Mercurial > repos > prog > lcmsmatching

comparison MsFileDb.R @ 2:20d69a062da3 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 d4048accde6bdfd5b3e14f5394902d38991854f8
author prog
date Thu, 02 Mar 2017 08:55:00 -0500
parents e66bb061af06
children fb9c0409d85c
comparison
equal deleted inserted replaced
1:253d531a0193 2:20d69a062da3
82 if (is.null(.self$.db)) { 82 if (is.null(.self$.db)) {
83 83
84 # Load database 84 # Load database
85 .db <<- read.table(.self$.file, sep = "\t", quote = "\"", header = TRUE, stringsAsFactors = FALSE, row.names = NULL) 85 .db <<- read.table(.self$.file, sep = "\t", quote = "\"", header = TRUE, stringsAsFactors = FALSE, row.names = NULL)
86 86
87 # Check that colnames are unique
88 dupcol <- duplicated(colnames(.self$.db))
89 if (any(dupcol))
90 stop(paste("Database header contains duplicated names: ", paste(unique(colnames(.self$.db)[dupcol]), collapse = ', '), "."))
91
92 # Check that columns names supplied through field map are unique
93 dupfields <- duplicated(.self$.fields)
94 if (any(dupfields))
95 stop(paste("Some db column names supplied are duplicated: ", paste(unique(.self$.fields[dupfields]), collapse = ', '), "."))
96
87 # Rename columns 97 # Rename columns
88 colnames(.self$.db) <- vapply(colnames(.self$.db), function(c) if (c %in% .self$.fields) names(.self$.fields)[.self$.fields %in% c] else c, FUN.VALUE = '') 98 colnames(.self$.db) <- vapply(colnames(.self$.db), function(c) if (c %in% .self$.fields) names(.self$.fields)[.self$.fields %in% c] else c, FUN.VALUE = '')
89 } 99 }
90 }) 100 })
91 101
149 159
150 #################### 160 ####################
151 # GET MOLECULE IDS # 161 # GET MOLECULE IDS #
152 #################### 162 ####################
153 163
154 MsFileDb$methods( getMoleculeIds = function() { 164 MsFileDb$methods( getMoleculeIds = function(max.results = NA_integer_) {
155 165
156 # Init db 166 # Init db
157 .self$.init.db() 167 .self$.init.db()
158 168
159 # Get IDs 169 # Get IDs
160 mol.ids <- as.character(.self$.get.col(MSDB.TAG.MOLID)) 170 mol.ids <- as.character(.self$.get.col(MSDB.TAG.MOLID))
161 mol.ids <- mol.ids[ ! duplicated(mol.ids)] 171 mol.ids <- mol.ids[ ! duplicated(mol.ids)]
162 mol.ids <- sort(mol.ids) 172 mol.ids <- sort(mol.ids)
173
174 # Cut results
175 if ( ! is.na(max.results) && length(mol.ids) > max.results)
176 mol.ids <- mol.ids[1:max.results]
163 177
164 return(mol.ids) 178 return(mol.ids)
165 }) 179 })
166 180
167 #################### 181 ####################
414 ################# 428 #################
415 # GET MZ VALUES # 429 # GET MZ VALUES #
416 ################# 430 #################
417 431
418 # Returns a numeric vector of all masses stored inside the database. 432 # Returns a numeric vector of all masses stored inside the database.
419 MsFileDb$methods( getMzValues = function(mode = NULL) { 433 MsFileDb$methods( getMzValues = function(mode = NULL, max.results = NA_integer_) {
420 434
421 # Init db 435 # Init db
422 .self$.init.db() 436 .self$.init.db()
423 db <- .self$.db 437 db <- .self$.db
424 438
432 # Get masses 446 # Get masses
433 mz <- .self$.get(db, col = MSDB.TAG.MZTHEO) 447 mz <- .self$.get(db, col = MSDB.TAG.MZTHEO)
434 448
435 # Remove duplicates 449 # Remove duplicates
436 mz <- mz[ ! duplicated(mz)] 450 mz <- mz[ ! duplicated(mz)]
451
452 # Apply cut-off
453 if ( ! is.na(max.results))
454 mz <- mz[1:max.results]
437 455
438 return(mz) 456 return(mz)
439 }) 457 })
440 458
441 ####################### 459 #######################