Mercurial > repos > proteore > proteore_prot_features

comparison get_data_nextprot.R @ 0:e3b52db3d583 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit abb24d36c776520e73220d11386252d848173697-dirty
author proteore
date Sun, 26 Nov 2017 19:45:52 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:e3b52db3d583
1 # Usage : Rscript --vanilla get_data_nextprot.R --inputtype copypaste (or
2 # tabfile) --input file.txt --nextprot result_nextprot.txt --column column
3 # --argsP1 IsoPoint,SeqLength,MW
4 # --argsP2 Chr,SubcellLocations --argsP3 Diseases --type id nextprot (uniprot)
5 # --output output.txt --header TRUE
6
7 # e.g :
8 # Rscript --vanilla get_data_nextprot.R --inputtype copypaste --input P01133 P00533 P62158 Q16566 P31323 P17612 P10644
9 # P22612 P31321 P13861 P22694 P25098 P16220 Q14573 Q14571 Q14643 Q05655 Q02156
10 # P19174 O43865 Q01064 P54750 Q14123 P51828 Q08828 O60266 Q08462 O60503 O43306
11 # Q8NFM4 O95622 P40145 P17252 P05129 --nextprot
12 # result_nextprot.txt--column c1 --argsP1 IsoPoint --argsP2
13 # Chr --argsP3 Diseases --typeid uniprot --output output.txt --header FALSE
14
15 # Useful functions
16
17 '%!in%' <- function(x,y)!('%in%'(x,y))
18
19 # Parse arguments
20
21 args = commandArgs(trailingOnly = TRUE)
22
23 # create a list of the arguments from the command line, separated by a blank space
24 hh <- paste(unlist(args),collapse=' ')
25 # delete the first element of the list which is always a blank space
26 listoptions <- unlist(strsplit(hh,'--'))[-1]
27 # for each input, split the arguments with blank space as separator, unlist, and delete the first element which is the input name (e.g --protalas)
28 options.args <- sapply(listoptions,function(x){
29 unlist(strsplit(x, ' '))[-1]
30 })
31 # same as the step above, except that only the names are kept
32 options.names <- sapply(listoptions,function(x){
33 option <- unlist(strsplit(x, ' '))[1]
34 })
35 names(options.args) <- unlist(options.names)
36
37
38 typeinput = as.character(options.args[1])
39 nextprot = read.table(as.character(options.args[3]),header=TRUE,sep="\t",quote="\"")
40 listfile = as.character(options.args[2])
41 column = as.numeric(gsub("c","",options.args[4]))
42 P1_args = as.character(options.args[5])
43 P2_args = as.character(options.args[6])
44 P3_args = as.character(options.args[7])
45 typeid = as.character(options.args[8])
46 filename = as.character(options.args[9])
47 header = as.character(options.args[10])
48
49 if (typeinput=="copypaste"){
50 sample = as.data.frame(unlist(listfile))
51 sample = sample[,column]
52 }
53 if (typeinput=="tabfile"){
54
55 if (header=="TRUE"){
56 listfile = read.table(listfile,header=TRUE,sep="\t",quote="\"",fill=TRUE)
57 }else{
58 listfile = read.table(listfile,header=FALSE,sep="\t",quote="\"",fill=TRUE)
59 }
60 sample = listfile[,column]
61
62 }
63 # Change the sample ids if they are uniprot ids to be able to match them with
64 # Nextprot data
65 if (typeid=="uniprot"){
66 sample = gsub("^","NX_",sample)
67 }
68
69 # Select user input protein ids in nextprot
70
71 if ((length(sample[sample %in% nextprot[,1]]))==0){
72
73 write.table("None of the input ids are can be found in Nextprot",file=filename,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE)
74
75 }else{
76
77
78 to_keep = c()
79
80 if (P1_args!="None"){
81 P1_args = unlist(strsplit(P1_args,","))
82 for (arg in P1_args){
83 colnb = which(colnames(nextprot) %in% c(arg))
84 to_keep = c(to_keep,colnb)
85 }
86 }
87
88 if (P2_args!="None"){
89 P2_args = unlist(strsplit(P2_args,","))
90 for (arg in P2_args){
91 colnb = which(colnames(nextprot) %in% c(arg))
92 to_keep = c(to_keep,colnb)
93 }
94 }
95
96 if (P3_args!="None"){
97 P3_args = unlist(strsplit(P3_args,","))
98 for (arg in P3_args){
99 colnb = which(colnames(nextprot) %in% c(arg))
100 to_keep = c(to_keep,colnb)
101 }
102 }
103 to_keep = c(1,to_keep)
104 lines = which(nextprot[,1] %in% sample)
105 data = nextprot[lines,]
106
107 data = data[,to_keep]
108
109
110 # if only some of the proteins were not found in nextprot they will be added to
111 # the file with the fields "Protein not found in Nextprot"
112 if (length(which(sample %!in% nextprot[,1]))!=0){
113 proteins_not_found = as.data.frame(sample[which(sample %!in% nextprot[,1])])
114
115 proteins_not_found = cbind(proteins_not_found,matrix(rep("Protein not found in Nextprot",length(proteins_not_found)),nrow=length(proteins_not_found),ncol=length(colnames(data))-1))
116
117 colnames(proteins_not_found)=colnames(data)
118 data = rbind(data,proteins_not_found)
119 }
120
121 # Merge original data and data selected from nextprot
122
123 # Before that, if the initial ids were uniprot ids change them back from
124 # Nextprot to uniprot ids in data
125 if (typeid=="uniprot"){
126 data[,1] = gsub("^NX_","",data[,1])
127 }
128 data = merge(listfile, data, by.x = column, by.y=1)
129 if (typeid=="uniprot"){
130 colnames(data)[1] = "UniprotID"
131 }
132 if (typeid=="nextprot"){
133 colnames(data)[1] = "NextprotID"
134 }
135 # Write result
136 write.table(data,file=filename,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE)
137
138 }