From 403773ce7efa90c8d11f0902785ba117fd6fffcb Mon Sep 17 00:00:00 2001
From: Aaron <aaronquinlan@gmail.com>
Date: Tue, 6 Sep 2011 20:36:18 -0400
Subject: [PATCH] Version 2.13.1: Added -s, -S, and -names to tagBam.
---
RELEASE_HISTORY | 142 ++++++++++++++++++++++++++++++++++++
src/fjoin/Makefile | 42 +++++++++++
src/fjoin/fjoin.cpp | 3 +-
src/fjoin/fjoin.h | 10 +--
src/utils/version/version.h | 4 +-
5 files changed, 193 insertions(+), 8 deletions(-)
create mode 100644 src/fjoin/Makefile
diff --git a/RELEASE_HISTORY b/RELEASE_HISTORY
index bd3f8a25..0114aa24 100644
--- a/RELEASE_HISTORY
+++ b/RELEASE_HISTORY
@@ -1,3 +1,145 @@
+Version 2.13.1 (6-Sept-2011)
+
+New options
+===========
+1. tagBam now has -s and -S options for only annotating alignments with features on the same and opposite strand, respectively.
+2. tagBam now has a -names option for annotating alignments with the "name" field in annotation files. This overrides the default behavior, which is to use the -labels associated with the annotation files passed in on the command line. Currently, this works well with BED files, but given the limited metadata support for GFF files, annotating with -names and GFF files may not work as well as wished, depending on the type of GFF file used.
+
+
+
+Version 2.13.0 (1-Sept-2011)
+
+New tools
+=========
+1. tagBam. This tool annotates a BAM file with custom tag fields based on overlaps with BED/GFF/VCF files.
+For example:
+$ tagBam -i aln.bam -files exons.bed introns.bed cpg.bed utrs.bed \
+ -tags exonic intonic cpg utr \
+ > aln.tagged.bam
+For alignments that have overlaps, you should see new BAM tags like "YB:Z:exonic", "YB:Z:cpg;utr"
+
+2. multiBamCov. The new tool counts sequence coverage for multiple bams at specific loci defined in a BED/GFF/VCF file.
+For example:
+
+$ multiBamCov -bams aln.1.bam aln.2.bam aln3.bam -bed exons.bed
+chr1 861306 861409 SAMD11 1 + 181 280 236
+chr1 865533 865718 SAMD11 2 + 249 365 374
+chr1 866393 866496 SAMD11 3 + 162 298 322
+
+where the last 3 columns represent the number of alignments overlapping each interval from the three BAM file.
+
+The following options are available to control which types of alignments are are counted.
+-q Minimum mapping quality allowed. Default is 0.
+
+-D Include duplicate-marked reads. Default is to count non-duplicates only
+
+-F Include failed-QC reads. Default is to count pass-QC reads only
+
+-p Only count proper pairs. Default is to count all alignments with MAPQ
+ greater than the -q argument, regardless of the BAM FLAG field.
+
+3. nucBed. This new tool profiles the nucleotide content of intervals in a fasta file. The following information will be reported after each original BED/GFF/VCF entry:
+ 1) %AT content
+ 2) %GC content
+ 3) Number of As observed
+ 4) Number of Cs observed
+ 5) Number of Gs observed
+ 6) Number of Ts observed
+ 7) Number of Ns observed
+ 8) Number of other bases observed
+ 9) The length of the explored sequence/interval.
+ 10) The sequence extracted from the FASTA file. (optional, if -seq is used)
+ 11) The number of times a user defined pattern was observed. (optional, if -pattern is used.)
+
+
+
+For example:
+$ nucBed -fi ~/data/genomes/hg18/hg18.fa -bed simrep.bed | head -3
+#1_usercol 2_usercol 3_usercol 4_usercol 5_usercol 6_usercol 7_pct_at 8_pct_gc 9_num_A 10_num_C 11_num_G 12_num_T 13_num_N 14_num_oth 15_seq_len
+chr1 10000 10468 trf 789 + 0.540598 0.459402 155 96 119 98 0 0 468
+chr1 10627 10800 trf 346 + 0.445087 0.554913 54 55 41 23 0 0 173
+
+
+One can also report the sequence itself:
+$ nucBed -fi ~/data/genomes/hg18/hg18.fa -bed simrep.bed -seq | head -3
+#1_usercol 2_usercol 3_usercol 4_usercol 5_usercol 6_usercol 7_pct_at 8_pct_gc 9_num_A 10_num_C 11_num_G 12_num_T 13_num_N 14_num_oth 15_seq_len 16_seq
+chr1 10000 10468 trf 789 + 0.540598 0.459402 155 96 119 98 0 0 468 ccagggg...
+chr1 10627 10800 trf 346 + 0.445087 0.554913 54 55 41 23 0 0 173 TCTTTCA...
+
+Or, one can count the number of times that a specific pattern occur in the intervals (reported as the last column):
+$ nucBed -fi ~/data/genomes/hg18/hg18.fa -bed simrep.bed -pattern CGTT | head
+#1_usercol 2_usercol 3_usercol 4_usercol 5_usercol 6_usercol 7_pct_at 8_pct_gc 9_num_A 10_num_C 11_num_G 12_num_T 13_num_N 14_num_oth 15_seq_len 16_user_patt_count
+chr1 10000 10468 trf 789 + 0.540598 0.459402 155 96 119 98 0 0 468 0
+chr1 10627 10800 trf 346 + 0.445087 0.554913 54 55 41 23 0 0 173 0
+chr1 10757 10997 trf 434 + 0.370833 0.629167 49 70 81 40 0 0 240 0
+chr1 11225 11447 trf 273 + 0.463964 0.536036 44 86 33 59 0 0 222 0
+chr1 11271 11448 trf 187 + 0.463277 0.536723 37 69 26 45 0 0 177 0
+chr1 11283 11448 trf 199 + 0.466667 0.533333 37 64 24 40 0 0 165 0
+chr1 19305 19443 trf 242 + 0.282609 0.717391 17 57 42 22 0 0 138 1
+chr1 20828 20863 trf 70 + 0.428571 0.571429 10 7 13 5 0 0 35 0
+chr1 30862 30959 trf 79 + 0.556701 0.443299 35 22 21 19 0 0 97 0
+
+
+
+New options
+===========
+1. Support for named pipes and FIFOs.
+2. "-" is now allowable to indicate that data is being sent via stdin.
+
+3. Multiple tools. Added new -S option to annotateBed, closestBed, coverageBed, intersectBed, pairToBed, subtractBed, and windowBed (-Sm). This new option does the opposite of the -s option: that is, overlaps are only processed if they are on _opposite_ strands. Thanks to Sol Katzman for the great suggestion. Very useful for certain RNA-seq analyses.
+
+4. coverageBed. Added a new -counts option to coverageBed that only reports the count of overlaps, instead of also computing fractions, etc. This is much faster and uses much less memory.
+
+5. fastaFromBed. Added a new -full option that uses the full BED entry when naming each output sequence. Also removed the -fo option such that all output is now written to stdout.
+
+6. genomeCoverageBed.
+ - Added new -scale option that allows the coverage values to be scaled by a constant. Useful for normalizing coverage with RPM, RPKM, etc. Thanks to Ryan Dale for the useful suggestion.
+ - Added new -5, -3, -trackline, -trackopts, and -dz options. Many thanks to Assaf Gordon for these improvements.
+ -5: Calculate coverage of 5" positions (instead of entire interval)
+ -3: Calculate coverage of 3" positions (instead of entire interval).
+ -trackline: Adds a UCSC/Genome-Browser track line definition in the first line of the output.
+ -trackopts: rites additional track line definition parameters in the first line.
+ -dz: Report the depth at each genome position with zero-based coordinates, instead of zero-based.
+
+7. closestBed. See below, thanks to Brent Pedersen, Assaf Gordon, Ryan Layer and Dan Webster for the helpful discussions.
+ - closestBed now reports _all_ features in B that overlap A by default. This allows folks to decide which is the "best" overlapping feature on their own.
+
+ 2. closestBed now has a "-io" option that ignores overlapping features. In other words, it will only report the closest, non-overlapping feature.
+
+ An example:
+
+ $ cat a.bed
+ chr1 10 20
+
+ $ cat b.bed
+ chr1 15 16
+ chr1 16 40
+ chr1 100 1000
+ chr1 200 1000
+
+ $ bin/closestBed -a a.bed -b b.bed
+ chr1 10 20 chr1 15 16
+ chr1 10 20 chr1 16 40
+
+ $ bin/closestBed -a a.bed -b b.bed -io
+ chr1 10 20 chr1 100 1000
+
+Updates
+=======
+1. Updated to the latest version of BamTools. This allows greater functionality and will facilitate new options and tools in the future.
+
+ -
+Bug Fixes
+=========
+1. GFF files cannot have zero-length features.
+2. Corrected an erroneous check on the start coordinates in VCF files. Thanks to Jan Vogel for the correction.
+3. mergeBed now always reports output in BED format.
+3. Updated the text file Tokenizer function to yield 15% speed improvement.
+4. Various tweaks and improvements.
+
+
+
+
Version 2.12.0 (April-3-2011)
New Tool
diff --git a/src/fjoin/Makefile b/src/fjoin/Makefile
new file mode 100644
index 00000000..c98c6696
--- /dev/null
+++ b/src/fjoin/Makefile
@@ -0,0 +1,42 @@
+UTILITIES_DIR = ../utils/
+OBJ_DIR = ../../obj/
+BIN_DIR = ../../bin/
+
+# -------------------
+# define our includes
+# -------------------
+INCLUDES = -I$(UTILITIES_DIR)/bedFile/ -I$(UTILITIES_DIR)/lineFileUtilities/ -I$(UTILITIES_DIR)/version/ -I$(UTILITIES_DIR)/gzstream/ -I$(UTILITIES_DIR)/fileType/
+
+# ----------------------------------
+# define our source and object files
+# ----------------------------------
+SOURCES= fjoinMain.cpp fjoin.cpp
+OBJECTS= $(SOURCES:.cpp=.o)
+_EXT_OBJECTS=bedFile.o lineFileUtilities.o gzstream.o fileType.o
+EXT_OBJECTS=$(patsubst %,$(OBJ_DIR)/%,$(_EXT_OBJECTS))
+BUILT_OBJECTS= $(patsubst %,$(OBJ_DIR)/%,$(OBJECTS))
+PROGRAM= fjoin
+
+all: $(PROGRAM)
+
+.PHONY: all
+
+$(PROGRAM): $(BUILT_OBJECTS) $(EXT_OBJECTS)
+ @echo " * linking $(PROGRAM)"
+ @$(CXX) $(LDFLAGS) $(CXXFLAGS) -o $(BIN_DIR)/$@ $^ $(LIBS)
+
+$(BUILT_OBJECTS): $(SOURCES)
+ @echo " * compiling" $(*F).cpp
+ @$(CXX) -c -o $@ $(*F).cpp $(LDFLAGS) $(CXXFLAGS) $(INCLUDES)
+
+$(EXT_OBJECTS):
+ @$(MAKE) --no-print-directory -C $(UTILITIES_DIR)/bedFile/
+ @$(MAKE) --no-print-directory -C $(UTILITIES_DIR)/lineFileUtilities/
+ @$(MAKE) --no-print-directory -C $(UTILITIES_DIR)/gzstream/
+ @$(MAKE) --no-print-directory -C $(UTILITIES_DIR)/fileType/
+
+clean:
+ @echo "Cleaning up."
+ @rm -f $(OBJ_DIR)/* $(BIN_DIR)/*
+
+.PHONY: clean
diff --git a/src/fjoin/fjoin.cpp b/src/fjoin/fjoin.cpp
index 2ca5c33d..b1de416a 100644
--- a/src/fjoin/fjoin.cpp
+++ b/src/fjoin/fjoin.cpp
@@ -286,8 +286,9 @@ void BedIntersect::IntersectBed() {
aStatus = _bedA->GetNextBed(*a, aLineNum);
bStatus = _bedB->GetNextBed(*b, bLineNum);
+ cout << a->chrom << " " << a->start << " " << a->chrom << " " << b->start << endl;
while (aStatus != BED_INVALID || bStatus != BED_INVALID) {
-
+
if ((a->start <= b->start) && (a->chrom == b->chrom)) {
prevA = a;
_lastPick = 0;
diff --git a/src/fjoin/fjoin.h b/src/fjoin/fjoin.h
index dd0a111b..c7aabd46 100644
--- a/src/fjoin/fjoin.h
+++ b/src/fjoin/fjoin.h
@@ -13,11 +13,11 @@
#define INTERSECTBED_H
#include "bedFile.h"
-#include "BamReader.h"
-#include "BamWriter.h"
-#include "BamAncillary.h"
-#include "BamAux.h"
-using namespace BamTools;
+// #include "BamReader.h"
+// #include "BamWriter.h"
+// #include "BamAncillary.h"
+// #include "BamAux.h"
+// using namespace BamTools;
#include <vector>
diff --git a/src/utils/version/version.h b/src/utils/version/version.h
index 763a208e..01d9d2e7 100644
--- a/src/utils/version/version.h
+++ b/src/utils/version/version.h
@@ -3,6 +3,6 @@
// define the version. All tools in the
// suite carry the same version number.
-#define VERSION "2.13.0"
+#define VERSION "2.13.1"
-#endif /* VERSION_H */
+#endif /* VERSION_H */
\ No newline at end of file
--
GitLab