Consider the read start in the Cys location

README.md

@@ -63,6 +63,6 @@ command invokes it:
 
 The script will generate 2 files under the data directory:
 
-|HVR.fastq  |Contains the original CDR3 sequence |
+|HVR.fastq  | curesim-HVR.fastq |
 |:----:|:-----:|
-|CuReSim-HVR.fastq | Contains CDR3 after the read simulation, with sequencing errors |
+|Contains the original CDR3 sequence|Contains CDR3 after the read simulation, with sequencing errors |

src/alignment.r

@@ -34,7 +34,11 @@ parse_metadata <- function(metadata) {
 #' @return A \code{character} containing the gene sequence
 match_id_sequence <- function(names, vdj_segments, id) {
   matches <- grep(names, pattern = id)
+  if(id == "TRBJ2-2"){
+    row <- matches[2]
+  } else {
     row <- matches[1]
+  }
   return(as.character(vdj_segments[row]))
 }
 
@@ -106,8 +110,9 @@ get_cys_coordinates <- function(alignment) {
   insertion <- unlist(Biostrings::insertion(alignment))
   deletion <- unlist(Biostrings::deletion(alignment))
   delta_coordinates <- handle_indels(insertion, deletion, cys, alignment)
-  cys_start <- cys$start + delta_coordinates$start
+  read_start <- unlist(start(Biostrings::Views(alignment)))
-  cys_end <- cys$end + delta_coordinates$end
+  cys_start <- cys$start + delta_coordinates$start + read_start - 1
+  cys_end <- cys$end + delta_coordinates$end + read_start
   return(list("start" = cys_start, "end" = cys_end))
 }
 
@@ -126,7 +131,7 @@ get_hvr_sequences <- function(sequences, vdj_segments, cores = detectCores()) {
   )
   cys_coordinates <- parallel::mclapply(v_alignment, FUN = get_cys_coordinates)
   cys_df <- as.data.frame(do.call(rbind, cys_coordinates))
-  remaining <- Biostrings::subseq(sequences, start = unlist(cys_df$end))
+  remaining <- Biostrings::subseq(sequences, start = unlist(cys_df$end) + 1)
   j_alignment <- parallel::mcmapply(remaining,
     df$j_seq,
     FUN = align_sequence,
@@ -145,4 +150,4 @@ get_hvr_sequences <- function(sequences, vdj_segments, cores = detectCores()) {
 
 data <- parse_data(file = "data/curesim_sequence.fastq")
 hvr <- get_hvr_sequences(sequences = data[[1]], vdj_segments = data[[2]])
-Biostrings::writeXStringSet(hvr, "data/CuReSim-HVR.fastq", format = "fastq")
+Biostrings::writeXStringSet(hvr, "data/curesim-HVR.fastq", format = "fastq")