In uzh/ezRun: An R meta-package for the analysis of Next Generation Sequencing Data

knitr::opts_chunk$set(echo = TRUE,warning=FALSE, message=FALSE, out.width = "49%")
## This report requires summary files form mothur
debug <- FALSE

##Prodigal
summaryScorePlotList <- summaryScorePlot(fullSummPlot)

summaryConfPlotList <-summaryConfPlot(subsetDataToPartial00Plot)

summaryGcContPlotList <- summaryGcContPlot(subsetDataToPartial00Plot)

summaryRBSSpacePlotList <- summaryRBSSpacePlot(subsetDataToPartial00Plot)

summaryRBSMotifPlotList <- summaryRBSMotifPlot(subsetDataToPartial00Plot)

## Inteproscan
### summary  plots : matching score 
summaryMatchScorePlot <-   summaryMatchScorePlot(interproscanListForPlot)

### heatmaps and diff. table 
if (isGroupThere) {
heatmapGOPlot <- summaryHeatmap(GOTermMatrixForHeatmap, 
                                     isGroupThere, 
                                     dataset=dataset, 
                                     numberOfTopNCategories)
heatmapDescPlot <- summaryHeatmap(descTermMatrixForHeatmap, 
                                     isGroupThere, 
                                     dataset=dataset, 
                                     numberOfTopNCategories)
if (areThereRepl){
diffTableGOTerms <- metagMetatrDifferentialAnalysis_tableAndPlots(GOTermMatrixForDiffExpr,
                                                                  dataset,
                                                                  group,sampleGroup,refGroup,
                                                                  N=numberOfTopNCategories,
                                                                  mode="function")
diffTableFunc <- metagMetatrDifferentialAnalysis_tableAndPlots(descTermMatrixForDiffExpr,
                                                               dataset,
                                                               group,sampleGroup,refGroup,
                                                               N=numberOfTopNCategories,
                                                               mode="function")
}
}else{
heatmapGOPlot <- summaryHeatmap(GOTermMatrixForHeatmap, 
                                     isGroupThere,
                                     numberOfTopNCategories = numberOfTopNCategories) 
heatmapDescPlot <- summaryHeatmap(descTermMatrixForHeatmap, 
                                     isGroupThere,
                                     numberOfTopNCategories = numberOfTopNCategories)
}

## Binning
binBasedAbundTable <- createAbundTable(mergedSummaryBinDF)
### histogrm binning count
histBinSummPlotList <- lapply(names(mergedSummaryBinDFList),function(z){
  y <- mergedSummaryBinDFList[[z]]
  binIDmostAbundOrg <- sapply(levels(y[["binID"]]),function(x){
    names(sort(table(y[y[["binID"]]==x,]$organism), decreasing = T)[1])
  })
   hh <- cbind(data.frame(table(y[["binID"]])),binIDmostAbundOrg)
   names(hh) <- c("binID","count","mostAbundantOrganism")
  plotTemp <- ggplot(hh, aes(x=reorder(binID,count), y=count,
                             fill=stringr::str_wrap(mostAbundantOrganism,30))) +
    geom_bar(stat = "identity") +
    labs(fill="Most abundant organism", x = "bin ID", y= "count") +
    ggtitle(z)
    plotTemp + theme(legend.text = element_text(size=6), 
          legend.title = element_text(size=7.5),
          legend.key.size = unit(0.3, "cm"), axis.title.x = element_text(size = 8),
          axis.title.y = element_text(size = 8),
          plot.title = element_text(size=8)) 
})

###  binning coverage
coverageBinSummPlot <- ggplot(mergedSummaryBinDF, aes(x=ID, y=log(coverage), color=binID)) +
  geom_point() + 
  facet_wrap(vars(sample),nrow = 3) + 
  scale_color_discrete(brewer.pal(9, "RdYlGn"),guide=guide_legend(title="bin ID")) +
  theme(axis.text.x = element_blank(), axis.ticks.x = element_blank() )

### binning length
lengthBinSummPlot<- ggplot(mergedSummaryBinDF, aes(x=ID, y=log(length), color=binID)) +
  geom_point() + 
  facet_wrap(vars(sample),nrow = 3) + 
  scale_color_discrete(brewer.pal(9, "RdYlGn"),guide=guide_legend(title="bin ID")) +
  theme(axis.text.x = element_blank(), axis.ticks.x = element_blank() )

## abundance Heatmap
if (isGroupThere) {
orgAbundHeatmap <- summaryHeatmap(binBasedAbundTable, 
                                     isGroupThere, 
                                     dataset=dataset, 
                                     numberOfTopNCategories)
}else{
orgAbundHeatmap <- summaryHeatmap(binBasedAbundTable, 
                                     isGroupThere,
                                     numberOfTopNCategories = numberOfTopNCategories) 
}

## rarefaction
plotTitle_1 <- paste("Rarefaction plots")
plotTitle_2 <- paste("Saturation plots")
rarefPlot_1 <- rarefactionPlot(binBasedAbundTable,1) +labs(title=plotTitle_1) + 
    theme(plot.title=element_text(size=11,hjust=0.5))
rarefPlot_2 <- rarefactionPlot(binBasedAbundTable,2) +labs(title=plotTitle_2) + 
    theme(plot.title=element_text(size=11,hjust=0.5))

Started on r format(Sys.time(), "%Y-%m-%d %H:%M:%S")

Data pre-processing {.tabset}

Binning summary: size

plot_grid(plotlist = histBinSummPlotList,ncol = 2)

Binning summary: coverage

plot(coverageBinSummPlot)

Binning summary: contig length

plot(lengthBinSummPlot)

Rarefaction curves

plot(rarefPlot_1)

Organism abundance heatmap

orgAbundHeatmap()

Prodigal gene prediction:summary score

plot(summaryScorePlotList)

Prodigal gene prediction: confidence, GC_content and RBS

plot(summaryConfPlotList)
plot(summaryGcContPlotList)
plot(summaryRBSSpacePlotList)
plot(summaryRBSMotifPlotList)

Interproscan annotation: proteins match scores

plot(summaryMatchScorePlot)

Interproscan annotation: GO annotation

heatmapGOPlot()
if (areThereRepl){
DT::datatable(diffTableGOTerms)
}

Interproscan annotation: functional annotation

heatmapDescPlot()
if (areThereRepl){
DT::datatable(diffTableFunc)
}

uzh/ezRun documentation built on April 19, 2024, 8:25 a.m.