Merge pull request #40 from fmicompbio/hgvs-names

HGVS names

Author: mbstadler

.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_15", cran: "https://demo.rstudiopm.com/all/__linux__/xenial/latest"}
+        - { os: ubuntu-latest, image: "bioconductor/bioconductor_docker:RELEASE_3_16", cran: "https://demo.rstudiopm.com/all/__linux__/xenial/latest"}
 
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: mutscan
 Title: Preprocessing and Analysis of Deep Mutational Scanning Data
-Version: 0.2.34
+Version: 0.2.35
 Authors@R: 
     c(person(given = "Charlotte",
              family = "Soneson",

NEWS.md

@@ -1,3 +1,11 @@
+# mutscan 0.2.35
+
+* Add alternative names for variants (including HGVS identifiers)
+
+# mutscan 0.2.34
+
+* Expand examples in function documentation
+
 # mutscan 0.2.33
 
 * Replace Matrix.utils::aggregate.Matrix (removed from CRAN) by DelayedArray::rowsum

R/RcppExports.R

@@ -32,6 +32,14 @@ translateString <- function(s) {
     .Call(`_mutscan_translateString`, s)
 }
 
+makeBaseHGVS <- function(mutationsSorted, mutNameDelimiter, wtSeq, varSeq) {
+    .Call(`_mutscan_makeBaseHGVS`, mutationsSorted, mutNameDelimiter, wtSeq, varSeq)
+}
+
+test_makeAAHGVS <- function(mutationsSorted, mutNameDelimiter, wtSeq) {
+    .Call(`_mutscan_test_makeAAHGVS`, mutationsSorted, mutNameDelimiter, wtSeq)
+}
+
 test_decomposeRead <- function(sseq, squal, elements, elementLengths, primerSeqs, umiSeq, varSeq, varQual, varLengths, constSeq, constQual, nNoPrimer, nReadWrongLength) {
     .Call(`_mutscan_test_decomposeRead`, sseq, squal, elements, elementLengths, primerSeqs, umiSeq, varSeq, varQual, varLengths, constSeq, constQual, nNoPrimer, nReadWrongLength)
 }

R/collapseMutantsByAA.R

@@ -58,8 +58,13 @@ collapseMutantsByAA <- function(se, nameCol = "mutantNameAA") {
     rd <- mergeValues(SummarizedExperiment::rowData(se)[[nameCol]],
                       SummarizedExperiment::rowData(se)$sequence) %>%
         stats::setNames(c(nameCol, "sequence"))
-    for (v in c("mutantName", "sequenceAA", "mutationTypes",
-                "nbrMutBases", "nbrMutCodons", "nbrMutAAs")) {
+    for (v in setdiff(
+        intersect(c("mutantName", "mutantNameBase", "mutantNameBaseHGVS",
+                    "mutantNameCodon", "mutantNameAA", "mutantNameAAHGVS",
+                    "sequenceAA", "mutationTypes",
+                    "nbrMutBases", "nbrMutCodons", "nbrMutAAs"),
+                  colnames(SummarizedExperiment::rowData(se))),
+        nameCol)) {
         tmp <- mergeValues(SummarizedExperiment::rowData(se)[[nameCol]],
                            SummarizedExperiment::rowData(se)[[v]])
         rd[[v]] <- tmp$valueColl[match(rd[[nameCol]], tmp$mutantNameColl)]

R/digestFastqs.R

@@ -193,10 +193,18 @@
 #' \item{summaryTable}{A \code{data.frame} that contains, for each observed
 #' mutation combination, the corresponding variable region sequences (or pair of
 #' sequences), the number of observed such sequences, and the number of unique
-#' UMIs observed for the sequence. It also has a column named 'maxNbrReads',
-#' which contains the number of reads for the most frequent observed sequence
+#' UMIs observed for the sequence. It also has additional columns: 'maxNbrReads'
+#' contains the number of reads for the most frequent observed sequence
 #' represented by the feature (only relevant if similar variable regions are
-#' collapsed).}
+#' collapsed). 'nbrMutBases', 'nbrMutCodons' and 'nbrMutAAs' give the number of
+#' mutated bases, codons or amino acids in each variant. Alternative variant
+#' names based on base, codon or amino acid sequence are provided in columns
+#' 'mutantNameBase', 'mutantNameCodon', 'mutantNameAA'. In addition,
+#' 'mutantNameBaseHGVS' and 'mutantNameAAHGVS' give base- and amino acid-based
+#' names following the HGVS nomenclature (https://varnomen.hgvs.org/). Please
+#' note that the provided reference sequence names are used for the HGVS
+#' sequence identifiers. It is up to the user to use appropriately named 
+#' reference sequences in order to obtain valid HGVS variant names.}
 #' \item{filterSummary}{A \code{data.frame} that contains the number of input
 #' reads, the number of reads filtered out in the processing, and the number of
 #' retained reads. The filters are named according to the convention

R/summarizeExperiment.R

@@ -148,8 +148,12 @@ summarizeExperiment <- function(x, coldata, countType = "umis") {
     ## Also here, each column can contain multiple values separated with ,
     ## (e.g. if variable sequences were collapsed to WT in digestFastqs)
     ## ------------------------------------------------------------------------
-    for (v in c("nbrMutBases", "nbrMutCodons", "nbrMutAAs",
-                "sequenceAA", "mutantNameAA", "mutationTypes", "varLengths")) {
+    for (v in intersect(c("nbrMutBases", "nbrMutCodons", "nbrMutAAs", 
+                          "mutantNameBase", "mutantNameBaseHGVS",
+                          "mutantNameCodon", "mutantNameAA", "mutantNameAAHGVS",
+                          "sequenceAA", "mutationTypes",
+                          "varLengths"),
+                        colnames(tmpdf))) {
         tmp <- mergeValues(tmpdf$mutantName, tmpdf[[v]]) %>%
             stats::setNames(c("mutantName", v))
         allSequences[[v]] <- tmp[[v]][match(allSequences$mutantName,

inst/extdata/GSE102901_cis_se.rds

@@ -37,16 +37,43 @@ BEGIN_RCPP
 END_RCPP
 }
 // translateString
-std::string translateString(std::string& s);
+std::string translateString(const std::string& s);
 RcppExport SEXP _mutscan_translateString(SEXP sSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
     Rcpp::RNGScope rcpp_rngScope_gen;
-    Rcpp::traits::input_parameter< std::string& >::type s(sSEXP);
+    Rcpp::traits::input_parameter< const std::string& >::type s(sSEXP);
     rcpp_result_gen = Rcpp::wrap(translateString(s));
     return rcpp_result_gen;
 END_RCPP
 }
+// makeBaseHGVS
+std::string makeBaseHGVS(const std::vector<std::string> mutationsSorted, const std::string mutNameDelimiter, const std::string wtSeq, const std::string varSeq);
+RcppExport SEXP _mutscan_makeBaseHGVS(SEXP mutationsSortedSEXP, SEXP mutNameDelimiterSEXP, SEXP wtSeqSEXP, SEXP varSeqSEXP) {
+BEGIN_RCPP
+    Rcpp::RObject rcpp_result_gen;
+    Rcpp::RNGScope rcpp_rngScope_gen;
+    Rcpp::traits::input_parameter< const std::vector<std::string> >::type mutationsSorted(mutationsSortedSEXP);
+    Rcpp::traits::input_parameter< const std::string >::type mutNameDelimiter(mutNameDelimiterSEXP);
+    Rcpp::traits::input_parameter< const std::string >::type wtSeq(wtSeqSEXP);
+    Rcpp::traits::input_parameter< const std::string >::type varSeq(varSeqSEXP);
+    rcpp_result_gen = Rcpp::wrap(makeBaseHGVS(mutationsSorted, mutNameDelimiter, wtSeq, varSeq));
+    return rcpp_result_gen;
+END_RCPP
+}
+// test_makeAAHGVS
+std::string test_makeAAHGVS(const std::vector<std::string> mutationsSorted, const std::string mutNameDelimiter, const std::string wtSeq);
+RcppExport SEXP _mutscan_test_makeAAHGVS(SEXP mutationsSortedSEXP, SEXP mutNameDelimiterSEXP, SEXP wtSeqSEXP) {
+BEGIN_RCPP
+    Rcpp::RObject rcpp_result_gen;
+    Rcpp::RNGScope rcpp_rngScope_gen;
+    Rcpp::traits::input_parameter< const std::vector<std::string> >::type mutationsSorted(mutationsSortedSEXP);
+    Rcpp::traits::input_parameter< const std::string >::type mutNameDelimiter(mutNameDelimiterSEXP);
+    Rcpp::traits::input_parameter< const std::string >::type wtSeq(wtSeqSEXP);
+    rcpp_result_gen = Rcpp::wrap(test_makeAAHGVS(mutationsSorted, mutNameDelimiter, wtSeq));
+    return rcpp_result_gen;
+END_RCPP
+}
 // test_decomposeRead
 List test_decomposeRead(const std::string sseq, const std::string squal, const std::string elements, const std::vector<int> elementLengths, const std::vector<std::string> primerSeqs, std::string umiSeq, std::string varSeq, std::string varQual, std::vector<int> varLengths, std::string constSeq, std::string constQual, int nNoPrimer, int nReadWrongLength);
 RcppExport SEXP _mutscan_test_decomposeRead(SEXP sseqSEXP, SEXP squalSEXP, SEXP elementsSEXP, SEXP elementLengthsSEXP, SEXP primerSeqsSEXP, SEXP umiSeqSEXP, SEXP varSeqSEXP, SEXP varQualSEXP, SEXP varLengthsSEXP, SEXP constSeqSEXP, SEXP constQualSEXP, SEXP nNoPrimerSEXP, SEXP nReadWrongLengthSEXP) {
@@ -243,6 +270,8 @@ static const R_CallMethodDef CallEntries[] = {
     {"_mutscan_calcNearestStringDist", (DL_FUNC) &_mutscan_calcNearestStringDist, 3},
     {"_mutscan_compareCodonPositions", (DL_FUNC) &_mutscan_compareCodonPositions, 3},
     {"_mutscan_translateString", (DL_FUNC) &_mutscan_translateString, 1},
+    {"_mutscan_makeBaseHGVS", (DL_FUNC) &_mutscan_makeBaseHGVS, 4},
+    {"_mutscan_test_makeAAHGVS", (DL_FUNC) &_mutscan_test_makeAAHGVS, 3},
     {"_mutscan_test_decomposeRead", (DL_FUNC) &_mutscan_test_decomposeRead, 13},
     {"_mutscan_test_mergeReadPairPartial", (DL_FUNC) &_mutscan_test_mergeReadPairPartial, 12},
     {"_mutscan_findClosestRefSeq", (DL_FUNC) &_mutscan_findClosestRefSeq, 4},