Fix/issue309

.travis.yml

@@ -1,5 +1,5 @@
 language: r
-r: bioc-devel
+r: bioc-release
 cache: packages
 
 # Set CXX1X for R-devel, as R-devel does not detect CXX1X support for gcc 4.6.3,

DESCRIPTION

@@ -1,17 +1,18 @@
 Package: RMassBank
 Type: Package
 Title: Workflow to process tandem MS files and build MassBank records
-Version: 2.99.2
+Version: 3.7.1
 Authors@R: c(
     person(given = "RMassBank at Eawag", email = "massbank@eawag.ch",
     role=c("cre")),
     person(given = "Michael A.", family = "Stravs", email =
     "michael.stravs@eawag.ch", role=c("aut")), person(given = "Emma L.",
-    family = "Schymanski", email = "emma.schymanski@eawag.ch", role=c("aut")),
+    family = "Schymanski", email = "emma.schymanski@uni.lu", role=c("aut")),
     person(given = "Steffen", family = "Neumann", role = "aut", email =
     "sneumann@ipb-halle.de"), person(given = "Erik", family = "Muller", role =
-    "aut", email = "erik.mueller@student.uni-halle.de"), person(given =
-    "Tobias", family = "Schulze", role = "ctb", email =
+    "aut", email = "erik.mueller@ufz.de"), person(given = "Paul", family = "Stahlhofen", role =
+    "aut", email = "paul-jonas.stahlhofen@ufz.de"),
+	person(given = "Tobias", family = "Schulze", role = "ctb", email =
     "tobias.schulze@ufz.de"), person(given =
     "Hendrik", family = "Treutler", role = "ctb", email =
     "hendrik.treutler@gmail.com") )
@@ -33,13 +34,15 @@ Encoding: UTF-8
 Imports:
     XML,rjson,S4Vectors,digest,
     rcdk,yaml,mzR,methods,Biobase,MSnbase,httr,
-    enviPat,assertthat
+    enviPat,assertthat,logger,RCurl,readJDX,webchem,
+    ChemmineR,ChemmineOB,R.utils,data.table
 Suggests:
-    BiocStyle,gplots,RMassBankData,
+    BiocStyle,gplots,RMassBankData (>= 1.33.1),
     xcms (>= 1.37.1),
     CAMERA,
     RUnit,
-    knitr
+    knitr,
+    rmarkdown
 Collate:
     'alternateAnalyze.R'
     'formulaCalculator.R'
@@ -71,4 +74,6 @@ Collate:
     'fillback.R'
     'parseMbRecord.R'
     'zzz.R'
-RoxygenNote: 7.1.1
+    'log_wrapper.R'
+    'createCompoundlist.R'
+RoxygenNote: 7.1.2

NAMESPACE

@@ -1,6 +1,8 @@
 # Generated by roxygen2: do not edit by hand
 
+export("property<-")
 export(.updateObject.RmbSpectrum2.formulaSource)
+export(CAS2SMILES)
 export(CTS.externalIdSubset)
 export(CTS.externalIdTypes)
 export(RmbDefaultSettings)
@@ -21,6 +23,8 @@ export(checkIsotopes)
 export(checkSpectra)
 export(cleanElnoise)
 export(combineMultiplicities)
+export(compoundlist2SDF)
+export(createCompoundlist)
 export(createMolfile)
 export(dbe)
 export(deprofile)
@@ -30,6 +34,7 @@ export(deprofile.scan)
 export(deprofile.spline)
 export(exportMassbank)
 export(fillback)
+export(filterCompoundlist)
 export(filterMultiplicity)
 export(filterPeakSatellites)
 export(filterPeaksMultiplicity)
@@ -42,7 +47,7 @@ export(findMsMsHR)
 export(findMsMsHR.direct)
 export(findMsMsHR.mass)
 export(findMsMsHR.ticms2)
-export(findMsMsHRperMsp.direct)
+export(findMsMsHRperMsp)
 export(findMsMsHRperxcms)
 export(findMsMsHRperxcms.direct)
 export(findMz)
@@ -60,9 +65,9 @@ export(gatherPubChem)
 export(getAnalyticalInfo)
 export(getCSID)
 export(getCactus)
-export(getCompTox)
 export(getCtsKey)
 export(getCtsRecord)
+export(getField)
 export(getMolecule)
 export(getPcId)
 export(is.valid.formula)
@@ -77,8 +82,8 @@ export(makeMollist)
 export(makePeaksCache)
 export(makeRecalibration)
 export(mbWorkflow)
-export(mergePeaks.df)
-export(mergeSpectra.RmbSpectrum2List)
+export(mergePeaks)
+export(mergeSpectra)
 export(msmsRead)
 export(msmsRead.RAW)
 export(msmsWorkflow)
@@ -97,6 +102,7 @@ export(ppm)
 export(problematicPeaks)
 export(processProblematicPeaks)
 export(progressBarHook)
+export(property)
 export(readMbdata)
 export(reanalyzeFailpeak)
 export(reanalyzeFailpeaks)
@@ -110,13 +116,21 @@ export(recalibrateSingleSpec)
 export(recalibrateSpectra)
 export(resetInfolists)
 export(resetList)
+export(rmb_log_debug)
+export(rmb_log_error)
+export(rmb_log_fatal)
+export(rmb_log_info)
+export(rmb_log_success)
+export(rmb_log_trace)
+export(rmb_log_warn)
 export(selectPeaks)
 export(selectSpectra)
 export(smiles2mass)
 export(spectraCount)
 export(to.limits.rcdk)
 export(toMassbank)
 export(toRMB)
+export(updateHeader)
 export(updateSettings)
 export(validate)
 exportClasses(RmbSpectraSet)
@@ -125,38 +139,42 @@ exportClasses(RmbSpectrum2)
 exportClasses(RmbSpectrum2List)
 exportClasses(mbWorkspace)
 exportClasses(msmsWorkspace)
-exportMethods("property<-")
 exportMethods(addProperty)
-exportMethods(buildRecord)
 exportMethods(checkSpectra)
 exportMethods(cleanElnoise)
-exportMethods(fillback)
 exportMethods(getData)
-exportMethods(mergePeaks)
-exportMethods(mergeSpectra)
 exportMethods(normalize)
 exportMethods(peaksMatched)
 exportMethods(peaksUnmatched)
-exportMethods(property)
 exportMethods(selectPeaks)
 exportMethods(selectSpectra)
 exportMethods(setData)
 exportMethods(show)
 exportMethods(spectraCount)
 exportMethods(toMassbank)
 import(MSnbase)
+import(R.utils)
+import(RCurl)
 import(Rcpp)
 import(S4Vectors)
 import(XML)
 import(assertthat)
 import(digest)
 import(httr)
+import(logger)
 import(methods)
 import(mzR)
 import(rcdk)
+import(readJDX)
 import(rjson)
 import(yaml)
 importFrom(Biobase,"classVersion<-")
 importFrom(Biobase,classVersion)
 importFrom(Biobase,isCurrent)
-importFrom(Biobase,isVersioned)
+importFrom(Biobase,isVersioned)
+importFrom(ChemmineR,smiles2sdf)
+importFrom(ChemmineR,validSDF)
+importFrom(ChemmineR,write.SDF)
+importFrom(data.table,fread)
+importFrom(data.table,fwrite)
+importFrom(webchem,cir_query)

R/Generics.R

@@ -39,5 +39,45 @@ setGeneric("selectPeaks", function(o, ...) standardGeneric("selectPeaks"))
 #' @export
 setGeneric("addProperty", function(o, name, type, value=NA) standardGeneric("addProperty"))
 
+#' Get a property of an RmbSpectrum2 object
+#'
+#' This searches the 'properties' slot of the object
+#' and returns a column with matching name (if found)
+#' or NULL otherwise.
+#'
+#' @param o \code{RmbSpectrum2}
+#' @param property character
+#' The name of a property
+#' @return The corresponding column of \code{o@properties}
+#' @rdname property
+#' @export
 setGeneric("property", function(o, property) standardGeneric("property"))
-setGeneric("property<-", function(o, property, value, addNew = FALSE, class="") standardGeneric("property<-"))
+
+#' Replacement function to set properties of an RmbSpectrum2 object
+#'
+#' Update the 'properties' slot of the given object.
+#' If the column you want to update does not exist yet and
+#' \code{addNew = FALSE} (default), this will cause a warning
+#' and the object will not be changed
+#'
+#' Please note that this is a replacement method, meaning that
+#' \code{property(o, property) <- value}
+#' can be used as a short-hand for the equivalent
+#' \code{o <- 'property<-'(o, property, value)}
+#'
+#' @usage property(o, property, addNew=FALSE, class="") <- value
+#' @param o \code{RmbSpectrum2}
+#' The object whos 'properties' slot should be updated
+#' @param property character
+#' The name of the column in the 'properties' data frame to be updated
+#' @param addNew logical, Default: FALSE
+#' Whether or not a new column should be added in case a column of the
+#' given name does not exist yet.
+#' @param class character or missing
+#' The class of the entries for the column to be added/updated
+#' @param value ANY
+#' The value(s) to be written into the column
+#' @return The \code{RmbSpectrum2} object with an updated 'properties' slot
+#' @rdname property-set
+#' @export
+setGeneric("property<-", function(o, property, addNew = FALSE, class="", value) standardGeneric("property<-"))

R/Isotopic_Annotation.R

@@ -102,7 +102,7 @@ checkIsotopes <- function(w, mode = "pH", intensity_cutoff = 0, intensity_precis
 			if(nrow(currentMPeaks)){
 				rownames(currentMPeaks) <- 1:nrow(currentMPeaks)
 			} else {
-				message(paste0("Compound ", id, " in spectrum #", specEnv$specNum," does not have matched peaks, so no isotopes can be found"))
+				rmb_log_info(paste0("Compound ", id, " in spectrum #", specEnv$specNum," does not have matched peaks, so no isotopes can be found"))
 				if(plotSpectrum){
 					plot(currentMPeaks$mzFound, currentMPeaks$intensity,type="h", main=paste(id,findName(id)), col="black", xlab="m/z", ylab="intensity", lwd=3)
 				}
@@ -130,7 +130,7 @@ checkIsotopes <- function(w, mode = "pH", intensity_cutoff = 0, intensity_precis
 
             # If there are no peaks left, then abort for this spectrum
 			if(!length(peaksToCheck)){
-				message(paste0("The already annotated peaks of compound ", id, " in spectrum #", specEnv$specNum," are not intense enough to search for isotopic peaks"))
+				rmb_log_info(paste0("The already annotated peaks of compound ", id, " in spectrum #", specEnv$specNum," are not intense enough to search for isotopic peaks"))
 				if(plotSpectrum){
 					plot(currentMPeaks$mzFound, currentMPeaks$intensity,type="h", main=paste(id,findName(id)), col="black", xlab="m/z", ylab="intensity", lwd=3)
 				}

R/RmbSpectrum2Update.R

@@ -36,9 +36,9 @@
 #' 
 #' TODO: consider whether to add functionality to move reanalysis stuff from legacy data back in.
 #' 
-#' @param w 
-#' @returnType 
-#' @return 
+#' @param w RmbSpectrum2
+#' The object to be updated
+#' @return The updated RmbSpectrum2 object
 #' 
 #' @author stravsmi
 #' @export
@@ -83,10 +83,10 @@
 
 .updateObject.RmbSpectraSet.updatePolarity <- function(w)
 {
-  w@parent@polarity <- .polarity[[w@mode]]
+  w@parent@polarity <- getAdductPolarity(w@mode)
   for(n in seq_len(length(w@children)))
   {
-    w@children[[n]]@polarity <- .polarity[[w@mode]]
+    w@children[[n]]@polarity <- getAdductPolarity(w@mode)
   }
   w
 }

R/SpectrumClasses.R

@@ -1,7 +1,76 @@
 #' @import MSnbase
 #' @importFrom Biobase classVersion
 #' @import S4Vectors
+NULL
 
+#' @title RMassBank Representation of an MSMS Spectrum
+#'
+#' @description This extends the \code{Spectrum2} class of the \code{MSnbase}
+#' package and introduces further slots that are used to store information
+#' during the \code{RMassBank} workflow.
+#'
+#' @slot satellite logical
+#' If \code{TRUE}, the corresponding peak was removed as satellite.
+#' @slot low logical
+#' If \code{TRUE}, the corresponding peak was removed
+#' because it failed the intensity cutoff.
+#' @slot rawOk logical
+#' If \code{TRUE}, the peak passed satellite and low-intensity cutoff removal.
+#' @slot good logical
+#' If \code{TRUE}, a formula could be found for the peak
+#' and the peak passed all filter criteria. (see the
+#' \code{RMassBank} vignette or the documentation of \code{\link{analyzeMsMs}}#' for details on filter settings)
+#' @slot mzCalc numeric
+#' The mz value calculated from the found formula for each peak (if any)
+#' @slot formula character
+#' The formula found for each peak.
+#' \code{\link[rcdk]{generate.formula}} is used
+#' for formula-fitting
+#' @slot dbe numeric
+#' The number of double bond equivalents.
+#' This is calculated from the found formula for each peak (if any)
+#' @slot formulaCount integer
+#' The number of different formulae found for each peak.
+#' Note: A peak for which multiple formulas were found will appear
+#' multiple times. Hence there may be multiple entries in the \code{formula}
+#' , \code{dppm} and \code{mzCalc} slot for the same mz value.
+#' @slot formulaSource character "analyze" or "reanalysis"
+#' Shows whether the current formula for the peak was determined by normal
+#' analysis ("analyze") or by reanalysis of a failpeak ("reanalysis")
+#' @slot dppm numeric
+#' The ppm deviation of the mz value from the found formula (if any).
+#' @slot dppmBest numeric
+#' The ppm deviation of the mz value from the best formula found.
+#' @slot ok logical one-element vector
+#' If this is \code{TRUE}, the spectrum was successfully processed
+#' with at least one resulting peak.
+#' Otherwise, one of the following cases applies:
+#' \itemize{
+#' \item All peaks failed the intensity cutoff
+#' i.e. the whole spectrum contains low intensity peaks, only.
+#' \item All peaks were marked as satellites.
+#' \item All peaks in the spectrum have a lower intensity than the value
+#' given in the \code{specOkLimit} filter setting. (see the \code{RMassBank}
+#' vignette or the documentation of \code{\link{analyzeMsMs}})
+#' \item The precursor ion formula is invalid (see \code{\link{is.valid.formula}})
+#' \item The spectrum is empty.
+#' \item No molecular formula could be found for any of the peaks.
+#' \item All peaks failed the \code{dbeMinLimit} criterion. (see the
+#' \code{RMassBank} vignette or the documentation of \code{\link{analyzeMsMs}})
+#' }
+#' @slot info list
+#' Spectrum identifying information
+#' (collision energy, resolution, collision mode) from the \code{spectraList}
+#' @slot properties data.frame
+#' This is used as a flexible placeholder to store additional properties
+#' for each peak throughout the workflow. After the last step of the
+#' \code{mbWorkflow}, this will typically contain columns \code{mzRaw},
+#' \code{noise}, \code{formulaMultiplicity}, \code{bestMultiplicity}
+#' and \code{filterOK}. However, new columns may be added on demand
+#' (see \code{\link{property<-}})
+#' @seealso \code{\link[rcdk]{generate.formula}}, \code{\link{property<-}}
+#' \code{\link{analyzeMsMs}}, \code{\link{generate.formula}},
+#' \code{\link{is.valid.formula}}
 #' @exportClass RmbSpectrum2
 .RmbSpectrum2 <- setClass("RmbSpectrum2",
 		representation = representation(