Merge branch 'master' into master_fixes. Merged up to release bwa-0.7.4-r385.

Makefile

@@ -7,7 +7,7 @@ AOBJS=		QSufSort.o bwt_gen.o bwase.o bwaseqio.o bwtgap.o bwtaln.o bamlite.o \
 			is.o bwtindex.o bwape.o kopen.o pemerge.o \
 			bwtsw2_core.o bwtsw2_main.o bwtsw2_aux.o bwt_lite.o \
 			bwtsw2_chain.o fastmap.o bwtsw2_pair.o
-PROG=		bwa bwamem-lite
+PROG=		bwa
 INCLUDES=	
 LIBS=		-lm -lz -lpthread
 SUBDIRS=	.

NEWS

@@ -1,3 +1,36 @@
+Release 0.7.4 (23 April, 2013)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+This is a bugfix release. Most of bugs are considered to be minor which only
+ very rarely.
+ ccur
+
+ * Bugfix: wrong CIGAR when a query sequence bridges three or more target
+   sequences. This only happens when aligning reads to short assembly contigs.
+
+ * Bugfix: leading "D" operator in CIGAR.
+
+ * Extend more seeds for better alignment around tandem repeats. This is also
+   a cause of the leading "D" operator in CIGAR.
+
+ * Bugfix: SSE2-SSW may occasionally find incorrect query starting position
+   around tandem repeat. This will lead to a suboptimal CIGAR in BWA-MEM and
+   a wrong CIGAR in BWA.
+
+ * Bugfix: clipping penalty does not work as is intended when there is a gap
+   towards the end of a read.
+
+ * Fixed an issue caused by a bug in the libc from Mac/Darwin. In Darwin,
+   fread() is unable to read a data block longer than 2GB due to an integer
+   overflow bug in its implementation.
+
+Since version 0.7.4, BWA-MEM is considered to reach similar stability to
+BWA-backtrack for short-read mapping.
+
+(0.7.4: 23 April, r385)
+
+
+
 Release 0.7.3a (15 March, 2013)
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

bwa.1

@@ -1,4 +1,4 @@
-.TH bwa 1 "15 March 2013" "bwa-0.7.4" "Bioinformatics tools"
+.TH bwa 1 "23 April 2013" "bwa-0.7.4" "Bioinformatics tools"
 .SH NAME
 .PP
 bwa - Burrows-Wheeler Alignment Tool
@@ -44,7 +44,12 @@ for the BWA-MEM algorithm.
 .SH COMMANDS AND OPTIONS
 .TP
 .B index
-bwa index [-p prefix] [-a algoType] <in.db.fasta>
+.B bwa index
+.RB [ -p
+.IR prefix ]
+.RB [ -a
+.IR algoType ]
+.I db.fa
 
 Index database sequences in the FASTA format.
 
@@ -55,20 +60,16 @@ Index database sequences in the FASTA format.
 Prefix of the output database [same as db filename]
 .TP
 .BI -a \ STR
-Algorithm for constructing BWT index. Available options are:
+Algorithm for constructing BWT index. BWA implements two algorithms for BWT
-.RS
+construction:
-.TP
 .B is
-IS linear-time algorithm for constructing suffix array. It requires
+and
-5.37N memory where N is the size of the database. IS is moderately fast,
+.BR bwtsw .
-but does not work with database larger than 2GB. IS is the default
+The first algorithm is a little faster for small database but requires large
-algorithm due to its simplicity. The current codes for IS algorithm are
+RAM and does not work for databases with total length longer than 2GB. The
-reimplemented by Yuta Mori.
+second algorithm is adapted from the BWT-SW source code. It in theory works
-.TP
+with database with trillions of bases. When this option is not specified, the
-.B bwtsw
+appropriate algorithm will be chosen automatically.
-Algorithm implemented in BWT-SW. This method works with the whole human
-genome.
-.RE
 .RE
 
 .TP
@@ -220,10 +221,12 @@ 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. [17]
+two scores to determine whether we should force pairing. A larger value leads to
+more aggressive read pair. [17]
 .TP
 .B -p
-Assume the first input query file is interleaved paired-end FASTA/Q. See the command description for details.
+Assume the first input query file is interleaved paired-end FASTA/Q. See the
+command description for details.
 .TP
 .BI -R \ STR
 Complete read group header line. '\\t' can be used in

main.c

@@ -3,7 +3,7 @@
 #include "utils.h"
 
 #ifndef PACKAGE_VERSION
-#define PACKAGE_VERSION "0.7.3-r382-beta"
+#define PACKAGE_VERSION "0.7.4-r385"
 #endif
 
 int bwa_fa2pac(int argc, char *argv[]);
@@ -46,6 +46,10 @@ static int usage()
 	fprintf(stderr, "         bwtupdate     update .bwt to the new format\n");
 	fprintf(stderr, "         bwt2sa        generate SA from BWT and Occ\n");
 	fprintf(stderr, "\n");
+	fprintf(stderr, "Note: To use BWA, you need to first index the genome with `bwa index'. There are\n");
+	fprintf(stderr, "      three alignment algorithms in BWA: `mem', `bwasw' and `aln/samse/sampe'. If\n");
+	fprintf(stderr, "      you are not sure which to use, try `bwa mem' first. Please `man ./bwa.1' for\n");
+	fprintf(stderr, "      for the manual.\n\n");
 	return 1;
 }