Mercurial > repos > proteore > proteore_prot_features_mouse
comparison add_protein_features_mouse.R @ 0:1e856941a888 draft
planemo upload commit 8de59a5dbf9206fa3d9f7a1c07e79ccb792b3e3f-dirty
author | proteore |
---|---|
date | Fri, 08 Feb 2019 08:46:04 -0500 |
parents | |
children | f10816a9dd0b |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:1e856941a888 |
---|---|
1 # Read file and return file content as data.frame | |
2 order_columns <- function (df,ncol,file){ | |
3 if (ncol==1){ #already at the right position | |
4 return (df) | |
5 } else { | |
6 df = df[,c(2:ncol,1,(ncol+1):dim.data.frame(df)[2])] | |
7 } | |
8 return (df) | |
9 } | |
10 | |
11 get_list_from_cp <-function(list){ | |
12 list = strsplit(list, "[ \t\n]+")[[1]] | |
13 list = gsub("NA","",list) | |
14 list = list[list != ""] #remove empty entry | |
15 list = gsub("-.+", "", list) #Remove isoform accession number (e.g. "-2") | |
16 return(list) | |
17 } | |
18 | |
19 check_ids <- function(vector,type) { | |
20 uniprot_pattern = "^([OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2})$" | |
21 entrez_id = "^([0-9]+|[A-Z]{1,2}_[0-9]+|[A-Z]{1,2}_[A-Z]{1,4}[0-9]+)$" | |
22 if (type == "entrez") | |
23 return(grepl(entrez_id,vector)) | |
24 else if (type == "uniprot") { | |
25 return(grepl(uniprot_pattern,vector)) | |
26 } | |
27 } | |
28 | |
29 get_args <- function(){ | |
30 | |
31 ## Collect arguments | |
32 args <- commandArgs(TRUE) | |
33 | |
34 ## Default setting when no arguments passed | |
35 if(length(args) < 1) { | |
36 args <- c("--help") | |
37 } | |
38 | |
39 ## Help section | |
40 if("--help" %in% args) { | |
41 cat("Selection and Annotation HPA | |
42 Arguments: | |
43 --inputtype: type of input (list of id or filename) | |
44 --input: input | |
45 --uniprot_file: path to uniprot reference file | |
46 --column: the column number which you would like to apply... | |
47 --header: true/false if your file contains a header | |
48 --pc_features: IsoPoint,SeqLength,MW | |
49 --output: text output filename \n") | |
50 | |
51 q(save="no") | |
52 } | |
53 | |
54 parseArgs <- function(x) strsplit(sub("^--", "", x), "=") | |
55 argsDF <- as.data.frame(do.call("rbind", parseArgs(args))) | |
56 args <- as.list(as.character(argsDF$V2)) | |
57 names(args) <- argsDF$V1 | |
58 | |
59 return(args) | |
60 } | |
61 | |
62 str2bool <- function(x){ | |
63 if (any(is.element(c("t","true"),tolower(x)))){ | |
64 return (TRUE) | |
65 }else if (any(is.element(c("f","false"),tolower(x)))){ | |
66 return (FALSE) | |
67 }else{ | |
68 return(NULL) | |
69 } | |
70 } | |
71 | |
72 #take data frame, return data frame | |
73 split_ids_per_line <- function(line,ncol){ | |
74 | |
75 #print (line) | |
76 header = colnames(line) | |
77 line[ncol] = gsub("[[:blank:]]|\u00A0","",line[ncol]) | |
78 | |
79 if (length(unlist(strsplit(as.character(line[ncol]),";")))>1) { | |
80 if (length(line)==1 ) { | |
81 lines = as.data.frame(unlist(strsplit(as.character(line[ncol]),";")),stringsAsFactors = F) | |
82 } else { | |
83 if (ncol==1) { #first column | |
84 lines = suppressWarnings(cbind(unlist(strsplit(as.character(line[ncol]),";")), line[2:length(line)])) | |
85 } else if (ncol==length(line)) { #last column | |
86 lines = suppressWarnings(cbind(line[1:ncol-1],unlist(strsplit(as.character(line[ncol]),";")))) | |
87 } else { | |
88 lines = suppressWarnings(cbind(line[1:ncol-1], unlist(strsplit(as.character(line[ncol]),";"),use.names = F), line[(ncol+1):length(line)])) | |
89 } | |
90 } | |
91 colnames(lines)=header | |
92 return(lines) | |
93 } else { | |
94 return(line) | |
95 } | |
96 } | |
97 | |
98 #create new lines if there's more than one id per cell in the columns in order to have only one id per line | |
99 one_id_one_line <-function(tab,ncol){ | |
100 | |
101 if (ncol(tab)>1){ | |
102 | |
103 tab[,ncol] = sapply(tab[,ncol],function(x) gsub("[[:blank:]]","",x)) | |
104 header=colnames(tab) | |
105 res=as.data.frame(matrix(ncol=ncol(tab),nrow=0)) | |
106 for (i in 1:nrow(tab) ) { | |
107 lines = split_ids_per_line(tab[i,],ncol) | |
108 res = rbind(res,lines) | |
109 } | |
110 }else { | |
111 res = unlist(sapply(tab[,1],function(x) strsplit(x,";")),use.names = F) | |
112 res = data.frame(res[which(!is.na(res[res!=""]))],stringsAsFactors = F) | |
113 colnames(res)=colnames(tab) | |
114 } | |
115 return(res) | |
116 } | |
117 | |
118 # Get information from neXtProt | |
119 get_uniprot_info <- function(ids,pc_features,uniprot_file){ | |
120 | |
121 cols = c("Entry",pc_features) | |
122 cols=cols[cols!="None"] | |
123 info = uniprot_file[match(ids,uniprot_file$Entry),cols] | |
124 colnames(info)[1]="UniProt-AC" | |
125 | |
126 return(info) | |
127 } | |
128 | |
129 main <- function() { | |
130 | |
131 args <- get_args() | |
132 | |
133 #save(args,file="/home/dchristiany/proteore_project/ProteoRE/tools/add_protein_features_mouse/args.rda") | |
134 #load("/home/dchristiany/proteore_project/ProteoRE/tools/add_protein_features_mouse/args.rda") | |
135 | |
136 #setting variables | |
137 inputtype = args$inputtype | |
138 if (inputtype == "copy_paste") { | |
139 ids = get_list_from_cp(args$input) | |
140 | |
141 #Check for UniProt-AC ids | |
142 if (all(!check_ids(ids,'uniprot'))){ | |
143 stop ("No UniProt-AC found in ids.") | |
144 } else if (any(!check_ids(ids,'uniprot'))) { | |
145 print ('Some ids in ids are not uniprot-AC:') | |
146 print (ids[which(!check_ids(ids,'uniprot'))]) | |
147 } | |
148 file = data.frame(ids,stringsAsFactors = F) | |
149 ncol=1 | |
150 | |
151 } else if (inputtype == "file") { | |
152 filename = args$input | |
153 ncol = args$column | |
154 # Check ncol | |
155 if (! as.numeric(gsub("c", "", ncol)) %% 1 == 0) { | |
156 stop("Please enter an integer for level") | |
157 } else { | |
158 ncol = as.numeric(gsub("c", "", ncol)) | |
159 } | |
160 | |
161 header = str2bool(args$header) | |
162 file = read.table(filename, header = header , sep = "\t", fill = TRUE, stringsAsFactors = FALSE, quote="", check.names = F, comment.char = "") # Get file content | |
163 if (any(grep(";",file[,ncol]))) {file = one_id_one_line(file,ncol)} | |
164 ids=file[,ncol] | |
165 } | |
166 | |
167 # Read reference file | |
168 uniprot_file <- read.table(args$uniprot_file, header = TRUE , sep = "\t", fill = TRUE,stringsAsFactors = FALSE, quote="", check.names = F, comment.char = "") | |
169 | |
170 # Parse arguments | |
171 pc_features = gsub("__ob__","[",gsub("__cb__","]",strsplit(args$pc_features, ",")[[1]])) | |
172 output = args$output | |
173 | |
174 #output file | |
175 res <- get_uniprot_info(ids,pc_features,uniprot_file) | |
176 res = res[!duplicated(res$`UniProt-AC`),] | |
177 output_content = merge(file, res,by.x=ncol,by.y="UniProt-AC",incomparables = NA,all.x=T) | |
178 output_content = order_columns(output_content,ncol,file) | |
179 output_content <- as.data.frame(apply(output_content, c(1,2), function(x) gsub("^$|^ $", NA, x))) #convert "" et " " to NA | |
180 write.table(output_content, output, row.names = FALSE, sep = "\t", quote = FALSE) | |
181 | |
182 } | |
183 | |
184 if(!interactive()) { | |
185 main() | |
186 } |