Mercurial > repos > tomnl > create_sqlite_db

comparison anticipated_purity_dims.R @ 8:f6996ad60d8f draft

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 0aa10df0ec1ed71601f932cfb11d7d4d4f620d80-dirty
author tomnl
date Wed, 02 May 2018 14:17:22 -0400
parents d7f4696a1f86
children cc4464eb380f
comparison
equal deleted inserted replaced
7:d7f4696a1f86 8:f6996ad60d8f
30 df <- read.table(opt$peaks_file, header = TRUE, sep='\t') 30 df <- read.table(opt$peaks_file, header = TRUE, sep='\t')
31 filename = NA 31 filename = NA
32 }else{ 32 }else{
33 indf <- read.table(opt$peaks_file, 33 indf <- read.table(opt$peaks_file,
34 header = TRUE, sep='\t', stringsAsFactors = FALSE) 34 header = TRUE, sep='\t', stringsAsFactors = FALSE)
35 35
36 filename = colnames(indf)[8:ncol(indf)][opt$file_num_dimspy] 36 filename = colnames(indf)[8:ncol(indf)][opt$file_num_dimspy]
37 print(filename)
37 # check if the data file is mzML or RAW (can only use mzML currently) so 38 # check if the data file is mzML or RAW (can only use mzML currently) so
38 # we expect an mzML file of the same name in the same folder 39 # we expect an mzML file of the same name in the same folder
39 indf$i <- indf[,colnames(indf)==filename] 40 indf$i <- indf[,colnames(indf)==filename]
40 indf[,colnames(indf)==filename] <- as.numeric(indf[,colnames(indf)==filename]) 41 indf[,colnames(indf)==filename] <- as.numeric(indf[,colnames(indf)==filename])
41 42
42 filename = sub("raw", "mzML", filename, ignore.case = TRUE) 43 filename = sub("raw", "mzML", filename, ignore.case = TRUE)
43 44 print(filename)
44 df <- indf[4:nrow(indf),] 45 df <- indf[3:nrow(indf),]
45 if ('blank_flag' %in% colnames(df)){ 46 if ('blank_flag' %in% colnames(df)){
46 df <- df[df$blank_flag==1,] 47 df <- df[df$blank_flag==1,]
47 } 48 }
48 49
49 colnames(df)[colnames(df)=='m.z'] <- 'mz' 50 colnames(df)[colnames(df)=='m.z'] <- 'mz'
82 if (is.na(filename)){ 83 if (is.na(filename)){
83 print('ERROR: If a directory is provided then a filename needs to be entered 84 print('ERROR: If a directory is provided then a filename needs to be entered
84 directory or automatically obtained by using a dimspy output') 85 directory or automatically obtained by using a dimspy output')
85 quit() 86 quit()
86 }else{ 87 }else{
88 print('filename derived from dimspy')
87 mzml_file <- file.path(opt$mzML_file, filename) 89 mzml_file <- file.path(opt$mzML_file, filename)
88 } 90 }
89 }else{ 91 }else{
90 mzml_file <- opt$mzML_file 92 mzml_file <- opt$mzML_file
91 } 93 }
115 iwNormFun = msPurity::iwNormQE.5() 117 iwNormFun = msPurity::iwNormQE.5()
116 } 118 }
117 119
118 print('FIRST ROWS OF PEAK FILE') 120 print('FIRST ROWS OF PEAK FILE')
119 print(head(df)) 121 print(head(df))
120 122 print(mzml_file)
121 predicted <- msPurity::dimsPredictPuritySingle(df$mz, 123 predicted <- msPurity::dimsPredictPuritySingle(df$mz,
122 filepth=mzml_file, 124 filepth=mzml_file,
123 minOffset=minOffset, 125 minOffset=minOffset,
124 maxOffset=maxOffset, 126 maxOffset=maxOffset,
125 ppm=opt$ppm, 127 ppm=opt$ppm,