In 47Lies/isoformnspectRe: Companion package of a nextflow pipeline

CurrentSession<-sessioninfo::package_info()
if(!"Biostrings" %in% CurrentSession$package) library("Biostrings", character.only = TRUE, quietly = TRUE, verbose = FALSE)
if(!"DT" %in% CurrentSession$package) library("DT", character.only = TRUE, quietly = TRUE, verbose = FALSE)
if(!"data.table" %in% CurrentSession$package) library("data.table", character.only = TRUE, quietly = TRUE, verbose = FALSE)
if(!"GenomicFeatures" %in% CurrentSession$package) library("GenomicFeatures", character.only = TRUE, quietly = TRUE, verbose = FALSE)
if(!"ggplot2" %in% CurrentSession$package) library("ggplot2", character.only = TRUE, quietly = TRUE, verbose = FALSE)
if(!"plotly" %in% CurrentSession$package) library("plotly", character.only = TRUE, quietly = TRUE, verbose = FALSE)
if(!"rtracklayer" %in% CurrentSession$package) library("rtracklayer", character.only = TRUE, quietly = TRUE, verbose = FALSE)
if(!"httr" %in% CurrentSession$package) library("httr", character.only = TRUE, quietly = TRUE, verbose = FALSE)
if(!"xml2" %in% CurrentSession$package) library("xml2", character.only = TRUE, quietly = TRUE, verbose = FALSE)
if(!"viridisLite" %in% CurrentSession$package) library("viridisLite", character.only = TRUE, quietly = TRUE, verbose = FALSE)

CurrentList<-ls()
if(!"BANK" %in% CurrentList) BANK<-Biostrings::readAAStringSet(params$ProteinBankFasta)
if(!"PEPTIDES" %in% CurrentList){ PEPTIDES<-data.table::fread(params$PeptideResults,integer64 = "numeric")
if("UpdateProteins" %in% colnames(PEPTIDES)){
  PEPTIDES$Proteins<-PEPTIDES$UpdateProteins
}
if("UpdatedSequence" %in% colnames(PEPTIDES)){
  PEPTIDES$Sequence<-PEPTIDES$UpdatedSequence
}}
CurrentList<-ls()
if(!"SampleDescription" %in% CurrentList) SampleDescription <- data.table::fread(params$SampleDescription, header = TRUE)

#source("./SharedFunctionAcrossRmd.R")
#source(params$Utils)

names(BANK)<-gsub(" .*$","",names(BANK))
LocalProt<-BANK[params$ProteinOfInterest]
if("SplitedUpdateProteins" %in% colnames(PEPTIDES)) {
  LocalPeptides <-
    PEPTIDES[`SplitedUpdateProteins` == params$ProteinOfInterest]
} else{
  LocalPeptides <-
    PEPTIDES[`Leading razor protein` == params$ProteinOfInterest]
}
LightIntensitiesName <- colnames(LocalPeptides)[
  grep(params$IntensityPrefix,
       colnames(LocalPeptides))]
MaxIntensities<-apply(
  LocalPeptides[,..LightIntensitiesName],
  1,max)

LocalPeptides[, (LightIntensitiesName) := lapply(.SD, function(x) x/MaxIntensities), .SDcols = LightIntensitiesName]


#SampleDescription <- read.table(params$SampleDescription, header = TRUE)
if(length(grep(" $",params$IntensityPrefix))>0){
  UsablePrefix<-params$IntensityPrefix
}else{
  UsablePrefix<-paste(params$IntensityPrefix," ",sep="")
}
Groups <- unique(unlist(SampleDescription[,params$SampleGroupName,with=FALSE],use.names=FALSE))
Groups <- Groups[!duplicated(Groups)]
# SamplesByGroup <- lapply(as.vector(Groups),
#                          function(x, SampleDescription) {
#                            paste(UsablePrefix, as.vector(SampleDescription[SampleDescription[,params$SampleGroupName] == x, params$SampleName]),sep="")
#                          }, SampleDescription = SampleDescription)
# names(SamplesByGroup) <- Groups

SamplesByGroup <-
  lapply(Groups,
         function(x, SampleDescription) {
           paste0(UsablePrefix,unlist(SampleDescription[get(params$SampleGroupName) == x, ][, .SD, .SDcols = params$SampleName], use.names = FALSE))
         }, SampleDescription = SampleDescription)
names(SamplesByGroup) <- Groups

for(LocalGroup in Groups) {
  LocalPeptides[, paste(LocalGroup, "Infos") := paste(.SD, collapse = ","), .SDcols =
                  SamplesByGroup[[LocalGroup]], by = Sequence]
}

PeptideColumnOfInterest<-c("Proteins",
                           "Sequence",
                           paste(Groups,"Infos"),
                           "Start position",
                           "End position",
                           #"Score",
                           "PEP"
                           )

if("UpdateProteins" %in% colnames(LocalPeptides)){
  LocalPeptides$Proteins<-LocalPeptides$UpdateProteins
}


#Discard the peptides that came from nowhere 
#Most likely found only on Heavy intensities
#Silac's Burden
LocalPeptides <-
  LocalPeptides[MaxIntensities > 0, ..PeptideColumnOfInterest]
LocalPeptides <- LocalPeptides[,
                               PEP := formatC(PEP,
                                              format = "e",
                                              digits = 2)]

PeptidesCols<-c("Start position","End position","PEP","Proteins","Sequence")
LocalPep <- data.frame(LocalPeptides[, ..PeptidesCols])
colnames(LocalPep)<-c("Start","End","Pep","Proteins","Sequence")
LocalPep$Proteins <-
  unlist(lapply(LocalPep$Proteins, function(x) {
    paste(unlist(lapply(
      unlist(strsplit(split = ';', x)), STRING_ProteinShortName
    )), collapse = " ")
  }))
LocalProteinSequence<-HTML_Pretty_Sequence(
  Sequence=as.vector(LocalProt),
  Peptides=LocalPep,
  LineWidth=60)

Column {data-width=600}

Peptides

Table description

All the peptides that match this protein, each line is a peptide.

Proteins: Number of proteins that match this peptide. You can hover over the number to have more informations on the different proteins matched by this peptide.
Sequence: Peptide sequence. If the peptide sequence is too long, you can hover over it to see the whole sequence in a popup.
Infos: Normalized intensities of the peptides across all the sample of a group. Group are defined by values presents in the sample sheet file. You can hover over the bars to see the sample name.
Start position: matching start position of the peptide in the protein sequence
End position: matching end position of the peptide in the protein sequence
PEP: FDR of the peptide identification

#LocalPeptides$Proteins<-unlist(
#    lapply(LocalPeptides$Proteins,NProteins)
#  )
LocalPeptides <- LocalPeptides[,
                               Sequence := HTML_VECTOR_Peptide2Popover(Sequence, 15)]
LocalDatatable <- DT::datatable(
  LocalPeptides[,..PeptideColumnOfInterest],
  width = "100%",
  #extension =c("Responsive"),
  options = LIST_ComputeDatatableOptions(LIST_SampleNames=SamplesByGroup),
  rownames = FALSE,
  escape = FALSE
)
#LocalDatatable<-formatSignif(LocalDatatable,"PEP",digits=3)
LocalDatatable$dependencies <-
  append(LocalDatatable$dependencies,
         htmlwidgets:::getDependency("sparkline"))
LocalDatatable

Column {data-width=350}

Protein

Protein legend

Protein sequence as provided in the protein bank.

Matching peptide is displayed with this FORMALISM
Matching proteotypic peptide is displayed with this FORMALISM
Variation to the canonical form (splicing variant)is displayed with this FORMALISM

You can hover over each formalism to have more informations. A specific positon on the protein sequence can have several features of interest such as overlapping peptide due to misscleavage or a peptide overlaping a aplicing variant, each of these features will be diplayed in the informations.