.

script/CorrectionSeance4.R

 #JuG le 20230310
 #E30 Studium- 8h-12h
 
+# libraries ---------------------------------------------------------------
+
+library(tidyverse)
+
+
+
 # Lire les données --------------------------------------------------------
 
 #upload data
 webPath <- "https://static-content.springer.com/esm/art%3A10.1038%2Fnature10719/MediaObjects/41586_2012_BFnature10719_MOESM289_ESM.xls"
-destPath <- "./data/SuppData1.xls"
+destPath <- "./ed414_DS/data/SuppData1.xls"
 download.file(url = webPath, destfile = destPath)
-library(tidyverse)
 #read data
 df1 <- readxl::read_xls(path = destPath, sheet = 1, col_names = T)
 
-
-
-
 # Explorer les données ----------------------------------------------------
-
+dim(df1)
 head(df1)
 tail(df1)
 str(df1)
@@ -49,24 +51,36 @@ df1[df1$Prey == "O75688" & df1$Bait == "GP120" & df1$Isolation == "Bead", c("Nam
 
 # utiliser dplyr ----------------------------------------------------------
 
-library(tidyverse)
 
 df1 %>% filter(Prey == "O75688",Bait == "GP120", Isolation == "Bead") %>% 
   select(Name, Intensity)
 
+# exercie supplementaire
+
+# sortir les preys qui sont presentes sur toutes les Baits avec une intensité 
+# minimale de 1e6
+
+df1 %>% filter(Intensity >= 1e6) %>% 
+  group_by(Prey) %>% 
+  summarise(n=length(unique(Bait))) %>% 
+  filter(n>=18) %>% 
+  arrange(desc(n))
+
+df1 %>% filter(Prey == "Q9HCC0") 
+
+
 
 
 # Joindre des fichiers de données -----------------------------------------
 
 webPath <- "https://static-content.springer.com/esm/art%3A10.1038%2Fnature10719/MediaObjects/41586_2012_BFnature10719_MOESM290_ESM.xls"
-destPath2 <-  "./data/SuppData2.xls"
+destPath2 <-  "./ed414_DS/data/SuppData2.xls"
 download.file(url = webPath, destfile = destPath2)
-#supp 2
-dataPath <-  "./data/SuppData2.xls"
+
 
 #read data
-hek <- readxl::read_xls(path = dataPath, sheet = 1, col_names = T)
-jurkat <- readxl::read_xls(path = dataPath, sheet = 2, col_names = T)
+hek <- readxl::read_xls(path = destPath2, sheet = 1, col_names = T)
+jurkat <- readxl::read_xls(path = destPath2, sheet = 2, col_names = T)
 
 hek_sel <- hek %>% select(Prey, Bait, `Prey Name`, `MiST score`)
 jurkat_sel <- jurkat %>% select(Prey, Bait, `Prey Name`, `MiST score`)
@@ -76,13 +90,30 @@ df2 <- full_join(x = hek_sel, y = jurkat_sel, by=c("Prey", "Bait")  )
 
 
 
+# -------------------------------------------------------------------------
 # Reproduire la table de la fig 4 -----------------------------------------
+# -------------------------------------------------------------------------
 
 
-df2$`Prey Name.x`[grep(pattern = "initiation factor 3 subunit", x = df2$`Prey Name.x`)]%>% unique()
+
+# un peu de nettoyage -----------------------------------------------------
+
 df2$`Prey Name.x`[grep(pattern = "^EIF3", x = df2$`Prey Name.x`)] %>% unique() %>% sort()
+df2$`Prey Name.x`[grep(pattern = "^EIF3", x = df2$`Prey Name.x`)] %>% unique() %>% sort()
+
 
-#renomer G
+df2$`Prey Name.x`[grep(pattern = "initiation factor 3 subunit", x = df2$`Prey Name.x`)]%>% unique() %>% sort(.)
+uniprotCode <- df2$Prey[grep(pattern = "^IF3EI_HUMAN", x = df2$`Prey Name.x`)] %>% unique() %>% sort()
+uniprotCode
+
+#renommer L
+browseURL(paste("https://www.uniprot.org/uniprotkb/",ProtCode,"/entry",sep=""))
+df2$`Prey Name.x`[grep(pattern = "^IF3EI_HUMAN", x = df2$`Prey Name.x`)]
+df2$`Prey Name.x`[grep(pattern = "^IF3EI_HUMAN", x = df2$`Prey Name.x`)]<- "EIF3L_HUMAN Eukaryotic translation initiation factor 3 subunit L" 
+
+#renommer G
+df2$`Prey Name.x`[grep(pattern = "subunit G", x = df2$`Prey Name.x`)]
+df2$`Prey Name.y`[grep(pattern = "subunit G", x = df2$`Prey Name.y`)]
 df2$`Prey Name.x`[grep(pattern = "subunit G", x = df2$`Prey Name.x`)] <- "EIF3G_HUMAN Eukaryotic translation initiation factor 3 subunit G" 
 #tabRes$`Prey Name.x`[grep(pattern = "IF3EI_HUMAN Eukaryotic translation initiation factor 3 subunit E-interacting protein", x = tabRes$`Prey Name.x`)] <- "EIF3L_HUMAN Eukaryotic translation initiation factor 3 subunit L" 
 
@@ -99,11 +130,37 @@ tabPr <- df2 %>% filter(Bait == "PR",str_detect(`Prey Name.x`,pattern = "^EIF3")
 tabFin <- full_join(x = tabPol,y =  tabPr, by ="Prey Name.x" )
 tabFin $`Prey Name.x` <- str_sub(string = tabFin$`Prey Name.x`, 1, end = 5)
 colnames(tabFin) <- c("EIF3_i", "HEK_POL", "Jurkat_POL","HEK_PR", "Jurkat_PR" )
-tabFin <- tabFin[,c(1,3,2,5,4)]
+tabFin <- tabFin[,c(1,3,2,5,4)] %>% as.data.frame()
+
 
 #pas exactement les mêmes valeurs.....????
 
 
+
+# read the data  ----------------------------------------------------------
+
+url <- "https://static-content.springer.com/esm/art%3A10.1038%2Fnature10719/MediaObjects/41586_2012_BFnature10719_MOESM291_ESM.xls"
+download.file(url = url, destfile = "./ed414_DS/data/dataS3.xls")
+#read data
+df3 <- readxl::read_xls(path = "./ed414_DS/data/dataS3.xls", sheet = 2, col_names = T)
+head(df3)
+tail(df3)
+names(df3)[1] <- "Bait"
+
+tabPol2 <- df3 %>% filter(Bait == "POL",str_detect(ProteinName,pattern = "^EIF3")) %>%
+  #select(`Prey Name.x`, `MiST score.x`,  `MiST score.y` ) %>% 
+  arrange(ProteinName)
+tabPr2 <- df3 %>% filter(Bait == "PR",str_detect(ProteinName,pattern = "^EIF3")) %>%
+  #select(`Prey Name.x`,`MiST score.x`, `MiST score.y` ) %>% 
+  arrange(ProteinName)
+tabFin2 <- full_join(x = tabPol2,y =  tabPr2, by ="ProteinName" )
+tabFin2$ProteinName <- str_sub(string = tabFin2$ProteinName, 1, end = 5)
+tabFin2 <-tabFin2[,c(6,4,3,10,9)] 
+print(tabFin2, digits = 3)
+
+c('d','k','c','a','l','e','h','f','b','i','g','m')%in%letters[1:12]
+# toujours pas.....????
+
 # Exo5 compter les interactions pour chaque protéine virale -----------------------