Version 2.1.0

DESCRIPTION

@@ -1,21 +1,22 @@
 Package: UniprotR
 Title: Retrieving Information of Proteins from Uniprot
-Version: 2.0.7
+Version: 2.1.0
 Authors@R: c(person("Mohamed", "Soudy", email = "MohmedSoudy2009@gmail.com", role=c("aut", "cre")), person("Ali", "Mostafa", email = "ali.mo.anwar@std.agr.cu.edu.eg", role = "aut"))
 Author: Mohamed Soudy [aut, cre],
   Ali Mostafa [aut]
 Maintainer: Mohamed Soudy <MohmedSoudy2009@gmail.com>
 Description: Connect to Uniprot <https://www.uniprot.org/> to retrieve information about proteins using their accession number such information could be name or taxonomy information, For detailed information kindly read the publication <https://www.sciencedirect.com/science/article/pii/S1874391919303859>.
 License: GPL-3
 Encoding: UTF-8
-RoxygenNote: 7.1.1
+RoxygenNote: 7.1.2
 Imports: utils , grDevices , stats , grid , graphics , httr , plyr ,
         dplyr , scales , magrittr , magick , data.tree , ggplot2 ,
-        tidyverse , gridExtra , ggpubr , curl, networkD3,
-        stringr , qdapRegex , htmlwidgets , alakazam (>= 1.0.0), gprofiler2, progress
+        tidyverse , gridExtra , ggpubr , curl, networkD3, stringr ,
+        qdapRegex , htmlwidgets , alakazam (>= 1.0.0), gprofiler2,
+        progress, ggsci
 URL: https://github.com/Proteomicslab57357/UniprotR
 BugReports: https://github.com/Proteomicslab57357/UniprotR/issues
 NeedsCompilation: no
-Packaged: 2021-04-06 10:17:45 UTC; RSH
+Packaged: 2021-09-22 14:25:38 UTC; RSH
 Repository: CRAN
 Date/Publication: 2020-07-26 13:20:05 UTC

NAMESPACE

@@ -21,6 +21,7 @@ import(stringr)
 import(ggplot2)
 import(data.tree)
 import(ggpubr)
+import(ggsci)
 import(grid)
 import(gridExtra)
 import(networkD3)
@@ -69,6 +70,9 @@ export(Plot.GOSubCellular)
 export(PlotAcidity)
 export(PlotCharge)
 export(PlotChromosomeInfo)
+export(PlotEnrichedGO)
+export(PlotEnrichedPathways)
+export(PlotGOAll)
 export(PlotGOBiological)
 export(PlotGenesNetwork)
 export(PlotGoInfo)

R/GETSeqFastaUniprot.R

@@ -1,24 +1,28 @@
 #' Connect and parse UniProt information.
 #'
-#' This Function is used to download sequences of given protein list in a fasta format
+#' This Function is used to get Sequence information of accession/s from Uniprot as a Fasta file.
 #'
-#' @usage GETSeqFastaUniprot(Accessions, FileName = NULL)
+#' @usage GETSeqFastaUniprot(Accessions,FilePath = NULL, FileName = NULL)
 #'
-#' @param Accessions  list of Uniprot accessions 
+#' @param Accessions Vector of UniProt Accession/s
 #'
-#' @param FileName OUtput file name 
+#' @param FilePath path of directory to save the output fasta.
+#' 
+#' @param FileName Name of the fasta file.
 #'
 #' @author Mohmed Soudy \email{Mohamed.soudy@57357.com} and Ali Mostafa \email{ali.mo.anwar@std.agr.cu.edu.eg}
 #'
 #' @export
-GETSeqFastaUniprot <- function(Accessions, FileName = NULL)
+GETSeqFastaUniprot <- function(Accessions, FilePath = NULL ,FileName = NULL)
 {
-  OutNumber <- 0
+  message("Please wait we are processing your accessions ...")
+  pb <- progress::progress_bar$new(total = length(Accessions))
+
   for (Acc in Accessions)
   {
     Request <- tryCatch(
       {
-        GET(paste0("https://www.uniprot.org/uniprot/" , Acc , ".Fasta"))
+        GET(paste0("https://www.uniprot.org/uniprot/" , Acc , ".Fasta") , timeout(10))
       },error = function(cond)
       {
         message("Internet connection problem occurs and the function will return the original error")
@@ -27,15 +31,11 @@ GETSeqFastaUniprot <- function(Accessions, FileName = NULL)
     )
     if (Request$status_code == 200)
     {
-      OutNumber <<- OutNumber + 1
       Fastadata <- read.csv(paste0("https://www.uniprot.org/uniprot/" , Acc , ".Fasta") , header = F , sep = "\t")
       Sequences <- paste0(as.character(unlist(Fastadata)) , collapse = "\n")
-      if (!is.null(FileName))
-      {
-        write.table(x = Sequences , file = paste0(FileName ,".fasta") , quote = F , row.names = F , col.names = F, append = T)
-      }
+      write.table(x = Sequences , file = paste0(FileName ,".fasta") , quote = F , row.names = F , col.names = F, append = T)
+      pb$tick()
     }
 
   }
-  return(OutNumber)
-}
+}

R/GetAccessionList.R

@@ -14,7 +14,7 @@
 GetAccessionList <- function(DataObjPath)
 {
   DataSet <- read.csv(DataObjPath)
-  AccessionList <- as.array(as.character(DataSet[,1]))
+  AccessionList <- trimws(unique(as.character(DataSet[,1])))
   return(AccessionList)
 }
 

R/GetProteinFunction.R

@@ -31,7 +31,7 @@ GetProteinFunction <- function(ProteinAccList , directorypath = NULL)
   }
   ProteinInfoParsed_total = data.frame()
   baseUrl <- "http://www.uniprot.org/uniprot/"
-  Colnames = "ec,comment(ABSORPTION),comment(CATALYTIC ACTIVITY),chebi,chebi(Catalytic activity),chebi(Cofactor),chebi-id,comment(COFACTOR),comment(ENZYME REGULATION),comment(FUNCTION),comment(KINETICS),comment(PATHWAY),comment(REDOX POTENTIAL),comment(TEMPERATURE DEPENDENCE),comment(PH DEPENDENCE),feature(ACTIVE SITE),feature(BINDING SITE),feature(DNA BINDING),feature(METAL BINDING),feature(NP BIND),feature(SITE)"
+  Colnames = "ec,comment(ABSORPTION),comment(CATALYTIC ACTIVITY),chebi,chebi(Catalytic activity),chebi(Cofactor),chebi-id,comment(COFACTOR),comment(ACTIVITY REGULATION),comment(FUNCTION),comment(KINETICS),comment(PATHWAY),comment(REDOX POTENTIAL),comment(TEMPERATURE DEPENDENCE),comment(PH DEPENDENCE),feature(ACTIVE SITE),feature(BINDING SITE),feature(DNA BINDING),feature(METAL BINDING),feature(NP BIND),feature(SITE)"
 
   message("Please wait we are processing your accessions ...")
   pb <- progress::progress_bar$new(total = length(ProteinAccList))

R/PlotEnrichedGO.R

@@ -0,0 +1,59 @@
+#' Connect and parse UniProt information
+#'
+#' This function is used to generate a combined plot for the enriched Gene Ontology terms  
+#'
+#' @usage PlotEnrichedGO(Accs,OS="hsapiens",p_value=0.05,Path=NULL,theme="aaas",width=7,height=7)
+#'
+#' @param Accs Vector of UniProt Accession/s or genes 
+#' 
+#' @param OS  organism name Example: human - 'hsapiens', mouse - 'mmusculus'
+#' 
+#' @param p_value custom p-value threshold for significance, default = 0.05
+#' 
+#' @param theme optional parameter to generate specific theme for journals ex: "aaas", "nature", "lancet", "jama"
+#' 
+#' @param Path Path to save output plot 
+#' 
+#' @param width width of the generated plot 
+#' 
+#' @param height height of the generated plot
+#'
+#' @export
+#'
+#' @author Mohmed Soudy \email{Mohamed.soudy@57357.com} and Ali Mostafa \email{ali.mo.anwar@std.agr.cu.edu.eg}
+#' 
+PlotEnrichedGO <- function(Accs,OS="hsapiens",p_value=0.05,Path=NULL,theme="aaas",width=7,height= 7)
+{
+  Enr.data <- gost(Accs)
+
+  Enr.frame <- Enr.data$result
+
+  GOs <- Enr.frame[Enr.frame$source %in% c("GO:BP", "GO:CC", "GO:MF"),]
+  GOs$`-log10 (p)` <- -log10(GOs$p_value)
+
+  P <- ggbarplot(GOs, x = "term_name", y = "-log10 (p)",
+                 fill = "source",               
+                 color = "white",            
+                 palette = "jco",            
+                 sort.val = "asc",           
+                 sort.by.groups = TRUE,      
+                 x.text.angle = 90          
+  )
+  if (tolower(theme) == "aaas")
+    P <- P + scale_fill_aaas() + xlab("") +  coord_flip()
+  if (tolower(theme) == "lancet")
+    P <- P + scale_fill_lancet() + xlab("") +  coord_flip()
+  if (tolower(theme) == "jama")
+    P <- P + scale_fill_jama() + xlab("") +  coord_flip()
+  if (tolower(theme) == "nature")
+    P <- P + scale_fill_nejm() + xlab("") +  coord_flip()
+
+  if (!is.null(Path))
+  {
+    if (dim(GOs)[1] < 50)
+      ggsave(path = Path, filename = "Significant GOs.jpeg", plot = P,width = width, height = height, dpi = 300)
+    if (dim(GOs)[1] > 50)
+      ggsave(path = Path, filename = "Significant GO.jppeg", plot = P,width = width, height =height, dpi = 300)
+  }
+  plot(P)
+}

R/PlotEnrichedPathways.R

@@ -0,0 +1,59 @@
+#' Connect and parse UniProt information
+#'
+#' This function is used to generate a combined plot for the enriched pathways from KEGG and REACTOME 
+#'
+#' @usage PlotEnrichedPathways(Accs,OS="hsapiens",p_value=0.05,Path=NULL,theme="aaas",w=w,h=h)
+#'
+#' @param Accs Vector of UniProt Accession/s or genes 
+#' 
+#' @param OS  organism name Example: human - 'hsapiens', mouse - 'mmusculus'
+#' 
+#' @param p_value custom p-value threshold for significance, default = 0.05
+#' 
+#' @param theme optional parameter to generate specific theme for journals ex: "aaas", "nature", "lancet", "jama"
+#' 
+#' @param Path Path to save output plot 
+#' 
+#' @param w width of the generated plot 
+#' 
+#' @param h height of the generated plot
+#'
+#' @export
+#'
+#' @author Mohmed Soudy \email{Mohamed.soudy@57357.com} and Ali Mostafa \email{ali.mo.anwar@std.agr.cu.edu.eg}
+#' 
+PlotEnrichedPathways <- function(Accs,OS="hsapiens",p_value=0.05,Path=NULL,theme="aaas",w=w,h=h)
+{
+  Enr.data <- gost(Accs)
+
+  Enr.frame <- Enr.data$result
+
+  Pathways <- Enr.frame[Enr.frame$source %in% c("KEGG", "REAC"),]
+  Pathways$`-log10 (p)` <- -log10(Pathways$p_value)
+
+  P <- ggbarplot(Pathways, x = "term_name", y = "-log10 (p)",
+                 fill = "source",               
+                 color = "white",            
+                 palette = "jco",            
+                 sort.val = "asc",           
+                 sort.by.groups = TRUE,      
+                 x.text.angle = 90          
+  )
+  if (tolower(theme) == "aaas")
+    P <- P + scale_fill_aaas() + xlab("") +  coord_flip()
+  if (tolower(theme) == "lancet")
+    P <- P + scale_fill_lancet() + xlab("") +  coord_flip()
+  if (tolower(theme) == "jama")
+    P <- P + scale_fill_jama() + xlab("") +  coord_flip()
+  if (tolower(theme) == "nature")
+    P <- P + scale_fill_nejm() + xlab("") +  coord_flip()
+
+  if (!is.null(Path))
+  {
+    if (dim(Pathways)[1] < 50)
+      ggsave(path = Path, filename = "Significant Pathways.jpeg", plot = P,width = w, height = h, dpi = 300)
+    if (dim(Pathways)[1] > 50)
+      ggsave(path = Path, filename = "Significant Pathways.jpeg", plot = P,width = w, height = h, dpi = 300)
+  }
+  plot(P)
+}

R/PlotGOAll.R

@@ -0,0 +1,62 @@
+#' Connect and parse UniProt information.
+#'
+#' This Function is used to plot the retrieved Gene Ontology from function 'GetProteinGOInfo'.
+#'
+#' @usage PlotGOAll(GOObj, Top = 10, directorypath = NULL, width = width, height = height)
+#'
+#' @param GOObj  Dataframe returned from UniprotR Function "GetProteinGOInfo"
+#'
+#' @param Top Number of molecular functions to be visualized
+#'
+#' @param directorypath path to save Output plot.
+#' 
+#' @param width width of the generated plot
+#' 
+#' @param height height of the generated plot 
+#' 
+#' @author Mohmed Soudy \email{Mohamed.soudy@57357.com} and Ali Mostafa \email{ali.mo.anwar@std.agr.cu.edu.eg}
+#'
+#' @export
+#'
+PlotGOAll <- function(GOObj, Top = 10, directorypath = NULL, width = width, height = height)
+{
+  BiologicalDF <- Goparse(GOObj, 3)
+  if (dim(BiologicalDF)[1] < 10)
+    Top <- dim(BiologicalDF)[1]
+  BiologicalDF <- BiologicalDF[1:Top, ]
+  BiologicalDF <- na.omit(BiologicalDF)
+  BiologicalDF$source <- "BP"
+
+  CellularDF <- Goparse(GOObj, 5)
+  if (dim(CellularDF)[1] < 10)
+    Top <- dim(CellularDF)[1]
+  CellularDF <- CellularDF[1:Top, ]
+  CellularDF <- na.omit(CellularDF)
+  CellularDF$source <- "CC"
+
+
+  MolecularDF <- Goparse(GOObj, 4)
+  if (dim(MolecularDF)[1] < 10)
+    Top <- dim(MolecularDF)[1]
+  MolecularDF <- MolecularDF[1:Top, ]
+  MolecularDF <- na.omit(MolecularDF)
+  MolecularDF$source <- "MF"
+
+  GO.terms <- rbind(BiologicalDF, CellularDF)
+  GO.terms <- rbind(GO.terms, MolecularDF)
+
+  P <- ggbarplot(GO.terms, x = "Goterm", y = "Count",
+                 fill = "source",               
+                 color = "white",            
+                 palette = "jco",            
+                 sort.val = "asc",           
+                 sort.by.groups = TRUE,      
+                 x.text.angle = 90          
+  )
+  P <- P + scale_fill_lancet() + coord_flip()
+  if(!is.null(directorypath))
+  {
+    ggsave(plot = P, filename = paste0(directorypath, "/", "GO All.jpeg"), device = "jpeg", width = width, height = height)
+  }
+  plot(P)
+}