Mercurial > repos > proteore > proteore_id_converter
comparison id_converter_UniProt.R @ 0:f2d0b13d9615 draft
planemo upload commit 5774fd6a5a746f36f6bf4671a51a39ea2b978300-dirty
author | proteore |
---|---|
date | Fri, 16 Feb 2018 03:16:29 -0500 |
parents | |
children | 134949593a3b |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:f2d0b13d9615 |
---|---|
1 # Read file and return file content as data.frame | |
2 readfile = function(filename, header) { | |
3 if (header == "true") { | |
4 # Read only first line of the file as header: | |
5 headers <- read.table(filename, nrows = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE) | |
6 #Read the data of the files (skipping the first row) | |
7 file <- read.table(filename, skip = 1, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE) | |
8 # Remove empty rows | |
9 file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE] | |
10 #And assign the header to the data | |
11 names(file) <- headers | |
12 } | |
13 else { | |
14 file <- read.table(filename, header = FALSE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings=c("", "NA"), blank.lines.skip = TRUE) | |
15 # Remove empty rows | |
16 file <- file[!apply(is.na(file) | file == "", 1, all), , drop=FALSE] | |
17 } | |
18 return(file) | |
19 } | |
20 | |
21 # Mapping IDs using file built from | |
22 # - HUMAN_9606_idmapping_selected.tab | |
23 # Tarball downloaded from ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/ | |
24 # - nextprot_ac_list_all.txt | |
25 # Downloaded from ftp://ftp.nextprot.org/pub/current_release/ac_lists/ | |
26 # Available databases: | |
27 # UNIPROT_AC: Uniprot accession number (e.g. P31946) | |
28 # UNIPROT_ID: Uniprot identifiers (e.g 1433B_HUMAN) | |
29 # GeneID_EntrezGene: Entrez gene ID (serie of digit) (e.g. 7529) | |
30 # RefSeq: RefSeq (NCBI) protein (e.g. NP_003395.1; NP_647539.1; XP_016883528.1) | |
31 # GI_number: GI (NCBI GI number) ID (serie of digits) assigned to each sequence record processed by NCBI (e.g; 21328448; 377656701; 67464627; 78101741) | |
32 # PDB: Protein DataBank Identifiers (e.g. 2BR9:A; 3UAL:A; 3UBW:A) | |
33 # GO_ID: GOterms (Gene Ontology) Identifiers (e.g. GO:0070062; GO:0005925; GO:0042470; GO:0016020; GO:0005739; GO:0005634) | |
34 # PIR: Protein Information Resource ID (e.g. S34755) | |
35 # OMIM: OMIM (Online Mendelian Inheritance in Man database) ID (serie of digits) (e.g: 601289) | |
36 # UniGene: Unigene Identifier (e.g. Hs.643544) | |
37 # Ensembl_ENSG: Ensembl gene identifiers (e.g. ENSG00000166913) | |
38 # Ensembl_ENST: Ensembl transcript identifiers (e.g. ENST00000353703; ENST00000372839) | |
39 # Ensembl_ENSP: Ensembl protein identifiers (e.g. ENSP00000300161; ENSP00000361930) | |
40 | |
41 mapping = function() { | |
42 # Extract arguments | |
43 args = commandArgs(trailingOnly = TRUE) | |
44 #print(args) | |
45 if (length(args) != 6) { | |
46 stop("Not enough/Too many arguments", call. = FALSE) | |
47 } | |
48 else { | |
49 input_id_type = args[1] | |
50 list_id = args[2] | |
51 list_id_input_type = args[3] | |
52 options = strsplit(args[4], ",")[[1]] | |
53 output = args[5] | |
54 human_id_mapping_file = args[6] | |
55 | |
56 # Extract ID maps | |
57 human_id_map = read.table(human_id_mapping_file, header = TRUE, sep = "\t", stringsAsFactors = FALSE, fill = TRUE, na.strings = "") | |
58 | |
59 # Extract input IDs | |
60 if (list_id_input_type == "list") { | |
61 list_id = strsplit(args[2], " ")[[1]] | |
62 # Remove isoform accession number (e.g. "-2") | |
63 list_id = gsub("-.+", "", list_id) | |
64 } | |
65 else if (list_id_input_type == "file") { | |
66 filename = as.character(strsplit(list_id, ",")[[1]][1]) | |
67 column_number = as.numeric(gsub("c", "" ,strsplit(list_id, ",")[[1]][2])) | |
68 header = strsplit(list_id, ",")[[1]][3] | |
69 file_all = readfile(filename, header) | |
70 print(class(file_all)) | |
71 str(file_all) | |
72 print(class(file_all[,1])) | |
73 list_id = c() | |
74 list_id = sapply(strsplit(file_all[,column_number], ";"), "[", 1) | |
75 # Remove isoform accession number (e.g. "-2") | |
76 list_id = gsub("-.+", "", list_id) | |
77 } | |
78 names = c() | |
79 | |
80 # Map IDs | |
81 res = matrix(nrow=length(list_id), ncol=0) | |
82 | |
83 for (opt in options) { | |
84 names = c(names, opt) | |
85 mapped = human_id_map[match(list_id, human_id_map[input_id_type][,]),][opt][,] | |
86 res = cbind(res, matrix(mapped)) | |
87 } | |
88 | |
89 # Write output | |
90 if (list_id_input_type == "list") { | |
91 res = cbind(as.matrix(list_id), res) | |
92 names = c(input_id_type, names) | |
93 colnames(res) = names | |
94 write.table(res, output, row.names = FALSE, sep = "\t", quote = FALSE) | |
95 } | |
96 else if (list_id_input_type == "file") { | |
97 names(res) = options | |
98 names = c(names(file_all), names) | |
99 output_content = cbind(file_all, res) | |
100 colnames(output_content) = names | |
101 write.table(output_content, output, row.names = FALSE, sep = "\t", quote = FALSE) | |
102 } | |
103 } | |
104 } | |
105 | |
106 mapping() | |
107 | |
108 #Rscript id_converter_UniProt.R "UniProt.AC" "test-data/UnipIDs.txt,c1,false" "file" "Ensembl_PRO,Ensembl,neXtProt_ID" "test-data/output.txt" ../../utils/mapping_file.txt |