Mercurial > repos > prog > lcmsmatching

comparison MassbankSpectrum.R @ 1:253d531a0193 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit 36c9d8099c20a1ae848f1337c16564335dd8fb2b
author prog
date Sat, 03 Sep 2016 17:02:01 -0400
parents e66bb061af06
children
comparison
equal deleted inserted replaced
0:e66bb061af06 1:253d531a0193
19 19
20 spectra <- list() 20 spectra <- list()
21 21
22 # Define fields regex 22 # Define fields regex
23 regex <- character() 23 regex <- character()
24 regex[[RBIODB.ACCESSION]] <- "^ACCESSION: (.+)$" 24 regex[[BIODB.ACCESSION]] <- "^ACCESSION: (.+)$"
25 regex[[RBIODB.MSDEV]] <- "^AC\\$INSTRUMENT: (.+)$" 25 regex[[BIODB.MSDEV]] <- "^AC\\$INSTRUMENT: (.+)$"
26 regex[[RBIODB.MSDEVTYPE]] <- "^AC\\$INSTRUMENT_TYPE: (.+)$" 26 regex[[BIODB.MSDEVTYPE]] <- "^AC\\$INSTRUMENT_TYPE: (.+)$"
27 regex[[RBIODB.MSTYPE]] <- "^AC\\$MASS_SPECTROMETRY: MS_TYPE (.+)$" 27 regex[[BIODB.MSTYPE]] <- "^AC\\$MASS_SPECTROMETRY: MS_TYPE (.+)$"
28 regex[[RBIODB.MSPRECMZ]] <- "^MS\\$FOCUSED_ION: PRECURSOR_M/Z (.+)$" 28 regex[[BIODB.MSPRECMZ]] <- "^MS\\$FOCUSED_ION: PRECURSOR_M/Z (.+)$"
29 regex[[RBIODB.NB.PEAKS]] <- "^PK\\$NUM_PEAK: ([0-9]+)$" 29 regex[[BIODB.NB.PEAKS]] <- "^PK\\$NUM_PEAK: ([0-9]+)$"
30 regex[[RBIODB.MSPRECANNOT]] <- "^MS\\$FOCUSED_ION: PRECURSOR_TYPE (.+)$" 30 regex[[BIODB.MSPRECANNOT]] <- "^MS\\$FOCUSED_ION: PRECURSOR_TYPE (.+)$"
31 31
32 for (text in contents) { 32 for (text in contents) {
33 33
34 # Create instance 34 # Create instance
35 spectrum <- MassbankSpectrum$new() 35 spectrum <- MassbankSpectrum$new()
52 next 52 next
53 53
54 # MS MODE 54 # MS MODE
55 g <- str_match(s, "^AC\\$MASS_SPECTROMETRY: ION_MODE (.+)$") 55 g <- str_match(s, "^AC\\$MASS_SPECTROMETRY: ION_MODE (.+)$")
56 if ( ! is.na(g[1,1])) { 56 if ( ! is.na(g[1,1])) {
57 spectrum$setField(RBIODB.MSMODE, if (g[1,2] == 'POSITIVE') RBIODB.MSMODE.POS else RBIODB.MSMODE.NEG) 57 spectrum$setField(BIODB.MSMODE, if (g[1,2] == 'POSITIVE') BIODB.MSMODE.POS else BIODB.MSMODE.NEG)
58 next 58 next
59 } 59 }
60 60
61 # PEAKS 61 # PEAKS
62 if (.parse.peak.line(spectrum, s)) 62 if (.parse.peak.line(spectrum, s))
65 65
66 spectra <- c(spectra, spectrum) 66 spectra <- c(spectra, spectrum)
67 } 67 }
68 68
69 # Replace elements with no accession id by NULL 69 # Replace elements with no accession id by NULL
70 spectra <- lapply(spectra, function(x) if (is.na(x$getField(RBIODB.ACCESSION))) NULL else x) 70 spectra <- lapply(spectra, function(x) if (is.na(x$getField(BIODB.ACCESSION))) NULL else x)
71 71
72 # Set associated compounds 72 # Set associated compounds
73 compounds <- createMassbankCompoundFromTxt(contents) 73 compounds <- createMassbankCompoundFromTxt(contents)
74 for (i in seq(spectra)) 74 for (i in seq(spectra))
75 if ( ! is.null(spectra[[i]])) 75 if ( ! is.null(spectra[[i]]))
76 spectra[[i]]$setField(RBIODB.COMPOUND, compounds[[i]]) 76 spectra[[i]]$setField(BIODB.COMPOUND, compounds[[i]])
77 77
78 # If the input was a single element, then output a single object 78 # If the input was a single element, then output a single object
79 if (drop && length(contents) == 1) 79 if (drop && length(contents) == 1)
80 spectra <- spectra[[1]] 80 spectra <- spectra[[1]]
81 81
86 # PARSE PEAK LINE # 86 # PARSE PEAK LINE #
87 ################### 87 ###################
88 88
89 .parse.peak.line <- function(spectrum, line) { 89 .parse.peak.line <- function(spectrum, line) {
90 90
91 peaks <- RBIODB.PEAK.DF.EXAMPLE 91 peaks <- BIODB.PEAK.DF.EXAMPLE
92 92
93 # Annotation 93 # Annotation
94 g <- str_match(line, "^\\s+([0-9][0-9.]*) ([A-Z0-9+-]+) ([0-9]+) ([0-9][0-9.]*) ([0-9][0-9.]*)$") 94 g <- str_match(line, "^\\s+([0-9][0-9.]*) ([A-Z0-9+-]+) ([0-9]+) ([0-9][0-9.]*) ([0-9][0-9.]*)$")
95 if ( ! is.na(g[1,1])) 95 if ( ! is.na(g[1,1]))
96 peaks[1, c(RBIODB.PEAK.MZ, RBIODB.PEAK.FORMULA, RBIODB.PEAK.FORMULA.COUNT, RBIODB.PEAK.MASS, RBIODB.PEAK.ERROR.PPM)] <- list(as.double(g[1,2]), g[1,3], as.integer(g[1,4]), as.double(g[1,5]), as.double(g[1,6])) 96 peaks[1, c(BIODB.PEAK.MZ, BIODB.PEAK.FORMULA, BIODB.PEAK.FORMULA.COUNT, BIODB.PEAK.MASS, BIODB.PEAK.ERROR.PPM)] <- list(as.double(g[1,2]), g[1,3], as.integer(g[1,4]), as.double(g[1,5]), as.double(g[1,6]))
97 97
98 # Peak 98 # Peak
99 g <- str_match(line, "^\\s+([0-9][0-9.]*) ([0-9][0-9.]*) ([0-9]+)$") 99 g <- str_match(line, "^\\s+([0-9][0-9.]*) ([0-9][0-9.]*) ([0-9]+)$")
100 if ( ! is.na(g[1,1])) 100 if ( ! is.na(g[1,1]))
101 peaks[1, c(RBIODB.PEAK.MZ, RBIODB.PEAK.INTENSITY, RBIODB.PEAK.RELATIVE.INTENSITY)] <- list(as.double(g[1,2]), as.double(g[1,3]), as.integer(g[1,4])) 101 peaks[1, c(BIODB.PEAK.MZ, BIODB.PEAK.INTENSITY, BIODB.PEAK.RELATIVE.INTENSITY)] <- list(as.double(g[1,2]), as.double(g[1,3]), as.integer(g[1,4]))
102 102
103 if (nrow(peaks) > 0) { 103 if (nrow(peaks) > 0) {
104 104
105 # Get curent peaks and merge with new peaks 105 # Get curent peaks and merge with new peaks
106 current.peaks <- spectrum$getField(RBIODB.PEAKS) 106 current.peaks <- spectrum$getField(BIODB.PEAKS)
107 if ( ! is.null(current.peaks)) 107 if ( ! is.null(current.peaks))
108 peaks <- rbind(current.peaks, peaks) 108 peaks <- rbind(current.peaks, peaks)
109 109
110 spectrum$setField(RBIODB.PEAKS, peaks) 110 spectrum$setField(BIODB.PEAKS, peaks)
111 111
112 return(TRUE) 112 return(TRUE)
113 } 113 }
114 114
115 return(FALSE) 115 return(FALSE)