add linting step in dry run

.github/scripts/check_style.R

@@ -0,0 +1,10 @@
+files <- styler::style_pkg(
+    transformers = styler::tidyverse_style(indent_by = 4),
+    dry = "on"
+)
+
+if (any(files$changed)) {
+    message("The following files need styling. Please run:")
+    message("  styler::style_pkg(transformers = styler::tidyverse_style(indent_by = 4))")
+    quit(status = 1)
+}

.github/workflows/dry-run-build.yml

@@ -8,6 +8,13 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
+      - name: Setup R for linting
+        uses: r-lib/actions/setup-r@v2
+      - name: Check style
+        run: |
+          Rscript -e "install.packages('styler')"
+          Rscript -e "install.packages('roxygen2')"
+          Rscript .github/scripts/check_style.R
       - name: Setup R and Bioconductor
         uses: grimbough/bioc-actions/setup-bioc@v1
         with:

R/annotateProteinInfoFromIndra.R

@@ -2,11 +2,11 @@
 #'
 #' This function annotates a data frame with protein information from Indra.
 #'
-#' @param df output of \code{\link[MSstats]{groupComparison}} function's 
-#'      comparisonResult table, which contains a list of proteins and their 
-#'      corresponding p-values, logFCs, along with additional HGNC ID and HGNC 
+#' @param df output of \code{\link[MSstats]{groupComparison}} function's
+#'      comparisonResult table, which contains a list of proteins and their
+#'      corresponding p-values, logFCs, along with additional HGNC ID and HGNC
 #'      name columns
-#' @param proteinIdType A character string specifying the type of protein ID. 
+#' @param proteinIdType A character string specifying the type of protein ID.
 #'      It can be either "Uniprot", "Uniprot_Mnemonic", or "Hgnc_Name".
 #' @return A data frame with the following columns:
 #' \describe{
@@ -24,14 +24,14 @@
 #' head(annotated_df)
 #' @export
 annotateProteinInfoFromIndra <- function(df, proteinIdType) {
-        .validateAnnotateProteinInfoFromIndraInput(df)
-        df <- .populateUniprotIdsInDataFrame(df, proteinIdType)
-        df <- .populateHgncIdsInDataFrame(df, proteinIdType)
-        df <- .populateHgncNamesInDataFrame(df)
-        df <- .populateTranscriptionFactorInfoInDataFrame(df)
-        df <- .populateKinaseInfoInDataFrame(df)
-        df <- .populatePhophataseInfoInDataFrame(df)
-        return(df)
+    .validateAnnotateProteinInfoFromIndraInput(df)
+    df <- .populateUniprotIdsInDataFrame(df, proteinIdType)
+    df <- .populateHgncIdsInDataFrame(df, proteinIdType)
+    df <- .populateHgncNamesInDataFrame(df)
+    df <- .populateTranscriptionFactorInfoInDataFrame(df)
+    df <- .populateKinaseInfoInDataFrame(df)
+    df <- .populatePhophataseInfoInDataFrame(df)
+    return(df)
 }
 
 #' Validate Annotate Protein Info Input
@@ -41,86 +41,87 @@ annotateProteinInfoFromIndra <- function(df, proteinIdType) {
 #' @param df A data frame containing protein information.
 #' @return None. Throws an error if validation fails.
 .validateAnnotateProteinInfoFromIndraInput <- function(df) {
-        if (!"Protein" %in% colnames(df)) {
-                stop("Input dataframe must contain 'Protein' column.")
-        }
+    if (!"Protein" %in% colnames(df)) {
+        stop("Input dataframe must contain 'Protein' column.")
+    }
 }
 
 #' Populate Uniprot IDs in Data Frame
 #'
 #' This function populates the Uniprot IDs in the data frame based on the protein ID type.
 #'
 #' @param df A data frame containing protein information.
-#' @param proteinIdType A character string specifying the type of protein ID. 
+#' @param proteinIdType A character string specifying the type of protein ID.
 #'        It can be either "Uniprot" or "Uniprot_Mnemonic".
 #' @return A data frame with populated Uniprot IDs.
 .populateUniprotIdsInDataFrame <- function(df, proteinIdType) {
-        if ("GlobalProtein" %in% colnames(df)) {
-            protein_ids = unique(as.character(df$GlobalProtein))
-        } else {
-            df$Protein = as.character(df$Protein)
-            df$GlobalProtein = ifelse(grepl("_[A-Z][0-9]", df$Protein),
-                                 gsub("_[A-Z][0-9].*", "", df$Protein, perl = TRUE),
-                                 df$Protein)
-            protein_ids = unique(df$GlobalProtein)
-        }
-        df$UniprotId <- NA
-        if (proteinIdType == "Uniprot") {
-                df$UniprotId <- as.character(df$GlobalProtein)
-        }
-
-        if (proteinIdType == "Uniprot_Mnemonic") {
-                mnemonicProteins <- protein_ids
-                if (length(mnemonicProteins) > 0) {
-                        uniprotMapping <- .callGetUniprotIdsFromUniprotMnemonicIdsApi(as.list(mnemonicProteins))
-                        for (mnemonicId in names(uniprotMapping)) {
-                                if (!is.null(uniprotMapping[[mnemonicId]])) {
-                                        df$UniprotId[df$GlobalProtein == mnemonicId] <- uniprotMapping[[mnemonicId]]
-                                }
-                        }
+    if ("GlobalProtein" %in% colnames(df)) {
+        protein_ids <- unique(as.character(df$GlobalProtein))
+    } else {
+        df$Protein <- as.character(df$Protein)
+        df$GlobalProtein <- ifelse(grepl("_[A-Z][0-9]", df$Protein),
+            gsub("_[A-Z][0-9].*", "", df$Protein, perl = TRUE),
+            df$Protein
+        )
+        protein_ids <- unique(df$GlobalProtein)
+    }
+    df$UniprotId <- NA
+    if (proteinIdType == "Uniprot") {
+        df$UniprotId <- as.character(df$GlobalProtein)
+    }
+
+    if (proteinIdType == "Uniprot_Mnemonic") {
+        mnemonicProteins <- protein_ids
+        if (length(mnemonicProteins) > 0) {
+            uniprotMapping <- .callGetUniprotIdsFromUniprotMnemonicIdsApi(as.list(mnemonicProteins))
+            for (mnemonicId in names(uniprotMapping)) {
+                if (!is.null(uniprotMapping[[mnemonicId]])) {
+                    df$UniprotId[df$GlobalProtein == mnemonicId] <- uniprotMapping[[mnemonicId]]
                 }
+            }
         }
-
-        if (proteinIdType == "Hgnc_Name") {
-            df$UniprotId <- NA
-        }
-        return(df)
+    }
+
+    if (proteinIdType == "Hgnc_Name") {
+        df$UniprotId <- NA
+    }
+    return(df)
 }
 
 #' Populate HGNC IDs in Data Frame
 #'
 #' This function populates the HGNC IDs in the data frame based on the Uniprot IDs.
 #'
 #' @param df A data frame containing protein information.
-#' @param proteinIdType A character string specifying the type of protein ID. 
+#' @param proteinIdType A character string specifying the type of protein ID.
 #'        It can be either "Uniprot", "Uniprot_Mnemonic", or "Hgnc_Name".
 #' @return A data frame with populated HGNC IDs.
 .populateHgncIdsInDataFrame <- function(df, proteinIdType) {
-        df$HgncId <- NA
-        if (proteinIdType == "Uniprot" || proteinIdType == "Uniprot_Mnemonic") {
-            validMask <- !is.na(df$UniprotId)
-            validUniprots <- unique(df$UniprotId[validMask])
-            if (length(validUniprots) > 0) {
-                hgncMapping <- .callGetHgncIdsFromUniprotIdsApi(as.list(validUniprots))
-                for (uniprotId in names(hgncMapping)) {
-                    if (!is.null(hgncMapping[[uniprotId]])) {
-                        df$HgncId[df$UniprotId == uniprotId] <- hgncMapping[[uniprotId]]
-                    }
+    df$HgncId <- NA
+    if (proteinIdType == "Uniprot" || proteinIdType == "Uniprot_Mnemonic") {
+        validMask <- !is.na(df$UniprotId)
+        validUniprots <- unique(df$UniprotId[validMask])
+        if (length(validUniprots) > 0) {
+            hgncMapping <- .callGetHgncIdsFromUniprotIdsApi(as.list(validUniprots))
+            for (uniprotId in names(hgncMapping)) {
+                if (!is.null(hgncMapping[[uniprotId]])) {
+                    df$HgncId[df$UniprotId == uniprotId] <- hgncMapping[[uniprotId]]
                 }
             }
-        } else {
-            hgncNames <- unique(df$GlobalProtein)
-            if (length(hgncNames) > 0) {
-                hgncMapping <- .callGetHgncIdsFromGildaApi(as.list(hgncNames))
-                for (hgncName in names(hgncMapping)) {
-                    if (!is.null(hgncMapping[[hgncName]])) {
-                        df$HgncId[df$GlobalProtein == hgncName] <- hgncMapping[[hgncName]]
-                    }
+        }
+    } else {
+        hgncNames <- unique(df$GlobalProtein)
+        if (length(hgncNames) > 0) {
+            hgncMapping <- .callGetHgncIdsFromGildaApi(as.list(hgncNames))
+            for (hgncName in names(hgncMapping)) {
+                if (!is.null(hgncMapping[[hgncName]])) {
+                    df$HgncId[df$GlobalProtein == hgncName] <- hgncMapping[[hgncName]]
                 }
             }
         }
-
-        return(df)
+    }
+
+    return(df)
 }
 
 #' Populate HGNC Names in Data Frame
@@ -130,18 +131,18 @@ annotateProteinInfoFromIndra <- function(df, proteinIdType) {
 #' @param df A data frame containing protein information.
 #' @return A data frame with populated HGNC names.
 .populateHgncNamesInDataFrame <- function(df) {
-        df$HgncName <- NA
-        validHgncMask <- !is.na(df$HgncId)
-        validHgncs <- unique(df$HgncId[validHgncMask])
-        if (length(validHgncs) > 0) {
-                nameMapping <- .callGetHgncNamesFromHgncIdsApi(as.list(validHgncs))
-                for (hgncId in names(nameMapping)) {
-                        if (!is.null(nameMapping[[hgncId]])) {
-                                df$HgncName[df$HgncId == hgncId] <- nameMapping[[hgncId]]
-                        }
-                }
+    df$HgncName <- NA
+    validHgncMask <- !is.na(df$HgncId)
+    validHgncs <- unique(df$HgncId[validHgncMask])
+    if (length(validHgncs) > 0) {
+        nameMapping <- .callGetHgncNamesFromHgncIdsApi(as.list(validHgncs))
+        for (hgncId in names(nameMapping)) {
+            if (!is.null(nameMapping[[hgncId]])) {
+                df$HgncName[df$HgncId == hgncId] <- nameMapping[[hgncId]]
+            }
         }
-        return(df)
+    }
+    return(df)
 }
 
 #' Populate Transcription Factor Info in Data Frame
@@ -151,19 +152,19 @@ annotateProteinInfoFromIndra <- function(df, proteinIdType) {
 #' @param df A data frame containing protein information.
 #' @return A data frame with populated transcription factor information.
 .populateTranscriptionFactorInfoInDataFrame <- function(df) {
-        df$IsTranscriptionFactor <- NA
-        validNameMask <- !is.na(df$HgncName)
-        validNames <- unique(df$HgncName[validNameMask])
-        if (length(validNames) > 0) {
-                validNamesList <- as.list(validNames)
-                charMapping <- .callIsTranscriptionFactorApi(validNamesList)
-                for (hgncName in names(charMapping)) {
-                        if (!is.null(charMapping[[hgncName]])) {
-                                df$IsTranscriptionFactor[df$HgncName == hgncName] <- charMapping[[hgncName]]
-                        }
-                }
+    df$IsTranscriptionFactor <- NA
+    validNameMask <- !is.na(df$HgncName)
+    validNames <- unique(df$HgncName[validNameMask])
+    if (length(validNames) > 0) {
+        validNamesList <- as.list(validNames)
+        charMapping <- .callIsTranscriptionFactorApi(validNamesList)
+        for (hgncName in names(charMapping)) {
+            if (!is.null(charMapping[[hgncName]])) {
+                df$IsTranscriptionFactor[df$HgncName == hgncName] <- charMapping[[hgncName]]
+            }
         }
-        return(df)
+    }
+    return(df)
 }
 
 #' Populate Kinase Info in Data Frame
@@ -173,19 +174,19 @@ annotateProteinInfoFromIndra <- function(df, proteinIdType) {
 #' @param df A data frame containing protein information.
 #' @return A data frame with populated kinase information.
 .populateKinaseInfoInDataFrame <- function(df) {
-        df$IsKinase <- NA
-        validNameMask <- !is.na(df$HgncName)
-        validNames <- unique(df$HgncName[validNameMask])
-        if (length(validNames) > 0) {
-                validNamesList <- as.list(validNames)
-                charMapping <- .callIsKinaseApi(validNamesList)
-                for (hgncName in names(charMapping)) {
-                        if (!is.null(charMapping[[hgncName]])) {
-                                df$IsKinase[df$HgncName == hgncName] <- charMapping[[hgncName]]
-                        }
-                }
+    df$IsKinase <- NA
+    validNameMask <- !is.na(df$HgncName)
+    validNames <- unique(df$HgncName[validNameMask])
+    if (length(validNames) > 0) {
+        validNamesList <- as.list(validNames)
+        charMapping <- .callIsKinaseApi(validNamesList)
+        for (hgncName in names(charMapping)) {
+            if (!is.null(charMapping[[hgncName]])) {
+                df$IsKinase[df$HgncName == hgncName] <- charMapping[[hgncName]]
+            }
         }
-        return(df)
+    }
+    return(df)
 }
 
 #' Populate Phosphatase Info in Data Frame
@@ -195,17 +196,17 @@ annotateProteinInfoFromIndra <- function(df, proteinIdType) {
 #' @param df A data frame containing protein information.
 #' @return A data frame with populated phosphatase information.
 .populatePhophataseInfoInDataFrame <- function(df) {
-        df$IsPhosphatase <- NA
-        validNameMask <- !is.na(df$HgncName)
-        validNames <- unique(df$HgncName[validNameMask])
-        if (length(validNames) > 0) {
-                validNamesList <- as.list(validNames)
-                charMapping <- .callIsPhosphataseApi(validNamesList)
-                for (hgncName in names(charMapping)) {
-                        if (!is.null(charMapping[[hgncName]])) {
-                                df$IsPhosphatase[df$HgncName == hgncName] <- charMapping[[hgncName]]
-                        }
-                }
+    df$IsPhosphatase <- NA
+    validNameMask <- !is.na(df$HgncName)
+    validNames <- unique(df$HgncName[validNameMask])
+    if (length(validNames) > 0) {
+        validNamesList <- as.list(validNames)
+        charMapping <- .callIsPhosphataseApi(validNamesList)
+        for (hgncName in names(charMapping)) {
+            if (!is.null(charMapping[[hgncName]])) {
+                df$IsPhosphatase[df$HgncName == hgncName] <- charMapping[[hgncName]]
+            }
         }
-        return(df)
-}
+    }
+    return(df)
+}