refactor(converters): Migrate converters to MSstatsConvert

.gitignore

@@ -6,3 +6,4 @@
 ./*.txt
 *.Rproj
 *.DS_Store
+*.Rproj

DESCRIPTION

@@ -23,4 +23,4 @@ Encoding: UTF-8
 LazyData: true
 URL: http://msstats.org/msstatstmt/
 BugReports: https://groups.google.com/forum/#!forum/msstats
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3

NAMESPACE

@@ -16,13 +16,12 @@ importFrom(MSstats,dataProcess)
 importFrom(MSstats,getSelectedProteins)
 importFrom(MSstats,savePlot)
 importFrom(MSstats,theme_msstats)
-importFrom(MSstatsConvert,MSstatsBalancedDesign)
-importFrom(MSstatsConvert,MSstatsClean)
-importFrom(MSstatsConvert,MSstatsImport)
-importFrom(MSstatsConvert,MSstatsLogsSettings)
-importFrom(MSstatsConvert,MSstatsMakeAnnotation)
-importFrom(MSstatsConvert,MSstatsPreprocess)
 importFrom(MSstatsConvert,MSstatsSaveSessionInfo)
+importFrom(MSstatsConvert,MaxQtoMSstatsTMTFormat)
+importFrom(MSstatsConvert,OpenMStoMSstatsTMTFormat)
+importFrom(MSstatsConvert,PDtoMSstatsTMTFormat)
+importFrom(MSstatsConvert,PhilosophertoMSstatsTMTFormat)
+importFrom(MSstatsConvert,SpectroMinetoMSstatsTMTFormat)
 importFrom(grDevices,dev.off)
 importFrom(grDevices,hcl)
 importFrom(grDevices,pdf)

R/utils_MSstatsTMT.R

@@ -17,234 +17,8 @@
 #' @keywords internal
 "_PACKAGE"
 
-
-#' Example of output from Proteome Discoverer 2.2 for TMT-10plex experiments.
-#'
-#' Example of Proteome discover PSM sheet.
-#' It is the input for PDtoMSstatsTMTFormat function, with annotation file.
-#' Annotation file should be made by users.
-#' It includes peak intensities for 10 proteins
-#' among 15 MS runs with TMT-10plex.
-#' The variables are as follows:
-#'
-#' \itemize{
-#'   \item Master.Protein.Accessions
-#'   \item Protein.Accessions
-#'   \item Annotated.Sequence
-#'   \item Charge
-#'   \item Ions.Score
-#'   \item Spectrum.File
-#'   \item Quan.Info
-#'   \item Channels : 126, ..., 131
-#' }
-#'
-#' @format A data frame with 2858 rows and 50 variables.
-#' @examples
-#' head(raw.pd)
-#'
-"raw.pd"
-
-#' Example of annotation file for raw.pd,
-#' which is the PSM output of Proteome Discoverer
-#'
-#' Annotation of example data, raw.pd, in this package.
-#' It should be prepared by users.
-#' The variables are as follows:
-#'
-#' \itemize{
-#'   \item Run : MS run ID. It should be the same as Spectrum.File info
-#'   in raw.pd.
-#'   \item Channel : Labeling information (126, ... 131). It should be
-#'   consistent with the channel columns in raw.pd.
-#'   \item Condition : Condition (ex. Healthy, Cancer, Time0)
-#'   \item Mixture : Mixture of samples labeled with different TMT reagents, which can be analyzed in
-#'   a single mass spectrometry experiment. If the channal doesn't have sample, please add `Empty' under Condition.
-#'   \item TechRepMixture : Technical replicate of one mixture. One mixture may have multiple technical replicates.
-#'   For example, if `TechRepMixture' = 1, 2 are the two technical replicates of one mixture, then they should match
-#'   with same `Mixture' value.
-#'   \item Fraction : Fraction ID. One technical replicate of one mixture may be fractionated into multiple fractions to increase the analytical depth.
-#'   Then one technical replicate of one mixture should correspond to multuple fractions.
-#'   For example, if `Fraction' = 1, 2, 3 are three fractions of the first technical replicate of one TMT mixture of biological subjects,
-#'   then they should have same `TechRepMixture'  and `Mixture' value.
-#'   \item BioReplicate : Unique ID for biological subject. If the channal doesn't have sample, please add `Empty' under BioReplicate.
-#' }
-#'
-#' @format A data frame with 150 rows and 7 variables.
-#' @examples
-#' head(annotation.pd)
-#'
-"annotation.pd"
-
-#' Example of output from MaxQuant for TMT-10plex experiments.
-#'
-#' Example of evidence.txt from MaxQuant.
-#' It is the input for MaxQtoMSstatsTMTFormat function, with proteinGroups.txt
-#' and annotation file. Annotation file should be made by users.
-#' It includes peak intensities for 10 proteins among 15 MS runs with TMT10.
-#' The important variables are as follows:
-#'
-#' \itemize{
-#'   \item Proteins
-#'   \item Protein.group.IDs
-#'   \item Modified.sequence
-#'   \item Charge
-#'   \item Raw.file
-#'   \item Score
-#'   \item Potential.contaminant
-#'   \item Reverse
-#'   \item Channels : Reporter.intensity.corrected.0, ...,
-#'   Reporter.intensity.corrected.9
-#' }
-#'
-#' @format A data frame with 1075 rows and 105 variables.
-#' @examples
-#' head(evidence)
-#'
-"evidence"
-
-#' Example of proteinGroups file from MaxQuant for TMT-10plex experiments.
-#'
-#' Example of proteinGroup.txt file from MaxQuant,
-#' which is identified protein group information file.
-#' It is the input for MaxQtoMSstatsTMTFormat function, with evidence.txt
-#' and annotation file.
-#' It includes identified protein groups for 10 proteins
-#' among 15 MS runs with TMT10.
-#' The important variables are as follows:
-#'
-#' \itemize{
-#'   \item id
-#'   \item Protein.IDs
-#'   \item Only.identified.by.site
-#'   \item Potential.contaminant
-#'   \item Reverse
-#' }
-#'
-#' @format A data frame with 1075 rows and 105 variables.
-#' @examples
-#' head(proteinGroups)
-#'
-"proteinGroups"
-
-#' Example of annotation file for evidence, which is the output of MaxQuant.
-#'
-#' Annotation of example data, evidence, in this package.
-#' It should be prepared by users.
-#' The variables are as follows:
+#' Example dataset in MSstatsTMT format.
 #'
-#' \itemize{
-#'   \item Run : MS run ID. It should be the same as Raw.file info
-#'   in raw.mq
-#'   \item Channel : Labeling information (channel.0, ..., channel.9).
-#'   The channel index should be consistent with the channel columns in raw.mq.
-#'   \item Condition : Condition (ex. Healthy, Cancer, Time0)
-#'   \item Mixture : Mixture of samples labeled with different TMT reagents, which can be analyzed in
-#'   a single mass spectrometry experiment. If the channal doesn't have sample, please add `Empty' under Condition.
-#'   \item TechRepMixture : Technical replicate of one mixture. One mixture may have multiple technical replicates.
-#'   For example, if `TechRepMixture' = 1, 2 are the two technical replicates of one mixture, then they should match
-#'   with same `Mixture' value.
-#'   \item Fraction : Fraction ID. One technical replicate of one mixture may be fractionated into multiple fractions to increase the analytical depth.
-#'   Then one technical replicate of one mixture should correspond to multuple fractions.
-#'   For example, if `Fraction' = 1, 2, 3 are three fractions of the first technical replicate of one TMT mixture of biological subjects,
-#'   then they should have same `TechRepMixture'  and `Mixture' value.
-#'   \item BioReplicate : Unique ID for biological subject. If the channal doesn't have sample, please add `Empty' under BioReplicate.
-#' }
-#'
-#' @format A data frame with 150 rows and 7 variables.
-#' @examples
-#' head(annotation.mq)
-#'
-"annotation.mq"
-
-#' Example of output from SpectroMine for TMT-6plex experiments.
-#'
-#' Example of SpectroMine PSM sheet.
-#' It is the output of SpectroMine and the input for SpectroMinetoMSstatsTMTFormat function,
-#' with annotation file.
-#' Annotation file should be made by users.
-#' It includes peak intensities for 10 proteins among 12 MS runs with TMT-6plex.
-#' The important variables are as follows:
-#'
-#' \itemize{
-#'   \item PG.ProteinAccessions
-#'   \item P.MoleculeID
-#'   \item PP.Charge
-#'   \item R.FileName
-#'   \item PG.QValue
-#'   \item PSM.Qvalue
-#'   \item Channels : PSM.TMT6_126..Raw., ..., PSM.TMT6_131..Raw.
-#' }
-#'
-#' @format A data frame with 170 rows and 28 variables.
-#' @examples
-#' head(raw.mine)
-#'
-"raw.mine"
-
-#' Example of annotation file for raw.mine, which is the output of SpectroMine.
-#'
-#' Annotation of example data, raw.mine, in this package.
-#' It should be prepared by users.
-#' The variables are as follows:
-#'
-#' \itemize{
-#'   \item Run : MS run ID. It should be the same as R.FileName info
-#'   in raw.mine
-#'   \item Channel : Labeling information (TMT6_126, ..., TMT6_131).
-#'   The channels should be consistent with the channel columns in raw.mine.
-#'   \item Condition : Condition (ex. Healthy, Cancer, Time0). If the channal doesn't have sample, please add 'Empty' under Condition.
-#'   \item Mixture : Mixture of samples labeled with different TMT reagents, which can be analyzed in
-#'   a single mass spectrometry experiment.
-#'   \item TechRepMixture : Technical replicate of one mixture. One mixture may have multiple technical replicates.
-#'   For example, if 'TechRepMixture' = 1, 2 are the two technical replicates of one mixture, then they should match
-#'   with same 'Mixture' value.
-#'   \item Fraction : Fraction ID. One technical replicate of one mixture may be fractionated into multiple fractions to increase the analytical depth.
-#'   Then one technical replicate of one mixture should correspond to multuple fractions.
-#'   For example, if 'Fraction' = 1, 2, 3 are three fractions of the first technical replicate of one TMT mixture of biological subjects,
-#'   then they should have same 'TechRepMixture'  and 'Mixture' value.
-#'   \item BioReplicate : Unique ID for biological subject. If the channal doesn't have sample, please add 'Empty' under BioReplicate
-#' }
-#'
-#' @format A data frame with 72 rows and 7 variables.
-#' @examples
-#' head(annotation.mine)
-#'
-"annotation.mine"
-
-
-#' Example of MSstatsTMT report from OpenMS for TMT-10plex experiments.
-#'
-#' Example of MSstatsTMT PSM sheet from MaxQuant.
-#' It is the input for OpenMStoMSstatsTMTFormat function.
-#' It includes peak intensities for 10 proteins among 27 MS runs from three TMT10 mixtures.
-#' The important variables are as follows:
-#'
-#' \itemize{
-#'   \item RetentionTime
-#'   \item ProteinName
-#'   \item PeptideSequence
-#'   \item Charge
-#'   \item Channel
-#'   \item Condition
-#'   \item BioReplicate
-#'   \item Run
-#'   \item Mixture
-#'   \item TechRepMixture
-#'   \item Fraction
-#'   \item Intensity
-#'   \item Reference
-#' }
-#'
-#' @format A data frame with 860 rows and 13 variables.
-#' @examples
-#' head(raw.om)
-#'
-"raw.om"
-
-#' Example of output from PDtoMSstatsTMTFormat function
-#'
-#' It is made from \code{\link{raw.pd}} and \code{\link{annotation.pd}},
-#' which is the output of PDtoMSstatsTMTFormat function.
 #' It should include the required columns as below.
 #'
 #' \itemize{
@@ -294,6 +68,7 @@
 #' 
 "quant.pd.msstats"
 
+
 #' Example of output from groupComparisonTMT function
 #'
 #' It is the output of groupComparisonTMT function,

R/utils_docs.R

@@ -0,0 +1,20 @@
+#' A dummy function to store shared documentation items.
+#' 
+#' @import data.table
+#' 
+#' @param use_log_file logical. If TRUE, information about data processing
+#' will be saved to a file.
+#' @param append logical. If TRUE, information about data processing will be added
+#' to an existing log file.
+#' @param verbose logical. If TRUE, information about data processing wil be printed
+#' to the console.
+#' @param log_file_path character. Path to a file to which information about 
+#' data processing will be saved. 
+#' If not provided, such a file will be created automatically.
+#' If `append = TRUE`, has to be a valid path to a file.
+#' 
+#' @return NULL.
+#' @keywords internal
+.documentFunction = function() {
+  NULL
+}

data/datalist

@@ -1,11 +1,3 @@
-annotatio.mine
-annotation.mq
-annotation.pd
-evidence
-proteinGroups
-raw.mine
-raw.pd
-raw.om
-input.pd
-quant.pd.msstats
 test.pairwise
+input.pd
+quant.pd.msstats