From 2087dc162f5ff5eb6c8da5d4bead13199013864f Mon Sep 17 00:00:00 2001 From: Heng Li Date: Wed, 17 Apr 2013 16:50:20 -0400 Subject: [PATCH] r377: increased unpaired penalty from 9 to 17 This leads to more aggressive pairing - more properly paired reads. I have found a few cases where, for example, read1 is umambiguously mapped to chr20 while its 100bp mate has a perfect match to another chr but has 3 mismatches and 1 deletion when it is paired with read1 on chr20. With longer reads, it seems that the chr20 hit is correct, although it is not obvious how this happened in evolution. --- bwa.1 | 4 ++-- bwamem.c | 2 +- main.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/bwa.1 b/bwa.1 index 1edbf12..9d45a3d 100644 --- a/bwa.1 +++ b/bwa.1 @@ -1,4 +1,4 @@ -.TH bwa 1 "15 March 2013" "bwa-0.7.3a" "Bioinformatics tools" +.TH bwa 1 "15 March 2013" "bwa-0.7.4" "Bioinformatics tools" .SH NAME .PP bwa - Burrows-Wheeler Alignment Tool @@ -220,7 +220,7 @@ deducted. [5] Penalty for an unpaired read pair. BWA-MEM scores an unpaired read pair as .RI scoreRead1+scoreRead2- INT and scores a paired as scoreRead1+scoreRead2-insertPenalty. It compares these -two scores to determine whether we should force pairing. [9] +two scores to determine whether we should force pairing. [17] .TP .B -p Assume the first input query file is interleaved paired-end FASTA/Q. See the command description for details. diff --git a/bwamem.c b/bwamem.c index 182b57a..921b512 100644 --- a/bwamem.c +++ b/bwamem.c @@ -46,7 +46,7 @@ mem_opt_t *mem_opt_init() o->a = 1; o->b = 4; o->q = 6; o->r = 1; o->w = 100; o->T = 30; o->zdrop = 100; - o->pen_unpaired = 9; + o->pen_unpaired = 17; o->pen_clip = 5; o->min_seed_len = 19; o->split_width = 10; diff --git a/main.c b/main.c index 8c1343c..ea92d81 100644 --- a/main.c +++ b/main.c @@ -3,7 +3,7 @@ #include "utils.h" #ifndef PACKAGE_VERSION -#define PACKAGE_VERSION "0.7.3-r376-beta" +#define PACKAGE_VERSION "0.7.3-r377-beta" #endif int bwa_fa2pac(int argc, char *argv[]);