1, group2){
         setNames(x, sub(".*\\.", "", names(x)))))
 
     oldData <- as.data.frame(assay(dataSE))
-    keepDataCol <- which(vapply(colnames(oldData), function(x)
+    keepDataCol <- which(lapply(colnames(oldData), function(x)
         strsplit(x, "[.]")[[1]][1]) %in% c(group1, group2))
     keepOldData <- oldData[, keepDataCol]
 

R/helperCadFALSE.R

@@ -1,6 +1,11 @@
-helperCadFALSE <- function(cData, dataMetrics, metricPair, aggMethod, nC,
+helperCadFALSE <- function(data, cData, dataMetrics, metricPair, aggMethod, nC,
 threshVar, threshVal, verbose, vxAxis, saveFile, boxDat, xAxisLabel,
 yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
+
+    # Convert to data.frame in case tibble
+    data <- as.data.frame(data)
+    dataMetrics <- as.data.frame(dataMetrics)
+
     dendo = cData
     rownames(dendo) = NULL
     d = suppressWarnings(dist(as.matrix(dendo)))
@@ -21,8 +26,8 @@ yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
             xNames),]
             sigID = metricFDR[which(metricFDR[[threshVar]]<=threshVal),]$ID
             xSig = x[which(xNames %in% sigID),]
-            xSigNames = rownames(xSig)
-            nGenes = nrow(xSig) 
+            xSigNames = xNames
+            nGenes = nrow(xSig)  
         }
         else{
             xSig = x
@@ -31,34 +36,47 @@ yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
         }
 
         if (verbose==TRUE){
-            IDs = as.character(xNames)
-            saveRDS(IDs, file = paste(outDir, "/", plotName, "_", nC, "_",
+            IDs = as.character(sigID)
+            saveRDS(IDs, file = paste(outDir, "/", plotName, "_", nC, "_", 
             j, ".rds", sep=""))
         }
 
         xSig$ID = xSigNames
-        lastTwoIndices = c(ncol(xSig) -1, ncol(xSig))
-        xSig = xSig[, -lastTwoIndices]
-
-        pcpDat <- melt(xSig, id.vars="ID")
-        colnames(pcpDat) <- c("ID", "Sample", "Count")
-        pcpDat$Sample <- as.character(pcpDat$Sample)
-        pcpDat$ID <- as.factor(pcpDat$ID)
-
-        p <- ggplot(boxDat, aes_string(x = 'Sample', y = 'Count')) +
-        geom_boxplot() + geom_line(data=pcpDat, aes_string(x = 'Sample',
-        y = 'Count', group = 'ID'), colour = colList[j], alpha=lineAlpha,
-        size = lineSize) + ylab(yAxisLabel) + xlab(xAxisLabel) +
-        ggtitle(paste("Cluster ", j, " Genes (n=", format(nGenes,
-        big.mark=",", scientific=FALSE), ")",sep="")) +
-        theme(plot.title = element_text(hjust = 0.5, size=14,
-        face="plain"), axis.text=element_text(size=11),
-        axis.title=element_text(size=14))
-
+        if (nrow(xSig)>0){
+            lastTwoIndices = c(ncol(xSig) -1, ncol(xSig))
+            xSig = xSig[, -lastTwoIndices]
+            ############################## here!
+            nonPairIndex = which(data$ID %in% xSig$ID)
+            fullDat = data[nonPairIndex,]
+            fullDat$ID = as.factor(fullDat$ID)
+
+            pcpDat <- melt(fullDat, id.vars="ID")
+            colnames(pcpDat) <- c("ID", "Sample", "Count")
+            pcpDat$Sample <- as.character(pcpDat$Sample)
+            pcpDat$ID <- as.factor(pcpDat$ID)
+
+            p <- ggplot(boxDat, aes_string(x = 'Sample', y = 'Count')) + 
+                geom_boxplot() + geom_line(data=pcpDat,
+                aes_string(x = 'Sample', y = 'Count', group = 'ID'),
+                colour = colList[j], alpha=lineAlpha, size = lineSize) +
+                ylab(yAxisLabel) + xlab(xAxisLabel) + ggtitle(paste("Cluster ", j,
+                " Genes (n=", format(nGenes, big.mark=",", scientific=FALSE), ")",
+                sep="")) + theme(plot.title = element_text(hjust = 0.5, size=14,
+                face="plain"), axis.text=element_text(size=11),
+                axis.title=element_text(size=14))
+        }
+        else{
+            p <- ggplot(boxDat, aes_string(x = 'Sample', y = 'Count')) +
+                geom_boxplot() + ylab(yAxisLabel) + xlab(xAxisLabel) +
+                ggtitle(paste("Cluster ", j, " Genes (n=", format(nGenes,
+                big.mark = ",", scientific=FALSE), ")", sep="")) +
+                theme(plot.title = element_text(hjust = 0.5, size=14,
+                face="plain"), axis.text=element_text(size=11),
+                axis.title=element_text(size=14))            
+        }
         if (vxAxis == TRUE){
             p <- p + theme(axis.text.x = element_text(angle=90, hjust=1))
         }
-
         if (verbose==TRUE){
             fileName = paste(outDir, "/", plotName, "_", nC, "_", j, ".jpg",
             sep="")
@@ -68,6 +86,7 @@ yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
         }
         p
     })
+
     p = arrangeGrob(grobs=plot_clusters, ncol=2)
 
     if (saveFile == TRUE || verbose == TRUE){
@@ -77,4 +96,5 @@ yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
         invisible(dev.off())
     }
     return(p)
-}
+}
+

bigPint/R/helperCadFALSE.R → R/helperCadFALSEPair.R

@@ -1,6 +1,10 @@
-helperCadFALSE <- function(cData, dataMetrics, metricPair, aggMethod, nC,
+helperCadFALSEPair <- function(cData, dataMetrics, metricPair, aggMethod, nC,
 threshVar, threshVal, verbose, vxAxis, saveFile, boxDat, xAxisLabel,
 yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
+
+    # Convert to data.frame in case tibble
+    dataMetrics <- as.data.frame(dataMetrics)
+
     dendo = cData
     rownames(dendo) = NULL
     d = suppressWarnings(dist(as.matrix(dendo)))

R/helperCadTRUE.R

@@ -1,6 +1,11 @@
 helperCadTRUE <- function(data, dataMetrics, metricPair, aggMethod, nC,
 threshVar, threshVal, verbose, vxAxis, saveFile, boxDat, xAxisLabel,
 yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
+
+    # Convert to data.frame in case tibble
+    data <- as.data.frame(data)
+    dataMetrics <- as.data.frame(dataMetrics)
+
     dendo = data
     rownames(dendo) = NULL
     d = suppressWarnings(dist(as.matrix(dendo)))

bigPint/R/helperCadTRUE.R → R/helperCadTRUEPair.R

@@ -1,12 +1,17 @@
-helperCadTRUE <- function(data, dataMetrics, metricPair, aggMethod, nC,
+helperCadTRUEPair <- function(data, dataMetrics, metricPair, aggMethod, nC,
 threshVar, threshVal, verbose, vxAxis, saveFile, boxDat, xAxisLabel,
 yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
+
+    # Convert to data.frame in case tibble
+    data <- as.data.frame(data)
+    dataMetrics <- as.data.frame(dataMetrics)
+
     dendo = data
     rownames(dendo) = NULL
     d = suppressWarnings(dist(as.matrix(dendo)))
     hC = hclust(d, method=aggMethod)
     k = cutree(hC, k=nC)
-
+    
     seqVec = seq(nC)
     plot_clusters = lapply(seq_along(seqVec), function(j){
         i = rev(order(table(k)))[j]
@@ -38,29 +43,46 @@ yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
         if (nrow(xSig)>0){
             lastTwoIndices = c(ncol(xSig) -1, ncol(xSig))
             xSig = xSig[, -lastTwoIndices]
+
+            #New code to remove extra treatment groups
+            colNames = levels(boxDat$Sample)
+            seqVec <- seq_along(colNames)
+            colGroups <- vapply(seqVec, function(i){
+                strsplit(colNames[i],"[.]")[[1]][1]
+            }, character(1))
+            uColGroups <- unique(colGroups)
+
+            xCols = colnames(xSig[,-1])
+            seqVec <- seq_along(xCols)
+            colGroupsXSig <- vapply(seqVec, function(i){
+                strsplit(xCols[i],"[.]")[[1]][1]
+            }, character(1))
+            keepCol = which(colGroupsXSig %in% uColGroups) +1
+            xSig = xSig[,c(1,keepCol)]
+
             pcpDat <- melt(xSig, id.vars="ID")
             colnames(pcpDat) <- c("ID", "Sample", "Count")
             pcpDat$Sample <- as.character(pcpDat$Sample)
             pcpDat$ID <- as.factor(pcpDat$ID)
 
             p <- ggplot(boxDat, aes_string(x = 'Sample', y = 'Count')) + 
-            geom_boxplot() + geom_line(data=pcpDat,
-            aes_string(x = 'Sample', y = 'Count', group = 'ID'),
-            colour = colList[j], alpha=lineAlpha, size = lineSize) +
-            ylab(yAxisLabel) + xlab(xAxisLabel) + ggtitle(paste("Cluster ", j,
-            " Genes (n=", format(nGenes, big.mark=",", scientific=FALSE), ")",
-            sep="")) + theme(plot.title = element_text(hjust = 0.5, size=14,
-            face="plain"), axis.text=element_text(size=11),
-            axis.title=element_text(size=14))
+                geom_boxplot() + geom_line(data=pcpDat,
+                aes_string(x = 'Sample', y = 'Count', group = 'ID'),
+                colour = colList[j], alpha=lineAlpha, size = lineSize) +
+                ylab(yAxisLabel) + xlab(xAxisLabel) + ggtitle(paste("Cluster ", j,
+                " Genes (n=", format(nGenes, big.mark=",", scientific=FALSE), ")",
+                sep="")) + theme(plot.title = element_text(hjust = 0.5, size=14,
+                face="plain"), axis.text=element_text(size=11),
+                axis.title=element_text(size=14))
         }
         else{
             p <- ggplot(boxDat, aes_string(x = 'Sample', y = 'Count')) +
-            geom_boxplot() + ylab(yAxisLabel) + xlab(xAxisLabel) +
-            ggtitle(paste("Cluster ", j, " Genes (n=", format(nGenes,
-            big.mark = ",", scientific=FALSE), ")", sep="")) +
-            theme(plot.title = element_text(hjust = 0.5, size=14,
-            face="plain"), axis.text=element_text(size=11),
-            axis.title=element_text(size=14))            
+                geom_boxplot() + ylab(yAxisLabel) + xlab(xAxisLabel) +
+                ggtitle(paste("Cluster ", j, " Genes (n=", format(nGenes,
+                big.mark = ",", scientific=FALSE), ")", sep="")) +
+                theme(plot.title = element_text(hjust = 0.5, size=14,
+                face="plain"), axis.text=element_text(size=11),
+                axis.title=element_text(size=14))            
         }
         if (vxAxis == TRUE){
             p <- p + theme(axis.text.x = element_text(angle=90, hjust=1))
@@ -74,9 +96,9 @@ yAxisLabel, lineAlpha, lineSize, plotName, outDir, colList) {
         }
         p
     })
-
+    
     p = arrangeGrob(grobs=plot_clusters, ncol=2)
-
+    
     if (saveFile == TRUE || verbose == TRUE){
         fileName = paste(outDir, "/", plotName, "_", nC, ".jpg", sep="")
         jpeg(fileName)

R/helperTestData.R

@@ -1,10 +1,10 @@
 helperTestData <- function(data){
-
+    
 colNames = colnames(data[,-1])
 seqVec <- seq_along(colNames)
 
 generalMessage = "For more information about formatting the data
-object, see https://lrutter.github.io/bigPint/articles/data.html"
+object, see https://lindsayrutter.github.io/bigPint/articles/data.html"
 
 if (!methods::is(data, "data.frame")){ 
     stop(paste0("Data object must be of class 'data.frame'. If you are
@@ -13,6 +13,9 @@ if (!methods::is(data, "data.frame")){
     generalMessage))
 }
 
+# Convert to data.frame in case tibble
+data <- as.data.frame(data)
+
 logicClass = vapply(data[,-1], function(x) methods::is(x, "numeric") ||
 methods::is(x, "integer"), logical(length=1))
 

R/helperTestDataMetrics.R

@@ -1,11 +1,13 @@
-#' @importFrom methods is
 helperTestDataMetrics <- function(data, dataMetrics, threshVar){
 
+# Convert to data.frame in case tibble
+data <- as.data.frame(data)
+
 colNames = colnames(data[,-1])
 seqVec <- seq_along(colNames)
 
 generalMessage = "For more information about formatting the dataMetrics
-object, see https://lrutter.github.io/bigPint/articles/dataMetrics.html"
+object, see https://lindsayrutter.github.io/bigPint/articles/dataMetrics.html"
 
 if (!methods::is(dataMetrics, "list")){ 
     stop(paste0("Data metrics object must be of class 'list'. ",

R/helperTestDataMetricsLitreApp.R

@@ -2,7 +2,7 @@
 helperTestDataMetricsLitreApp <- function(data, dataMetrics){
 
 generalMessage = "For more information about formatting the dataMetrics
-object, see https://lrutter.github.io/bigPint/articles/dataMetrics.html"
+object, see https://lindsayrutter.github.io/bigPint/articles/dataMetrics.html"
 
 colNames = colnames(data[,-1])
 seqVec <- seq_along(colNames)

R/helperTestDataMetricsVolcano.R

@@ -6,7 +6,7 @@ colNames = colnames(data[,-1])
 seqVec <- seq_along(colNames)
 
 generalMessage = "For more information about formatting the dataMetrics
-objects, see https://lrutter.github.io/bigPint/articles/dataMetrics.html.
+objects, see https://lindsayrutter.github.io/bigPint/articles/dataMetrics.html.
 Note that volcano plots require that each element in the dataMetrics object
 has additional two columns, a PValue column and a logFC column."