diff --git a/.gitignore b/.gitignore index 8f26761..f2ff72c 100644 --- a/.gitignore +++ b/.gitignore @@ -6,3 +6,4 @@ ./*.txt *.Rproj *.DS_Store +*.Rproj diff --git a/DESCRIPTION b/DESCRIPTION index e445e6f..77a0444 100644 --- a/DESCRIPTION +++ b/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 diff --git a/MSstatsTMT.Rproj b/MSstatsTMT.Rproj deleted file mode 100644 index 21a4da0..0000000 --- a/MSstatsTMT.Rproj +++ /dev/null @@ -1,17 +0,0 @@ -Version: 1.0 - -RestoreWorkspace: Default -SaveWorkspace: Default -AlwaysSaveHistory: Default - -EnableCodeIndexing: Yes -UseSpacesForTab: Yes -NumSpacesForTab: 2 -Encoding: UTF-8 - -RnwWeave: Sweave -LaTeX: pdfLaTeX - -BuildType: Package -PackageUseDevtools: Yes -PackageInstallArgs: --no-multiarch --with-keep.source diff --git a/NAMESPACE b/NAMESPACE index 88db581..2f2ebb2 100644 --- a/NAMESPACE +++ b/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) diff --git a/R/converters.R b/R/converters.R index a72d9db..7027329 100644 --- a/R/converters.R +++ b/R/converters.R @@ -1,434 +1,19 @@ -#' A dummy function to store shared documentation items. -#' -#' @import data.table -#' @importFrom MSstatsConvert MSstatsImport MSstatsClean MSstatsPreprocess -#' MSstatsBalancedDesign MSstatsMakeAnnotation MSstatsSaveSessionInfo -#' MSstatsLogsSettings -#' -#' @param fewMeasurements 'remove'(default) will remove the features that have 1 or 2 measurements across runs. -#' @param useUniquePeptide TRUE (default) removes peptides that are assigned for more than one proteins. -#' We assume to use unique peptide for each protein. -#' @param summaryforMultipleRows max(default) or sum - when there are multiple measurements for certain feature and certain run, use highest or sum of multiple intensities. -#' @param removeProtein_with1Feature TRUE will remove the proteins which have only 1 feature, which is the combination of peptide, precursor charge, fragment and charge. FALSE is default. -#' @param removeProtein_with1Peptide TRUE will remove the proteins which have only 1 peptide and charge. FALSE is default. -#' @param removeOxidationMpeptides TRUE will remove the peptides including 'oxidation (M)' in modification. FALSE is default. -#' @param removeMpeptides TRUE will remove the peptides including 'M' sequence. FALSE is default. -#' @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(fewMeasurements, - useUniquePeptide, - summaryforMultipleRows, - removeProtein_with1Feature, - removeProtein_with1Protein, - removeOxidationMpeptides, - removeMpeptides) { - NULL -} - - -#' Generate MSstatsTMT required input format from MaxQuant output -#' -#' @param evidence name of 'evidence.txt' data, which includes feature-level data. -#' @param proteinGroups name of 'proteinGroups.txt' data. -#' @param annotation data frame which contains column Run, Fraction, TechRepMixture, Mixture, Channel, BioReplicate, Condition. Refer to the example 'annotation.mq' for the meaning of each column. -#' @param which.proteinid Use 'Proteins' (default) column for protein name. 'Leading.proteins' or 'Leading.razor.proteins' or 'Gene.names' can be used instead to get the protein ID with single protein. However, those can potentially have the shared peptides. -#' @param rmProt_Only.identified.by.site TRUE will remove proteins with '+' in 'Only.identified.by.site' column from proteinGroups.txt, which was identified only by a modification site. FALSE is the default. -#' @param useUniquePeptide TRUE(default) removes peptides that are assigned for more than one proteins. We assume to use unique peptide for each protein. -#' @param rmPSM_withfewMea_withinRun TRUE (default) will remove the features that have 1 or 2 measurements within each Run. -#' @param rmProtein_with1Feature TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE. -#' @param summaryforMultipleRows sum(default) or max - when there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value. -#' @param ... additional parameters to `data.table::fread`. -#' @inheritParams .documentFunction -#' -#' @return data.frame of class "MSstatsTMT" -#' #' @export -#' -#' @examples -#' head(evidence) -#' head(proteinGroups) -#' head(annotation.mq) -#' input.mq <- MaxQtoMSstatsTMTFormat(evidence, proteinGroups, annotation.mq) -#' head(input.mq) -#' -MaxQtoMSstatsTMTFormat = function( - evidence, proteinGroups, annotation, which.proteinid = 'Proteins', - rmProt_Only.identified.by.site = FALSE, useUniquePeptide = TRUE, - rmPSM_withfewMea_withinRun = TRUE, rmProtein_with1Feature = FALSE, - summaryforMultipleRows = sum, - use_log_file = TRUE, append = FALSE, verbose = TRUE, log_file_path = NULL, - ... -) { - MSstatsConvert::MSstatsLogsSettings(use_log_file, append, verbose, - log_file_path, - base = "MSstatsTMT_converter_log_") - - input = MSstatsConvert::MSstatsImport(list(evidence = evidence, - protein_groups = proteinGroups), - "MSstatsTMT", "MaxQuant", ...) - input = MSstatsConvert::MSstatsClean( - input, - protein_id_col = which.proteinid, - remove_by_site = rmProt_Only.identified.by.site, - channel_columns = "Reporterintensitycorrected") - annotation = MSstatsConvert::MSstatsMakeAnnotation(input, annotation) - - feature_columns = c("PeptideSequence", "PrecursorCharge") - input = MSstatsConvert::MSstatsPreprocess( - input, - annotation, - feature_columns, - remove_shared_peptides = useUniquePeptide, - remove_single_feature_proteins = rmProtein_with1Feature, - feature_cleaning = list(remove_features_with_few_measurements = rmPSM_withfewMea_withinRun, - summarize_multiple_psms = summaryforMultipleRows)) - input = MSstatsConvert::MSstatsBalancedDesign(input, feature_columns, - fix_missing = "zero_to_na") - data.table::setnames(input, "PrecursorCharge", "Charge", skip_absent = TRUE) - - msg_final = paste("** Finished preprocessing. The dataset is ready", - "to be processed by the proteinSummarization function.") - getOption("MSstatsLog")("INFO", msg_final) - getOption("MSstatsMsg")("INFO", msg_final) - getOption("MSstatsLog")("INFO", "\n") - input -} - +#' @importFrom MSstatsConvert MaxQtoMSstatsTMTFormat +MSstatsConvert::MaxQtoMSstatsTMTFormat -#' Generate MSstatsTMT required input format for OpenMS output -#' @param input MSstatsTMT report from OpenMS -#' @param useUniquePeptide TRUE(default) removes peptides that are assigned for more than one proteins. We assume to use unique peptide for each protein. -#' @param rmPSM_withfewMea_withinRun TRUE (default) will remove the features that have 1 or 2 measurements within each Run. -#' @param rmProtein_with1Feature TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE. -#' @param summaryforMultiplePSMs sum(default) or max - when there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value. -#' @param ... additional parameters to `data.table::fread`. -#' @inheritParams .documentFunction -#' -#' @return `data.frame` of class `MSstatsTMT`. -#' #' @export -#' -#' @examples -#' head(raw.om) -#' input.om <- OpenMStoMSstatsTMTFormat(raw.om) -#' head(input.om) -#' -OpenMStoMSstatsTMTFormat = function( - input, useUniquePeptide = TRUE, rmPSM_withfewMea_withinRun = TRUE, - rmProtein_with1Feature = FALSE, summaryforMultiplePSMs = sum, - use_log_file = TRUE, append = FALSE, verbose = TRUE, log_file_path = NULL, ... -) { - MSstatsConvert::MSstatsLogsSettings(use_log_file, append, verbose, - log_file_path, - base = "MSstatsTMT_converter_log_") - - input = MSstatsConvert::MSstatsImport(list(input = input), - "MSstatsTMT", "OpenMS", ...) - input = MSstatsConvert::MSstatsClean(input) - - feature_columns = c("PeptideSequence", "PrecursorCharge") - input = MSstatsConvert::MSstatsPreprocess( - input, - NULL, - feature_columns, - remove_shared_peptides = useUniquePeptide, - remove_single_feature_proteins = rmProtein_with1Feature, - feature_cleaning = list(remove_features_with_few_measurements = rmPSM_withfewMea_withinRun, - summarize_multiple_psms = summaryforMultiplePSMs) - ) - input = MSstatsConvert::MSstatsBalancedDesign(input, feature_columns, - fix_missing = "zero_to_na") - - data.table::setnames(input, "PrecursorCharge", "Charge", skip_absent = TRUE) - - msg_final = paste("** Finished preprocessing. The dataset is ready", - "to be processed by the proteinSummarization function.") - getOption("MSstatsLog")("INFO", msg_final) - getOption("MSstatsMsg")("INFO", msg_final) - getOption("MSstatsLog")("INFO", "\n") - input -} +#' @importFrom MSstatsConvert OpenMStoMSstatsTMTFormat +MSstatsConvert::OpenMStoMSstatsTMTFormat - -#' Convert Proteome Discoverer output to MSstatsTMT format. -#' -#' @param input PD report or a path to it. -#' @param annotation annotation with Run, Fraction, TechRepMixture, Mixture, Channel, -#' BioReplicate, Condition columns or a path to file. Refer to the example 'annotation' for the meaning of each column. -#' @param which.proteinid Use 'Protein.Accessions'(default) column for protein name. 'Master.Protein.Accessions' can be used instead to get the protein name with single protein. -#' @param useNumProteinsColumn logical, TURE(default) remove shared peptides by information of # Proteins column in PSM sheet. -#' @param useUniquePeptide logical, if TRUE (default) removes peptides that are assigned for more than one proteins. We assume to use unique peptide for each protein. -#' @param rmPSM_withfewMea_withinRun TRUE (default) will remove the features that have 1 or 2 measurements within each Run. -#' @param rmProtein_with1Feature TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE. -#' @param summaryforMultipleRows sum (default) or max - when there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value. -#' @param ... additional parameters to `data.table::fread`. -#' @inheritParams .documentFunction -#' -#' @return `data.frame` of class `MSstatsTMT` -#' #' @export -#' -#' @examples -#' head(raw.pd) -#' head(annotation.pd) -#' input.pd <- PDtoMSstatsTMTFormat(raw.pd, annotation.pd) -#' head(input.pd) -#' -PDtoMSstatsTMTFormat <- function( - input, annotation, which.proteinid = 'Protein.Accessions', - useNumProteinsColumn = TRUE, useUniquePeptide = TRUE, - rmPSM_withfewMea_withinRun = TRUE, rmProtein_with1Feature = FALSE, - summaryforMultipleRows = sum, - use_log_file = TRUE, append = FALSE, verbose = TRUE, log_file_path = NULL, ... -) { - MSstatsConvert::MSstatsLogsSettings(use_log_file, append, verbose, - log_file_path, - base = "MSstatsTMT_converter_log_") - - input = MSstatsConvert::MSstatsImport(list(input = input), - "MSstatsTMT", "ProteomeDiscoverer", ...) - input = MSstatsConvert::MSstatsClean( - input, - protein_id_column = which.proteinid, - remove_shared = useNumProteinsColumn, - remove_protein_groups = useNumProteinsColumn) - annotation = MSstatsConvert::MSstatsMakeAnnotation(input, annotation) - - feature_columns = c("PeptideSequence", "PrecursorCharge") - input = MSstatsConvert::MSstatsPreprocess( - input, - annotation, - feature_columns = c("PeptideSequence", "PrecursorCharge"), - remove_shared_peptides = useUniquePeptide, - remove_single_feature_proteins = rmProtein_with1Feature, - feature_cleaning = list(remove_features_with_few_measurements = rmPSM_withfewMea_withinRun, - summarize_multiple_psms = summaryforMultipleRows) - ) - input = MSstatsConvert::MSstatsBalancedDesign(input, feature_columns, - fix_missing = "zero_to_na") - data.table::setnames(input, "PrecursorCharge", "Charge", skip_absent = TRUE) - - msg_final = paste("** Finished preprocessing. The dataset is ready", - "to be processed by the proteinSummarization function.") - getOption("MSstatsLog")("INFO", msg_final) - getOption("MSstatsMsg")("INFO", msg_final) - getOption("MSstatsLog")("INFO", "\n") - input -} - - -#' Import data from SpectroMine -#' -#' @param input data name of SpectroMine PSM output. Read PSM sheet. -#' @param annotation data frame which contains column Run, Fraction, TechRepMixture, Mixture, Channel, BioReplicate, Condition. Refer to the example 'annotation.mine' for the meaning of each column. -#' @param filter_with_Qvalue TRUE(default) will filter out the intensities that have greater than qvalue_cutoff in EG.Qvalue column. Those intensities will be replaced with NA and will be considered as censored missing values for imputation purpose. -#' @param qvalue_cutoff Cutoff for EG.Qvalue. default is 0.01. -#' @param useUniquePeptide TRUE(default) removes peptides that are assigned for more than one proteins. We assume to use unique peptide for each protein. -#' @param rmPSM_withfewMea_withinRun TRUE (default) will remove the features that have 1 or 2 measurements within each Run. -#' @param rmProtein_with1Feature TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE. -#' @param summaryforMultipleRows sum(default) or max - when there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value. -#' @param ... additional parameters to `data.table::fread`. -#' @inheritParams .documentFunction -#' -#' @return `data.frame` of class `MSstatsTMT` -#' -#' @export -#' @examples -#' head(raw.mine) -#' head(annotation.mine) -#' input.mine <- SpectroMinetoMSstatsTMTFormat(raw.mine, annotation.mine) -#' head(input.mine) -#' -SpectroMinetoMSstatsTMTFormat <- function( - input, annotation, filter_with_Qvalue = TRUE, qvalue_cutoff = 0.01, - useUniquePeptide = TRUE, rmPSM_withfewMea_withinRun = TRUE, - rmProtein_with1Feature = FALSE, summaryforMultipleRows = sum, - use_log_file = TRUE, append = FALSE, verbose = TRUE, log_file_path = NULL, ... -) { - MSstatsConvert::MSstatsLogsSettings(use_log_file, append, verbose, - log_file_path, - base = "MSstatsTMT_converter_log_") - - input = MSstatsConvert::MSstatsImport(list(input = input), - "MSstatsTMT", "SpectroMine", ...) - input = MSstatsConvert::MSstatsClean(input) - annotation = MSstatsMakeAnnotation(input, annotation) - - pq_filter = list(score_column = "PGQValue", - score_threshold = 0.01, - direction = "smaller", - behavior = "fill", - handle_na = "keep", - fill_value = NA, - filter = TRUE, - drop_column = TRUE) - - qval_filter = list(score_column = "Qvalue", - score_threshold = qvalue_cutoff, - direction = "smaller", - behavior = "fill", - handle_na = "keep", - fill_value = NA, - filter = filter_with_Qvalue, - drop_column = TRUE) - - feature_columns = c("PeptideSequence", "PrecursorCharge") - input = MSstatsConvert::MSstatsPreprocess( - input, - annotation, - feature_columns, - remove_shared_peptides = useUniquePeptide, - remove_single_feature_proteins = rmProtein_with1Feature, - score_filtering = list(pgq = pq_filter, psm_q = qval_filter), - feature_cleaning = list(remove_features_with_few_measurements = rmPSM_withfewMea_withinRun, - summarize_multiple_psms = summaryforMultipleRows) - ) - input = MSstatsConvert::MSstatsBalancedDesign(input, feature_columns, - fix_missing = "zero_to_na") - data.table::setnames(input, "PrecursorCharge", "Charge", skip_absent = TRUE) - - msg_final = paste("** Finished preprocessing. The dataset is ready", - "to be processed by the proteinSummarization function.") - getOption("MSstatsLog")("INFO", msg_final) - getOption("MSstatsMsg")("INFO", msg_final) - getOption("MSstatsLog")("INFO", "\n") - input -} +#' @importFrom MSstatsConvert PDtoMSstatsTMTFormat +MSstatsConvert::PDtoMSstatsTMTFormat - -#' Convert Philosopher (Fragpipe) output to MSstatsTMT format. -#' -#' @param input data.frame of `msstats.csv` file produced by Philosopher -#' @param annotation annotation with Run, Fraction, TechRepMixture, Mixture, Channel, -#' BioReplicate, Condition columns or a path to file. Refer to the example 'annotation' for the meaning of each column. Channel column should be -#' consistent with the channel columns (Ignore the prefix "Channel ") in msstats.csv file. Run column should be consistent with the Spectrum.File columns in msstats.csv file. -#' @param protein_id_col Use 'Protein'(default) column for protein name. -#' 'Master.Protein.Accessions' can be used instead to get the protein ID with single protein. -#' @param peptide_id_col Use 'Peptide.Sequence'(default) column for peptide sequence. -#' 'Modified.Peptide.Sequence' can be used instead to get the modified peptide sequence. -#' @param Purity_cutoff Cutoff for purity. Default is 0.6 -#' @param PeptideProphet_prob_cutoff Cutoff for the peptide identification probability. Default is 0.7. -#' The probability is confidence score determined by PeptideProphet and higher values indicate greater confidence. -#' @param useUniquePeptide logical, if TRUE (default) removes peptides that are assigned for more than one proteins. -#' We assume to use unique peptide for each protein. -#' @param rmPSM_withfewMea_withinRun TRUE (default) will remove the features that have 1 or 2 measurements within each Run. -#' @param rmPeptide_OxidationM TRUE (default) will remove the peptides including oxidation (M) sequence. -#' @param rmProtein_with1Feature TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE. -#' @param summaryforMultipleRows sum (default) or max - when there are multiple measurements for certain feature in certain run, -#' select the feature with the largest summation or maximal value. -#' @param ... additional parameters to `data.table::fread`. -#' @inheritParams .documentFunction -#' -#' @return `data.frame` of class `MSstatsTMT` -#' -#' @examples -#' input_file_path = system.file("raw_data/Philosopher/msstats.csv", -#' package = "MSstatsTMT") -#' annotation_file_path = system.file("raw_data/Philosopher/MSstatsTMT_annotation.csv", -#' package = "MSstatsTMT") -#' input = data.table::fread(input_file_path) -#' annotation = data.table::fread(annotation_file_path) -#' msstats_format = PhilosophertoMSstatsTMTFormat(input, annotation) -#' head(msstats_format) -#' #' @export -PhilosophertoMSstatsTMTFormat = function( - input, annotation, protein_id_col = "Protein", - peptide_id_col = "Peptide.Sequence", Purity_cutoff = 0.6, - PeptideProphet_prob_cutoff = 0.7, useUniquePeptide = TRUE, - rmPSM_withfewMea_withinRun = TRUE, rmPeptide_OxidationM = TRUE, - rmProtein_with1Feature = FALSE, summaryforMultipleRows = sum, - use_log_file = TRUE, append = FALSE, verbose = TRUE, log_file_path = NULL, ... -) { - MSstatsConvert::MSstatsLogsSettings(use_log_file, append, verbose, - log_file_path, - base = "MSstatsTMT_converter_log_") - checkmate::assertTRUE(!is.null(input)) - - input[["Is.Unique"]] = as.logical(input[["Is.Unique"]]) - mixture_files = list(Mixture1=data.table(input)) - - input = MSstatsConvert::MSstatsImport(c(mixture_files, - list(annotation = annotation)), - type = "MSstatsTMT", - tool = "Philosopher") - channels = unique(annotation[["Channel"]]) - input = MSstatsConvert::MSstatsClean(input, protein_id_col, peptide_id_col, - channels, useUniquePeptide) - annotation = MSstatsMakeAnnotation(input, annotation) - - purity_filter = list(score_column = "Purity", - score_threshold = Purity_cutoff, - direction = "greater", - behavior = "remove", - handle_na = "keep", - fill_value = NULL, - filter = TRUE, - drop_column = FALSE) - probability_filter = list(score_column = "PeptideProphetProbability", - score_threshold = PeptideProphet_prob_cutoff, - direction = "greater", - behavior = "remove", - handle_na = "keep", - fill_value = NULL, - filter = TRUE, - drop_column = FALSE) - oxidation_filter = list(col_name = "PeptideSequence", - pattern = "Oxidation", - filter = rmPeptide_OxidationM, - drop_column = FALSE) - - feature_columns = c("PeptideSequence", "PrecursorCharge") - input = MSstatsPreprocess( - input, - annotation, - feature_columns, - remove_shared_peptides = useUniquePeptide, - remove_single_feature_proteins = rmProtein_with1Feature, - score_filtering = list(pur = purity_filter, prob = probability_filter), - pattern_filtering = list(ox = oxidation_filter), - feature_cleaning = list(remove_features_with_few_measurements = rmPSM_withfewMea_withinRun, - summarize_multiple_psms = summaryforMultipleRows) - ) - input = MSstatsConvert::MSstatsBalancedDesign(input, feature_columns, - fix_missing = "zero_to_na") - data.table::setnames(input, "PrecursorCharge", "Charge", skip_absent = TRUE) - - msg_final = paste("** Finished preprocessing. The dataset is ready", - "to be processed by the proteinSummarization function.") - getOption("MSstatsLog")("INFO", msg_final) - getOption("MSstatsMsg")("INFO", msg_final) - getOption("MSstatsLog")("INFO", "\n") - input -} +#' @importFrom MSstatsConvert SpectroMinetoMSstatsTMTFormat +MSstatsConvert::SpectroMinetoMSstatsTMTFormat - -#' Convert Philosopher parameters to consistent format -#' @inheritParams PhilosophertoMSstatsTMTFormat -#' @keywords internal -.getPhilosopherInput = function(input, path, folder) { - if (!is.null(input)) { - mixture_files = input - } else { - if (folder) { - mixture_files = list.files(path, pattern = "msstats", - full.names = TRUE) - } else { - mixture_files = path - } - } - mixture_files = as.list(mixture_files) - names(mixture_files) = paste0("Mixture", seq_along(mixture_files)) - mixture_files -} +#' @export +#' @importFrom MSstatsConvert PhilosophertoMSstatsTMTFormat +MSstatsConvert::PhilosophertoMSstatsTMTFormat \ No newline at end of file diff --git a/R/utils_MSstatsTMT.R b/R/utils_MSstatsTMT.R index a72e420..4dd2e36 100644 --- a/R/utils_MSstatsTMT.R +++ b/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, diff --git a/R/utils_docs.R b/R/utils_docs.R new file mode 100644 index 0000000..37b81ba --- /dev/null +++ b/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 +} \ No newline at end of file diff --git a/data/annotation.mine.rda b/data/annotation.mine.rda deleted file mode 100644 index e4a9da9..0000000 Binary files a/data/annotation.mine.rda and /dev/null differ diff --git a/data/annotation.mq.rda b/data/annotation.mq.rda deleted file mode 100644 index 28ae629..0000000 Binary files a/data/annotation.mq.rda and /dev/null differ diff --git a/data/annotation.pd.rda b/data/annotation.pd.rda deleted file mode 100644 index 465c80e..0000000 Binary files a/data/annotation.pd.rda and /dev/null differ diff --git a/data/datalist b/data/datalist index b4282c5..7261515 100644 --- a/data/datalist +++ b/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 \ No newline at end of file diff --git a/data/evidence.rda b/data/evidence.rda deleted file mode 100644 index 55ed5cc..0000000 Binary files a/data/evidence.rda and /dev/null differ diff --git a/data/proteinGroups.rda b/data/proteinGroups.rda deleted file mode 100644 index e5afcce..0000000 Binary files a/data/proteinGroups.rda and /dev/null differ diff --git a/data/raw.mine.rda b/data/raw.mine.rda deleted file mode 100644 index 931b9a0..0000000 Binary files a/data/raw.mine.rda and /dev/null differ diff --git a/data/raw.om.rda b/data/raw.om.rda deleted file mode 100644 index 9b5c660..0000000 Binary files a/data/raw.om.rda and /dev/null differ diff --git a/data/raw.pd.rda b/data/raw.pd.rda deleted file mode 100644 index 7249dc2..0000000 Binary files a/data/raw.pd.rda and /dev/null differ diff --git a/inst/raw_data/Philosopher/MSstatsTMT_annotation.csv b/inst/raw_data/Philosopher/MSstatsTMT_annotation.csv deleted file mode 100644 index fc84837..0000000 --- a/inst/raw_data/Philosopher/MSstatsTMT_annotation.csv +++ /dev/null @@ -1,61 +0,0 @@ -Run,Fraction,TechRepMixture,Mixture,Channel,BioReplicate,Condition -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,126,CPT0088900003_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,126,CPT0088900003_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,126,CPT0088900003_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,127N,CPT0079270003_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,127N,CPT0079270003_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,127N,CPT0079270003_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,127C,CPT0088920001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,127C,CPT0088920001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,127C,CPT0088920001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,128N,CPT0079300001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,128N,CPT0079300001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,128N,CPT0079300001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,128C,CPT0088550004_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,128C,CPT0088550004_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,128C,CPT0088550004_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,129N,QC6_QC,QC -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,129N,QC6_QC,QC -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,129N,QC6_QC,QC -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,129C,CPT0014450004_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,129C,CPT0014450004_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,129C,CPT0014450004_T,T -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,130N,CPT0088570001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,130N,CPT0088570001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,130N,CPT0088570001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,130C,CPT0014470001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,130C,CPT0014470001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,130C,CPT0014470001_N,N -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01,1,1,plex16,131N,pool16_NORM,Norm -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f02,2,1,plex16,131N,pool16_NORM,Norm -16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f03,3,1,plex16,131N,pool16_NORM,Norm -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,126,CPT0006730001_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,126,CPT0006730001_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,126,CPT0006730001_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,127N,CPT0069190001_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,127N,CPT0069190001_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,127N,CPT0069190001_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,127C,CPT0092730003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,127C,CPT0092730003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,127C,CPT0092730003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,128N,CPT0092740003_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,128N,CPT0092740003_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,128N,CPT0092740003_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,128C,QC7_QC,QC -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,128C,QC7_QC,QC -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,128C,QC7_QC,QC -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,129N,CPT0006630003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,129N,CPT0006630003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,129N,CPT0006630003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,129C,CPT0025920001_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,129C,CPT0025920001_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,129C,CPT0025920001_N,N -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,130N,CPT0025880003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,130N,CPT0025880003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,130N,CPT0025880003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,130C,CPT0069160003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,130C,CPT0069160003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,130C,CPT0069160003_T,T -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01,1,1,plex17,131N,pool17_NORM,Norm -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f02,2,1,plex17,131N,pool17_NORM,Norm -17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f03,3,1,plex17,131N,pool17_NORM,Norm \ No newline at end of file diff --git a/inst/raw_data/Philosopher/msstats.csv b/inst/raw_data/Philosopher/msstats.csv deleted file mode 100644 index 21795e2..0000000 --- a/inst/raw_data/Philosopher/msstats.csv +++ /dev/null @@ -1,95 +0,0 @@ -"Spectrum.Name","Spectrum.File","Peptide.Sequence","Modified.Peptide.Sequence","Probability","Charge","Protein.Start","Protein.End","Gene","Mapped.Genes","Protein","Protein.ID","Mapped.Proteins","Protein.Description","Is.Unique","Purity","Intensity","Channel.126","Channel.127N","Channel.127C","Channel.128N","Channel.128C","Channel.129N","Channel.129C","Channel.130N","Channel.130C","Channel.131N" -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.04225.04225.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","SSDGGSEEPPDRR","n[230]SSDGGSEEPPDRR",1,3,21,33,"TANC2","","sp|Q9HCD6|TANC2_HUMAN","Q9HCD6","","Protein TANC2",TRUE,0.5,29058558,53473.1016,66971.8594,27558.7285,66180.9219,94775.4531,72129.5234,93412.9375,52533.7422,58089.5234,44198.957 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.05945.05945.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","MDDSDQDSCR","n[230]MDDSDQDSCR",1,2,198,207,"PAX8","","sp|Q06710|PAX8_HUMAN","Q06710","","Paired box protein",TRUE,1,64983984,133589.7656,277471.9688,339930.8125,458741,27250.6348,599682,374046.5,396600.1562,288080.5625,243704.3906 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.07087.07087.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","AEAEAEAGSPRPDPR","n[230]AEAEAEAGSPRPDPR",1,3,4637,4651,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,1,65230552,324756.4688,18408.9414,127025.6328,16732.8223,30560.0566,22088.2109,234934.5938,99157,117041.4609,88308.0156 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.07988.07988.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","QDGDYSPDNSAQPGDR","n[230]QDGDYSPDNSAQPGDR",1,2,309,324,"DHTKD1","","sp|Q96HY7|DHTK1_HUMAN","Q96HY7","","2-oxoadipate dehydrogenase complex component",TRUE,1,134390016,62969.4297,68964.1328,292931.4375,112034.7734,33149.5703,53302.7773,90751.3359,231425.7344,268154.9375,173834.125 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.08116.08116.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","QDGDYSPDNSAQPGDR","n[230]QDGDYSPDNSAQPGDR",1,2,309,324,"DHTKD1","","sp|Q96HY7|DHTK1_HUMAN","Q96HY7","","2-oxoadipate dehydrogenase complex component",TRUE,1,149889712,131517.6562,80017.8438,272977.5938,151596.1875,68935.0391,71528.5312,91335.1562,207628.3906,256628.2969,215388.0781 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.10882.10882.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","EGQGEGETQEAAAATAAAR","n[230]EGQGEGETQEAAAATAAAR",1,3,3681,3699,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,0.67,48511452,194037.7812,24009.9629,82478.3828,57474.3984,71291.9922,63427.7773,164748.5625,116056.3984,84174.4219,71237.1328 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.11114.11114.4","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","QTSDGNWLMVHR","n[230]QTS[316]DGNWLM[147]VHR",0.9993,4,168,179,"CPNE3","","sp|O75131|CPNE3_HUMAN","O75131","","Copine-3",TRUE,0.74,34173808,178713.8594,179251.4688,138970.8125,189085.2188,146196.4531,231841.9062,233118.375,177988.6562,171249.7969,137565.25 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.14116.14116.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","LTMLNTVSK","n[230]LTM[147]LNTVSK",0.9157,3,68,76,"SH3GL1","","sp|Q99961|SH3G1_HUMAN","Q99961","","Endophilin-A2",TRUE,1,98872056,419643.4062,395606.6875,286063.0625,292227.6562,596860.1875,241903.7812,688371.25,352771.9375,357452,347223.0938 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.14145.14145.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","ESTESSNTTIEDEDVK","n[230]ESTESSNTTIEDEDVK",1,3,329,344,"CAMK2D","","sp|Q13557|KCC2D_HUMAN","Q13557","","Calcium/calmodulin-dependent protein kinase type II subunit delta",TRUE,1,289236352,124410.7422,121518.8047,152290.9375,149399.6562,216064.2969,825769.25,196175.1875,199284.9531,209662.1562,141410.4375 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.14393.14393.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","ESTESSNTTIEDEDVK","n[230]ESTESSNTTIEDEDVK",1,3,329,344,"CAMK2D","","sp|Q13557|KCC2D_HUMAN","Q13557","","Calcium/calmodulin-dependent protein kinase type II subunit delta",TRUE,0.76,229207472,70812,71602.7891,86021.3984,87021.6875,104304.7969,389823,98218.8047,111910.8359,112847.5938,82529.75 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.14625.14625.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","YQQETSVSQLPGRPK","n[230]YQQETSVSQLPGRPK",1,3,1564,1578,"TANC2","","sp|Q9HCD6|TANC2_HUMAN","Q9HCD6","","Protein TANC2",TRUE,1,28733976,162676.0156,163120.3125,136647.4844,186262.5781,288684.6562,190590.3125,258702.3438,162000.1719,160732.6875,166368.1094 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.14901.14901.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","GAILTTMLATR","n[230]GAILTTM[147]LATR",0.9999,3,302,312,"CAMK2D","CAMK2A;CAMK2B","sp|Q13557|KCC2D_HUMAN","Q13557","sp|Q13554|KCC2B_HUMAN;sp|Q9UQM7|KCC2A_HUMAN","Calcium/calmodulin-dependent protein kinase type II subunit delta",FALSE,1,40487512,87156.6953,123929.8359,136017.3125,113796.1328,325175.4062,204953.2969,183429.3438,175068,133387.4844,120227.0469 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.15525.15525.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","ALETMNK","n[230]ALETMNK",0.994,2,157,163,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,32466892,208282.125,533066.25,294146.9062,563202.25,460770.9375,823593.25,570828.875,537096.9375,312645.3438,404656.75 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.17357.17357.4","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","KGGDGIKPPPIIGR","n[230]KGGDGIKPPPIIGR",1,4,5,18,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,1,909555584,166787.9062,270603.9062,255155.9844,254222.8438,258203.4531,233064.1406,280672.3125,311485.6875,324233.6875,275042.7188 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.18897.18897.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","SSLYCSDIGK","n[230]SSLYCSDIGK",1,2,379,388,"DHTKD1","","sp|Q96HY7|DHTK1_HUMAN","Q96HY7","","2-oxoadipate dehydrogenase complex component",TRUE,1,322046880,364898.125,424766.8125,1384306,574772.625,287451.5625,273002.1875,449773.7812,788061.625,1179433,859890.6875 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.19684.19684.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","GCGVVEFK","n[230]GCGVVEFK",0.9999,2,142,149,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,0.82,207355840,442496.6562,487739.3125,484301.2188,803611.875,281926.2812,1078799,718019.6875,721879.5,705089.3125,622555.375 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.21444.21444.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","YLEANMTQSALPK","n[230]YLEANM[147]TQSALPK",1,2,282,294,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,1,26254800,116355.8203,137655.3438,139374.0781,126379.3984,133682.4375,153402.6562,155367.5469,164374.6562,175618.3594,148088.8125 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.25901.25901.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","NIGNTFFK","n[230]NIGNTFFK",1,2,228,235,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,1,376800160,2421456.75,1371379.25,3077288.75,1682978.25,3848730.75,4906989,2402642.75,3504737.75,3080020.25,2810615 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.28250.28250.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","LYGPTNFSPIINHVAR","n[230]LYGPTNFSPIINHVAR",1,3,391,406,"CPNE3","","sp|O75131|CPNE3_HUMAN","O75131","","Copine-3",TRUE,0.54,455828640,114046.5234,148080.125,141590.0938,121584.5938,145680.7656,177571.0938,193098.9844,172152.4531,169095.2031,142382.5781 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.28315.28315.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","LYGPTNFSPIINHVAR","n[230]LYGPTNFSPIINHVAR",1,2,391,406,"CPNE3","","sp|O75131|CPNE3_HUMAN","O75131","","Copine-3",TRUE,1,36354812,131424.2031,176060.875,141853.5625,130879.4219,136574.2188,210731.9219,243962.1875,172536.0781,167103.6094,133787.7344 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.28349.28349.6","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","LVGRPPLPVPAVGIGTVHLHQHEDILAK","n[230]LVGRPPLPVPAVGIGTVHLHQHEDILAK",1,6,889,916,"DHTKD1","","sp|Q96HY7|DHTK1_HUMAN","Q96HY7","","2-oxoadipate dehydrogenase complex component",TRUE,1,63040900,100460.5078,99387.3672,214580.3594,101788.9766,58616.668,88769.5547,110691.8438,183040.7344,199704.375,135561.6719 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.28377.28377.5","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","LVGRPPLPVPAVGIGTVHLHQHEDILAK","n[230]LVGRPPLPVPAVGIGTVHLHQHEDILAK",1,5,889,916,"DHTKD1","","sp|Q96HY7|DHTK1_HUMAN","Q96HY7","","2-oxoadipate dehydrogenase complex component",TRUE,0.37,48322436,145621.6562,147147.1875,273589.5625,172246.8281,142203.9688,411355.625,192515.2969,249207.5781,266824.125,210832.5156 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.28533.28533.5","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","LVGRPPLPVPAVGIGTVHLHQHEDILAK","n[230]LVGRPPLPVPAVGIGTVHLHQHEDILAK",1,5,889,916,"DHTKD1","","sp|Q96HY7|DHTK1_HUMAN","Q96HY7","","2-oxoadipate dehydrogenase complex component",TRUE,1,60786052,104359.125,98972.8203,257540.7969,136414.8281,64393.293,178737.9375,120276.2578,212543.3125,225913.1875,168611.0781 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.34349.34349.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","VFISNIPYDMK","n[230]VFISNIPYDMK",1,2,102,112,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,135656624,141339.875,168169.3281,192865.7344,290690.75,68942.9531,515769.2188,470512.0938,255537.8438,240030.5156,203183.7969 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.34351.34351.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","VFISNIPYDMK","n[230]VFISNIPYDMK",1,2,102,112,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,141525264,187644.5781,211548.6406,237330.9844,377179.9375,67541.7344,600410.5625,550691.5,280020.7812,260654.5312,233607.5938 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.34531.34531.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","VFFDVDIGGER","n[230]VFFDVDIGGER",1,2,18,28,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,1,61006892,495034.5312,386296.7188,616756.5625,321886.5312,568345.25,712595.5625,595983.4375,633466.3125,564178.3125,559268.8125 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.34545.34545.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","VFFDVDIGGER","n[230]VFFDVDIGGER",1,2,18,28,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,0.85,133909016,516421.2188,413345.4688,677029.875,362656.0312,699778.0625,853199,621233.75,752521.0625,637508,632195.3125 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.36974.36974.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","NLPFDLTWQK","n[230]NLPFDLTWQK",1,2,529,538,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,95639424,193262.8594,201530.3125,233439.0625,348824.0312,59749.125,570347.375,532727.5,275453.4062,241193,213682.25 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.37048.37048.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","NLPFDLTWQK","n[230]NLPFDLTWQK",1,3,529,538,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,58497004,451318.5938,182573.125,233350.5469,393898.3438,71178.7734,611627.875,505575.3438,250232.9062,258799.3594,424330.2812 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.38089.38089.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",1,3,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,0.46,476562400,252029.7969,364502.8438,335493.5312,326679.8438,345861.8438,298383.1875,345714.875,394625.875,394398.7188,338799.6875 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.38628.38628.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",1,3,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,1,25428448,61291.4375,74236.0938,74793.1719,70132.7344,86858.2422,84709.7734,78207.6562,90386.7812,81704.6797,77328.6953 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.38674.38674.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",1,3,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,0,28157016,58978.7656,93921.3906,81770.9609,72799.4375,100891.75,87043.7891,92984.625,103720.1719,89025.9297,89494.5312 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.39183.39183.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",1,3,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,0.51,11338453,68699.5469,112747.4609,94652.0469,85027.4844,122260.9219,97572.8906,124826.6797,134252.0469,103595.9766,99187.1328 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.39554.39554.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",0.9951,2,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,0.72,88392712,139607.5156,144368.6562,139572.2031,206676.2969,180988.375,195630.7031,206411.4688,190020.9375,158484.1875,153422.9375 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.39907.39907.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","AVPVWDVLASGYVSR","n[230]AVPVWDVLASGYVSR",1,2,2533,2547,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,1,299018944,260604.5312,91985.125,115962.3594,100326.4375,131405.6719,185918.7344,207543.0781,144858.0938,124957.3594,123795.7578 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.39927.39927.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","AVPVWDVLASGYVSR","n[230]AVPVWDVLASGYVSR",1,3,2533,2547,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,0.64,330016224,91648.2734,32969.4844,49777.0156,28548.3887,41787.3242,42108.5586,83213.7188,51249.25,52722.7188,51162.3242 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.40654.40654.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","IGGGIGFGGLEAMNSMGGFGGVGR","n[230]IGGGIGFGGLEAMNSMGGFGGVGR",1,2,377,400,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,11922556,32318.0098,40199.4727,48802.3125,79679.25,19577.9219,135823.5312,139380.5625,63022.6055,60150.9727,52114.4062 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.40656.40656.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","AVPVWDVLASGYVSGAAR","n[230]AVPVWDVLASGYVSGAAR",1,3,4670,4687,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,1,23206878,27124.5215,31872.9922,30046.9648,29435.6699,36784.6758,43625.1875,32007.9844,38299.5664,31733.7734,33042.3867 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.40681.40681.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","AVPVWDVLASGYVSGAAR","n[230]AVPVWDVLASGYVSGAAR",1,3,4670,4687,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,0.5,21937412,25091.125,36462.4062,38040.6289,37406.9805,46805.7891,42903.9414,33362.8633,54484.8008,36414.4258,40665.082 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.40691.40691.2","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","IGGGIGFGGLEAMNSMGGFGGVGR","n[230]IGGGIGFGGLEAMNSMGGFGGVGR",1,2,377,400,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,23614896,19902.084,25722.5449,30856.2891,53319.3359,17193.6094,88146.3125,82855.4922,42723.2109,44937.7969,34712.3594 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.41760.41760.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","IGGGIGFGGLEAMNSMGGFGGVGR","n[230]IGGGIGFGGLEAMNSMGGFGGVGR",1,3,377,400,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,42251600,29582.5547,17857.0117,32220.4473,46160.5039,69615.25,24384.7812,24639.2344,61988.4805,28249.7246,39099.5781 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.41769.41769.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","IGGGIGFGGLEAMNSMGGFGGVGR","n[230]IGGGIGFGGLEAMNSMGGFGGVGR",0.9925,3,377,400,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,54659052,35201.3281,20490.1738,36982.5273,60244.6719,86075.9141,35940.3945,31682.4629,81067.7969,36042.9336,55780.2695 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.42141.42141.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","VTEQLIEAINNGDFEAYTK","n[230]VTEQLIEAINNGDFEAYTK",1,3,353,371,"CAMK2D","","sp|Q13557|KCC2D_HUMAN","Q13557","","Calcium/calmodulin-dependent protein kinase type II subunit delta",TRUE,1,38082916,29490.8418,42304.6992,64342.2188,53508.7109,59340.5703,120144.7266,46964.8555,75260.3672,64764.7734,55852.5195 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.43194.43194.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","VVPVSLSEVYLLQCNMK","n[230]VVPVSLSEVYLLQCNMK",1,3,678,694,"TANC2","","sp|Q9HCD6|TANC2_HUMAN","Q9HCD6","","Protein TANC2",TRUE,0.55,18145966,64383.0625,72356.75,62743.9414,83371.1094,160412.4219,65540.2969,115095.0391,73954.4844,64807.9141,74519.0156 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.43245.43245.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","VVPVSLSEVYLLQCNMK","n[230]VVPVSLSEVYLLQCNMK",1,3,678,694,"TANC2","","sp|Q9HCD6|TANC2_HUMAN","Q9HCD6","","Protein TANC2",TRUE,1,26033156,46445.7109,46907.8828,48813.9492,56522.8516,92719.6953,65682.0469,81809.6328,58241.6367,50470.1406,60289.3867 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.43806.43806.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","MSNWQGAIDSCLEALELDPSNTK","n[230]MSNWQGAIDSCLEALELDPSNTK",1,3,286,308,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,0.69,52481592,148117.8594,92800.6094,221245.25,120612.1875,274593.2812,355536.0938,204307.1875,280591.625,264797.7188,157907.4219 -"16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.43952.43952.3","16CPTAC_CCRCC_W_JHU_20180322_LUMOS_f01.mzML","PTLWALLNSEYVTEEK","n[230]PTLWALLNSEYVTEEK",1,3,2120,2135,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,1,0,79958.6016,78765.4922,58813.5,70517.5703,50280.9492,55388.6875,106719.5078,66978.3203,77686.1406,89003.4688 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.04217.04217.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","MDDSDQDSCR","M[147]DDS[316]DQDSCR",0.9649,2,198,207,"PAX8","","sp|Q06710|PAX8_HUMAN","Q06710","","Paired box protein",TRUE,1,0,39884.5547,24974.3711,10091.1748,45095.1836,65185.8672,11669.0918,46138.5039,12993.4316,7988.5972,28517.9414 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.04442.04442.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","SSDGGSEEPPDRR","n[230]SSDGGSEEPPDRR",1,3,21,33,"TANC2","","sp|Q9HCD6|TANC2_HUMAN","Q9HCD6","","Protein TANC2",TRUE,0.46,29357696,80028.9844,87967.7031,101598.375,100496.8203,161275.25,75225.3281,102696.9766,151036.8125,112668.5312,87605.2266 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.06260.06260.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","MDDSDQDSCR","n[230]MDDSDQDSCR",1,2,198,207,"PAX8","","sp|Q06710|PAX8_HUMAN","Q06710","","Paired box protein",TRUE,1,0,645713.125,424796.3125,158219.7656,768707.3125,1102303.375,143281.8125,740439.8125,208636,127572.9922,468972.4688 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.07347.07347.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","AEAEAEAGSPRPDPR","n[230]AEAEAEAGSPRPDPR",1,3,4637,4651,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,0,16365115,56689.6445,23033.5801,53335.7188,58941.5312,33175.4492,161275.4531,35977.3672,39647.7148,16958.6289,59307.1016 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.08148.08148.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","QDGDYSPDNSAQPGDR","n[230]QDGDYSPDNSAQPGDR",1,2,309,324,"DHTKD1","","sp|Q96HY7|DHTK1_HUMAN","Q96HY7","","2-oxoadipate dehydrogenase complex component",TRUE,0,607792704,311020.75,83619.4922,15097.6104,244208.8125,32794.9023,23036.8516,147349.2031,34465.832,34978.2461,103739.0312 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.08283.08283.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","QDGDYSPDNSAQPGDR","n[230]QDGDYSPDNSAQPGDR",1,3,309,324,"DHTKD1","","sp|Q96HY7|DHTK1_HUMAN","Q96HY7","","2-oxoadipate dehydrogenase complex component",TRUE,1,44890952,73168.4844,48403.0742,44231.7891,74292.75,92910.3984,37685.4336,54651.9258,40100.1172,31234.9414,47870.6953 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.08693.08693.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","QAIVNASR","n[230]QAIVNASR",0.9765,2,439,446,"CPNE3","","sp|O75131|CPNE3_HUMAN","O75131","","Copine-3",TRUE,1,38503400,264351.5312,73569.4766,104912.6797,925377.4375,926166.5625,115570.0391,255436.5469,359862.0625,118511.7656,222946.0781 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.11554.11554.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","EGQGEGETQEAAAATAAAR","n[230]EGQGEGETQEAAAATAAAR",1,2,3681,3699,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,1,78320048,286248.1875,5069.1895,148892.875,174360.5625,23365.2344,1148353,0,90918.5547,11632.6582,230870.7344 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.14929.14929.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","ESTESSNTTIEDEDVK","n[230]ESTESSNTTIEDEDVK",1,2,329,344,"CAMK2D","","sp|Q13557|KCC2D_HUMAN","Q13557","","Calcium/calmodulin-dependent protein kinase type II subunit delta",TRUE,0.53,323311072,170361.1406,110277.1016,138648.9688,223351.3125,956790.5625,148163.6094,261563.7812,157353.5938,63688.7539,157772.6719 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.14932.14932.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","ESTESSNTTIEDEDVK","n[230]ESTESSNTTIEDEDVK",1,2,329,344,"CAMK2D","","sp|Q13557|KCC2D_HUMAN","Q13557","","Calcium/calmodulin-dependent protein kinase type II subunit delta",TRUE,0.84,367648320,294106.0938,197443.0938,211006.4219,347610.2188,1605381.625,210632.7656,287321.125,235184.5312,65819.9688,214612.3438 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.14999.14999.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","LTMLNTVSK","n[230]LTM[147]LNTVSK",0.9685,3,68,76,"SH3GL1","","sp|Q99961|SH3G1_HUMAN","Q99961","","Endophilin-A2",TRUE,1,102373936,251949.125,222550.4375,368102.75,308361.75,211980.5,354011.0312,235623,314508.6562,529611.75,287265.7812 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.15353.15353.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","YQQETSVSQLPGRPK","n[230]YQQETSVSQLPGRPK",1,3,1564,1578,"TANC2","","sp|Q9HCD6|TANC2_HUMAN","Q9HCD6","","Protein TANC2",TRUE,0.51,34279500,170198.5781,181599.8125,231989.8438,181305.1562,202064.2188,182056.5,217149.4531,250748.7031,417306.125,197622.9688 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.15360.15360.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","QETVDCLKK","n[230]QETVDCLKK",0.9997,3,285,293,"CAMK2D","CAMK2A","sp|Q13557|KCC2D_HUMAN","Q13557","sp|Q9UQM7|KCC2A_HUMAN","Calcium/calmodulin-dependent protein kinase type II subunit delta",FALSE,1,28139004,582990.0625,460514.4062,417378.2188,784666.8125,2302350,582810.6875,761050.875,905113.0625,408943.625,720424.8125 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.15775.15775.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","GAILTTMLATR","n[230]GAILTTM[147]LATR",0.9993,3,302,312,"CAMK2D","CAMK2A;CAMK2B","sp|Q13557|KCC2D_HUMAN","Q13557","sp|Q13554|KCC2B_HUMAN;sp|Q9UQM7|KCC2A_HUMAN","Calcium/calmodulin-dependent protein kinase type II subunit delta",FALSE,1,41957356,233198.9375,647530.5,291124.5938,207511.2656,183859.0625,236534.7031,259046.6719,266516,505518.5,317696.9375 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.18335.18335.4","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","KGGDGIKPPPIIGR","n[230]KGGDGIKPPPIIGR",1,4,5,18,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,0.53,852943488,626924.1875,493673.1875,549643.9375,669143.25,557778.375,600955.625,620787.0625,692777.875,751812.25,614106.75 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.19909.19909.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","SSLYCSDIGK","n[230]SSLYCSDIGK",1,2,379,388,"DHTKD1","","sp|Q96HY7|DHTK1_HUMAN","Q96HY7","","2-oxoadipate dehydrogenase complex component",TRUE,0.78,574903552,1490700.375,777483.9375,274506.375,1270474.25,195244.4375,193378.8281,707655.9375,217172.8438,576605.5,493141.75 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.20818.20818.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","GCGVVEFK","n[230]GCGVVEFK",0.9993,2,142,149,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,84356144,655077.0625,691005.75,413556.125,820350.0625,1725507.25,477492.875,711612.375,480527,527165.3125,627089.5625 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.21141.21141.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","EVTLGQVAK","n[230]EVTLGQVAK",1,2,858,866,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,1,134854928,563873,634774.4375,276654.25,426296.1875,295429.5,1566543.25,598150.625,584907,2069509.125,634058.0625 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.22375.22375.4","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","TDAFSQHHLEPLECPFER","n[230]TDAFS[316]QHHLEPLECPFER",1,4,225,242,"PAX8","","sp|Q06710|PAX8_HUMAN","Q06710","","Paired box protein",TRUE,0.7,58449232,458507.2188,513900.5625,226675.6719,617443.75,602702.8125,242153.3906,593551.625,234262.2812,333595.3438,393703.7188 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.22693.22693.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","YLEANMTQSALPK","n[230]YLEANM[147]TQSALPK",1,2,282,294,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,0,57207080,230010.5625,171998.4219,289487.75,284056.0625,279422.75,324813.2812,215798.75,300698.5625,268676.5,265244.1562 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.23568.23568.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","GFIMAEVMK","n[230]GFIMAEVM[147]K",0.9998,3,341,349,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,0.53,192811952,381783.25,320458.0312,293958.4062,455412.3125,314296.4062,320917,354925.3125,412719.375,285399.3438,322876.8125 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.27297.27297.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","NIGNTFFK","n[230]NIGNTFFK",0.9999,2,228,235,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,1,308300352,1407065.5,1176072.875,1140584.875,2051653.875,2011354,953537.5625,1140141.125,1015642.375,1213439.75,1162606.25 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.27978.27978.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","MSIYQAMWK","n[230]MSIYQAM[147]WK",0.9987,2,2243,2251,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,1,49858092,195778.5156,156972.75,150975.2031,144945.9688,202314.625,569375.5,210106.9844,200318.7031,620879.625,221239.9688 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.30118.30118.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","LYGPTNFSPIINHVAR","n[230]LYGPTNFSPIINHVAR",1,3,391,406,"CPNE3","","sp|O75131|CPNE3_HUMAN","O75131","","Copine-3",TRUE,1,818442432,444449.6562,333486.5312,336277.8125,474924.5312,583425.25,455661.5,461092.3438,509625.7188,212036.7344,393608.9062 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.33926.33926.4","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","DETSGLHLLPLPESAPALPTEEQVQR","n[230]DETS[316]GLHLLPLPESAPALPTEEQVQR",1,4,1105,1130,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,1,27931840,93912.0859,73017.7969,105501.5078,81444.6328,106202.4375,136859.3594,101720.3828,85035.3359,173821.5,95881.3125 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.36993.36993.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","VFISNIPYDMK","n[230]VFISNIPYDMK",1,2,102,112,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,0,213793568,274607.6562,287806.4375,142782.8906,336661.3125,613073.3125,221936.8125,309082.8125,214189.9688,216644.1094,213545.7344 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.37251.37251.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","VFFDVDIGGER","n[230]VFFDVDIGGER",1,2,18,28,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,1,135256704,423658.875,368475,375158.625,595656.125,504886.0625,410409.9062,421033.1562,481889.0938,458576.1562,390816.9375 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.37258.37258.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","VFFDVDIGGER","n[230]VFFDVDIGGER",1,2,18,28,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,0.7,119022536,247996.5781,198754.5781,182371.2031,342746.625,242807.2969,201411.5938,242962.125,177235.2969,172215.6094,215763.6875 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.37385.37385.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","VFFDVDIGGER","n[230]VFFDVDIGGER",1,2,18,28,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,0.83,34606448,269148.1875,264996.5625,207258.7031,387409.9062,385264.2812,278787.25,352958.0938,326427.5625,245497.6875,322449 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.39432.39432.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","NLPFDLTWQK","n[230]NLPFDLTWQK",1,2,529,538,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,219495120,905735.75,884228.8125,541994.5,1104416.625,2232653.5,769780.6875,1162127.625,560233.5,656731.5625,747008.125 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.40586.40586.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",1,2,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,1,577487424,455174.9375,374895.125,369373.9062,532853.6875,377832.5,417925.25,447886.0938,569163.5,365027.2188,428961.0625 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.41044.41044.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",1,2,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,0,32589512,131456.6406,115541.7266,104787.4688,158574.4375,145473.2344,120317.9141,119284.8203,155569.7656,108984.6016,135410.625 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.41389.41389.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",1,2,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,1,23473386,146337.2031,112537.0469,121689.4531,165904.375,150646.5938,158694.375,136980.1562,189462.1875,136669.3281,147227.0938 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.41415.41415.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",1,2,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,1,28783936,143430.1406,115676.2188,113914.6953,163258.2344,145756.3906,129612.1094,129360,157746.9688,128474.9922,135603.2188 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.41964.41964.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","NYIVEDGDIIFFK","n[230]NYIVEDGDIIFFK",1,2,374,386,"OLA1","","sp|Q9NTK5|OLA1_HUMAN","Q9NTK5","","Obg-like ATPase 1",TRUE,0,11347740,106565.4531,107700.4766,107787.6406,118916.9922,107449.9062,101757.6875,105692.7812,122248.8281,179382.0938,105824.6094 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.42210.42210.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","TIELSDDDFLGECECTLGQIVSSK","n[230]TIELS[316]DDDFLGECECTLGQIVSSK",1,3,86,109,"CPNE3","","sp|O75131|CPNE3_HUMAN","O75131","","Copine-3",TRUE,0.58,0,48777.8867,42912.3398,37636.5039,54476.2656,75080.4141,27422.7656,56114.1719,65788.3359,29758.7129,48177.3555 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.42698.42698.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","AVPVWDVLASGYVSR","n[230]AVPVWDVLASGYVSR",1,2,2533,2547,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,0.83,174371808,322448.8438,146438.1406,225681.625,305485.7812,213480.8438,980352.3125,224591.4375,249991.2344,548354.9375,340692.2188 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.43223.43223.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","TIELSDDDFLGECECTLGQIVSSK","n[230]TIELSDDDFLGECECTLGQIVS[316]SK",1,3,86,109,"CPNE3","","sp|O75131|CPNE3_HUMAN","O75131","","Copine-3",TRUE,0,0,47441.75,42593.125,34984.9922,51164.2109,71581.8828,27126.6055,49920.3672,61010.0586,26807.5566,50033.0078 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.43482.43482.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","SDPLCVLFLNTSGQQWYEVER","n[230]SDPLCVLFLNTS[316]GQQWYEVER",1,3,27,47,"CPNE3","","sp|O75131|CPNE3_HUMAN","O75131","","Copine-3",TRUE,0.84,18769052,176958.6719,137091.8594,106044.6016,222733.8281,251033.0938,72343.1094,174954.9219,169680.6719,74412.8047,128556.2578 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.43554.43554.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","IGGGIGFGGLEAMNSMGGFGGVGR","n[230]IGGGIGFGGLEAMNSMGGFGGVGR",1,3,377,400,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,43202416,41619.168,49190.7617,37504.8555,44412.4688,65305.5781,47820.7305,54133.8164,37978.6992,84100.1094,48975.4883 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.43562.43562.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","IGGGIGFGGLEAMNSMGGFGGVGR","n[230]IGGGIGFGGLEAMNSMGGFGGVGR",1,2,377,400,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,1,40426140,87986.5312,117469.6172,53320.3477,111176.1875,246044.4219,67546.0859,131629.4844,70657.6875,77868.3594,86337.0859 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.43605.43605.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","IGGGIGFGGLEAMNSMGGFGGVGR","n[230]IGGGIGFGGLEAMNSMGGFGGVGR",1,3,377,400,"MYEF2","","sp|Q9P2K5|MYEF2_HUMAN","Q9P2K5","","Myelin expression factor 2",TRUE,0,0,31483.1602,46732.5,34811.7773,31429.8223,38235.8359,41466.0352,37983.0781,32965.4727,50718.332,32575.7988 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.43698.43698.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","AVPVWDVLASGYVSGAAR","n[230]AVPVWDVLASGYVSGAAR",1,3,4670,4687,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,0,24352304,18913.9551,18430.5742,23662.7012,23380.3691,31197.4531,22906.9043,25586.7188,22859.916,24170.2852,23688.5195 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.43711.43711.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","AVPVWDVLASGYVSGAAR","n[230]AVPVWDVLASGYVSGAAR",1,3,4670,4687,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,0,0,20426,20898.4668,18721.1504,22153.2617,30320.668,20762.3145,22914.25,20001.4941,25546.123,20352.9941 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.43717.43717.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","AVPVWDVLASGYVSGAAR","n[230]AVPVWDVLASGYVSGAAR",1,3,4670,4687,"EPPK1","","sp|P58107|EPIPL_HUMAN","P58107","","Epiplakin",TRUE,1,30402308,17394.6738,16882.2852,18113.1719,20978.8965,32042.8125,20866.4355,26597.0215,21222.6465,24294.4336,15848.207 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.43912.43912.3","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","MSNWQGAIDSCLEALELDPSNTK","M[147]S[316]NWQGAIDSCLEALELDPSNTK",1,3,286,308,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,1,27560010,122582.1953,82481.7656,79387.1484,133003.0625,178821.0625,89622.9766,136408.0781,120745.6406,73213.2656,114462.5547 -"17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.46161.46161.2","17CPTAC_CCRCC_W_JHU_20180517_LUMOS_f01.mzML","MSNWQGAIDSCLEALELDPSNTK","n[230]MSNWQGAIDSCLEALELDPSNTK",1,2,286,308,"PPID","","sp|Q08752|PPID_HUMAN","Q08752","","Peptidyl-prolyl cis-trans isomerase D",TRUE,0,0,24850.3398,22807.7891,14892.9639,26095.6797,36738.7422,12269.0049,26776.502,20596.3926,14881.5625,19730.4785 diff --git a/man/MaxQtoMSstatsTMTFormat.Rd b/man/MaxQtoMSstatsTMTFormat.Rd deleted file mode 100644 index 9deb38d..0000000 --- a/man/MaxQtoMSstatsTMTFormat.Rd +++ /dev/null @@ -1,72 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/converters.R -\name{MaxQtoMSstatsTMTFormat} -\alias{MaxQtoMSstatsTMTFormat} -\title{Generate MSstatsTMT required input format from MaxQuant output} -\usage{ -MaxQtoMSstatsTMTFormat( - evidence, - proteinGroups, - annotation, - which.proteinid = "Proteins", - rmProt_Only.identified.by.site = FALSE, - useUniquePeptide = TRUE, - rmPSM_withfewMea_withinRun = TRUE, - rmProtein_with1Feature = FALSE, - summaryforMultipleRows = sum, - use_log_file = TRUE, - append = FALSE, - verbose = TRUE, - log_file_path = NULL, - ... -) -} -\arguments{ -\item{evidence}{name of 'evidence.txt' data, which includes feature-level data.} - -\item{proteinGroups}{name of 'proteinGroups.txt' data.} - -\item{annotation}{data frame which contains column Run, Fraction, TechRepMixture, Mixture, Channel, BioReplicate, Condition. Refer to the example 'annotation.mq' for the meaning of each column.} - -\item{which.proteinid}{Use 'Proteins' (default) column for protein name. 'Leading.proteins' or 'Leading.razor.proteins' or 'Gene.names' can be used instead to get the protein ID with single protein. However, those can potentially have the shared peptides.} - -\item{rmProt_Only.identified.by.site}{TRUE will remove proteins with '+' in 'Only.identified.by.site' column from proteinGroups.txt, which was identified only by a modification site. FALSE is the default.} - -\item{useUniquePeptide}{TRUE(default) removes peptides that are assigned for more than one proteins. We assume to use unique peptide for each protein.} - -\item{rmPSM_withfewMea_withinRun}{TRUE (default) will remove the features that have 1 or 2 measurements within each Run.} - -\item{rmProtein_with1Feature}{TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE.} - -\item{summaryforMultipleRows}{sum(default) or max - when there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value.} - -\item{use_log_file}{logical. If TRUE, information about data processing -will be saved to a file.} - -\item{append}{logical. If TRUE, information about data processing will be added -to an existing log file.} - -\item{verbose}{logical. If TRUE, information about data processing wil be printed -to the console.} - -\item{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.} - -\item{...}{additional parameters to `data.table::fread`.} -} -\value{ -data.frame of class "MSstatsTMT" -} -\description{ -Generate MSstatsTMT required input format from MaxQuant output -} -\examples{ -head(evidence) -head(proteinGroups) -head(annotation.mq) -input.mq <- MaxQtoMSstatsTMTFormat(evidence, proteinGroups, annotation.mq) -head(input.mq) - -} diff --git a/man/OpenMStoMSstatsTMTFormat.Rd b/man/OpenMStoMSstatsTMTFormat.Rd deleted file mode 100644 index 59d66a2..0000000 --- a/man/OpenMStoMSstatsTMTFormat.Rd +++ /dev/null @@ -1,58 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/converters.R -\name{OpenMStoMSstatsTMTFormat} -\alias{OpenMStoMSstatsTMTFormat} -\title{Generate MSstatsTMT required input format for OpenMS output} -\usage{ -OpenMStoMSstatsTMTFormat( - input, - useUniquePeptide = TRUE, - rmPSM_withfewMea_withinRun = TRUE, - rmProtein_with1Feature = FALSE, - summaryforMultiplePSMs = sum, - use_log_file = TRUE, - append = FALSE, - verbose = TRUE, - log_file_path = NULL, - ... -) -} -\arguments{ -\item{input}{MSstatsTMT report from OpenMS} - -\item{useUniquePeptide}{TRUE(default) removes peptides that are assigned for more than one proteins. We assume to use unique peptide for each protein.} - -\item{rmPSM_withfewMea_withinRun}{TRUE (default) will remove the features that have 1 or 2 measurements within each Run.} - -\item{rmProtein_with1Feature}{TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE.} - -\item{summaryforMultiplePSMs}{sum(default) or max - when there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value.} - -\item{use_log_file}{logical. If TRUE, information about data processing -will be saved to a file.} - -\item{append}{logical. If TRUE, information about data processing will be added -to an existing log file.} - -\item{verbose}{logical. If TRUE, information about data processing wil be printed -to the console.} - -\item{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.} - -\item{...}{additional parameters to `data.table::fread`.} -} -\value{ -`data.frame` of class `MSstatsTMT`. -} -\description{ -Generate MSstatsTMT required input format for OpenMS output -} -\examples{ -head(raw.om) -input.om <- OpenMStoMSstatsTMTFormat(raw.om) -head(input.om) - -} diff --git a/man/PDtoMSstatsTMTFormat.Rd b/man/PDtoMSstatsTMTFormat.Rd deleted file mode 100644 index 37abd75..0000000 --- a/man/PDtoMSstatsTMTFormat.Rd +++ /dev/null @@ -1,69 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/converters.R -\name{PDtoMSstatsTMTFormat} -\alias{PDtoMSstatsTMTFormat} -\title{Convert Proteome Discoverer output to MSstatsTMT format.} -\usage{ -PDtoMSstatsTMTFormat( - input, - annotation, - which.proteinid = "Protein.Accessions", - useNumProteinsColumn = TRUE, - useUniquePeptide = TRUE, - rmPSM_withfewMea_withinRun = TRUE, - rmProtein_with1Feature = FALSE, - summaryforMultipleRows = sum, - use_log_file = TRUE, - append = FALSE, - verbose = TRUE, - log_file_path = NULL, - ... -) -} -\arguments{ -\item{input}{PD report or a path to it.} - -\item{annotation}{annotation with Run, Fraction, TechRepMixture, Mixture, Channel, -BioReplicate, Condition columns or a path to file. Refer to the example 'annotation' for the meaning of each column.} - -\item{which.proteinid}{Use 'Protein.Accessions'(default) column for protein name. 'Master.Protein.Accessions' can be used instead to get the protein name with single protein.} - -\item{useNumProteinsColumn}{logical, TURE(default) remove shared peptides by information of # Proteins column in PSM sheet.} - -\item{useUniquePeptide}{logical, if TRUE (default) removes peptides that are assigned for more than one proteins. We assume to use unique peptide for each protein.} - -\item{rmPSM_withfewMea_withinRun}{TRUE (default) will remove the features that have 1 or 2 measurements within each Run.} - -\item{rmProtein_with1Feature}{TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE.} - -\item{summaryforMultipleRows}{sum (default) or max - when there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value.} - -\item{use_log_file}{logical. If TRUE, information about data processing -will be saved to a file.} - -\item{append}{logical. If TRUE, information about data processing will be added -to an existing log file.} - -\item{verbose}{logical. If TRUE, information about data processing wil be printed -to the console.} - -\item{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.} - -\item{...}{additional parameters to `data.table::fread`.} -} -\value{ -`data.frame` of class `MSstatsTMT` -} -\description{ -Convert Proteome Discoverer output to MSstatsTMT format. -} -\examples{ -head(raw.pd) -head(annotation.pd) -input.pd <- PDtoMSstatsTMTFormat(raw.pd, annotation.pd) -head(input.pd) - -} diff --git a/man/PhilosophertoMSstatsTMTFormat.Rd b/man/PhilosophertoMSstatsTMTFormat.Rd deleted file mode 100644 index dfa8d15..0000000 --- a/man/PhilosophertoMSstatsTMTFormat.Rd +++ /dev/null @@ -1,88 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/converters.R -\name{PhilosophertoMSstatsTMTFormat} -\alias{PhilosophertoMSstatsTMTFormat} -\title{Convert Philosopher (Fragpipe) output to MSstatsTMT format.} -\usage{ -PhilosophertoMSstatsTMTFormat( - input, - annotation, - protein_id_col = "Protein", - peptide_id_col = "Peptide.Sequence", - Purity_cutoff = 0.6, - PeptideProphet_prob_cutoff = 0.7, - useUniquePeptide = TRUE, - rmPSM_withfewMea_withinRun = TRUE, - rmPeptide_OxidationM = TRUE, - rmProtein_with1Feature = FALSE, - summaryforMultipleRows = sum, - use_log_file = TRUE, - append = FALSE, - verbose = TRUE, - log_file_path = NULL, - ... -) -} -\arguments{ -\item{input}{data.frame of `msstats.csv` file produced by Philosopher} - -\item{annotation}{annotation with Run, Fraction, TechRepMixture, Mixture, Channel, -BioReplicate, Condition columns or a path to file. Refer to the example 'annotation' for the meaning of each column. Channel column should be -consistent with the channel columns (Ignore the prefix "Channel ") in msstats.csv file. Run column should be consistent with the Spectrum.File columns in msstats.csv file.} - -\item{protein_id_col}{Use 'Protein'(default) column for protein name. -'Master.Protein.Accessions' can be used instead to get the protein ID with single protein.} - -\item{peptide_id_col}{Use 'Peptide.Sequence'(default) column for peptide sequence. -'Modified.Peptide.Sequence' can be used instead to get the modified peptide sequence.} - -\item{Purity_cutoff}{Cutoff for purity. Default is 0.6} - -\item{PeptideProphet_prob_cutoff}{Cutoff for the peptide identification probability. Default is 0.7. -The probability is confidence score determined by PeptideProphet and higher values indicate greater confidence.} - -\item{useUniquePeptide}{logical, if TRUE (default) removes peptides that are assigned for more than one proteins. -We assume to use unique peptide for each protein.} - -\item{rmPSM_withfewMea_withinRun}{TRUE (default) will remove the features that have 1 or 2 measurements within each Run.} - -\item{rmPeptide_OxidationM}{TRUE (default) will remove the peptides including oxidation (M) sequence.} - -\item{rmProtein_with1Feature}{TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE.} - -\item{summaryforMultipleRows}{sum (default) or max - when there are multiple measurements for certain feature in certain run, -select the feature with the largest summation or maximal value.} - -\item{use_log_file}{logical. If TRUE, information about data processing -will be saved to a file.} - -\item{append}{logical. If TRUE, information about data processing will be added -to an existing log file.} - -\item{verbose}{logical. If TRUE, information about data processing wil be printed -to the console.} - -\item{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.} - -\item{...}{additional parameters to `data.table::fread`.} -} -\value{ -`data.frame` of class `MSstatsTMT` -} -\description{ -Convert Philosopher (Fragpipe) output to MSstatsTMT format. -} -\examples{ -input_file_path = system.file("raw_data/Philosopher/msstats.csv", - package = "MSstatsTMT") -annotation_file_path = system.file("raw_data/Philosopher/MSstatsTMT_annotation.csv", - package = "MSstatsTMT") -input = data.table::fread(input_file_path) -annotation = data.table::fread(annotation_file_path) -msstats_format = PhilosophertoMSstatsTMTFormat(input, annotation) -head(msstats_format) - -} diff --git a/man/SpectroMinetoMSstatsTMTFormat.Rd b/man/SpectroMinetoMSstatsTMTFormat.Rd deleted file mode 100644 index 9013fe7..0000000 --- a/man/SpectroMinetoMSstatsTMTFormat.Rd +++ /dev/null @@ -1,68 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/converters.R -\name{SpectroMinetoMSstatsTMTFormat} -\alias{SpectroMinetoMSstatsTMTFormat} -\title{Import data from SpectroMine} -\usage{ -SpectroMinetoMSstatsTMTFormat( - input, - annotation, - filter_with_Qvalue = TRUE, - qvalue_cutoff = 0.01, - useUniquePeptide = TRUE, - rmPSM_withfewMea_withinRun = TRUE, - rmProtein_with1Feature = FALSE, - summaryforMultipleRows = sum, - use_log_file = TRUE, - append = FALSE, - verbose = TRUE, - log_file_path = NULL, - ... -) -} -\arguments{ -\item{input}{data name of SpectroMine PSM output. Read PSM sheet.} - -\item{annotation}{data frame which contains column Run, Fraction, TechRepMixture, Mixture, Channel, BioReplicate, Condition. Refer to the example 'annotation.mine' for the meaning of each column.} - -\item{filter_with_Qvalue}{TRUE(default) will filter out the intensities that have greater than qvalue_cutoff in EG.Qvalue column. Those intensities will be replaced with NA and will be considered as censored missing values for imputation purpose.} - -\item{qvalue_cutoff}{Cutoff for EG.Qvalue. default is 0.01.} - -\item{useUniquePeptide}{TRUE(default) removes peptides that are assigned for more than one proteins. We assume to use unique peptide for each protein.} - -\item{rmPSM_withfewMea_withinRun}{TRUE (default) will remove the features that have 1 or 2 measurements within each Run.} - -\item{rmProtein_with1Feature}{TRUE will remove the proteins which have only 1 peptide and charge. Defaut is FALSE.} - -\item{summaryforMultipleRows}{sum(default) or max - when there are multiple measurements for certain feature in certain run, select the feature with the largest summation or maximal value.} - -\item{use_log_file}{logical. If TRUE, information about data processing -will be saved to a file.} - -\item{append}{logical. If TRUE, information about data processing will be added -to an existing log file.} - -\item{verbose}{logical. If TRUE, information about data processing wil be printed -to the console.} - -\item{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.} - -\item{...}{additional parameters to `data.table::fread`.} -} -\value{ -`data.frame` of class `MSstatsTMT` -} -\description{ -Import data from SpectroMine -} -\examples{ -head(raw.mine) -head(annotation.mine) -input.mine <- SpectroMinetoMSstatsTMTFormat(raw.mine, annotation.mine) -head(input.mine) - -} diff --git a/man/annotation.mine.Rd b/man/annotation.mine.Rd deleted file mode 100644 index 6ab4f30..0000000 --- a/man/annotation.mine.Rd +++ /dev/null @@ -1,41 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/utils_MSstatsTMT.R -\docType{data} -\name{annotation.mine} -\alias{annotation.mine} -\title{Example of annotation file for raw.mine, which is the output of SpectroMine.} -\format{ -A data frame with 72 rows and 7 variables. -} -\usage{ -annotation.mine -} -\description{ -Annotation of example data, raw.mine, in this package. -It should be prepared by users. -The variables are as follows: -} -\details{ -\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 -} -} -\examples{ -head(annotation.mine) - -} -\keyword{datasets} diff --git a/man/annotation.mq.Rd b/man/annotation.mq.Rd deleted file mode 100644 index 82d2e70..0000000 --- a/man/annotation.mq.Rd +++ /dev/null @@ -1,41 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/utils_MSstatsTMT.R -\docType{data} -\name{annotation.mq} -\alias{annotation.mq} -\title{Example of annotation file for evidence, which is the output of MaxQuant.} -\format{ -A data frame with 150 rows and 7 variables. -} -\usage{ -annotation.mq -} -\description{ -Annotation of example data, evidence, in this package. -It should be prepared by users. -The variables are as follows: -} -\details{ -\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. -} -} -\examples{ -head(annotation.mq) - -} -\keyword{datasets} diff --git a/man/annotation.pd.Rd b/man/annotation.pd.Rd deleted file mode 100644 index d5c91a1..0000000 --- a/man/annotation.pd.Rd +++ /dev/null @@ -1,42 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/utils_MSstatsTMT.R -\docType{data} -\name{annotation.pd} -\alias{annotation.pd} -\title{Example of annotation file for raw.pd, -which is the PSM output of Proteome Discoverer} -\format{ -A data frame with 150 rows and 7 variables. -} -\usage{ -annotation.pd -} -\description{ -Annotation of example data, raw.pd, in this package. -It should be prepared by users. -The variables are as follows: -} -\details{ -\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. -} -} -\examples{ -head(annotation.pd) - -} -\keyword{datasets} diff --git a/man/dot-documentFunction.Rd b/man/dot-documentFunction.Rd index 8d0f54b..b1df687 100644 --- a/man/dot-documentFunction.Rd +++ b/man/dot-documentFunction.Rd @@ -1,35 +1,12 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/converters.R +% Please edit documentation in R/utils_docs.R \name{.documentFunction} \alias{.documentFunction} \title{A dummy function to store shared documentation items.} \usage{ -.documentFunction( - fewMeasurements, - useUniquePeptide, - summaryforMultipleRows, - removeProtein_with1Feature, - removeProtein_with1Protein, - removeOxidationMpeptides, - removeMpeptides -) +.documentFunction() } \arguments{ -\item{fewMeasurements}{'remove'(default) will remove the features that have 1 or 2 measurements across runs.} - -\item{useUniquePeptide}{TRUE (default) removes peptides that are assigned for more than one proteins. -We assume to use unique peptide for each protein.} - -\item{summaryforMultipleRows}{max(default) or sum - when there are multiple measurements for certain feature and certain run, use highest or sum of multiple intensities.} - -\item{removeProtein_with1Feature}{TRUE will remove the proteins which have only 1 feature, which is the combination of peptide, precursor charge, fragment and charge. FALSE is default.} - -\item{removeOxidationMpeptides}{TRUE will remove the peptides including 'oxidation (M)' in modification. FALSE is default.} - -\item{removeMpeptides}{TRUE will remove the peptides including 'M' sequence. FALSE is default.} - -\item{removeProtein_with1Peptide}{TRUE will remove the proteins which have only 1 peptide and charge. FALSE is default.} - \item{use_log_file}{logical. If TRUE, information about data processing will be saved to a file.} diff --git a/man/dot-getPhilosopherInput.Rd b/man/dot-getPhilosopherInput.Rd deleted file mode 100644 index 6705e05..0000000 --- a/man/dot-getPhilosopherInput.Rd +++ /dev/null @@ -1,15 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/converters.R -\name{.getPhilosopherInput} -\alias{.getPhilosopherInput} -\title{Convert Philosopher parameters to consistent format} -\usage{ -.getPhilosopherInput(input, path, folder) -} -\arguments{ -\item{input}{data.frame of `msstats.csv` file produced by Philosopher} -} -\description{ -Convert Philosopher parameters to consistent format -} -\keyword{internal} diff --git a/man/evidence.Rd b/man/evidence.Rd deleted file mode 100644 index d54ae83..0000000 --- a/man/evidence.Rd +++ /dev/null @@ -1,38 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/utils_MSstatsTMT.R -\docType{data} -\name{evidence} -\alias{evidence} -\title{Example of output from MaxQuant for TMT-10plex experiments.} -\format{ -A data frame with 1075 rows and 105 variables. -} -\usage{ -evidence -} -\description{ -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: -} -\details{ -\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 -} -} -\examples{ -head(evidence) - -} -\keyword{datasets} diff --git a/man/input.pd.Rd b/man/input.pd.Rd index e7dd21e..975b1b6 100644 --- a/man/input.pd.Rd +++ b/man/input.pd.Rd @@ -3,7 +3,7 @@ \docType{data} \name{input.pd} \alias{input.pd} -\title{Example of output from PDtoMSstatsTMTFormat function} +\title{Example dataset in MSstatsTMT format.} \format{ A data frame with 20110 rows and 11 variables. } @@ -11,8 +11,6 @@ A data frame with 20110 rows and 11 variables. input.pd } \description{ -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. } \details{ diff --git a/man/proteinGroups.Rd b/man/proteinGroups.Rd deleted file mode 100644 index ea208ac..0000000 --- a/man/proteinGroups.Rd +++ /dev/null @@ -1,35 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/utils_MSstatsTMT.R -\docType{data} -\name{proteinGroups} -\alias{proteinGroups} -\title{Example of proteinGroups file from MaxQuant for TMT-10plex experiments.} -\format{ -A data frame with 1075 rows and 105 variables. -} -\usage{ -proteinGroups -} -\description{ -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: -} -\details{ -\itemize{ - \item id - \item Protein.IDs - \item Only.identified.by.site - \item Potential.contaminant - \item Reverse -} -} -\examples{ -head(proteinGroups) - -} -\keyword{datasets} diff --git a/man/raw.mine.Rd b/man/raw.mine.Rd deleted file mode 100644 index 9f9243f..0000000 --- a/man/raw.mine.Rd +++ /dev/null @@ -1,36 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/utils_MSstatsTMT.R -\docType{data} -\name{raw.mine} -\alias{raw.mine} -\title{Example of output from SpectroMine for TMT-6plex experiments.} -\format{ -A data frame with 170 rows and 28 variables. -} -\usage{ -raw.mine -} -\description{ -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: -} -\details{ -\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. -} -} -\examples{ -head(raw.mine) - -} -\keyword{datasets} diff --git a/man/raw.om.Rd b/man/raw.om.Rd deleted file mode 100644 index ac9430e..0000000 --- a/man/raw.om.Rd +++ /dev/null @@ -1,40 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/utils_MSstatsTMT.R -\docType{data} -\name{raw.om} -\alias{raw.om} -\title{Example of MSstatsTMT report from OpenMS for TMT-10plex experiments.} -\format{ -A data frame with 860 rows and 13 variables. -} -\usage{ -raw.om -} -\description{ -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: -} -\details{ -\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 -} -} -\examples{ -head(raw.om) - -} -\keyword{datasets} diff --git a/man/raw.pd.Rd b/man/raw.pd.Rd deleted file mode 100644 index 7bec393..0000000 --- a/man/raw.pd.Rd +++ /dev/null @@ -1,37 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/utils_MSstatsTMT.R -\docType{data} -\name{raw.pd} -\alias{raw.pd} -\title{Example of output from Proteome Discoverer 2.2 for TMT-10plex experiments.} -\format{ -A data frame with 2858 rows and 50 variables. -} -\usage{ -raw.pd -} -\description{ -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: -} -\details{ -\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 -} -} -\examples{ -head(raw.pd) - -} -\keyword{datasets} diff --git a/man/reexports.Rd b/man/reexports.Rd new file mode 100644 index 0000000..2bc452c --- /dev/null +++ b/man/reexports.Rd @@ -0,0 +1,20 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/converters.R +\docType{import} +\name{reexports} +\alias{reexports} +\alias{MaxQtoMSstatsTMTFormat} +\alias{OpenMStoMSstatsTMTFormat} +\alias{PDtoMSstatsTMTFormat} +\alias{SpectroMinetoMSstatsTMTFormat} +\alias{PhilosophertoMSstatsTMTFormat} +\title{Objects exported from other packages} +\keyword{internal} +\description{ +These objects are imported from other packages. Follow the links +below to see their documentation. + +\describe{ + \item{MSstatsConvert}{\code{\link[MSstatsConvert]{MaxQtoMSstatsTMTFormat}}, \code{\link[MSstatsConvert]{OpenMStoMSstatsTMTFormat}}, \code{\link[MSstatsConvert]{PDtoMSstatsTMTFormat}}, \code{\link[MSstatsConvert]{PhilosophertoMSstatsTMTFormat}}, \code{\link[MSstatsConvert]{SpectroMinetoMSstatsTMTFormat}}} +}} + diff --git a/tests/testthat/test-converters.R b/tests/testthat/test-converters.R deleted file mode 100644 index 3e45fa8..0000000 --- a/tests/testthat/test-converters.R +++ /dev/null @@ -1,41 +0,0 @@ -context("PDtoMSstatsTMTFormat") -context("MaxQtoMSstatsTMTFormat") -context("SpectroMinetoMSstatsTMTFormat") - -test_that("PDtoMSstatsTMTFormat works", { - - expect_error(PDtoMSstatsTMTFormat(input = MSstatsTMT::raw.pd[, !colnames(MSstatsTMT::raw.pd) == "Protein.Accessions"], # missing columns in input - annotation = MSstatsTMT::annotation.pd)) - - expect_error(PDtoMSstatsTMTFormat(input = MSstatsTMT::raw.pd, - annotation = MSstatsTMT::annotation.pd[, !colnames(MSstatsTMT::annotation.pd) == "Condition"])) # missing columns in annotation - -}) - -test_that("MaxQtoMSstatsTMTFormat works", { - - expect_error(MaxQtoMSstatsTMTFormat(evidence = MSstatsTMT::evidence, proteinGroups = MSstatsTMT::proteinGroups, - annotation = MSstatsTMT::annotation.pd)) # wrong annotation file - -}) - -test_that("SpectroMinetoMSstatsTMTFormat works", { - - expect_error(SpectroMinetoMSstatsTMTFormat(input = MSstatsTMT::raw.mine, - annotation = MSstatsTMT::annotation.mine, - summaryforMultipleRows = average)) # wrong argument value - -}) - -test_that("PhilosophertoMSstatsTMTFormat works", { - - input_file_path = system.file("raw_data/Philosopher/msstats.csv", - package = "MSstatsTMT") - annotation_file_path = system.file("raw_data/Philosopher/MSstatsTMT_annotation.csv", - package = "MSstatsTMT") - input = data.table::fread(input_file_path) - annotation = data.table::fread(annotation_file_path) - msstats_format = PhilosophertoMSstatsTMTFormat(input, annotation) - expect_equal(nrow(msstats_format), 550) - -}) diff --git a/vignettes/MSstatsTMT.Rmd b/vignettes/MSstatsTMT.Rmd index 191b61a..6c3c9f6 100644 --- a/vignettes/MSstatsTMT.Rmd +++ b/vignettes/MSstatsTMT.Rmd @@ -47,6 +47,11 @@ MSstatsTMT includes the following three steps for statistical testing: , identify and quantify peptide ions. The preferred structure of data for use in MSstatsTMT is a .csv file in a *long* format with at least 9 columns representing the following variables: **ProteinName**, **PeptideSequence**, **Charge**, **PSM**, **Channel**, **Condition**, **BioReplicate**, **Mixture**, **Intensity**. The variable names are fixed, but are case-insensitive. ```{r, eval=T, echo=F, warning=F} +raw.pd = data.table::fread(system.file("tinytest/raw_data/PDTMT/pdtmt_input.csv", + package = "MSstatsConvert")) +annotation.pd = data.table::fread(system.file("tinytest/raw_data/PDTMT/pd_annotation.csv", + package = "MSstatsConvert")) +input.pd = PDtoMSstatsTMTFormat(raw.pd, annotation.pd) head(input.pd) ``` @@ -71,15 +76,19 @@ Preprocess PSM data from Proteome Discoverer and convert into the required input ```{r} # read in PD PSM sheet # raw.pd <- read.delim("161117_SILAC_HeLa_UPS1_TMT10_5Mixtures_3TechRep_UPSdB_Multiconsensus_PD22_Intensity_PSMs.txt") +raw.pd = data.table::fread(system.file("tinytest/raw_data/PDTMT/pdtmt_input.csv", + package = "MSstatsConvert")) head(raw.pd) # Read in annotation including condition and biological replicates per run and channel. # Users should make this annotation file. It is not the output from Proteome Discoverer. # annotation.pd <- read.csv(file="PD_Annotation.csv", header=TRUE) +annotation.pd = data.table::fread(system.file("tinytest/raw_data/PDTMT/pd_annotation.csv", + package = "MSstatsConvert")) head(annotation.pd) # use Protein.Accessions as protein name -input.pd <- PDtoMSstatsTMTFormat(raw.pd, annotation.pd, +input.pd <- PDtoMSstatsTMTFormat(raw.pd, annotation.pd, which.proteinid = "Protein.Accessions") head(input.pd) @@ -119,11 +128,16 @@ Preprocess PSM-level data from MaxQuant and convert into the required input form ```{r} # Read in MaxQuant files # proteinGroups <- read.table("proteinGroups.txt", sep="\t", header=TRUE) - # evidence <- read.table("evidence.txt", sep="\t", header=TRUE) +evidence = data.table::fread(system.file("tinytest/raw_data/MaxQuantTMT/mq_ev.csv", + package = "MSstatsConvert")) +proteinGroups = data.table::fread(system.file("tinytest/raw_data/MaxQuantTMT/mq_pg.csv", + package = "MSstatsConvert")) # Users should make this annotation file. It is not the output from MaxQuant. # annotation.mq <- read.csv(file="MQ_Annotation.csv", header=TRUE) +annotation.mq = data.table::fread(system.file("tinytest/raw_data/MaxQuantTMT/mq_annotation.csv", + package = "MSstatsConvert")) input.mq <- MaxQtoMSstatsTMTFormat(evidence, proteinGroups, annotation.mq) head(input.mq) @@ -150,9 +164,13 @@ Preprocess PSM data from SpectroMine and convert into the required input format ```{r} # Read in SpectroMine PSM report # raw.mine <- read.csv('20180831_095547_CID-OT-MS3-Short_PSM Report_20180831_103118.xls', sep="\t") +raw.mine = data.table::fread(system.file("tinytest/raw_data/SpectroMine/spectromine_input.csv", + package = "MSstatsConvert")) # Users should make this annotation file. It is not the output from SpectroMine # annotation.mine <- read.csv(file="Mine_Annotation.csv", header=TRUE) +annotation.mine = data.table::fread(system.file("tinytest/raw_data/SpectroMine/spectromine_annotation.csv", + package = "MSstatsConvert")) input.mine <- SpectroMinetoMSstatsTMTFormat(raw.mine, annotation.mine) head(input.mine) @@ -175,6 +193,8 @@ Preprocess MSstatsTMT report from OpenMS and convert into the required input for ```{r} # read in MSstatsTMT report from OpenMS # raw.om <- read.csv("OpenMS_20200222/20200225_MSstatsTMT_OpenMS_Export.csv") +raw.om = data.table::fread(system.file("tinytest/raw_data/OpenMSTMT/openmstmt_input.csv", + package = "MSstatsConvert")) head(raw.om) # the function only requries one input file @@ -205,8 +225,15 @@ Preprocess MSstats report from Philosopher of Fragpipe and convert into the requ #### Example ```{r} -# Example code is skipped for Philosopher Converter -# since the input is a path to the folder with all the Philosopher msstats csv files +input_file_path = system.file("tinytest/raw_data/Philosopher/msstats.csv", + package = "MSstatsConvert") +annotation_file_path = system.file("tinytest/raw_data/Philosopher/MSstatsTMT_annotation.csv", + package = "MSstatsConvert") +input = data.table::fread(input_file_path) +annotation = data.table::fread(annotation_file_path) + +input.philosopher <- PhilosophertoMSstatsTMTFormat(input, annotation) +head(input.philosopher) ``` ## 2. Protein summarization, normalization and visualization @@ -249,7 +276,7 @@ quant.msstats <- proteinSummarization(input.pd, ``` ```{r} -head(quant.pd.msstats$ProteinLevelData) +head(quant.msstats$ProteinLevelData) ``` ```{r, message=F, warning=F, results='hide'} @@ -313,13 +340,13 @@ dataProcessPlotsTMT(data=quant.msstats, There are two pdfs with all the proteins, first is profile plot and second plot is profile plot with summarized and normalized data. `XXX_ProfilePlot.pdf` shows each peptide ions across runs and channels, grouped per condition. Each panel represents one MS run and each dot within one panel is one channel within one Run. Each peptide has a different colour/type layout. The dots are linked with line per peptide ion If line is disconnected, that means there is no value (missing value). Profile plot is good visualization to check individual measurements. `XXX_ProfilePlot_wSummarization.pdf` shows the same peptide ions in grey, with the values as summarized by the model overlayed in red. -Instead of making all profile plots for all proteins, we can make plot for individual protein. Here is the example of protein`P04406` +Instead of making all profile plots for all proteins, we can make plot for individual protein. Here is the example of protein`O75947` ```{r, message=F, warning=F, results='hide'} dataProcessPlotsTMT(data=quant.msstats, type='ProfilePlot', # choice of visualization width = 21, height = 7, - which.Protein = 'P04406') + which.Protein = 'O75947') ``` ```{r}