Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

#

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

added support for PD 3.1 column naming #98

Merged
merged 3 commits into from
Oct 18, 2024
Merged

added support for PD 3.1 column naming #98

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
16e2f4f
added support for PD 3.1 column naming
mstaniak Jul 31, 2024
7cd97bf
updated support for PD 3.1 column names
mstaniak Jul 31, 2024
59db56f
fixed a mistake in handling alternative Run column names for PD
mstaniak Jul 31, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 10 additions & 6 deletions R/clean_ProteomeDiscoverer.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,19 +36,20 @@
protein_id_column = .standardizeColnames(protein_id_column)
sequence_column = .standardizeColnames(sequence_column)
quantification_column = .standardizeColnames(quantification_column)
run_column = ifelse(any(grepl("FileID", colnames(pd_input))), "FileID", "SpectrumFile")

if (remove_shared & is.element("XProteins", colnames(pd_input))) {
pd_input = pd_input[XProteins == "1", ]
}
pd_cols = c(protein_id_column, sequence_column,
"Modifications", "Charge", "SpectrumFile", quantification_column)
"Modifications", "Charge", run_column, quantification_column)
if (any(is.element(colnames(pd_input), "Fraction"))) {
pd_cols = c(pd_cols, "Fraction")
}
pd_input = pd_input[, pd_cols, with = FALSE]
data.table::setnames(
pd_input,
c(protein_id_column, sequence_column, "SpectrumFile",
c(protein_id_column, sequence_column, run_column,
quantification_column, "Charge"),
c("ProteinName", "PeptideSequence", "Run",
"Intensity", "PrecursorCharge"),
Expand Down Expand Up @@ -96,17 +97,18 @@
}

channels = .getChannelColumns(colnames(pd_input), intensity_columns_regexp)
.validatePDTMTInputColumns(pd_input, protein_id_column, num_proteins, channels)
run_column = ifelse(any(grepl("FileID", colnames(pd_input))), "FileID", "SpectrumFile")
.validatePDTMTInputColumns(pd_input, protein_id_column, num_proteins, run_column, channels)

pd_cols = intersect(c(protein_id_column, num_proteins, "AnnotatedSequence",
"Charge", "PrecursorCharge", "IonsScore",
"SpectrumFile", "QuanInfo",
run_column, "QuanInfo",
"IsolationInterference", channels),
colnames(pd_input))
pd_input = pd_input[, pd_cols, with = FALSE]
data.table::setnames(pd_input,
c(protein_id_column, num_proteins, "AnnotatedSequence",
"SpectrumFile", "Charge"),
run_column, "Charge"),
c("ProteinName", "numProtein", "PeptideSequence",
"Run", "PrecursorCharge"),
skip_absent = TRUE)
Expand Down Expand Up @@ -137,14 +139,16 @@
#' @param pd_input data.frame input
#' @param protein_id_column column name for protein passed from user
#' @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
.validatePDTMTInputColumns = function(pd_input,
protein_id_column,
num_proteins_column,
run_column,
channels
) {
required_columns = c(protein_id_column, num_proteins_column, "AnnotatedSequence",
"SpectrumFile")
run_column)
missing_columns = setdiff(required_columns, colnames(pd_input))
if (length(missing_columns) > 0) {
msg = paste("The following columns are missing from the input data:",
Expand Down
Loading