Merge pull request #9 from fmicompbio/add-seq

Add sequence windows
fmicompbio · Jul 2, 2023 · 27eb897 · 27eb897
2 parents f1e5580 + 87c5e59
commit 27eb897
Show file tree

Hide file tree

Showing 112 changed files with 3,100 additions and 1,201 deletions.
diff --git a/.github/workflows/R-CMD-check.yaml b/.github/workflows/R-CMD-check.yaml
@@ -19,7 +19,7 @@ jobs:
         config:
         - { os: macOS-latest, bioc: 'release', curlConfigPath: '/usr/bin/'}
         - { os: windows-latest, bioc: 'release'}
-        - { os: ubuntu-latest, image: "bioconductor/bioconductor_docker:RELEASE_3_16", cran: "https://demo.rstudiopm.com/all/__linux__/xenial/latest"}
+        - { os: ubuntu-latest, image: "bioconductor/bioconductor_docker:RELEASE_3_17", cran: "https://demo.rstudiopm.com/all/__linux__/xenial/latest"}
 
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: einprot
 Type: Package
 Title: A collection of proteomics analysis utilities and workflows
-Version: 0.7.1
+Version: 0.7.4
 Authors@R: c(
     person("Charlotte", "Soneson", email = "charlotte.soneson@fmi.ch", 
            role = c("aut", "cre"), comment = c(ORCID = "0000-0003-3833-2169")),
@@ -12,7 +12,7 @@ Authors@R: c(
            role = c("cph")))
 Description: The einprot package contains utilities for performing analysis 
     of proteomics data. It provides end-to-end analysis workflows for data 
-    quantified using MaxQuant and Proteome Discoverer, as well as 
+    quantified using MaxQuant, FragPipe and Proteome Discoverer. It also has 
     functionality for assembling databases of known protein complexes. 
 License: MIT + file LICENSE
 Encoding: UTF-8
@@ -70,7 +70,12 @@ Imports:
     tidyselect,
     GGally,
     scuttle,
-    stringdist
+    stringdist,
+    shiny,
+    writexl,
+    tools,
+    grid,
+    ggseqlogo
 RoxygenNote: 7.2.3
 Suggests: 
     BiocManager,
@@ -79,3 +84,4 @@ Suggests:
     matrixStats
 Config/testthat/edition: 3
 VignetteBuilder: knitr
+biocViews: Proteomics, DataImport
diff --git a/NAMESPACE b/NAMESPACE
@@ -14,6 +14,7 @@ export(filterFragPipe)
 export(filterMaxQuant)
 export(filterPDTMT)
 export(fixFeatureIds)
+export(formatTableColumns)
 export(getCalibrationFrompdAnalysis)
 export(getColumnNames)
 export(getContaminantsDatabaseFrompdAnalysis)
@@ -34,6 +35,8 @@ export(getUniProtToIDMapping)
 export(getValidationInfoFrompdAnalysis)
 export(importExperiment)
 export(listComplexDBs)
+export(makeAbundanceExport)
+export(makeAbundanceHeatmap)
 export(makeComplexDB)
 export(makeDbLinkTable)
 export(makeIntensityBoxplots)
@@ -61,14 +64,17 @@ export(runPDTMTptmAnalysis)
 export(runPTMTest)
 export(runTest)
 export(saText)
+export(seqLogoApp)
 export(testText)
 import(STRINGdb)
 importFrom(BiocSingular,ExactParam)
 importFrom(ComplexHeatmap,Heatmap)
 importFrom(ComplexHeatmap,columnAnnotation)
 importFrom(ComplexHeatmap,draw)
 importFrom(ComplexUpset,upset)
+importFrom(DT,DTOutput)
 importFrom(DT,datatable)
+importFrom(DT,renderDT)
 importFrom(ExploreModelMatrix,VisualizeDesign)
 importFrom(GGally,ggpairs)
 importFrom(IRanges,CharacterList)
@@ -108,6 +114,7 @@ importFrom(dplyr,everything)
 importFrom(dplyr,filter)
 importFrom(dplyr,full_join)
 importFrom(dplyr,group_by)
+importFrom(dplyr,if_any)
 importFrom(dplyr,last_col)
 importFrom(dplyr,left_join)
 importFrom(dplyr,matches)
@@ -157,6 +164,7 @@ importFrom(ggplot2,geom_smooth)
 importFrom(ggplot2,geom_text)
 importFrom(ggplot2,geom_vline)
 importFrom(ggplot2,ggplot)
+importFrom(ggplot2,ggsave)
 importFrom(ggplot2,ggtitle)
 importFrom(ggplot2,labs)
 importFrom(ggplot2,layer_data)
@@ -174,8 +182,11 @@ importFrom(ggplot2,theme)
 importFrom(ggplot2,theme_bw)
 importFrom(ggplot2,theme_minimal)
 importFrom(ggrepel,geom_text_repel)
+importFrom(ggseqlogo,ggseqlogo)
+importFrom(ggseqlogo,theme_logo)
 importFrom(grDevices,dev.off)
 importFrom(grDevices,pdf)
+importFrom(grid,gpar)
 importFrom(htmltools,tagList)
 importFrom(iSEEu,registerAveAbFields)
 importFrom(iSEEu,registerFeatureSetCollections)
@@ -215,6 +226,18 @@ importFrom(scales,percent)
 importFrom(scales,percent_format)
 importFrom(scater,runPCA)
 importFrom(scuttle,makePerCellDF)
+importFrom(shiny,downloadButton)
+importFrom(shiny,downloadHandler)
+importFrom(shiny,fluidPage)
+importFrom(shiny,mainPanel)
+importFrom(shiny,plotOutput)
+importFrom(shiny,reactive)
+importFrom(shiny,renderPlot)
+importFrom(shiny,renderText)
+importFrom(shiny,shinyApp)
+importFrom(shiny,sidebarLayout)
+importFrom(shiny,sidebarPanel)
+importFrom(shiny,textOutput)
 importFrom(stats,median)
 importFrom(stats,model.matrix)
 importFrom(stats,p.adjust)
@@ -231,6 +254,7 @@ importFrom(tidyr,pivot_wider)
 importFrom(tidyr,separate_rows)
 importFrom(tidyr,unnest)
 importFrom(tidyselect,any_of)
+importFrom(tools,file_ext)
 importFrom(utils,combn)
 importFrom(utils,download.file)
 importFrom(utils,head)
@@ -241,6 +265,8 @@ importFrom(utils,stack)
 importFrom(utils,tail)
 importFrom(utils,unzip)
 importFrom(utils,write.table)
+importFrom(utils,zip)
+importFrom(writexl,write_xlsx)
 importFrom(xfun,Rscript_call)
 importFrom(xml2,read_xml)
 importFrom(xml2,xml_attr)

diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,25 @@
+# einprot 0.7.4
+
+* Add argument to allow limiting the labeling to only features with positive/negative logFCs
+* Add function to generate heatmaps
+* Add function to create summary of abundance values for significant features
+* Add argument to define the assays(s) to use for exported values and barplots
+* Harmonize treatment of merged groups in runTest and plotVolcano
+* Sort exported test results by p-value instead of logFC
+
+# einprot 0.7.3
+
+* Combine download buttons and pagelength selection for tables
+* Add check and stop if no features are left after filtering
+
+# einprot 0.7.2
+
+* Add option to export link table to csv
+* Add summary table with sequence windows to PTM workflow
+* Add shiny app to generate sequence logos for PTMs
+* Add link to workflow overview in table of contents
+* Include link to top feature sets for each comparison in table of contents
+
 # einprot 0.7.1
 
 * Add scale and subset_row arguments to doPCA

diff --git a/R/addSampleAnnots.R b/R/addSampleAnnots.R
@@ -1,24 +1,33 @@
 #' Add sample annotations to SummarizedExperiment object
 #'
+#' Add sample annotations from an external annotation table to an existing
+#' `SummarizedExperiment` object.
+#'
 #' @param sce A \code{SummarizedExperiment} object (or a derivative).
 #' @param sampleAnnot A \code{data.frame} with sample annotations. Must
 #'     have at least columns named \code{sample} (which must contain
 #'     all the column names of \code{sce}) and \code{group} (which contains
 #'     the group assignment for each sample).
 #'
-#' @return An object of the same type as \code{sce} with additional sample
+#' @returns An object of the same type as \code{sce} with additional sample
 #'     annotations.
 #'
 #' @examples
+#' ## Import example data
 #' mqFile <- system.file("extdata", "mq_example", "1356_proteinGroups.txt",
 #'                       package = "einprot")
 #' samples <- c("Adnp_IP04", "Adnp_IP05", "Adnp_IP06",
 #'              "Chd4BF_IP07", "Chd4BF_IP08", "Chd4BF_IP09",
 #'              "RBC_ctrl_IP01", "RBC_ctrl_IP02", "RBC_ctrl_IP03")
 #' out <- importExperiment(inFile = mqFile, iColPattern = "^iBAQ\\.",
 #'                         includeOnlySamples = samples)
+#'
+#' ## Define sample annotations
 #' sampleAnnot <- data.frame(sample = samples,
-#'                           group = gsub("_IP.*", "", samples))
+#'                           group = gsub("_IP.*", "", samples),
+#'                           random = sample(seq_len(9), 9))
+#'
+#' ## Add sample annotations to SCE
 #' sce <- addSampleAnnots(out$sce, sampleAnnot = sampleAnnot)
 #' SummarizedExperiment::colData(sce)  ## group information added to sce
 #'

diff --git a/R/checkArgumentsFragPipe.R b/R/checkArgumentsFragPipe.R
@@ -9,14 +9,14 @@
     templateRmd, outputDir, outputBaseName, reportTitle, reportAuthor,
     forceOverwrite, experimentInfo, species, fragpipeDir,
     idCol, labelCol, geneIdCol, proteinIdCol, stringIdCol,
-    iColPattern, sampleAnnot, includeOnlySamples,
-    excludeSamples, minScore, minPeptides, imputeMethod, mergeGroups,
+    iColPattern, sampleAnnot, includeOnlySamples, excludeSamples, minScore,
+    minPeptides, imputeMethod, assaysForExport, mergeGroups,
     comparisons, ctrlGroup, allPairwiseComparisons, singleFit,
     subtractBaseline, baselineGroup, normMethod, spikeFeatures, stattest,
     minNbrValidValues, minlFC, samSignificance, nperm, volcanoAdjPvalThr,
-    volcanoLog2FCThr, volcanoMaxFeatures, volcanoS0, volcanoFeaturesToLabel,
-    addInteractiveVolcanos, interactiveDisplayColumns, interactiveGroupColumn,
-    complexFDRThr, maxNbrComplexesToPlot, seed,
+    volcanoLog2FCThr, volcanoMaxFeatures, volcanoLabelSign, volcanoS0,
+    volcanoFeaturesToLabel, addInteractiveVolcanos, interactiveDisplayColumns,
+    interactiveGroupColumn, complexFDRThr, maxNbrComplexesToPlot, seed,
     includeFeatureCollections, minSizeToKeepSet, customComplexes,
     complexSpecies, complexDbPath, stringVersion, stringDir, linkTableColumns,
     customYml, doRender
@@ -135,6 +135,7 @@
     ## Method choices
     .assertScalar(x = imputeMethod, type = "character",
                   validValues = c("impSeqRob", "MinProb"))
+    .assertVector(x = assaysForExport, type = "character", allowNULL = TRUE)
     .assertScalar(x = normMethod, type = "character",
                   validValues = c(MsCoreUtils::normalizeMethods(), "none"))
     .assertVector(x = spikeFeatures, type = "character", allowNULL = TRUE)
@@ -149,18 +150,23 @@
     .assertScalar(x = volcanoAdjPvalThr, type = "numeric", rngIncl = c(0, 1))
     .assertScalar(x = volcanoLog2FCThr, type = "numeric", rngIncl = c(0, Inf))
     .assertScalar(x = volcanoMaxFeatures, type = "numeric", rngIncl = c(0, Inf))
+    .assertScalar(x = volcanoLabelSign, type = "character",
+                  validValues = c("both", "pos", "neg"))
     .assertScalar(x = volcanoS0, type = "numeric", rngIncl = c(0, Inf))
     .assertScalar(x = complexFDRThr, type = "numeric", rngIncl = c(0, 1))
-    .assertScalar(x = maxNbrComplexesToPlot, type = "numeric", rngIncl = c(0, Inf))
+    .assertScalar(x = maxNbrComplexesToPlot, type = "numeric",
+                  rngIncl = c(0, Inf))
     .assertScalar(x = minSizeToKeepSet, type = "numeric", rngIncl = c(0, Inf))
     .assertVector(x = volcanoFeaturesToLabel, type = "character")
     .assertVector(x = mergeGroups, type = "list")
     .assertVector(x = comparisons, type = "list")
     .assertScalar(x = ctrlGroup, type = "character")
     .assertScalar(x = allPairwiseComparisons, type = "logical")
     .assertScalar(x = addInteractiveVolcanos, type = "logical")
-    .assertVector(x = interactiveDisplayColumns, type = "character", allowNULL = TRUE)
-    .assertScalar(x = interactiveGroupColumn, type = "character", allowNULL = TRUE)
+    .assertVector(x = interactiveDisplayColumns, type = "character",
+                  allowNULL = TRUE)
+    .assertScalar(x = interactiveGroupColumn, type = "character",
+                  allowNULL = TRUE)
     .assertScalar(x = singleFit, type = "logical")
     .assertScalar(x = subtractBaseline, type = "logical")
     .assertScalar(x = baselineGroup, type = "character")

diff --git a/R/checkArgumentsMaxQuant.R b/R/checkArgumentsMaxQuant.R
@@ -9,14 +9,14 @@
     templateRmd, outputDir, outputBaseName, reportTitle, reportAuthor,
     forceOverwrite, experimentInfo, species, mqFile, mqParameterFile,
     idCol, labelCol, geneIdCol, proteinIdCol, stringIdCol,
-    iColPattern, sampleAnnot, includeOnlySamples,
-    excludeSamples, minScore, minPeptides, imputeMethod, mergeGroups,
+    iColPattern, sampleAnnot, includeOnlySamples, excludeSamples, minScore,
+    minPeptides, imputeMethod, assaysForExport, mergeGroups,
     comparisons, ctrlGroup, allPairwiseComparisons, singleFit,
     subtractBaseline, baselineGroup, normMethod, spikeFeatures, stattest,
     minNbrValidValues, minlFC, samSignificance, nperm, volcanoAdjPvalThr,
-    volcanoLog2FCThr, volcanoMaxFeatures, volcanoS0, volcanoFeaturesToLabel,
-    addInteractiveVolcanos, interactiveDisplayColumns, interactiveGroupColumn,
-    complexFDRThr, maxNbrComplexesToPlot, seed,
+    volcanoLog2FCThr, volcanoMaxFeatures, volcanoLabelSign, volcanoS0,
+    volcanoFeaturesToLabel, addInteractiveVolcanos, interactiveDisplayColumns,
+    interactiveGroupColumn, complexFDRThr, maxNbrComplexesToPlot, seed,
     includeFeatureCollections, minSizeToKeepSet, customComplexes,
     complexSpecies, complexDbPath, stringVersion, stringDir, linkTableColumns,
     customYml, doRender
@@ -120,6 +120,7 @@
     ## Method choices
     .assertScalar(x = imputeMethod, type = "character",
                   validValues = c("impSeqRob", "MinProb"))
+    .assertVector(x = assaysForExport, type = "character", allowNULL = TRUE)
     .assertScalar(x = normMethod, type = "character",
                   validValues = c(MsCoreUtils::normalizeMethods(), "none"))
     .assertVector(x = spikeFeatures, type = "character", allowNULL = TRUE)
@@ -134,18 +135,23 @@
     .assertScalar(x = volcanoAdjPvalThr, type = "numeric", rngIncl = c(0, 1))
     .assertScalar(x = volcanoLog2FCThr, type = "numeric", rngIncl = c(0, Inf))
     .assertScalar(x = volcanoMaxFeatures, type = "numeric", rngIncl = c(0, Inf))
+    .assertScalar(x = volcanoLabelSign, type = "character",
+                  validValues = c("both", "pos", "neg"))
     .assertScalar(x = volcanoS0, type = "numeric", rngIncl = c(0, Inf))
     .assertScalar(x = complexFDRThr, type = "numeric", rngIncl = c(0, 1))
-    .assertScalar(x = maxNbrComplexesToPlot, type = "numeric", rngIncl = c(0, Inf))
+    .assertScalar(x = maxNbrComplexesToPlot, type = "numeric",
+                  rngIncl = c(0, Inf))
     .assertScalar(x = minSizeToKeepSet, type = "numeric", rngIncl = c(0, Inf))
     .assertVector(x = volcanoFeaturesToLabel, type = "character")
     .assertVector(x = mergeGroups, type = "list")
     .assertVector(x = comparisons, type = "list")
     .assertScalar(x = ctrlGroup, type = "character")
     .assertScalar(x = allPairwiseComparisons, type = "logical")
     .assertScalar(x = addInteractiveVolcanos, type = "logical")
-    .assertVector(x = interactiveDisplayColumns, type = "character", allowNULL = TRUE)
-    .assertScalar(x = interactiveGroupColumn, type = "character", allowNULL = TRUE)
+    .assertVector(x = interactiveDisplayColumns, type = "character",
+                  allowNULL = TRUE)
+    .assertScalar(x = interactiveGroupColumn, type = "character",
+                  allowNULL = TRUE)
     .assertScalar(x = singleFit, type = "logical")
     .assertScalar(x = subtractBaseline, type = "logical")
     .assertScalar(x = baselineGroup, type = "character")