Merge branch 'develop'

CHANGES

@@ -1,7 +1,13 @@
+0.1.2 - 2013-12-09
+==================
+Fix issue where BED intervals with chromosome names not starting with "c" were silently being ignored (reported by Aaron Hardin)
+Fix clint dependency issue (no longer requires custom version of clint)
+Fix spelling error in CHANGES
+
 0.1.1 - 2013-12-05
 ==================
 Misc. small bug fixes
-Fixed Python 2.6 Compatability
+Fixed Python 2.6 Compatibility
 Added JSON export script
 
 0.1.0 - 2013-09-01

examples/example.bed

@@ -1,2 +1,8 @@
-track name=exampleFile description="This is an example" useScore=1
-chr6	170863142	170863532	0	0	+
+#This is a comment line and should be ignored.
+#The following lines should also be ignores as they are valid BED Headers
+browser position chr6:170863142-170863532
+browser hide all
+track name="ItemRGBDemo" description="Item RGB demonstration" visibility=2
+itemRgb="On"
+visibility=2 colorByStrand="255,0,0 0,0,255"
+chr6	170863142	170863532	0	0	+

pyDNase/__init__.py

@@ -12,7 +12,7 @@
 #
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
-__version__ = "0.1.1"
+__version__ = "0.1.2"
 
 import os
 import numpy as np
@@ -246,12 +246,12 @@ def loadBEDFile(self,filename):
 
         #This is done so that if a malformed BED record is detected, no intervals are loaded.
         records = []
-
+        
         intervalCount = max(enumerate(open(filename)))[0] + 1
         for _ in progress.bar(range(intervalCount)):
             line    = BEDfile.readline()
-            #NOTE! Assume that lines not starting with c are comments or track descriptions.
-            if line[0] == "c":
+            #Skip lines in the bed files which are UCSC track metadata or comments
+            if not self.__isBEDHeader(line):
                 records.append(self.__parseBEDString(line))
 
         for i in records:
@@ -270,6 +270,22 @@ def __malformedBEDline(self,BEDString):
         exceptionString = "Malformed BED line: {0}".format(BEDString)
         raise Exception(exceptionString)
 
+    def __isBEDHeader(self,string):
+        """
+        Returns True/False whether a line in a bed file should be ignored according to
+        http://genome.ucsc.edu/goldenPath/help/customTrack.html#TRACK
+        """
+        if string[0] == "#":
+            return True
+
+        headers = ["name","description","type","visibility","color","itemRgb","useScore","group",
+                   "priority","db","offset","maxItems","url","htmlUrl","bigDataUrl","track","browser"]
+
+        for each in headers:
+            if string.startswith(each):
+                return True
+        return False
+
     def __parseBEDString(self,BEDString):
         """
         Parses the following BED formats
@@ -292,9 +308,13 @@ def __parseBEDString(self,BEDString):
             self.__malformedBEDline(BEDString)
 
         #Default if only Chrom Start End is detected
-        chrom   = BEDSplit[0]
-        startbp = int(BEDSplit[1])
-        endbp   = int(BEDSplit[2])
+        try:
+            chrom   = BEDSplit[0]
+            startbp = int(BEDSplit[1])
+            endbp   = int(BEDSplit[2])
+        except:
+            self.__malformedBEDline(BEDString)
+
         label = 0
         score = 0
         strand = "+"

setup.py

@@ -16,7 +16,7 @@
 
 setup(
     name='pyDNase',
-    version="0.1.1",
+    version="0.1.2",
     description='DNase-seq analysis library',
     long_description=open('README.rst',"rt").read(),
     author='Jason Piper',
@@ -29,15 +29,12 @@
         'pyDNase.footprinting',
     ],
 
-    #Uses a custom version of clint that has a time estimator on the progress bar
-    dependency_links = ["http://github.com/jpiper/clint/tarball/develop#egg=clint-0.3.0p"],
-
     install_requires=[
         "numpy",
         "scipy",
         "matplotlib",
         "pysam",
-        "clint==0.3.0p"
+        "clint"
     ],
 
     package_data = {'pyDNase':["data/*"]},