Push current fixed version

git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/RMassBank@116140 bc3139a8-67e5-0310-9ffc-ced21a209358

inst/unitTests/runit.NOPEAKS.R → inst/unitTests/test_NOPEAKS.R

 test.nopeaks <- function(){
 	w <- newMsmsWorkspace()
 	w@aggregated <- data.frame(mzFound = numeric(0), intensity = numeric(0), good = logical(0), mzCalc = numeric(0), formula = character(0), dbe = numeric(0),
-	formulaCount = integer(0), dppm = numeric(0), dppmBest = numeric(0), scan = integer(0), cpdID = character(0), parentScan = integer(0), dppmRc = numeric(0),
-	index = integer(0), noise = logical(0), reanalyzed.formula = character(0), reanalyzed.mzCalc = numeric(0), reanalyzed.dppm = numeric(0),reanalyzed.formulaCount = numeric(0),
-	reanalyzed.dbe = numeric(0),matchedReanalysis = logical(0))
+		formulaCount = integer(0), dppm = numeric(0), dppmBest = numeric(0), scan = integer(0), cpdID = character(0), parentScan = integer(0), dppmRc = numeric(0),
+		index = integer(0), noise = logical(0), reanalyzed.formula = character(0), reanalyzed.mzCalc = numeric(0), reanalyzed.dppm = numeric(0),reanalyzed.formulaCount = numeric(0),
+		reanalyzed.dbe = numeric(0),matchedReanalysis = logical(0))
 	filterMultiplicity(w, mode="pH")
-	RUnit::checkTrue(TRUE)
+	checkTrue(TRUE)
 }
\ No newline at end of file

inst/unitTests/runit.DA.R → inst/unitTests/test_mzR.R

@@ -2,7 +2,6 @@ test.mzRRead <- function(){
 	allOK <- TRUE
 	records <- list.files("XX/recdata",full.names=TRUE)
 	rightrecords <- list.files(system.file("records/XX/recdata", package="RMassBankData"), full.names=TRUE)
-	
 	for(i in 1:length(records)){
 		gen <- file(description = records[i], open = "r", blocking = TRUE,
 		encoding = getOption("encoding"), raw = FALSE)

man/checkIsotopes.Rd

@@ -4,8 +4,8 @@
 \alias{checkIsotopes}
 \title{Checks for isotopes in a \code{msmsWorkspace}}
 \usage{
-checkIsotopes(w, mode = "pH", intensity_cutoff = 1000,
-  intensity_precision = "low", conflict = "dppm", isolationWindow = 4,
+checkIsotopes(w, mode = "pH", intensity_cutoff = 0,
+  intensity_precision = "none", conflict = "strict", isolationWindow = 2,
   evalMode = "complete", plotSpectrum = TRUE,
   settings = getOption("RMassBank"))
 }
@@ -15,7 +15,8 @@ checkIsotopes(w, mode = "pH", intensity_cutoff = 1000,
 \item{mode}{\code{"pH", "pNa", "pM", "pNH4", "mH", "mM", "mFA"} for different ions 
 ([M+H]+, [M+Na]+, [M]+, [M+NH4]+, [M-H]-, [M]-, [M+FA]-).}
 
-\item{intensity_cutoff}{The cutoff (as an absolute intensity value) under which isotopic peaks shouldn't be checked for or accepted as valid.}
+\item{intensity_cutoff}{The cutoff (as an absolute intensity value) under which isotopic peaks shouldn't be checked for or accepted as valid.
+Please note: The cutoff is not hard in the sense that it interacts with the intensity_precision parameter.}
 
 \item{intensity_precision}{The difference that is accepted between the calculated and observed intensity of a possible isotopic peak. Further details down below.}
 

man/compileRecord.Rd

@@ -4,7 +4,7 @@
 \alias{compileRecord}
 \title{Compile MassBank records}
 \usage{
-compileRecord(spec, mbdata, aggregated, additionalPeaks = NULL)
+compileRecord(spec, mbdata, aggregated, additionalPeaks = NULL, retrieval="standard")
 }
 \arguments{
 \item{spec}{A \code{RmbSpectraSet} for a compound, after analysis (\code{\link{analyzeMsMs}}).
@@ -20,6 +20,10 @@ usage information.)}
 
 \item{additionalPeaks}{If present, a table with additional peaks to add into the spectra.
 As loaded with \code{\link{addPeaks}}.}
+
+\item{retrieval}{A value that determines whether the files should be handled either as "standard",
+if the compoundlist is complete, "tentative", if at least a formula is present or "unknown"
+if the only know thing is the m/z}
 }
 \value{
 Returns a MassBank record in list format: e.g.

man/findMass.Rd

@@ -4,11 +4,19 @@
 \alias{findMass}
 \title{Calculate exact mass}
 \usage{
-findMass(cpdID_or_smiles)
+findMass(cpdID_or_smiles, retrieval = "standard", mode = "pH")
 }
 \arguments{
 \item{cpdID_or_smiles}{SMILES code or compound ID of the molecule. (Numerics
 are treated as compound ID).}
+
+\item{retrieval}{A value that determines whether the files should be handled either as "standard",
+if the compoundlist is complete, "tentative", if at least a formula is present or "unknown"
+if the only know thing is the m/z}
+
+\item{mode}{\code{"pH", "pNa", "pM", "pNH4", "mH", "mM", "mFA"} for different ions 
+            ([M+H]+, [M+Na]+, [M]+, [M+NH4]+, [M-H]-, [M]-, [M+FA]-).
+Only needed for retrieval="unknown"}
 }
 \value{
 Returns the exact mass of the uncharged molecule.

man/findMsMsHR.Rd

@@ -12,7 +12,7 @@ findMsMsHR(fileName = NULL, msRaw = NULL, cpdID, mode = "pH",
   fillPrecursorScan = getOption("RMassBank")$findMsMsRawSettings$fillPrecursorScan,
   rtMargin = getOption("RMassBank")$rtMargin,
   deprofile = getOption("RMassBank")$deprofile, headerCache = NULL,
-  peaksCache = NULL)
+  peaksCache = NULL, retrieval = "standard")
 
 findMsMsHR.mass(msRaw, mz, limit.coarse, limit.fine, rtLimits = NA,
   maxCount = NA, headerCache = NULL, fillPrecursorScan = FALSE,
@@ -60,6 +60,10 @@ freshly from \code{msRaw} for every compound.}
 \item{peaksCache}{If present, the complete output of \code{mzR::peaks(msRaw)}. This speeds up the lookup
 if multiple compounds should be searched in the same file.}
 
+\item{retrieval}{A value that determines whether the files should be handled either as "standard",
+if the compoundlist is complete, "tentative", if at least a formula is present or "unknown"
+if the only know thing is the m/z}
+
 \item{mz}{The mass to use for spectrum search.}
 
 \item{limit.coarse}{Parameter in \code{findMsMsHR.mass} corresponding to \code{mzCoarse}.

man/findMz.Rd

@@ -3,23 +3,26 @@
 \name{findMz}
 \alias{findCAS}
 \alias{findFormula}
+\alias{findLevel}
 \alias{findMz}
 \alias{findName}
 \alias{findRt}
 \alias{findSmiles}
 \title{Find compound information}
 \usage{
-findMz(cpdID, mode = "pH", ppm = 10, deltaMz = 0)
+findMz(cpdID, mode = "pH", ppm = 10, deltaMz = 0, retrieval="standard")
 
 findRt(cpdID) 
 
 findSmiles(cpdID) 
 
-findFormula(cpdID) 
+findFormula(cpdID, retrieval="standard") 
 
 findCAS(cpdID)
 
 findName(cpdID)
+
+findLevel(cpdID, compact=FALSE)
 }
 \arguments{
 \item{cpdID}{The compound ID in the compound list.}
@@ -37,6 +40,13 @@ molecular mass + and - 10 ppm).}
 \item{deltaMz}{Specifies additional m/z window to add to the range (deltaMz
 = 0.02 will return the range of the molecular mass +- 0.02 (and additionally
 +- the set ppm value).}
+
+\item{retrieval}{A value that determines whether the files should be handled either as "standard",
+if the compoundlist is complete, "tentative", if at least a formula is present or "unknown"
+if the only know thing is the m/z}
+
+\item{compact}{Only for \code{findLevel}, returns the "retrieval" parameter used for many functions 
+within RMassBank if TRUE}
 }
 \value{
 \code{findMz} will return a \code{list(mzCenter=, mzMin=, mzMax=)}

man/gatherCompound.Rd

@@ -5,10 +5,10 @@
 \alias{gatherSpectrum}
 \title{Compose data block of MassBank record}
 \usage{
-gatherCompound(spec, aggregated, additionalPeaks = NULL)
+gatherCompound(spec, aggregated, additionalPeaks = NULL, retrieval="standard")
 
 		gatherSpectrum(spec, msmsdata, ac_ms, ac_lc, aggregated, 
- 		additionalPeaks = NULL)
+ 		additionalPeaks = NULL, retrieval="standard")
 }
 \arguments{
 \item{spec}{A \code{RmbSpectraSet} object, representing a compound with multiple spectra.}
@@ -18,6 +18,10 @@ gatherCompound(spec, aggregated, additionalPeaks = NULL)
 \item{additionalPeaks}{If present, a table with additional peaks to add into the spectra.
 As loaded with \code{\link{addPeaks}}.}
 
+\item{retrieval}{A value that determines whether the files should be handled either as "standard",
+if the compoundlist is complete, "tentative", if at least a formula is present or "unknown"
+if the only know thing is the m/z}
+
 \item{msmsdata}{A \code{RmbSpectrum2} object from the \code{spec} spectra set, representing a single spectrum to give a record.}
 
 \item{ac_ms, ac_lc}{Information for the AC\$MASS_SPECTROMETRY and

man/gatherDataUnknown.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/createMassBank.R
+\name{gatherDataUnknown}
+\alias{gatherDataUnknown}
+\title{Retrieve annotation data}
+\usage{
+gatherDataUnknown(id, mode, retrieval)
+}
+\arguments{
+\item{id}{The compound ID.}
+
+\item{mode}{\code{"pH", "pNa", "pM", "pNH4", "mH", "mM", "mFA"} for different ions 
+([M+H]+, [M+Na]+, [M]+, [M+NH4]+, [M-H]-, [M]-, [M+FA]-).}
+
+\item{retrieval}{A value that determines whether the files should be handled either as "standard",
+if the compoundlist is complete, "tentative", if at least a formula is present or "unknown"
+if the only know thing is the m/z}
+}
+\value{
+Returns a list of type \code{list(id= \var{compoundID}, ...,
+'ACCESSION' = '', 'RECORD_TITLE' = '', )} etc. %% ...
+}
+\description{
+Retrieves annotation data for an unknown compound by using basic information present
+}
+\details{
+Composes the "upper part" of a MassBank record filled with chemical data
+about the compound: name, exact mass, structure, CAS no..  
+The instrument type is also written into this block (even
+if not strictly part of the chemical information). Additionally, index
+fields are added at the start of the record, which will be removed later:
+\code{id, dbcas, dbname} from the compound list.
+
+Additionally, the fields \code{ACCESSION} and \code{RECORD_TITLE} are
+inserted empty and will be filled later on.
+
+This function is used to generate the data in case a substance is unknown,
+i.e. not enough information is present to derive anything about formulas or links
+}
+\examples{
+
+# Gather data for compound ID 131
+\dontrun{gatherDataUnknown(131,"pH")}
+
+}
+\author{
+Michael Stravs, Erik Mueller
+}
+\references{
+MassBank record format:
+\url{http://www.massbank.jp/manuals/MassBankRecord_en.pdf}
+}
+\seealso{
+\code{\link{mbWorkflow}}
+}
+

man/mbWorkflow.Rd

@@ -17,7 +17,7 @@ which should then be manually inspected.}
 
 \item{gatherData}{A variable denoting whether to retrieve information using several online databases \code{gatherData= "online"}
 or to use the local babel installation \code{gatherData= "babel"}. Note that babel is used either way, if a directory is given 
-in the settings}
+in the settings. This setting will be ignored if retrieval is set to "standard"}
 }
 \value{
 The processed \code{mbWorkspace}.

man/processProblematicPeaks.Rd

@@ -11,7 +11,9 @@ processProblematicPeaks(w, mode, archivename = NA)
 
 \item{mode}{Processing mode (pH etc)}
 
-\item{archivename}{Base name of the archive to write to (for "abc" the exported failpeaks list will be "abc_Failpeaks.csv").}
+\item{archivename}{Base name of the archive to write to (for "abc" the exported failpeaks list will be "abc_Failpeaks.csv").
+if the compoundlist is complete, "tentative", if at least a formula is present or "unknown"
+if the only know thing is the m/z}
 }
 \value{
 Returns the aggregate data.frame with added column "\code{problematic}" (logical) which marks peaks which match the problematic criteria

tests/doRUnit.R

+#### doRUnit.R --- Run RUnit tests
+####------------------------------------------------------------------------
+
+### Structure borrowed from rcppgls:
+### https://github.com/eddelbuettel/rcppgsl/blob/master/tests/doRUnit.R
+
+if(require("RUnit", quietly = TRUE)) {
+	if(require("RMassBankData", quietly = TRUE) && !(compareVersion(installed.packages()["RMassBankData","Version"],"1.99.0") == -1)) {
+		pkg <- "RMassBank"
+		print("Starting tests")
+		require(pkg, character.only=TRUE)
+
+		path <- system.file("unitTests", package = pkg)
+
+		stopifnot(file.exists(path), file.info(path.expand(path))$isdir)
+
+		source(file.path(path, "runTests.R"), echo = TRUE)
+	} else {
+		## Taking this message out until the new RMassBankData is on bioc, just to avoid confusion.
+        # message("Package RMassBankData with version > 1.99 not available, cannot run unit tests")
+	}
+} else {
+	message("Package RUnit not available, cannot run unit tests")
+}