From 0870e2b18698f20be2b8406ba1642644772c2971 Mon Sep 17 00:00:00 2001 From: Tony Wu Date: Fri, 6 Feb 2026 15:16:25 -0500 Subject: [PATCH 1/2] fix(diann): Add q-value filtering to DIANN big clean function --- R/clean_DIANN.R | 10 +++++++--- R/converters.R | 11 ++++++----- man/bigDIANNtoMSstatsFormat.Rd | 22 +++++++++++++++++++--- 3 files changed, 32 insertions(+), 11 deletions(-) diff --git a/R/clean_DIANN.R b/R/clean_DIANN.R index 77ea3e4..9aca175 100644 --- a/R/clean_DIANN.R +++ b/R/clean_DIANN.R @@ -49,10 +49,14 @@ cleanDIANNChunk = function(input, output_path, MBR, quantificationColumn, pos, qvalue_cutoff = 0.01, pg_qvalue_cutoff = 0.01) { input = MSstatsImport(list(input = input), - "MSstats", "DIANN") + "MSstats", "DIANN") input = MSstatsClean( - input, MBR, quantificationColumn - #Todo: Add , global_qvalue_cutoff, qvalue_cutoff, pg_qvalue_cutoff params + input, + MBR = MBR, + quantificationColumn = quantificationColumn, + global_qvalue_cutoff = global_qvalue_cutoff, + qvalue_cutoff = qvalue_cutoff, + pg_qvalue_cutoff = pg_qvalue_cutoff ) .writeChunkToFile(input, output_path, pos) NULL diff --git a/R/converters.R b/R/converters.R index 799d768..e9ff703 100644 --- a/R/converters.R +++ b/R/converters.R @@ -158,10 +158,7 @@ bigSpectronauttoMSstatsFormat <- function(input_file, output_file_name, #' Convert out-of-memory DIANN files to MSstats format. #' #' @inheritParams MSstatsPreprocessBig -#' @param MBR True if analysis was done with match between runs. -#' @param quantificationColumn Use 'FragmentQuantCorrected'(default) column for quantified intensities for DIANN 1.8.x. -#' Use 'FragmentQuantRaw' for quantified intensities for DIANN 1.9.x. -#' Use 'auto' for quantified intensities for DIANN 2.0+ +#' @inheritParams MSstatsConvert::DIANNtoMSstatsFormat #' #' @export #' @@ -173,6 +170,9 @@ bigDIANNtoMSstatsFormat <- function(input_file, backend, MBR = TRUE, quantificationColumn = "FragmentQuantCorrected", + global_qvalue_cutoff = 0.01, + qvalue_cutoff = 0.01, + pg_qvalue_cutoff = 0.01, max_feature_count = 100, filter_unique_peptides = FALSE, aggregate_psms = FALSE, @@ -186,7 +186,8 @@ bigDIANNtoMSstatsFormat <- function(input_file, reduceBigDIANN(input_file, paste0("reduce_output_", output_file_name), MBR, - quantificationColumn) + quantificationColumn, + global_qvalue_cutoff, qvalue_cutoff, pg_qvalue_cutoff) # Preprocess the cleaned data (feature selection, etc.) msstats_data <- MSstatsPreprocessBig( diff --git a/man/bigDIANNtoMSstatsFormat.Rd b/man/bigDIANNtoMSstatsFormat.Rd index 0f14cfc..244d6b9 100644 --- a/man/bigDIANNtoMSstatsFormat.Rd +++ b/man/bigDIANNtoMSstatsFormat.Rd @@ -10,6 +10,9 @@ bigDIANNtoMSstatsFormat( backend, MBR = TRUE, quantificationColumn = "FragmentQuantCorrected", + global_qvalue_cutoff = 0.01, + qvalue_cutoff = 0.01, + pg_qvalue_cutoff = 0.01, max_feature_count = 100, filter_unique_peptides = FALSE, aggregate_psms = FALSE, @@ -28,11 +31,24 @@ bigDIANNtoMSstatsFormat( \item{backend}{"arrow" or "sparklyr". Option "sparklyr" requires a spark installation and connection to spark instance provided in the `connection` parameter.} -\item{MBR}{True if analysis was done with match between runs.} +\item{MBR}{True if analysis was done with match between runs} \item{quantificationColumn}{Use 'FragmentQuantCorrected'(default) column for quantified intensities for DIANN 1.8.x. -Use 'FragmentQuantRaw' for quantified intensities for DIANN 1.9.x. -Use 'auto' for quantified intensities for DIANN 2.0+} +Use 'FragmentQuantRaw' for quantified intensities for DIANN 1.9.x. +Use 'auto' for quantified intensities for DIANN 2.x where each fragment intensity is a separate column, e.g. Fr0Quantity.} + +\item{global_qvalue_cutoff}{The qvalue cutoff for the Q.Value column, i.e. +the run-specific precursor q-value. Default is 0.01.} + +\item{qvalue_cutoff}{If MBR is false, the qvalue cutoff for the Global.Q.Value +column, i.e. global precursor q-value. If MBR is true, the qvalue cutoff for the +Lib.Q.Value column, i.e. the q-value for the library created after the first MBR pass. +Default is 0.01.} + +\item{pg_qvalue_cutoff}{If MBR is false, the qvalue cutoff for the Global.PG.Q.Value +column, i.e. the global q-value for the protein group. If MBR is true, the +qvalue cutoff for the Lib.PG.Q.Value column, i.e. the protein group q-value for +the library created after the first MBR pass. Default is 0.01.} \item{max_feature_count}{maximum number of features per protein. Features will be selected based on highest average intensity.} From 2877c012c37fee303bcb1c58a32829cd0d587b7c Mon Sep 17 00:00:00 2001 From: Tony Wu Date: Fri, 6 Feb 2026 15:19:23 -0500 Subject: [PATCH 2/2] add pull request template and dry run build workflow --- .github/.DS_Store | Bin 0 -> 6148 bytes .github/pull_request_template.md | 18 ++++++++++++++++++ .github/workflows/dry-run-build.yml | 19 +++++++++++++++++++ 3 files changed, 37 insertions(+) create mode 100644 .github/.DS_Store create mode 100644 .github/pull_request_template.md create mode 100644 .github/workflows/dry-run-build.yml diff --git a/.github/.DS_Store b/.github/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..a99cc2cda9bc2612ccc02301bb83370fc54d3331 GIT binary patch literal 6148 zcmeHKO>5gg5S?}0Mj`}!NWqtYAlHyOtqFu)gqt36jY4v0iz`)5E23y!OO6i4pmXwL za?LNv-)Z0Mu1if)dNZWVh}k#$@wDvQWj}~W4W{WnQHO{;IAhC4@`Q0c`y*?)k~UD8 ze++3tBlLq!^Q^3Ty$97=YrlB8?yY+p-skAMuA?fh zrsW`>eB|7z)_JmsE zD