v0.10

.Rbuildignore

@@ -2,3 +2,5 @@
 ^\.Rproj\.user$
 ^LICENSE\.md$
 ^\.github$
+^\.positai$
+^\.claude$

.github/workflows/R-CMD-check.yaml

@@ -22,7 +22,7 @@ jobs:
         config:
         - { os: macOS-latest, bioc: 'release', curlConfigPath: '/usr/bin/'}
         - { os: windows-latest, bioc: 'release'}
-        - { os: ubuntu-latest, image: "bioconductor/bioconductor_docker:RELEASE_3_20", cran: "https://demo.rstudiopm.com/all/__linux__/xenial/latest"}
+        - { os: ubuntu-latest, image: "bioconductor/bioconductor_docker:RELEASE_3_23", cran: "https://demo.rstudiopm.com/all/__linux__/xenial/latest"}
 
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
@@ -35,7 +35,7 @@ jobs:
 
     steps:
       - name: Check out repo
-        uses: actions/checkout@v3
+        uses: actions/checkout@v7
 
       - name: Set up R and install BiocManager
         uses: grimbough/bioc-actions/setup-bioc@v1
@@ -60,7 +60,7 @@ jobs:
 
       - name: Cache R packages
         if: runner.os != 'Windows' && matrix.config.image == null
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: ${{ env.R_LIBS_USER }}
           key: ${{ env.cache-version }}-${{ runner.os }}-bioc-${{ matrix.config.bioc }}-${{ hashFiles('depends.Rds') }}

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: einprot
 Type: Package
 Title: A collection of proteomics analysis utilities and workflows
-Version: 0.9.9
+Version: 0.10.2
 Authors@R: c(
     person("Charlotte", "Soneson", email = "charlotte.soneson@fmi.ch", 
            role = c("aut", "cre"), comment = c(ORCID = "0000-0003-3833-2169")),
@@ -17,7 +17,7 @@ Description: The einprot package contains utilities for performing analysis
     functionality for assembling databases of known protein complexes. 
 License: MIT + file LICENSE
 Encoding: UTF-8
-Depends: R (>= 4.0)
+Depends: R (>= 4.1)
 Imports: 
     babelgene,
     circlize,
@@ -78,12 +78,13 @@ Imports:
     motifStack,
     msigdbrdata
 Remotes: msigdbrdata=github::igordot/msigdbrdata
-RoxygenNote: 7.3.3
 Suggests: 
     BiocManager,
     testthat (>= 3.0.0),
     iSEE,
-    matrixStats
+    matrixStats,
+    arrow
 Config/testthat/edition: 3
 VignetteBuilder: knitr
 biocViews: Proteomics, DataImport
+Config/roxygen2/version: 8.0.0

NAMESPACE

@@ -9,14 +9,17 @@ export(defineAssayNames)
 export(doImputation)
 export(doNormalization)
 export(doPCA)
+export(einprotDIANNFiltersDF)
+export(einprotFragPipeFilters)
+export(einprotMQFilters)
+export(einprotPDTMTPeptideGroupFilters)
+export(einprotPDTMTProteinFilters)
+export(einprotSpectronautFilters)
 export(emptySampleText)
 export(expDesignText)
 export(featureCollectionText)
 export(filterByModText)
-export(filterFragPipe)
-export(filterMaxQuant)
-export(filterPDTMT)
-export(filterSpectronaut)
+export(filterFeaturesSE)
 export(fixFeatureIds)
 export(formatTableColumns)
 export(getCalibrationFrompdAnalysis)
@@ -73,6 +76,7 @@ export(runMaxQuantAnalysis)
 export(runPDTMTAnalysis)
 export(runPDTMTptmAnalysis)
 export(runPTMTest)
+export(runSEAnalysis)
 export(runSpectronautAnalysis)
 export(runTest)
 export(saText)
@@ -108,6 +112,7 @@ importFrom(SummarizedExperiment,"rowData<-")
 importFrom(SummarizedExperiment,assay)
 importFrom(SummarizedExperiment,assayNames)
 importFrom(SummarizedExperiment,colData)
+importFrom(SummarizedExperiment,colnames)
 importFrom(SummarizedExperiment,rowData)
 importFrom(XML,xmlParse)
 importFrom(XML,xmlToList)
@@ -122,14 +127,18 @@ importFrom(dplyr,arrange)
 importFrom(dplyr,between)
 importFrom(dplyr,bind_cols)
 importFrom(dplyr,bind_rows)
+importFrom(dplyr,collect)
+importFrom(dplyr,compute)
 importFrom(dplyr,contains)
+importFrom(dplyr,count)
 importFrom(dplyr,desc)
 importFrom(dplyr,distinct)
 importFrom(dplyr,everything)
 importFrom(dplyr,filter)
 importFrom(dplyr,full_join)
 importFrom(dplyr,group_by)
 importFrom(dplyr,if_any)
+importFrom(dplyr,inner_join)
 importFrom(dplyr,last_col)
 importFrom(dplyr,left_join)
 importFrom(dplyr,matches)
@@ -269,6 +278,7 @@ importFrom(stats,setNames)
 importFrom(stringdist,amatch)
 importFrom(stringr,str_extract)
 importFrom(tibble,rownames_to_column)
+importFrom(tibble,tibble)
 importFrom(tidyr,gather)
 importFrom(tidyr,pivot_longer)
 importFrom(tidyr,pivot_wider)
@@ -279,6 +289,7 @@ importFrom(tidyr,unite)
 importFrom(tidyr,unnest)
 importFrom(tidyselect,any_of)
 importFrom(tools,file_ext)
+importFrom(tools,file_path_sans_ext)
 importFrom(utils,combn)
 importFrom(utils,download.file)
 importFrom(utils,head)

NEWS.md

@@ -1,3 +1,23 @@
+# einprot 0.10.2
+
+* Expose additional arguments to doImputation() in workflow functions
+* Rename 'method' argument of doImputation() to 'imputeMethod'
+* Add 'valueType' argument to plotFractionDetectedPerSample()
+* Add normalization methods 'diff.mean.shared' and 'diff.median.shared'
+
+# einprot 0.10.1
+
+* Limit the set of supported normalization methods in the workflows to make sure they are suitable for the input type
+* Add runSEAnalysis function to run workflow starting from a SummarizedExperiment object
+* Add clusterRows argument to makeAbundanceHeatmap()
+* Add "sorted" setting to plotMissingValuesHeatmap()
+* Change settings to not cluster very large heatmaps (>10,000 rows)
+
+# einprot 0.10.0
+
+* Breaking change: redesign the feature filtering framework to make it more flexible and consistent across tools
+* Add p-value histograms to pdfs with test result plots
+
 # einprot 0.9.8
 
 * Expose argument to include or exclude abundance values from result tables

R/checkArgumentsDIANN.R

@@ -4,14 +4,13 @@
 #' @noRd
 #' @author Charlotte Soneson
 #'
-#' @importFrom MsCoreUtils normalizeMethods
 .checkArgumentsDIANN <- function(
     templateRmd, outputDir, outputBaseName, reportTitle, reportAuthor,
     forceOverwrite, experimentInfo, species, diannFile, diannFileType,
     outLevel, diannLogFile, aName, idCol, labelCol, geneIdCol, proteinIdCol,
     stringIdCol, extraFeatureCols, sampleAnnot, includeOnlySamples,
-    excludeSamples, minScore, minPeptides, imputeMethod, assaysForExport, 
-    addAbundanceValues, addHeatmaps, mergeGroups,
+    excludeSamples, imputeMethod, imputeArgs, filtersDF, filtersSE,
+    assaysForExport, addAbundanceValues, addHeatmaps, mergeGroups,
     comparisons, ctrlGroup, allPairwiseComparisons, singleFit,
     subtractBaseline, baselineGroup, normMethod, spikeFeatures, stattest,
     minNbrValidValues, minlFC, samSignificance, nperm, volcanoAdjPvalThr,
@@ -55,7 +54,8 @@
     }
 
     .assertScalar(x = diannFileType, type = "character",
-                  validValues = c("pg_matrix", "pr_matrix", "main_report"))
+                  validValues = c("pg_matrix", "pr_matrix", "main_report",
+                                  "parquet"))
     .assertScalar(x = outLevel, type = "character",
                   validValues = c("pg", "pr"))
     if (diannFileType == "pg_matrix" && outLevel == "pr") {
@@ -135,19 +135,38 @@
 
     .assertVector(x = linkTableColumns, type = "character", allowNULL = TRUE)
 
-    ## Score thresholds
-    .assertScalar(x = minScore, type = "numeric", allowNULL = TRUE)
-    .assertScalar(x = minPeptides, type = "numeric", allowNULL = TRUE)
+    ## Filter functions
+    .assertVector(x = filtersDF, type = "list")
+    if (length(filtersDF) > 0) {
+        .assertVector(x = names(filtersDF), type = "character")
+        for (f in filtersDF) {
+            stopifnot(is(f, "function"))
+            stopifnot(length(formals(f)) == 1)
+        }
+    }
+    .assertVector(x = filtersSE, type = "list")
+    if (length(filtersSE) > 0) {
+        .assertVector(x = names(filtersSE), type = "character")
+        for (f in filtersSE) {
+            stopifnot(is(f, "function"))
+            stopifnot(length(formals(f)) == 1)
+        }
+    }
 
     ## Method choices
     .assertScalar(x = imputeMethod, type = "character",
-                  validValues = c("impSeqRob", "MinProb", "MinProbGlobal"))
+                  validValues = c("impSeqRob", "MinProb", "MinProbGlobal",
+                                  "MinProbOffset", "MinProbGlobalOffset",
+                                  "custom"))
+    .assertVector(x = imputeArgs, type = "list")
     .assertVector(x = assaysForExport, type = "character", allowNULL = TRUE)
     .assertScalar(x = addAbundanceValues, type = "logical")
     .assertScalar(x = addHeatmaps, type = "logical")
     .assertScalar(x = normMethod, type = "character",
-                  validValues = c(MsCoreUtils::normalizeMethods(), "none",
-                                  "center.mean.shared", "center.median.shared"))
+                  validValues = c("center.mean", "center.median",
+                                  "diff.median", "vsn", "none",
+                                  "center.mean.shared", "center.median.shared",
+                                  "diff.mean.shared", "diff.median.shared"))
     .assertVector(x = spikeFeatures, type = "character", allowNULL = TRUE)
     .assertScalar(x = stattest, type = "character",
                   validValues = c("limma", "ttest", "proDA", "none"))

R/checkArgumentsFragPipe.R

@@ -4,14 +4,13 @@
 #' @noRd
 #' @author Charlotte Soneson
 #'
-#' @importFrom MsCoreUtils normalizeMethods
 .checkArgumentsFragPipe <- function(
     templateRmd, outputDir, outputBaseName, reportTitle, reportAuthor,
     forceOverwrite, experimentInfo, species, fragpipeDir,
     idCol, labelCol, geneIdCol, proteinIdCol, stringIdCol, extraFeatureCols,
-    iColPattern, sampleAnnot, includeOnlySamples, excludeSamples, minScore,
-    minPeptides, imputeMethod, assaysForExport, addAbundanceValues,
-    addHeatmaps, mergeGroups,
+    iColPattern, sampleAnnot, includeOnlySamples, excludeSamples,
+    imputeMethod, imputeArgs, assaysForExport, addAbundanceValues,
+    addHeatmaps, mergeGroups, filtersSE,
     comparisons, ctrlGroup, allPairwiseComparisons, singleFit,
     subtractBaseline, baselineGroup, normMethod, spikeFeatures, stattest,
     minNbrValidValues, minlFC, samSignificance, nperm, volcanoAdjPvalThr,
@@ -141,19 +140,30 @@
 
     .assertVector(x = linkTableColumns, type = "character", allowNULL = TRUE)
 
-    ## Score thresholds
-    .assertScalar(x = minScore, type = "numeric", allowNULL = TRUE)
-    .assertScalar(x = minPeptides, type = "numeric", allowNULL = TRUE)
+    ## Filter functions
+    .assertVector(x = filtersSE, type = "list")
+    if (length(filtersSE) > 0) {
+        .assertVector(x = names(filtersSE), type = "character")
+        for (f in filtersSE) {
+            stopifnot(is(f, "function"))
+            stopifnot(length(formals(f)) == 1)
+        }
+    }
 
     ## Method choices
     .assertScalar(x = imputeMethod, type = "character",
-                  validValues = c("impSeqRob", "MinProb", "MinProbGlobal"))
+                  validValues = c("impSeqRob", "MinProb", "MinProbGlobal",
+                                  "MinProbOffset", "MinProbGlobalOffset",
+                                  "custom"))
+    .assertVector(x = imputeArgs, type = "list")
     .assertVector(x = assaysForExport, type = "character", allowNULL = TRUE)
     .assertScalar(x = addAbundanceValues, type = "logical")
     .assertScalar(x = addHeatmaps, type = "logical")
     .assertScalar(x = normMethod, type = "character",
-                  validValues = c(MsCoreUtils::normalizeMethods(), "none",
-                                  "center.mean.shared", "center.median.shared"))
+                  validValues = c("center.mean", "center.median",
+                                  "diff.median", "vsn", "none",
+                                  "center.mean.shared", "center.median.shared",
+                                  "diff.mean.shared", "diff.median.shared"))
     .assertVector(x = spikeFeatures, type = "character", allowNULL = TRUE)
     .assertScalar(x = stattest, type = "character",
                   validValues = c("limma", "ttest", "proDA", "none"))

R/checkArgumentsMaxQuant.R

@@ -4,14 +4,13 @@
 #' @noRd
 #' @author Charlotte Soneson
 #'
-#' @importFrom MsCoreUtils normalizeMethods
 .checkArgumentsMaxQuant <- function(
     templateRmd, outputDir, outputBaseName, reportTitle, reportAuthor,
     forceOverwrite, experimentInfo, species, mqFile, mqParameterFile,
     idCol, labelCol, geneIdCol, proteinIdCol, stringIdCol, extraFeatureCols,
-    iColPattern, sampleAnnot, includeOnlySamples, excludeSamples, minScore,
-    minPeptides, imputeMethod, assaysForExport, addAbundanceValues, 
-    addHeatmaps, mergeGroups,
+    iColPattern, sampleAnnot, includeOnlySamples, excludeSamples,
+    imputeMethod, imputeArgs, assaysForExport, addAbundanceValues,
+    addHeatmaps, mergeGroups, filtersSE,
     comparisons, ctrlGroup, allPairwiseComparisons, singleFit,
     subtractBaseline, baselineGroup, normMethod, spikeFeatures, stattest,
     minNbrValidValues, minlFC, samSignificance, nperm, volcanoAdjPvalThr,
@@ -126,19 +125,30 @@
 
     .assertVector(x = linkTableColumns, type = "character", allowNULL = TRUE)
 
-    ## Score thresholds
-    .assertScalar(x = minScore, type = "numeric", allowNULL = TRUE)
-    .assertScalar(x = minPeptides, type = "numeric", allowNULL = TRUE)
+    ## Filter functions
+    .assertVector(x = filtersSE, type = "list")
+    if (length(filtersSE) > 0) {
+        .assertVector(x = names(filtersSE), type = "character")
+        for (f in filtersSE) {
+            stopifnot(is(f, "function"))
+            stopifnot(length(formals(f)) == 1)
+        }
+    }
 
     ## Method choices
     .assertScalar(x = imputeMethod, type = "character",
-                  validValues = c("impSeqRob", "MinProb", "MinProbGlobal"))
+                  validValues = c("impSeqRob", "MinProb", "MinProbGlobal",
+                                  "MinProbOffset", "MinProbGlobalOffset",
+                                  "custom"))
+    .assertVector(x = imputeArgs, type = "list")
     .assertVector(x = assaysForExport, type = "character", allowNULL = TRUE)
     .assertScalar(x = addAbundanceValues, type = "logical")
     .assertScalar(x = addHeatmaps, type = "logical")
     .assertScalar(x = normMethod, type = "character",
-                  validValues = c(MsCoreUtils::normalizeMethods(), "none",
-                                  "center.mean.shared", "center.median.shared"))
+                  validValues = c("center.mean", "center.median",
+                                  "diff.median", "vsn", "none",
+                                  "center.mean.shared", "center.median.shared",
+                                  "diff.mean.shared", "diff.median.shared"))
     .assertVector(x = spikeFeatures, type = "character", allowNULL = TRUE)
     .assertScalar(x = stattest, type = "character",
                   validValues = c("limma", "ttest", "proDA", "none"))