annotate dimsPredictPuritySingle.R @ 9:da36e8bbcfbd draft

planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 20a48a1862267264f98b7c514287f9a5cba1143f
author computational-metabolomics
date Thu, 13 Jun 2024 11:35:07 +0000
parents a0ee43397d1e
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
1 library(msPurity)
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
2 library(optparse)
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
3 print(sessionInfo())
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
4
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
5 option_list <- list(
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
6 make_option(c("--mzML_file"), type = "character"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
7 make_option(c("--mzML_files"), type = "character"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
8 make_option(c("--mzML_filename"), type = "character", default = ""),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
9 make_option(c("--mzML_galaxy_names"), type = "character", default = ""),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
10 make_option(c("--peaks_file"), type = "character"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
11 make_option(c("-o", "--out_dir"), type = "character"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
12 make_option("--minoffset", default = 0.5),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
13 make_option("--maxoffset", default = 0.5),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
14 make_option("--ilim", default = 0.05),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
15 make_option("--ppm", default = 4),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
16 make_option("--dimspy", action = "store_true"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
17 make_option("--sim", action = "store_true"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
18 make_option("--remove_nas", action = "store_true"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
19 make_option("--iwNorm", default = "none", type = "character"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
20 make_option("--file_num_dimspy", default = 1),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
21 make_option("--exclude_isotopes", action = "store_true"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
22 make_option("--isotope_matrix", type = "character")
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
23 )
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
24
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
25 # store options
6
a67b129cd78e "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
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
27
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
28 print(sessionInfo())
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
29 print(opt)
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
30
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
31 print(opt$mzML_files)
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
32 print(opt$mzML_galaxy_names)
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
33
6
a67b129cd78e "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
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
35 print(x)
6
a67b129cd78e "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
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
37 return(x[x != ""])
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
38 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
39
6
a67b129cd78e "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
5d0461edc7fd "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)
5d0461edc7fd "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)
5d0461edc7fd "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
a67b129cd78e "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) {
a67b129cd78e "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])
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
46 } else {
0
5d0461edc7fd "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))
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
48 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
49 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
50
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
51
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
52 if (is.null(opt$dimspy)) {
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
53 df <- read.table(opt$peaks_file, header = TRUE, sep = "\t")
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
54 if (file.exists(opt$mzML_file)) {
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
55 mzML_file <- opt$mzML_file
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
56 } else if (!is.null(opt$mzML_files)) {
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
57 mzML_file <- find_mzml_file(
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
58 opt$mzML_files, opt$mzML_galaxy_names,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
59 opt$mzML_filename
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
60 )
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
61 } else {
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
62 mzML_file <- file.path(opt$mzML_file, filename)
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
63 }
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
64 } else {
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
65 indf <- read.table(opt$peaks_file,
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
66 header = TRUE, sep = "\t", stringsAsFactors = FALSE
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
67 )
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
68
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
69 filename <- colnames(indf)[8:ncol(indf)][opt$file_num_dimspy]
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
70 print(filename)
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
71 # check if the data file is mzML or RAW (can only use mzML currently) so
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
72 # we expect an mzML file of the same name in the same folder
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
73 indf$i <- indf[, colnames(indf) == filename]
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
74 indf[, colnames(indf) == filename] <- as.numeric(indf[, colnames(indf) == filename])
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
75
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
76 filename <- sub("raw", "mzML", filename, ignore.case = TRUE)
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
77 print(filename)
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
78
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
79 if (file.exists(opt$mzML_file)) {
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
80 mzML_file <- opt$mzML_file
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
81 } else if (!is.null(opt$mzML_files)) {
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
82 mzML_file <- find_mzml_file(opt$mzML_files, opt$mzML_galaxy_names, filename)
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
83 } else {
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
84 mzML_file <- file.path(opt$mzML_file, filename)
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
85 }
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
86
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
87 # Update the dimspy output with the correct information
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
88 df <- indf[4:nrow(indf), ]
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
89 if ("blank_flag" %in% colnames(df)) {
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
90 df <- df[df$blank_flag == 1, ]
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
91 }
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
92 colnames(df)[colnames(df) == "m.z"] <- "mz"
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
93
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
94 if ("nan" %in% df$mz) {
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
95 df[df$mz == "nan", ]$mz <- NA
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
96 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
97 df$mz <- as.numeric(df$mz)
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
98 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
99
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
100 if (!is.null(opt$remove_nas)) {
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
101 df <- df[!is.na(df$mz), ]
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
102 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
103
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
104 if (is.null(opt$isotope_matrix)) {
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
105 im <- NULL
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
106 } else {
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
107 im <- read.table(opt$isotope_matrix,
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
108 header = TRUE, sep = "\t", stringsAsFactors = FALSE
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
109 )
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
110 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
111
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
112 if (is.null(opt$exclude_isotopes)) {
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
113 isotopes <- FALSE
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
114 } else {
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
115 isotopes <- TRUE
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
116 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
117
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
118 if (is.null(opt$sim)) {
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
119 sim <- FALSE
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
120 } else {
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
121 sim <- TRUE
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
122 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
123
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
124 minOffset <- as.numeric(opt$minoffset)
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
125 maxOffset <- as.numeric(opt$maxoffset)
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
126
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
127 if (opt$iwNorm == "none") {
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
128 iwNorm <- FALSE
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
129 iwNormFun <- NULL
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
130 } else if (opt$iwNorm == "gauss") {
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
131 iwNorm <- TRUE
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
132 iwNormFun <- msPurity::iwNormGauss(minOff = -minOffset, maxOff = maxOffset)
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
133 } else if (opt$iwNorm == "rcosine") {
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
134 iwNorm <- TRUE
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
135 iwNormFun <- msPurity::iwNormRcosine(minOff = -minOffset, maxOff = maxOffset)
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
136 } else if (opt$iwNorm == "QE5") {
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
137 iwNorm <- TRUE
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
138 iwNormFun <- msPurity::iwNormQE.5()
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
139 }
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
140
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
141 print("FIRST ROWS OF PEAK FILE")
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
142 print(head(df))
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
143 print(mzML_file)
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
144 predicted <- msPurity::dimsPredictPuritySingle(df$mz,
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
145 filepth = mzML_file,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
146 minOffset = minOffset,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
147 maxOffset = maxOffset,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
148 ppm = opt$ppm,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
149 mzML = TRUE,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
150 sim = sim,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
151 ilim = opt$ilim,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
152 isotopes = isotopes,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
153 im = im,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
154 iwNorm = iwNorm,
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
155 iwNormFun = iwNormFun
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
156 )
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
157 predicted <- cbind(df, predicted)
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
158
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
159 print(head(predicted))
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
160 print(file.path(opt$out_dir, "dimsPredictPuritySingle_output.tsv"))
0
5d0461edc7fd "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
computational-metabolomics
parents:
diff changeset
161
6
a67b129cd78e "planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 2579c8746819670348c378f86116f83703c493eb"
computational-metabolomics
parents: 0
diff changeset
162 write.table(predicted,
8
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
163 file.path(opt$out_dir, "dimsPredictPuritySingle_output.tsv"),
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
164 row.names = FALSE, sep = "\t"
a0ee43397d1e planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit 7e1748612a9f9dce11a9e54ff36752b600e7aea3
computational-metabolomics
parents: 6
diff changeset
165 )