From e5e21cfe8f8b05f98e836d5f41f58b3de735fd95 Mon Sep 17 00:00:00 2001
From: Aaron <aaronquinlan@gmail.com>
Date: Wed, 18 Nov 2009 21:01:47 -0500
Subject: [PATCH] Version 2.3. Just before paper submission.
---
RELEASE_HISTORY | 13 +++++++++
USAGE_EXAMPLES | 7 ++---
scripts/gffToBed.py | 6 ++--
scripts/samToBed.py | 56 ++++++++++++++++++++++++-------------
src/utils/version/version.h | 2 +-
5 files changed, 56 insertions(+), 28 deletions(-)
diff --git a/RELEASE_HISTORY b/RELEASE_HISTORY
index a1564518..5c1a445b 100644
--- a/RELEASE_HISTORY
+++ b/RELEASE_HISTORY
@@ -1,3 +1,16 @@
+Version 2.3.0 (11/18/2009)
+1. Added four new tools:
+ - shuffleBed. Randomly permutes the locations of a BED file among a genome. Useful for testing for significant overlap enrichments.
+ - slopBed. Adds a requested number of base pairs to each end of a BED feature. Constrained by the size of each chromosome.
+ - maskFastaFromBed. Masks a FASTA file based on BED coordinates. Useful making custom genome files from targeted capture experiment, etc.
+ - pairToPair. Returns overlaps between two paired-end BED files. This is great for finding structural variants that are
+ private or shared among samples.
+
+2. Increased the speed of intersectBed by nearly 50%.
+3. Improved /corrected some of the help messages.
+4. Improved sanity checking for BED entries.
+
+
Version 2.2.4 (10/27/2009)
1. Updated the mergeBed documentation to describe the -names option which allows one to report the names of the
features that were merged (separated by semicolons).
diff --git a/USAGE_EXAMPLES b/USAGE_EXAMPLES
index 9dfdba4f..078499cc 100755
--- a/USAGE_EXAMPLES
+++ b/USAGE_EXAMPLES
@@ -1,13 +1,10 @@
==============================
-=== BEDTools Version 2.1.2 ===
+=== BEDTools ===
==============================
Created by Aaron Quinlan Spring 2009.
Copyright 2009 Aaron Quinlan. All rights reserved.
-http://people.virginia.edu/~arq5x/bedtools.html
-
-Free for non-profit or academic use. Please contact me for commercial use.
-
+http://code.google.com/p/bedtools
===Example Usage===
diff --git a/scripts/gffToBed.py b/scripts/gffToBed.py
index 5200e090..6d72ea95 100755
--- a/scripts/gffToBed.py
+++ b/scripts/gffToBed.py
@@ -15,9 +15,9 @@ import re
help_message = '''
-gffToBed -g <gff>
-
-OPTIONS:
+gffToBed.py -g <gff>
+
+ABSTRACT: Converts genome annotations in GFF format to BED format.
'''
"""
diff --git a/scripts/samToBed.py b/scripts/samToBed.py
index f3da61f0..ee541689 100755
--- a/scripts/samToBed.py
+++ b/scripts/samToBed.py
@@ -16,15 +16,30 @@ import re
help_message = '''
-samToBed -s <sam> -t <alignment type>
+samToBed.py -s <sam> -t <alignment type>
+
+ABSTRACT: Converts aligned reads in SAM format to BED format.
OPTIONS:
- -s The SAM file to be converted to BED
+ -s The SAM file to be converted to BED (use "stdin" for piped input)
-t What types of alignments should be reported?
"all" all aligned reads will be reported (Default)
"con" only concordant pairs will be reported
"dis" only discordant pairs will be reported
+EXAMPLE:
+ Can be used with samtools to extract alignments and compare them to BED
+ annotations.
+
+ (1) Land a BED file first.
+ $ samtools view reads.sorted.bam > read.sorted.sam
+ $ samToBed.py -s reads.sorted.sam -t all > reads.sorted.bed
+ $ intersectBed -a reads.sorted.bed -b refseq.bed > reads.intersect.refseq.bed
+
+ (2) "One-liner.
+ $ samtools view reads.sorted.bam | samToBed.py -s stdin -t all | \
+ intersectBed -a stdin -b refseq.bed > reads.intersect.refseq.bed
+
'''
@@ -35,15 +50,17 @@ class Usage(Exception):
def processSAM(file, alignType):
"""
- Load a SAM file and convert each line to BED format.
-
- We avoid readlines() in this case, as SAM files can
- be HUGE, and thus loading it into memory could be painful.
- """
- for line in open(file,'r'):
- samLine = splitLine(line.strip())
- makeBED(samLine, alignType)
- f.close()
+ Read a SAM file (or stdin) and convert each line to BED format.
+ """
+ if (file != "stdin"):
+ for line in open(file,'r'):
+ samLine = splitLine(line.strip())
+ makeBED(samLine, alignType)
+ f.close()
+ else:
+ for line in sys.stdin:
+ samLine = splitLine(line.strip())
+ makeBED(samLine, alignType)
def makeBED(samFields, aType):
@@ -116,17 +133,18 @@ def main(argv=None):
samFile = value
if option in ("-t", "--type"):
aType = value
-
- try:
- f = open(samFile, 'r')
- except IOError, msg:
- raise Usage(help_message)
-
+
+ if (samFile != "stdin"):
+ try:
+ f = open(samFile, 'r')
+ except IOError, msg:
+ raise Usage(help_message)
+
except Usage, err:
- print >> sys.stderr, sys.argv[0].split("/")[-1] + ": " + str(err.msg)
+ print >> sys.stderr, str(err.msg)
return 2
- # make a BED file of the SAM file.
+
processSAM(samFile, aType)
if __name__ == "__main__":
diff --git a/src/utils/version/version.h b/src/utils/version/version.h
index a06efc6f..c8144615 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 "2.2.4"
+#define VERSION "2.3.0"
#endif /* VERSION_H */
--
GitLab