From 6ea643ea8730109f509a10ab9a8b652827aaad7b Mon Sep 17 00:00:00 2001 From: tonywu1999 Date: Thu, 16 Jan 2025 17:47:25 -0500 Subject: [PATCH 1/2] docs(MSstatsBalancedDesign): Updated description of fill_incomplete parameter --- R/MSstatsConvert_core_functions.R | 8 ++++++-- man/MSstatsBalancedDesign.Rd | 8 ++++++-- man/MSstatsConvert.Rd | 14 -------------- man/ProteinProspectortoMSstatsTMTFormat.Rd | 4 ++-- man/dot-cleanRawPDMSstats.Rd | 3 ++- man/dot-cleanRawPDTMT.Rd | 3 ++- man/dot-validatePDTMTInputColumns.Rd | 3 +++ 7 files changed, 21 insertions(+), 22 deletions(-) diff --git a/R/MSstatsConvert_core_functions.R b/R/MSstatsConvert_core_functions.R index dc3ab08e7..0b6c03c85 100644 --- a/R/MSstatsConvert_core_functions.R +++ b/R/MSstatsConvert_core_functions.R @@ -393,8 +393,12 @@ MSstatsPreprocess = function( #' #' @param input `data.table` processed by the `MSstatsPreprocess` function #' @param feature_columns str, names of columns that define spectral features -#' @param fill_incomplete if TRUE (default), Intensity values for missing runs -#' will be added as NA +#' @param fill_incomplete if TRUE (default), ensures that rows with missing data +#' for specific features are added as NA. For example, if the y10 ion of +#' peptideA is measured in the "disease" samples but entirely missing for the +#' "healthy" samples, rows with NA values will be created for the y10 ion of +#' peptideA in the "healthy" group. This process increases the number of +#' rows to account for all possible feature-sample combinations. #' @param handle_fractions if TRUE (default), overlapping fractions will be resolved #' @param fix_missing str, optional. Defaults to NULL, which means no action. #' If not NULL, must be one of the options: "zero_to_na" or "na_to_zero". diff --git a/man/MSstatsBalancedDesign.Rd b/man/MSstatsBalancedDesign.Rd index 3ed646b0a..0163e4ccf 100644 --- a/man/MSstatsBalancedDesign.Rd +++ b/man/MSstatsBalancedDesign.Rd @@ -18,8 +18,12 @@ MSstatsBalancedDesign( \item{feature_columns}{str, names of columns that define spectral features} -\item{fill_incomplete}{if TRUE (default), Intensity values for missing runs -will be added as NA} +\item{fill_incomplete}{if TRUE (default), ensures that rows with missing data +for specific features are added as NA. For example, if the y10 ion of +peptideA is measured in the "disease" samples but entirely missing for the +"healthy" samples, rows with NA values will be created for the y10 ion of +peptideA in the "healthy" group. This process increases the number of +rows to account for all possible feature-sample combinations.} \item{handle_fractions}{if TRUE (default), overlapping fractions will be resolved} diff --git a/man/MSstatsConvert.Rd b/man/MSstatsConvert.Rd index 095984ade..ab9be1573 100644 --- a/man/MSstatsConvert.Rd +++ b/man/MSstatsConvert.Rd @@ -2,7 +2,6 @@ % Please edit documentation in R/utils_MSstatsConvert.R \docType{_PACKAGE} \name{MSstatsConvert} -\alias{MSstatsConvert-package} \alias{MSstatsConvert} \title{MSstatsConvert: An R Package to Convert Data from Mass Spectrometry Signal Processing Tools to MSstats Format} \description{ @@ -18,16 +17,3 @@ signal processing tools to a format suitable for statistical analysis with the M \code{\link{MSstatsBalancedDesign}} for handling fractions and creating balanced data. } -\author{ -\strong{Maintainer}: Mateusz Staniak \email{mtst@mstaniak.pl} - -Authors: -\itemize{ - \item Devon Kohler \email{kohler.d@northeastern.edu} - \item Anthony Wu \email{wu.anthon@northeastern.edu} - \item Meena Choi \email{mnchoi67@gmail.com} - \item Ting Huang \email{thuang0703@gmail.com} - \item Olga Vitek \email{o.vitek@northeastern.edu} -} - -} diff --git a/man/ProteinProspectortoMSstatsTMTFormat.Rd b/man/ProteinProspectortoMSstatsTMTFormat.Rd index 927cced9d..1c4383ae2 100644 --- a/man/ProteinProspectortoMSstatsTMTFormat.Rd +++ b/man/ProteinProspectortoMSstatsTMTFormat.Rd @@ -19,8 +19,8 @@ ProteinProspectortoMSstatsTMTFormat( ) } \arguments{ -\item{input}{txt report file from Protein Prospector with -\verb{Keep Replicates} option selected.} +\item{input}{Input txt peptide report file from Protein Prospector with +"Keep Replicates", "Mods in Peptide", and "Protein Mods" options selected.} \item{annotation}{data frame which contains column Run, Fraction, TechRepMixture, Mixture, Channel, BioReplicate, Condition.} diff --git a/man/dot-cleanRawPDMSstats.Rd b/man/dot-cleanRawPDMSstats.Rd index ac25d1f00..01382df2e 100644 --- a/man/dot-cleanRawPDMSstats.Rd +++ b/man/dot-cleanRawPDMSstats.Rd @@ -9,7 +9,8 @@ quantification_column, protein_id_column, sequence_column, - remove_shared + remove_shared, + run_column = "SpectrumFile" ) } \arguments{ diff --git a/man/dot-cleanRawPDTMT.Rd b/man/dot-cleanRawPDTMT.Rd index e1d77495c..9a684b0a0 100644 --- a/man/dot-cleanRawPDTMT.Rd +++ b/man/dot-cleanRawPDTMT.Rd @@ -9,7 +9,8 @@ remove_shared = TRUE, remove_protein_groups = TRUE, protein_id_column = "ProteinAccessions", - intensity_columns_regexp = "Abundance" + intensity_columns_regexp = "Abundance", + run_column = "SpectrumFile" ) } \arguments{ diff --git a/man/dot-validatePDTMTInputColumns.Rd b/man/dot-validatePDTMTInputColumns.Rd index eb5652b0c..0b05c691e 100644 --- a/man/dot-validatePDTMTInputColumns.Rd +++ b/man/dot-validatePDTMTInputColumns.Rd @@ -8,6 +8,7 @@ pd_input, protein_id_column, num_proteins_column, + run_column, channels ) } @@ -18,6 +19,8 @@ \item{num_proteins_column}{column name for number of protein groups passed from user} +\item{run_column}{column name for Run ID, depends on PD version} + \item{channels}{list of column names for channels} } \description{ From bb49ac22b1393226f4a083ae746bea6062257166 Mon Sep 17 00:00:00 2001 From: tonywu1999 Date: Thu, 16 Jan 2025 17:49:17 -0500 Subject: [PATCH 2/2] remove man file for validatePDTMTInputColumns --- R/clean_ProteomeDiscoverer.R | 1 + man/dot-validatePDTMTInputColumns.Rd | 28 ---------------------------- 2 files changed, 1 insertion(+), 28 deletions(-) delete mode 100644 man/dot-validatePDTMTInputColumns.Rd diff --git a/R/clean_ProteomeDiscoverer.R b/R/clean_ProteomeDiscoverer.R index fc3cc163c..4feba663e 100644 --- a/R/clean_ProteomeDiscoverer.R +++ b/R/clean_ProteomeDiscoverer.R @@ -141,6 +141,7 @@ #' @param num_proteins_column column name for number of protein groups passed from user #' @param run_column column name for Run ID, depends on PD version #' @param channels list of column names for channels +#' @noRd .validatePDTMTInputColumns = function(pd_input, protein_id_column, num_proteins_column, diff --git a/man/dot-validatePDTMTInputColumns.Rd b/man/dot-validatePDTMTInputColumns.Rd deleted file mode 100644 index 0b05c691e..000000000 --- a/man/dot-validatePDTMTInputColumns.Rd +++ /dev/null @@ -1,28 +0,0 @@ -% Generated by roxygen2: do not edit by hand -% Please edit documentation in R/clean_ProteomeDiscoverer.R -\name{.validatePDTMTInputColumns} -\alias{.validatePDTMTInputColumns} -\title{Helper method to validate input has necessary columns} -\usage{ -.validatePDTMTInputColumns( - pd_input, - protein_id_column, - num_proteins_column, - run_column, - channels -) -} -\arguments{ -\item{pd_input}{data.frame input} - -\item{protein_id_column}{column name for protein passed from user} - -\item{num_proteins_column}{column name for number of protein groups passed from user} - -\item{run_column}{column name for Run ID, depends on PD version} - -\item{channels}{list of column names for channels} -} -\description{ -Helper method to validate input has necessary columns -}