Mercurial > repos > computational-metabolomics > mspurity_frag4feature

comparison purityX.R @ 0:85bc606fd219 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
author computational-metabolomics
date Thu, 04 Mar 2021 12:22:55 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:85bc606fd219
1 library(msPurity)
2 library(optparse)
3 print(sessionInfo())
4
5 option_list <- list(
6 make_option(c("--xset_path"), type = "character"),
7 make_option(c("-o", "--out_dir"), type = "character"),
8 make_option(c("--mzML_path"), type = "character"),
9 make_option("--minOffset", default = 0.5),
10 make_option("--maxOffset", default = 0.5),
11 make_option("--ilim", default = 0.05),
12 make_option("--iwNorm", default = "none", type = "character"),
13 make_option("--exclude_isotopes", action = "store_true"),
14 make_option("--isotope_matrix", type = "character"),
15 make_option("--purityType", default = "purityFWHMmedian"),
16 make_option("--singleFile", default = 0),
17 make_option("--cores", default = 4),
18 make_option("--xgroups", type = "character"),
19 make_option("--rdata_name", default = "xset"),
20 make_option("--camera_xcms", default = "xset"),
21 make_option("--files", type = "character"),
22 make_option("--galaxy_files", type = "character"),
23 make_option("--choose_class", type = "character"),
24 make_option("--ignore_files", type = "character"),
25 make_option("--rtraw_columns", action = "store_true")
26 )
27
28
29 opt <- parse_args(OptionParser(option_list = option_list))
30 print(opt)
31
32
33 if (!is.null(opt$xgroups)) {
34 xgroups <- as.numeric(strsplit(opt$xgroups, ",")[[1]])
35 }else{
36 xgroups <- NULL
37 }
38
39
40 print(xgroups)
41
42 if (!is.null(opt$remove_nas)) {
43 df <- df[!is.na(df$mz), ]
44 }
45
46 if (is.null(opt$isotope_matrix)) {
47 im <- NULL
48 }else{
49 im <- read.table(opt$isotope_matrix,
50 header = TRUE, sep = "\t", stringsAsFactors = FALSE)
51 }
52
53 if (is.null(opt$exclude_isotopes)) {
54 isotopes <- FALSE
55 }else{
56 isotopes <- TRUE
57 }
58
59 if (is.null(opt$rtraw_columns)) {
60 rtraw_columns <- FALSE
61 }else{
62 rtraw_columns <- TRUE
63 }
64
65 loadRData <- function(rdata_path, xset_name) {
66 #loads an RData file, and returns the named xset object if it is there
67 load(rdata_path)
68 return(get(ls()[ls() == xset_name]))
69 }
70
71 target_obj <- loadRData(opt$xset_path, opt$rdata_name)
72
73 if (opt$camera_xcms == "camera") {
74 xset <- target_obj@xcmsSet
75 }else{
76 xset <- target_obj
77 }
78
79 print(xset)
80
81 minOffset <- as.numeric(opt$minOffset)
82 maxOffset <- as.numeric(opt$maxOffset)
83
84 if (opt$iwNorm == "none") {
85 iwNorm <- FALSE
86 iwNormFun <- NULL
87 }else if (opt$iwNorm == "gauss") {
88 iwNorm <- TRUE
89 iwNormFun <- msPurity::iwNormGauss(minOff = -minOffset, maxOff = maxOffset)
90 }else if (opt$iwNorm == "rcosine") {
91 iwNorm <- TRUE
92 iwNormFun <- msPurity::iwNormRcosine(minOff = -minOffset, maxOff = maxOffset)
93 }else if (opt$iwNorm == "QE5") {
94 iwNorm <- TRUE
95 iwNormFun <- msPurity::iwNormQE.5()
96 }
97
98 print(xset@filepaths)
99
100 if (!is.null(opt$files)) {
101 updated_filepaths <- trimws(strsplit(opt$files, ",")[[1]])
102 updated_filepaths <- updated_filepaths[updated_filepaths != ""]
103 print(updated_filepaths)
104 updated_filenames <- basename(updated_filepaths)
105 original_filenames <- basename(xset@filepaths)
106 update_idx <- match(updated_filenames, original_filenames)
107
108 if (!is.null(opt$galaxy_files)) {
109 galaxy_files <- trimws(strsplit(opt$galaxy_files, ",")[[1]])
110 galaxy_files <- galaxy_files[galaxy_files != ""]
111 xset@filepaths <- galaxy_files[update_idx]
112 }else{
113 xset@filepaths <- updated_filepaths[update_idx]
114 }
115 }
116
117 if (!is.null(opt$choose_class)) {
118 classes <- trimws(strsplit(opt$choose_class, ",")[[1]])
119
120 ignore_files_class <- which(!as.character(xset@phenoData$class) %in% classes)
121
122 print("choose class")
123 print(ignore_files_class)
124 }else{
125 ignore_files_class <- NA
126 }
127
128 if (!is.null(opt$ignore_files)) {
129 ignore_files_string <- trimws(strsplit(opt$ignore_files, ",")[[1]])
130 filenames <- rownames(xset@phenoData)
131 ignore_files <- which(filenames %in% ignore_files_string)
132
133 ignore_files <- unique(c(ignore_files, ignore_files_class))
134 ignore_files <- ignore_files[ignore_files != ""]
135 }else{
136 if (anyNA(ignore_files_class)) {
137 ignore_files <- NULL
138 }else{
139 ignore_files <- ignore_files_class
140 }
141
142 }
143
144 print("ignore_files")
145 print(ignore_files)
146
147
148 ppLCMS <- msPurity::purityX(xset = xset,
149 offsets = c(minOffset, maxOffset),
150 cores = opt$cores,
151 xgroups = xgroups,
152 purityType = opt$purityType,
153 ilim = opt$ilim,
154 isotopes = isotopes,
155 im = im,
156 iwNorm = iwNorm,
157 iwNormFun = iwNormFun,
158 singleFile = opt$singleFile,
159 fileignore = ignore_files,
160 rtrawColumns = rtraw_columns)
161
162 dfp <- ppLCMS@predictions
163
164 # to make compatable with deconrank
165 colnames(dfp)[colnames(dfp) == "grpid"] <- "peakID"
166 colnames(dfp)[colnames(dfp) == "median"] <- "medianPurity"
167 colnames(dfp)[colnames(dfp) == "mean"] <- "meanPurity"
168 colnames(dfp)[colnames(dfp) == "sd"] <- "sdPurity"
169 colnames(dfp)[colnames(dfp) == "stde"] <- "sdePurity"
170 colnames(dfp)[colnames(dfp) == "RSD"] <- "cvPurity"
171 colnames(dfp)[colnames(dfp) == "pknm"] <- "pknmPurity"
172
173 if (sum(is.na(dfp$medianPurity)) > 0) {
174 dfp[is.na(dfp$medianPurity), ]$medianPurity <- 0
175 }
176
177 print(head(dfp))
178 write.table(dfp, file.path(opt$out_dir, "purityX_output.tsv"), row.names = FALSE, sep = "\t")
179
180 save.image(file.path(opt$out_dir, "purityX_output.RData"))