annotate dimsPredictPuritySingle.R @ 6:090775983be7 draft

"planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
author computational-metabolomics
date Thu, 04 Mar 2021 12:24:27 +0000
parents e96082a25ff0
children 75b761fbacc0
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
1 library(msPurity)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
2 library(optparse)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
3 print(sessionInfo())
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
4
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
5 option_list <- list(
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
6 make_option(c("--mzML_file"), type = "character"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
7 make_option(c("--mzML_files"), type = "character"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
8 make_option(c("--mzML_filename"), type = "character", default = ""),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
9 make_option(c("--mzML_galaxy_names"), type = "character", default = ""),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
10 make_option(c("--peaks_file"), type = "character"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
11 make_option(c("-o", "--out_dir"), type = "character"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
12 make_option("--minoffset", default = 0.5),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
13 make_option("--maxoffset", default = 0.5),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
14 make_option("--ilim", default = 0.05),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
15 make_option("--ppm", default = 4),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
16 make_option("--dimspy", action = "store_true"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
17 make_option("--sim", action = "store_true"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
18 make_option("--remove_nas", action = "store_true"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
19 make_option("--iwNorm", default = "none", type = "character"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
20 make_option("--file_num_dimspy", default = 1),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
21 make_option("--exclude_isotopes", action = "store_true"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
22 make_option("--isotope_matrix", type = "character")
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
23 )
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
24
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
25 # store options
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
26 opt <- parse_args(OptionParser(option_list = option_list))
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
27
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
28 print(sessionInfo())
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
29 print(opt)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
30
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
31 print(opt$mzML_files)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
32 print(opt$mzML_galaxy_names)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
33
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
34 str_to_vec <- function(x) {
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
35 print(x)
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
36 x <- trimws(strsplit(x, ",")[[1]])
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
37 return(x[x != ""])
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
38 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
39
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
40 find_mzml_file <- function(mzML_files, galaxy_names, mzML_filename) {
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
41 mzML_filename <- trimws(mzML_filename)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
42 mzML_files <- str_to_vec(mzML_files)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
43 galaxy_names <- str_to_vec(galaxy_names)
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
44 if (mzML_filename %in% galaxy_names) {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
45 return(mzML_files[galaxy_names == mzML_filename])
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
46 }else{
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
47 stop(paste("mzML file not found - ", mzML_filename))
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
48 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
49 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
50
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
51
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
52 if (is.null(opt$dimspy)) {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
53 df <- read.table(opt$peaks_file, header = TRUE, sep = "\t")
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
54 if (file.exists(opt$mzML_file)) {
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
55 mzML_file <- opt$mzML_file
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
56 }else if (!is.null(opt$mzML_files)) {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
57 mzML_file <- find_mzml_file(opt$mzML_files, opt$mzML_galaxy_names,
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
58 opt$mzML_filename)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
59 }else{
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
60 mzML_file <- file.path(opt$mzML_file, filename)
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
61 }
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
62 }else{
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
63 indf <- read.table(opt$peaks_file,
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
64 header = TRUE, sep = "\t", stringsAsFactors = FALSE)
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
65
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
66 filename <- colnames(indf)[8:ncol(indf)][opt$file_num_dimspy]
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
67 print(filename)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
68 # check if the data file is mzML or RAW (can only use mzML currently) so
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
69 # we expect an mzML file of the same name in the same folder
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
70 indf$i <- indf[, colnames(indf) == filename]
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
71 indf[, colnames(indf) == filename] <- as.numeric(indf[, colnames(indf) == filename])
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
72
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
73 filename <- sub("raw", "mzML", filename, ignore.case = TRUE)
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
74 print(filename)
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
75
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
76 if (file.exists(opt$mzML_file)) {
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
77 mzML_file <- opt$mzML_file
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
78 }else if (!is.null(opt$mzML_files)) {
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
79 mzML_file <- find_mzml_file(opt$mzML_files, opt$mzML_galaxy_names, filename)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
80 }else{
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
81 mzML_file <- file.path(opt$mzML_file, filename)
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
82 }
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
83
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
84 # Update the dimspy output with the correct information
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
85 df <- indf[4:nrow(indf), ]
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
86 if ("blank_flag" %in% colnames(df)) {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
87 df <- df[df$blank_flag == 1, ]
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
88 }
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
89 colnames(df)[colnames(df) == "m.z"] <- "mz"
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
90
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
91 if ("nan" %in% df$mz) {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
92 df[df$mz == "nan", ]$mz <- NA
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
93 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
94 df$mz <- as.numeric(df$mz)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
95 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
96
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
97 if (!is.null(opt$remove_nas)) {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
98 df <- df[!is.na(df$mz), ]
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
99 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
100
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
101 if (is.null(opt$isotope_matrix)) {
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
102 im <- NULL
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
103 }else{
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
104 im <- read.table(opt$isotope_matrix,
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
105 header = TRUE, sep = "\t", stringsAsFactors = FALSE)
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
106 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
107
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
108 if (is.null(opt$exclude_isotopes)) {
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
109 isotopes <- FALSE
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
110 }else{
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
111 isotopes <- TRUE
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
112 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
113
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
114 if (is.null(opt$sim)) {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
115 sim <- FALSE
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
116 }else{
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
117 sim <- TRUE
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
118 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
119
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
120 minOffset <- as.numeric(opt$minoffset)
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
121 maxOffset <- as.numeric(opt$maxoffset)
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
122
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
123 if (opt$iwNorm == "none") {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
124 iwNorm <- FALSE
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
125 iwNormFun <- NULL
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
126 }else if (opt$iwNorm == "gauss") {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
127 iwNorm <- TRUE
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
128 iwNormFun <- msPurity::iwNormGauss(minOff = -minOffset, maxOff = maxOffset)
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
129 }else if (opt$iwNorm == "rcosine") {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
130 iwNorm <- TRUE
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
131 iwNormFun <- msPurity::iwNormRcosine(minOff = -minOffset, maxOff = maxOffset)
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
132 }else if (opt$iwNorm == "QE5") {
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
133 iwNorm <- TRUE
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
134 iwNormFun <- msPurity::iwNormQE.5()
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
135 }
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
136
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
137 print("FIRST ROWS OF PEAK FILE")
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
138 print(head(df))
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
139 print(mzML_file)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
140 predicted <- msPurity::dimsPredictPuritySingle(df$mz,
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
141 filepth = mzML_file,
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
142 minOffset = minOffset,
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
143 maxOffset = maxOffset,
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
144 ppm = opt$ppm,
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
145 mzML = TRUE,
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
146 sim = sim,
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
147 ilim = opt$ilim,
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
148 isotopes = isotopes,
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
149 im = im,
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
150 iwNorm = iwNorm,
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
151 iwNormFun = iwNormFun
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
152 )
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
153 predicted <- cbind(df, predicted)
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
154
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
155 print(head(predicted))
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
156 print(file.path(opt$out_dir, "dimsPredictPuritySingle_output.tsv"))
0
e96082a25ff0 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
157
6
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
158 write.table(predicted,
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
159 file.path(opt$out_dir, "dimsPredictPuritySingle_output.tsv"),
090775983be7 "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
160 row.names = FALSE, sep = "\t")