Skip to content

fix(maxQuant): Remove unmodified peptides from PTM dataset #116

New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Merged
tonywu1999 merged 4 commits into from
Jul 14, 2025
Merged

fix(maxQuant): Remove unmodified peptides from PTM dataset #116

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6424a03
fix(maxQuant): Remove unmodified peptides from PTM dataset
tonywu1999 Jul 10, 2025
55b5a49
refactor such that unmodified are removed when global profiling dataset
tonywu1999 Jul 10, 2025
fa3658e
add unit tests
tonywu1999 Jul 12, 2025
f7b3b2f
update unit test explanation
tonywu1999 Jul 12, 2025
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
8 changes: 5 additions & 3 deletions R/converters.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -640,8 +640,6 @@ MaxQtoMSstatsPTMFormat = function(evidence=NULL,
keep = 1)]
}

MSstatsPTMformat = list('PTM' = msstatsptm_input)

if (!is.null(evidence_prot)){
annotation_protein = as.data.table(annotation_protein)

Expand All @@ -657,9 +655,10 @@ MaxQtoMSstatsPTMFormat = function(evidence=NULL,
proteinID = which_proteinid_protein)
}

msstatsptm_input = msstatsptm_input[grepl(mod_id, msstatsptm_input$PeptideSequence),]
MSstatsPTMformat = list('PTM' = msstatsptm_input,
"PROTEIN" = msstats.abun)

return(MSstatsPTMformat)
}

if (use_unmod_peptides){
Expand All @@ -668,6 +667,9 @@ MaxQtoMSstatsPTMFormat = function(evidence=NULL,

MSstatsPTMformat = list(PTM = msstatsptm_input,
PROTEIN = msstats.abun)
} else {
msstatsptm_input = msstatsptm_input[grepl(mod_id, msstatsptm_input$PeptideSequence),]
Copy link

Copilot AI Jul 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Using grepl without fixed = TRUE treats mod_id as a regex. If mod_id is literal, add fixed = TRUE to avoid unintended regex interpretation.

Copilot uses AI. Check for mistakes.
MSstatsPTMformat = list('PTM' = msstatsptm_input)
}

return(MSstatsPTMformat)
Expand Down
50 changes: 43 additions & 7 deletions inst/tinytest/test_converters.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,15 @@
#' @author Anthony Wu
#'
#' @param msstats_ptm_input A list containing PTM and PROTEIN data tables
.validatePositiveNumberOfRows = function(msstats_ptm_input) {
#' @param global_profiling Default TRUE indicates msstats_ptm_input should have
#' the PROTEIN element
.validatePositiveNumberOfRows = function(msstats_ptm_input, global_profiling = TRUE) {
expect_true(nrow(msstats_ptm_input$PTM) > 0)
expect_true(nrow(msstats_ptm_input$PROTEIN) > 0)
if (global_profiling) {
expect_true(nrow(msstats_ptm_input$PROTEIN) > 0)
} else {
expect_true(is.null(msstats_ptm_input$PROTEIN))
}
}

#' Validate protein ID count in converter output
Expand Down Expand Up @@ -35,7 +41,7 @@
)
}

## MaxQ TMT
## MaxQ TMT useUnmodPeptides = TRUE
data("maxq_tmt_evidence", package = "MSstatsPTM")
data("maxq_tmt_annotation", package = "MSstatsPTM")

Expand Down Expand Up @@ -84,12 +90,26 @@ mq_imported = MaxQtoMSstatsPTMFormat(evidence=maxq_tmt_evidence,
.validateProteinId(mq_imported$PTM, "P29966_T150", 70)
.validateProteinId(mq_imported$PTM, "P29966_T143_S145", 10)
.validatePtmSubstring(
mq_imported$PTM, "Phospho \\(STY\\)",
length(mq_imported$PTM$PeptideSequence))
mq_imported$PTM, "Phospho \\(STY\\)",
length(mq_imported$PTM$PeptideSequence))
.validatePtmSubstring(
mq_imported$PROTEIN, "Phospho \\(STY\\)", 0)
mq_imported$PROTEIN, "Phospho \\(STY\\)", 0)

## MaxQ TMT useUnmodPeptides = FALSE
mq_imported = MaxQtoMSstatsPTMFormat(evidence=maxq_tmt_evidence,
annotation=maxq_tmt_annotation,
fasta=system.file("extdata", "maxq_tmt_fasta.fasta", package="MSstatsPTM"),
fasta_protein_name="uniprot_ac",
use_unmod_peptides=FALSE,
labeling_type = "TMT")
.validatePositiveNumberOfRows(mq_imported, global_profiling = FALSE)
.validateProteinId(mq_imported$PTM, "P29966_T150", 70)
.validateProteinId(mq_imported$PTM, "P29966_T143_S145", 10)
.validatePtmSubstring(
mq_imported$PTM, "Phospho \\(STY\\)",
length(mq_imported$PTM$PeptideSequence))

## MaxQ LF
## MaxQ LF useUnmodPeptides = TRUE
data("maxq_lf_evidence", package = "MSstatsPTM")
data("maxq_lf_annotation", package = "MSstatsPTM")

Expand Down Expand Up @@ -155,6 +175,22 @@ mq_imported = MaxQtoMSstatsPTMFormat(evidence=maxq_lf_evidence,
.validatePtmSubstring(
mq_imported$PROTEIN, "Phospho \\(STY\\)", 0)

## MaxQ LF useUnmodPeptides = FALSE
mq_imported = MaxQtoMSstatsPTMFormat(evidence=maxq_lf_evidence,
annotation=maxq_lf_annotation,
fasta=system.file("extdata", "maxq_lf_fasta.fasta", package="MSstatsPTM"),
fasta_protein_name="uniprot_ac",
mod_id="\\(Phospho \\(STY\\)\\)",
use_unmod_peptides=FALSE,
labeling_type = "LF",
which_proteinid_ptm = "Proteins")
.validatePositiveNumberOfRows(mq_imported, global_profiling = FALSE)
.validateProteinId(mq_imported$PTM, "P36578_S295", 66)
.validateProteinId(mq_imported$PTM, "Q13523_S431_S437", 33)
.validatePtmSubstring(
mq_imported$PTM, "Phospho \\(STY\\)",
length(mq_imported$PTM$PeptideSequence))

## Spectronaut
data("spectronaut_input", package = "MSstatsPTM")
data("spectronaut_annotation", package = "MSstatsPTM")
Expand Down
Loading