Merge pull request #35 from dpryan79/fix28_GenomicIntervalsComparisons

Fix #28, #31 and related issues

pyDNase/__init__.py

@@ -493,6 +493,93 @@ def __len__(self):
         """
         return self.endbp - self.startbp
 
+    def __lt__(self, other):
+        """
+        Implements foo < bar
+        """
+        if self.chromosome == other.chromosome:
+            if self.startbp < other.startbp:
+                return True
+            elif self.startbp == other.startbp:
+                if self.endbp < other.endbp:
+                    return True
+                else:
+                    return False
+            else:
+                return False
+        elif self.chromosome < other.chromosome:
+            return True
+        else:
+            return False
+
+    def __le__(self, other):
+        """
+        Implements foo <= bar
+        """
+        if self.chromosome == other.chromosome:
+            if self.startbp < other.startbp:
+                return True
+            elif self.startbp == other.startbp:
+                if self.endbp <= other.endbp:
+                    return True
+                else:
+                    return False
+            else:
+                return False
+        elif self.chromosome < other.chromosome:
+            return True
+        else:
+            return False
+
+    def __eq__(self, other):
+        """
+        Implements foo == bar
+        """
+        if self.chromosome == other.chromosome and \
+           self.startbp == other.startbp and \
+           self.endbp == other.endbp:
+            return True
+        return False
+
+    def __gt__(self, other):
+        """
+        Implements foo > bar
+        """
+        if self.chromosome == other.chromosome:
+            if self.startbp > other.startbp:
+                return True
+            elif self.startbp == other.startbp:
+                if self.endbp > other.endbp:
+                    return True
+                else:
+                    return False
+            else:
+                return False
+        elif self.chromosome > other.chromosome:
+            return True
+        else:
+            return False
+
+    def __ge__(self, other):
+        """
+        Implements foo >= bar
+        """
+        if self.chromosome == other.chromosome:
+            if self.startbp > other.startbp:
+                return True
+            elif self.startbp == other.startbp:
+                if self.endbp >= other.endbp:
+                    return True
+                else:
+                    return False
+            else:
+                return False
+        elif self.chromosome > other.chromosome:
+            return True
+        else:
+            return False
+
+
 class FASTAHandler(object):
     def __init__(self, fasta_file, vcf_file = None):
         self.ffile = pysam.Fastafile(fasta_file)

pyDNase/scripts/wellington_footprints.py

@@ -18,7 +18,7 @@
 parser.add_argument("-pv","--pv_cutoffs", help=" (Provide multiple values separated by spaces) Select footprints using a range of pvalue cutoffs (default: -10 -20 -30 -40 -50 -75 -100 -300 -500 -700",default=[-10,-20,-30,-40,-50,-75,-100,-300,-500,-700],type=int, nargs="+")
 parser.add_argument("-dm","--dont-merge-footprints",action="store_true", help="Disables merging of overlapping footprints (Default: False)",default=False)
 parser.add_argument("-o","--output_prefix", help="The prefix for results files (default: <reads.regions>)",default="",type=str)
-parser.add_argument("-p", help="Number of processes to use (default: uses all CPUs)",default=0,type=int)
+parser.add_argument("-p", help="Number of processes to use, use 0 to use all cores (default: 1)",default=1,type=int)
 parser.add_argument("-A",action="store_true", help="ATAC-seq mode (default: False)",default=False)
 parser.add_argument("regions", help="BED file of the regions you want to footprint")
 parser.add_argument("reads", help="The BAM file containing the DNase-seq reads")
@@ -83,7 +83,7 @@ def xrange_from_string(range_string):
 print("track type=wiggle_0", file=wigout)
 
 #Iterate in chromosome, basepair order
-orderedbychr = [item for sublist in sorted(regions.intervals.values(),key=lambda genomicIntervalList: genomicIntervalList[0].chromosome) for item in sorted(sublist, key=lambda peak: peak.startbp)]
+orderedbychr = [item for sublist in sorted(regions.intervals.values()) for item in sublist]  # Flatten the list of lists
 puts_err("Calculating footprints...")
 
 if clargs.p: