migrated fasta utils

R/bio/bioinfo_commons.R

+#library(BiocGenerics, quietly=T, warn.conflicts=F )
+#library(Biostrings, quietly=T)
+#require.auto(BiocGenerics )x
+
+require.auto(Biostrings)
+
+
+read.fasta <- function(fileName){
+    ## read a fasta file as data.fram
+
+    fastaData <- readBStringSet(fileName, "fasta")
+    #	fastaDataDF <- as.data.frame(as.character(fastaData), stringsAsFactors=FALSE)
+    fastaDataDF <- data.frame(Sequence=as.character(fastaData), GeneDesc=names(fastaData), stringsAsFactors=FALSE)
+    rownames(fastaDataDF) <- NULL
+    #	names(fastaDataDF)[1] <- "Sequence"
+    return(fastaDataDF)
+}
+
+getSeqLengthFromFasta <- function(fileName){
+    assembly <- mutate(read.fasta(fileName), seq_len=nchar(Sequence))
+    assembly$Sequence = NULL
+    return(assembly)
+}
+
+
+write.fasta <- function(seq_names, sequences, file){
+    fastaData <- AAStringSet(sequences)
+    names(fastaData) <- seq_names;
+    writeXStringSet(fastaData, file=file, format="fasta", width=80)
+}
+

R/core_commons.R

@@ -191,17 +191,8 @@ trimEnd <-function(fileNames, exts=c()){
     fileNames
 }
 
-chopFileExt <-function(fileNames, exts=c()){
-    warning("this method is deprecated. use trimEnd instead")
-    for(fileExt in exts){
-        fileNames <- str_replace(fileNames, paste(".", fileExt, "$",sep=""), "")
-    }
-
-    fileNames
-}
-
-write.delim <- function(df, header=TRUE,...){
-    write.table(df, row.names=FALSE, col.names=header, sep="\t", ...)
+write.delim <- function(df, file, header=TRUE,...){
+    write.table(df, file, row.names=FALSE, col.names=header, sep="\t", ...)
 }
 
 ## writes a table in bed format expecting columns being ordered according to bed spec already