diff --git a/RELEASE_HISTORY b/RELEASE_HISTORY
index 12c62202d8d875017f0bbfa3fbaad3bf703427e6..4b5becb1cd227cb338e4c7a73a88951fa61b9423 100644
--- a/RELEASE_HISTORY
+++ b/RELEASE_HISTORY
@@ -1,17 +1,29 @@
+Version 2.2.3 (10/23/2009)
+1. Changed windowBed to optionally define "left" and "right" windows based on strand. For example by default, -l 100 and -r 500 will
+add 100 bases to the left (lower coordinates) of a feature in A when scanning for hits in B and 500 bases to the right (higher coordinates).
+
+However if one chooses the -sw option (windows bases on strandedness), the behavior changes. Assume the above example except that a feature in A
+is on the negative strand ("-"). In this case, -l 100, -r 500 and -sw will add 100 bases to the right (higher coordinates) and 500 bases to the left (lower coordinates).
+
+In addition, there is a separate option (-sm) that can optionally force hits in B to only be tracked if they are on the same strand as A.
+
+***NOTE: This replaces the previous -s option and may affect existing pipelines***.
+
+
Version 2.2.2 (10/20/2009)
1. Improved the speed of genomeCoverageBed by roughly 100 fold. The memory usage is now less than 2.0 Gb.
+
Version 2.2.1
1. Fixed a very obvious bug in subtractBed that caused improper behavior when a feature in A was overlapped by more than one feature in B.
Many thanks to folks in the Hannon lab at CSHL for pointing this out.
Version 2.2.0
-
=== Notable changes in this release ===
1. coverageBed will optionally only count features in BED file A (e.g. sequencing reads) that overlap with
- the intervals/windows in BED file B. This has been requested several times recently and facilitates CHiP-Seq and
- RNA-Seq experiments.
+ the intervals/windows in BED file B on the same strand. This has been requested several times recently
+ and facilitates CHiP-Seq and RNA-Seq experiments.
2. intersectBed can now require a minimum __reciprocal__ overlap between intervals in BED A and BED B. For example,
previously, if one used -f 0.90, it required that a feature in B overlap 90% of the feature in A for the "hit"
@@ -65,18 +77,22 @@ VERSION 2.1.2
2. Change the "score" column (i.e. column 5) to b stored as a string. While this deviates
from the UCSC convention, it allows significantly more information to be packed into the column.
+
VERSION 2.1.1
1. Added limits.h to bedFile.h to fix compilation issues on some systems.
2. Fixed bug in testing for "track" or "browser" lines.
+
VERSION 2.1.0
1. Fixed a bug in peIntersectBed that prevented -a from being correctly handled when passed via stdin.
2. Added new functionality to coverageBed that calculates the density of coverage.
3. Fixed bug in geneomCoverageBed.
+
VERSION 2.0.1
1. Added the ability to retain UCSC browser track/browser headers in BED files.
+
VERSION 2.0
1. Sped up the file parsing. ~10-20% increase in speed.
2. Created reportBed() as a common method in the bedFile class. Cleans up the code quite nicely.
@@ -85,6 +101,7 @@ VERSION 2.0
5. Fixed bug that prevented overlaps from being reported when the overlap fraction requested is 1.0
+
VERSION 1.2, 04/27/2009. (1eb06115bdf3c49e75793f764a70c3501bb53f33)
1. Added subtractBed.
A. Fixed bug that prevented "split" overlaps from being reported.
diff --git a/src/utils/version/version.h b/src/utils/version/version.h
index 9d4887614377b8de2af8678e1e8f6ea48a8b0772..173345d9a1a47991747e376734962df75b789cc3 100644
--- a/src/utils/version/version.h
+++ b/src/utils/version/version.h
@@ -1,7 +1,8 @@
#ifndef VERSION_H
#define VERSION_H
-// define the version
-#define VERSION "2.2.2"
+// define the version. All tools in the
+// suite carry the same version number.
+#define VERSION "2.2.3"
#endif /* VERSION_H */
diff --git a/src/windowBed/windowBed.cpp b/src/windowBed/windowBed.cpp
index 5cfe8e90385681f0d308455a7b0dd8b6077b8207..7c6a84a1bb74674038078ff47867a0ad87fd9746 100755
--- a/src/windowBed/windowBed.cpp
+++ b/src/windowBed/windowBed.cpp
@@ -14,7 +14,8 @@
/*
Constructor
*/
-BedWindow::BedWindow(string &bedAFile, string &bedBFile, int &leftSlop, int &rightSlop, bool &anyHit, bool &noHit, bool &writeCount, bool &forceStrand) {
+BedWindow::BedWindow(string &bedAFile, string &bedBFile, int &leftSlop, int &rightSlop, bool &anyHit, bool &noHit,
+ bool &writeCount, bool &strandWindows, bool &matchOnStrand) {
this->bedAFile = bedAFile;
this->bedBFile = bedBFile;
@@ -25,8 +26,9 @@ BedWindow::BedWindow(string &bedAFile, string &bedBFile, int &leftSlop, int &rig
this->anyHit = anyHit;
this->noHit = noHit;
this->writeCount = writeCount;
- this->forceStrand = forceStrand;
-
+ this->strandWindows = strandWindows;
+ this->matchOnStrand = matchOnStrand;
+
this->bedA = new BedFile(bedAFile);
this->bedB = new BedFile(bedBFile);
}
@@ -48,14 +50,41 @@ void BedWindow::FindWindowOverlaps(BED &a, vector<BED> &hits) {
int aFudgeStart = 0;
int aFudgeEnd;
- if ((a.start - this->leftSlop) > 0) {
- aFudgeStart = a.start - this->leftSlop;
+
+ // Does the user want to treat the windows based on strand?
+ // If so,
+ // if "+", then left is left and right is right
+ // if "-", the left is right and right is left.
+ if (this->strandWindows) {
+
+ if (a.strand == "+") {
+ if ((a.start - this->leftSlop) > 0) {
+ aFudgeStart = a.start - this->leftSlop;
+ }
+ else {
+ aFudgeStart = 0;
+ }
+ aFudgeEnd = a.end + this->rightSlop;
+ }
+ else {
+ if ((a.start - this->rightSlop) > 0) {
+ aFudgeStart = a.start - this->rightSlop;
+ }
+ else {
+ aFudgeStart = 0;
+ }
+ aFudgeEnd = a.end + this->leftSlop;
+ }
}
else {
- aFudgeStart = 0;
+ if ((a.start - this->leftSlop) > 0) {
+ aFudgeStart = a.start - this->leftSlop;
+ }
+ else {
+ aFudgeStart = 0;
+ }
+ aFudgeEnd = a.end + this->rightSlop;
}
- aFudgeEnd = a.end + this->rightSlop;
-
bedB->binKeeperFind(bedB->bedMap[a.chrom], aFudgeStart, aFudgeEnd, hits);
@@ -64,7 +93,7 @@ void BedWindow::FindWindowOverlaps(BED &a, vector<BED> &hits) {
// if forcing strandedness, move on if the hit
// is not on the same strand as A.
- if ((this->forceStrand) && (a.strand != h->strand)) {
+ if ((this->matchOnStrand) && (a.strand != h->strand)) {
continue; // continue force the next iteration of the for loop.
}
diff --git a/src/windowBed/windowBed.h b/src/windowBed/windowBed.h
index bfc89a9bf2387e324bdad11ba5d0b3346b3c3ceb..f8bf0d0a2d5997eee2d24b93be24ce97a6a9e9a9 100755
--- a/src/windowBed/windowBed.h
+++ b/src/windowBed/windowBed.h
@@ -16,7 +16,7 @@ class BedWindow {
public:
// constructor
- BedWindow(string &, string &, int &, int &, bool &, bool &, bool &, bool &);
+ BedWindow(string &, string &, int &, int &, bool &, bool &, bool &, bool &, bool &);
// destructor
~BedWindow(void);
@@ -36,7 +36,8 @@ private:
int leftSlop;
int rightSlop;
bool noHit;
- bool forceStrand;
+ bool strandWindows;
+ bool matchOnStrand;
// instance of a bed file class.
BedFile *bedA, *bedB;
diff --git a/src/windowBed/windowMain.cpp b/src/windowBed/windowMain.cpp
index 8978cb79cee8b9f45bed83ed54d34be6ee88835f..ade5bd1116fde73200e419a54dc23fbb01582851 100755
--- a/src/windowBed/windowMain.cpp
+++ b/src/windowBed/windowMain.cpp
@@ -34,7 +34,8 @@ int main(int argc, char* argv[]) {
bool haveSlop = false;
bool haveLeft = false;
bool haveRight = false;
- bool forceStrand = false;
+ bool strandWindows = false;
+ bool matchOnStrand = false;
// check to see if we should print out some help
if(argc <= 1) showHelp = true;
@@ -74,8 +75,11 @@ int main(int argc, char* argv[]) {
else if (PARAMETER_CHECK("-v", 2, parameterLength)) {
noHit = true;
}
- else if (PARAMETER_CHECK("-s", 2, parameterLength)) {
- forceStrand = true;
+ else if (PARAMETER_CHECK("-sw", 3, parameterLength)) {
+ strandWindows = true;
+ }
+ else if (PARAMETER_CHECK("-sm", 3, parameterLength)) {
+ matchOnStrand = true;
}
else if (PARAMETER_CHECK("-w", 2, parameterLength)) {
haveSlop = true;
@@ -136,7 +140,7 @@ int main(int argc, char* argv[]) {
}
if (!showHelp) {
- BedWindow *bi = new BedWindow(bedAFile, bedBFile, leftSlop, rightSlop, anyHit, noHit, writeCount, forceStrand);
+ BedWindow *bi = new BedWindow(bedAFile, bedBFile, leftSlop, rightSlop, anyHit, noHit, writeCount, strandWindows, matchOnStrand);
bi->WindowIntersectBed();
return 0;
}
@@ -159,10 +163,11 @@ void ShowHelp(void) {
cerr << "Usage: " << PROGRAM_NAME << " [OPTIONS] -a <a.bed> -b <b.bed>" << endl << endl;
cerr << "OPTIONS: " << endl;
- cerr << "\t" << "-s\t\t\t" << "Force strandedness. Only report hits in B that overlap A on the same strand." << endl << "\t\t\t\tBy default, overlaps are reported without respect to strand." << endl << endl;
cerr << "\t" << "-w (def. 1000)\t\t" << "Base pairs added upstream and downstream of each entry in A when searching for overlaps in B." << endl << endl;
cerr << "\t" << "-l (def. 1000)\t\t" << "Base pairs added upstream (left of) of each entry in A when searching for overlaps in B." << endl << endl;
cerr << "\t" << "-r (def. 1000)\t\t" << "Base pairs added downstream (right of) of each entry in A when searching for overlaps in B." << endl << endl;
+ cerr << "\t" << "-sw\t\t\t" << "Define -l and -r based on strand. E.g. if used, -l 500 for a negative-stranded feature will add 500 bp downstream. Default = false." << endl << "\t\t\t\tBy default, overlaps are reported without respect to strand." << endl << endl;
+ cerr << "\t" << "-sm\t\t\t" << "Only report hits in B that overlap A on the same strand." << endl << "\t\t\t\tBy default, overlaps are reported without respect to strand." << endl << endl;
cerr << "\t" << "-u\t\t\t" << "Write ORIGINAL a.bed entry ONCE if ANY overlap with B.bed." << endl << "\t\t\t\tIn other words, just report the fact >=1 hit was found." << endl << endl;
cerr << "\t" << "-v \t\t\t" << "Only report those entries in A that have NO OVERLAP in B within the requested window." << endl << "\t\t\t\tSimilar to grep -v." << endl << endl;
cerr << "\t" << "-c \t\t\t" << "For each entry in A, report the number of hits in B within the requested window." << endl << "\t\t\t\tReports 0 for A entries that have no overlap with B." << endl << endl;