add no_duplex option

Author: sfchen

README.md

@@ -200,6 +200,7 @@ options:
   -r, --ref                      reference fasta file name (should be an uncompressed .fa/.fasta file) (string)
   -b, --bed                      bed file to specify the capturing region, none by default (string [=])
   -x, --duplex_only              only output duplex consensus sequences, which means single stranded consensus sequences will be discarded.
+      --no_duplex                don't merge single stranded consensus sequences to duplex consensus sequences.
   -u, --umi_prefix               the prefix for UMI, if it has. None by default. Check the README for the defails of UMI formats. (string [=auto])
   -s, --supporting_reads         only output consensus reads/pairs that merged by >= <supporting_reads> reads/pairs. The valud should be 1~10, and the default value is 1. (int [=1])
   -a, --ratio_threshold          if the ratio of the major base in a cluster is less than <ratio_threshold>, it will be further compared to the reference. The valud should be 0.5~1.0, and the default value is 0.8 (double [=0.8])

src/cluster.cpp

@@ -116,7 +116,7 @@ vector<Pair*> Cluster::clusterByUMI(int umiDiffThreshold, Stats* preStats, Stats
     vector<Pair*> resultConsensusPairs;
     int singleConsesusCount = 0;
     int duplexConsensusCount = 0;
-    if(hasUMI) {
+    if(hasUMI && !mOptions->disableDuplex) {
         // make duplex consensus read pairs
         while(singleConsensusPairs.size() > 0) {
             Pair* p1 = singleConsensusPairs.back();

src/main.cpp

@@ -33,6 +33,7 @@ int main(int argc, char* argv[]){
     cmd.add<string>("ref", 'r', "reference fasta file name (should be an uncompressed .fa/.fasta file)", true, "");
     cmd.add<string>("bed", 'b', "bed file to specify the capturing region, none by default", false, "");
     cmd.add("duplex_only", 'x', "only output duplex consensus sequences, which means single stranded consensus sequences will be discarded.");
+    cmd.add("no_duplex", 0, "don't merge single stranded consensus sequences to duplex consensus sequences.");
 
     // UMI
     cmd.add<string>("umi_prefix", 'u', "the prefix for UMI, if it has. None by default. Check the README for the defails of UMI formats.", false, "auto");
@@ -76,6 +77,10 @@ int main(int argc, char* argv[]){
     opt.duplexMismatchThreshold = cmd.get<int>("duplex_diff_threshold");
     opt.debug = cmd.exist("debug");
     opt.duplexOnly = cmd.exist("duplex_only");
+    opt.disableDuplex = cmd.exist("no_duplex");
+    if(opt.duplexOnly && opt.disableDuplex) {
+        error_exit("You cannot enable both duplex_only and no_duplex");
+    }
 
     // reporting
     opt.jsonFile = cmd.get<string>("json");

src/options.cpp

@@ -36,6 +36,7 @@ Options::Options(){
     coverageStep = 10000;
 
     duplexOnly = false;
+    disableDuplex = false;
 }
 
 bool Options::validate() {

src/options.h

@@ -57,6 +57,7 @@ class Options{
     int bedCoverageStep;
 
     bool duplexOnly;
+    bool disableDuplex;
 };
 
 #endif