comparison MsFileDb.R @ 6:b8f70d8216b3 draft

planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit b3a4e34cf9356447ae3507cc6fe2ff6a1f24afbc-dirty

5:18254e8d1b72

	MsFileDb$methods( .init.db = function() {

		if (is.null(.self$.db)) {

			# Load database
			.db <<- read.table(.self$.file, sep = "\t", quote = "\"", header = TRUE, stringsAsFactors = FALSE, row.names = NULL)

			# Check that colnames are unique
			dupcol <- duplicated(colnames(.self$.db))
			if (any(dupcol))
				stop(paste("Database header contains duplicated names: ", paste(unique(colnames(.self$.db)[dupcol]), collapse = ', '), "."))

		if ( ! is.null(col) && ! is.na(col))
			db <- db[db[[MSDB.TAG.COL]] %in% col,]

		# Filter on retention time
		if ( ! is.null(rt.low) && ! is.na(rt.low) && ! is.null(rt.high) && ! is.na(rt.high)) {
			scale <- if (.self$.rt.unit == MSDB.RTUNIT.MIN) 60 else 1
			db <- db[db[[MSDB.TAG.COLRT]] * scale >= rt.low & db[[MSDB.TAG.COLRT]] <= rt.high, ]
		}

		# Remove retention times and column information
		if (is.null(col) || is.na(col) || is.null(rt.low) || is.na(rt.low) || is.null(rt.high) || is.na(rt.high)) {
			db <- db[, ! (colnames(db) %in% c(MSDB.TAG.COL, MSDB.TAG.COLRT))]

			db <- db[ ! duplicated(db), ]
		}

		# Filter on mz
		db <- db[db[[MSDB.TAG.MZTHEO]] >= mz.low & db[[MSDB.TAG.MZTHEO]] <= mz.high, ]

		# Rename database fields
#		conv <- c( mz = 'mztheo', rt = 'colrt') # solving mismatch of field names between database and output
#		cols <- colnames(db)
#		for (db.field in names(.self$.fields)) {
#			output.field <- if (db.field %in% names(conv)) conv[[db.field]] else db.field
#			if (.self$.fields[[db.field]] %in% cols && output.field %in% names(.self$.output.fields))
#				cols[cols %in% .self$.fields[[db.field]]] <- .self$.output.fields[[output.field]]
#		}
#		colnames(db) <- cols

		# Remove unwanted columns
#		db <- db[, colnames(db) %in% .self$.output.fields]

		return(db)
	})
	
	#################

		for (col in cols) {
			colrts <- db[db[[MSDB.TAG.COL]] %in% col, MSDB.TAG.COLRT]
			rt[col] <- list(colrts)
		}

		if (.self$.rt.unit == MSDB.RTUNIT.MIN)
			rt <- 60 * rt

		return(rt)
	})

6:b8f70d8216b3

	MsFileDb$methods( .init.db = function() {

		if (is.null(.self$.db)) {

			# Load database
			.db <<- read.table(.self$.file, sep = "\t", quote = "\"", header = TRUE, stringsAsFactors = FALSE, row.names = NULL, check.names = FALSE, comment.char = '')

			# Check that colnames are unique
			dupcol <- duplicated(colnames(.self$.db))
			if (any(dupcol))
				stop(paste("Database header contains duplicated names: ", paste(unique(colnames(.self$.db)[dupcol]), collapse = ', '), "."))

		if ( ! is.null(col) && ! is.na(col))
			db <- db[db[[MSDB.TAG.COL]] %in% col,]

		# Filter on retention time
		if ( ! is.null(rt.low) && ! is.na(rt.low) && ! is.null(rt.high) && ! is.na(rt.high)) {
			scale <- if (.self$getRtUnit() == MSDB.RTUNIT.MIN) 60 else 1
			db <- db[db[[MSDB.TAG.COLRT]] * scale >= rt.low & db[[MSDB.TAG.COLRT]] * scale <= rt.high, ]
		}

		# Remove retention times and column information
		if (is.null(col) || is.na(col) || is.null(rt.low) || is.na(rt.low) || is.null(rt.high) || is.na(rt.high)) {
			db <- db[, ! (colnames(db) %in% c(MSDB.TAG.COL, MSDB.TAG.COLRT))]

			db <- db[ ! duplicated(db), ]
		}

		# Filter on mz
		db <- db[db[[MSDB.TAG.MZTHEO]] >= mz.low & db[[MSDB.TAG.MZTHEO]] <= mz.high, ]

		return(db)
	})
	
	#################

		for (col in cols) {
			colrts <- db[db[[MSDB.TAG.COL]] %in% col, MSDB.TAG.COLRT]
			rt[col] <- list(colrts)
		}

		if (.self$getRtUnit() == MSDB.RTUNIT.MIN)
			rt <- 60 * rt

		return(rt)
	})