Skip to content

Fix build #46

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

Open
tonywu1999 wants to merge 2 commits into
base: devel
Choose a base branch
from
Open

Fix build #46

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
28522d0
fix msstatsLiP invocation of MSstatsPTM
tonywu1999 Mar 5, 2026
ac43dfd
version bump
tonywu1999 Mar 5, 2026
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
4 changes: 2 additions & 2 deletions DESCRIPTION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
Type: Package
Package: MSstatsLiP
Title: LiP Significance Analysis in shotgun mass spectrometry-based proteomic experiments
Version: 1.17.0
Version: 1.17.1
Copy link

@coderabbitai coderabbitai bot Mar 5, 2026

Choose a reason for hiding this comment

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

⚠️ Potential issue | 🟠 Major

🧩 Analysis chain

🏁 Script executed:

git ls-files | head -20

Repository: Vitek-Lab/MSstatsLiP

Length of output: 518

🏁 Script executed:

cat -n DESCRIPTION | head -40

Repository: Vitek-Lab/MSstatsLiP

Length of output: 2352

🏁 Script executed:

fd -t f "groupComparisonLiP" -x cat -n {}

Repository: Vitek-Lab/MSstatsLiP

Length of output: 13499

🌐 Web query:

MSstatsPTM groupComparisonPTM function parameters ptm_label_type protein_label_type version history

💡 Result:

groupComparisonPTM() parameters: ptm_label_type, protein_label_type

  • ptm_label_type: labeling type for the PTM dataset; must be "LF" or "TMT" (default "LF"). [1,2]
  • protein_label_type: labeling type for the PROTEIN (global proteome) dataset; must be "LF" or "TMT" (default "LF"). [1,2]

These parameters let MSstatsPTM run group comparisons even when the PTM and global-protein datasets use different labeling types (e.g., PTM is TMT but the proteome is label-free). [3]

Version / history (what changed, and when)

  • Older MSstatsPTM (e.g., v2.0.3; Bioconductor 3.16, published 2023-04-10): groupComparisonPTM() used data.type (no ptm_label_type / protein_label_type). [4]
  • Current MSstatsPTM (v2.13.0; Bioconductor 3.23, published 2026-03-03): groupComparisonPTM() includes ptm_label_type and protein_label_type, and notes that data.type “will be deprecated” in favor of the two new parameters. [1]
  • The planned backwards-incompatible change was announced 2025-03-19, stating data.type would be replaced by ptm_label_type + protein_label_type, and advising for backward compatibility to set both new parameters to the old data.type value. [3]

Practical migration rule: if you previously did data.type = "LF" (or "TMT"), now do ptm_label_type="LF", protein_label_type="LF" (or both "TMT"), unless you intentionally want them to differ. [1,3]

References:
[1] Bioconductor MSstatsPTM 2.13.0 PDF manual (Bioc 3.23; published 2026-03-03). (bioconductor.posit.co)
[2] MSstatsPTM reference manual (HTML) documenting allowed values for ptm_label_type / protein_label_type. (bioc.r-universe.dev)
[3] MSstats Google Group announcement (2025-03-19) describing the parameter change and rationale. (groups.google.com)
[4] Bioconductor MSstatsPTM 2.0.3 PDF manual (Bioc 3.16; published 2023-04-10). (bioconductor.statistik.uni-dortmund.de)

Citations:

🏁 Script executed:

# Check if there are any version constraints in the codebase that reference MSstatsPTM versions
rg "MSstatsPTM.*>=" --type r
rg "MSstatsPTM.*version" --type r

Repository: Vitek-Lab/MSstatsLiP

Length of output: 46

🏁 Script executed:

# Check NAMESPACE file for any hints about MSstatsPTM
cat NAMESPACE

Repository: Vitek-Lab/MSstatsLiP

Length of output: 2530

🏁 Script executed:

# Check if there are any recent git commits or documentation that reference MSstatsPTM version requirements
rg "2\.[0-9]+\.[0-9]+" --type text DESCRIPTION README* 2>/dev/null | head -20

Repository: Vitek-Lab/MSstatsLiP

Length of output: 46

🌐 Web query:

MSstatsPTM version 2.1 2.2 2.3 ptm_label_type protein_label_type introduced when release date

💡 Result:

When were ptm_label_type / protein_label_type introduced?

They replaced the old single data.type parameter for groupComparisonPTM() as part of the Bioconductor 3.21 cycle; MSstatsPTM 2.10.0 (Date/Publication: 2025-04-15) is documented in Bioconductor materials for that release series. [1] (The change was announced ahead of time for the “upcoming MSstats 3.21 bioconductor release”.) [2]

You can see the old interface (data.type) in MSstatsPTM 2.0.3 examples. [2]
You can see the new interface (ptm_label_type, protein_label_type) in current manuals (e.g., dataProcessPTM() and groupComparisonPTM()). [3]

Release dates for MSstatsPTM 2.1 / 2.2 / 2.3 (Bioconductor evidence)

From the Bioconductor package archives I could access:

Version Release date (archive timestamp / Date/Publication) Source
2.2.0 2023-06-26 Bioc 3.17 archive listing [4]
2.2.2 2023-06-28 Bioc 3.17 archive listing [4]
2.1.x Not found in the Bioconductor archives I checked (no Bioc archive entry located)
2.3.x Not found in the Bioconductor archives I checked (no Bioc archive entry located)

If you want, tell me whether you mean Bioconductor releases specifically (recommended for “release date”), or GitHub tags/releases—and I can look up whether 2.1.x / 2.3.x exist as GitHub-only versions.

🌐 Web query:

MSstatsPTM changelog release notes ptm_label_type protein_label_type

💡 Result:

  • Where this change is documented (release notes / changelog context):

    • In the MSstats community announcement for the upcoming Bioconductor MSstats 3.21 release (posted Mar 19, 2025): groupComparisonPTM()’s data.type parameter is being replaced by two new parameters: ptm_label_type and protein_label_type, to support cases where PTM and proteome data use different label types (e.g., PTM=TMT, protein=LF). Back-compat guidance: set both new parameters to the old data.type value. [1]

  • What the current MSstatsPTM docs say:

    • In the MSstatsPTM reference manual, groupComparisonPTM() still lists data.type but states it “will be deprecated in favor of ptm_label_type and protein_label_type”, and documents both new args as accepting LF or TMT. [2]
    • The manual also documents dataProcessPTM() as taking ptm_label_type and protein_label_type explicitly (same allowed values: LF/TMT). [2]

Sources:
[1] MSstats Google Group announcement (Mar 19, 2025): “Upcoming Backwards-Incompatible Changes in MSstats 3.21 – Action Required”
[2] Bioconductor MSstatsPTM manual (PDF), sections for groupComparisonPTM and dataProcessPTM

Add MSstatsPTM (>= 2.10.0) version constraint in Imports before releasing.

groupComparisonLiP() calls groupComparisonPTM() with ptm_label_type and protein_label_type parameters, which were introduced in MSstatsPTM 2.10.0 (Bioconductor 3.21, released ~April 2025). Without a version bound, installations with older MSstatsPTM versions will fail at runtime.

🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@DESCRIPTION` at line 4, Add an explicit version bound for MSstatsPTM in the
DESCRIPTION Imports to require MSstatsPTM (>= 2.10.0) so runtime calls to
groupComparisonPTM from groupComparisonLiP that pass the new ptm_label_type and
protein_label_type parameters won't fail on older installs; update the Imports
entry to include "MSstatsPTM (>= 2.10.0)" ensuring the package dependency is
enforced at install time.

Date: 2024-3-19
Description: Tools for LiP peptide and protein significance analysis. Provides
functions for summarization, estimation of LiP peptide abundance,
Expand Down Expand Up @@ -31,4 +31,4 @@ BugReports: https://github.com/Vitek-Lab/MSstatsLiP/issues
Encoding: UTF-8
LazyData: TRUE
Roxygen: list(markdown = TRUE)
RoxygenNote: 7.3.2
RoxygenNote: 7.3.3
27 changes: 15 additions & 12 deletions R/groupComparisonLiP.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,23 +13,15 @@
#' @param data list of summarized datasets. Can be output of MSstatsLiP
#' summarization function \code{\link[MSstatsLiP]{dataSummarizationLiP}}. Must
#' include dataset named "LiP" as minimum.
#' @param contrast.matrix comparison between conditions of interests. Default
#' models full pairwise comparison between all conditions
#' @param fasta.path a file path to a fasta file that includes the proteins
#' listed in the data. Default is NULL. Include this parameter to determine
#' trypticity of peptides in LiP models.
#' @param log_base base of the logarithm used in dataProcess.
#' @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 will 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.
#' @param base start of the file name.
#' @inheritParams MSstatsPTM::groupComparisonPTM
#' @return list of modeling results. Includes LiP, PROTEIN, and ADJUSTED LiP
#' data.tables with their corresponding model results.
#' @examples
Expand Down Expand Up @@ -92,9 +84,20 @@ groupComparisonLiP <- function(data, contrast.matrix = "pairwise",
PROTEIN = data.protein)

## Model
model.data <- groupComparisonPTM(format.data, "LabelFree", contrast.matrix,
FALSE, "BH", log_base, use_log_file, append,
verbose, path, base)
model.data <- groupComparisonPTM(
format.data,
contrast.matrix = contrast.matrix,
ptm_label_type = "LF",
protein_label_type = "LF",
moderated = FALSE,
adj.method = "BH",
log_base = log_base,
save_fitted_models=TRUE,
use_log_file = use_log_file,
append = append,
verbose = verbose,
log_file_path = path
)
model.data$ADJUSTED.Model <- model.data$ADJUSTED.Model[!is.na(
model.data$ADJUSTED.Model$Protein)]

Expand Down
3 changes: 2 additions & 1 deletion man/groupComparisonLiP.Rd
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading