diff --git a/README b/README
index 0c36eca9643a33386885e673e949c2c36958bad2..be4d9f418d506a5dfa2521e96542d47c5f586da9 100644
--- a/README
+++ b/README
@@ -30,7 +30,6 @@ git pull origin master
# Requirements #
################
-- Python 2
- Python 3
- BioPython for Python3
diff --git a/SVsim b/SVsim
index 6aabb07415e9a439ba0a6f75877d358df29616e0..619f3aef3ad31c3eb6729e7a778919041edd7c5a 100755
--- a/SVsim
+++ b/SVsim
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
# -*- Mode: Python -*-
import sys
@@ -30,8 +30,8 @@ def handleException(err):
(foo, bar, tb) = sys.exc_info();
tbarr = traceback.extract_tb(tb);
(filename, lineno, funcname, foo) = tbarr[-1];
- print >>sys.stderr, str(err);
- print >>sys.stderr, "Error occurred in line", lineno, "of function", funcname, "of Python script", filename;
+ print(str(err), file=sys.stderr);
+ print("Error occurred in line", lineno, "of function", funcname, "of Python script", filename, file=sys.stderr);
return;
# Global Variables
@@ -49,13 +49,13 @@ maxSeqNameLen = 0;
def complement(base):
try:
inx = "ACGTacgt".index(base);
- except StandardError as err:
+ except Exception as err:
sys.stderr.write("Invalid base passed to complement (" + base + ")\n");
return base;
return "TGCAtgca"[inx];
def ensureACGTRegion(instr, off, len):
- for i in xrange(off, off+len):
+ for i in range(off, off+len):
base = instr[i];
if ("ACGTacgt".find(base) == -1):
return False;
@@ -85,7 +85,7 @@ def makeEventID(lreg, rreg):
if (len(lreg.events) == 0):
eventID += lreg.seq.name;
else:
- for i in xrange(0, len(lreg.events)):
+ for i in range(0, len(lreg.events)):
eventID += lreg.events[i].eventID();
if (i != len(lreg.events) - 1):
eventID += ":";
@@ -93,7 +93,7 @@ def makeEventID(lreg, rreg):
if (len(rreg.events) == 0):
eventID += rreg.seq.name;
else:
- for i in xrange(0, len(rreg.events)):
+ for i in range(0, len(rreg.events)):
eventID += rreg.events[i].eventID();
if (i != len(rreg.events) - 1):
eventID += ":";
@@ -125,9 +125,9 @@ class sequence (object):
def reportRandomLocationError():
if (GlobalOptions.WGM and GlobalOptions.distinct):
- raise StandardError("Unable to find valid region for event. Overloading event density in WGM distinct mode.");
+ raise Exception("Unable to find valid region for event. Overloading event density in WGM distinct mode.");
else:
- raise StandardError("Unable to find valid region for event.");
+ raise Exception("Unable to find valid region for event.");
# The library of all reference sequences
class refLib (object):
@@ -145,7 +145,7 @@ class refLib (object):
seqlen = int(splitLine[1]);
sstring = referenceFile.fetch(seqname);
temp = []
- for i in xrange(1, ploidy+1):
+ for i in range(1, ploidy+1):
seq = sequence(seqname, seqlen, sstring, i);
# seq = sequence(seqname, seqlen, "", i);
temp.append(seq);
@@ -159,7 +159,7 @@ class refLib (object):
def printDebug(self):
for seqlist in self.seqs:
for seq in seqlist:
- print seq.name, seq.num, seq.length;
+ print(seq.name, seq.num, seq.length);
def reset(self):
for seqlist in self.seqs:
@@ -174,7 +174,7 @@ class refLib (object):
return self.getRandomOrigRegion(pad, length);
def getRandomOrigRegion(self, pad, length):
- for i in xrange(0, 1000):
+ for i in range(0, 1000):
off = random.randint(0, self.totalOrigLength - 1);
loc = self.findSeqLocation(off);
soff = loc.offset - pad;
@@ -192,7 +192,7 @@ class refLib (object):
seqnum = random.randint(0, GlobalOptions.ploidy - 1);
print seqnum;
'''
- for i in xrange(0, 1000):
+ for i in range(0, 1000):
off = random.randint(0, self.totalMutLength - 1)
loc = self.findRLLocation(off, seqnum);
soff = loc.offset - pad;
@@ -249,7 +249,7 @@ class refLib (object):
lbreak = sbreaksSeq[0];
ebreaksSeq = [];
ebreaksSeq.append(lbreak);
- for i in xrange(1, len(sbreaksSeq)):
+ for i in range(1, len(sbreaksSeq)):
rbreak = sbreaksSeq[i];
if (abs(lbreak[1] - rbreak[1]) > 1):
ebreaksSeq.append(rbreak);
@@ -342,7 +342,7 @@ class refLib (object):
# Now add up the states.
count = 0;
retval = []
- for i in xrange(0, maxstates):
+ for i in range(0, maxstates):
if (states[i]):
count += 1;
retval.append(str(i));
@@ -389,7 +389,7 @@ class refLib (object):
# Now add up the states.
count = 0;
retval = []
- for i in xrange(0, maxstates):
+ for i in range(0, maxstates):
if (states[i]):
count += 1;
retval.append(str(i));
@@ -482,7 +482,7 @@ class region:
totalBasesOutput += outlen;
if (self.inverted):
ERO = self.SRO();
- for i in xrange(soff, soff + outlen):
+ for i in range(soff, soff + outlen):
fastaFile.write(complement(self.seq.seq[ERO - i]));
else:
fastaFile.write(self.seq.seq[self.rSRO + soff:self.rSRO + soff + outlen]);
@@ -571,7 +571,7 @@ class regionList:
def findAllRegLocs(self, seq, offset):
retval = [];
- for i in xrange(0, len(self.regList)):
+ for i in range(0, len(self.regList)):
reg = self.regList[i];
if (reg.seq == seq and offset >= reg.rSRO and offset <= reg.rERO()):
rlOffset = reg.MROFF(offset);
@@ -584,7 +584,7 @@ class regionList:
# TODO: This should be doing a binary search.
# Maybe Bisect can be used, but how will it know what is the comparison function?
def findOffset(self, offset, startinx = 0):
- for i in xrange(startinx, len(self.regList)):
+ for i in range(startinx, len(self.regList)):
reg = self.regList[i];
if (offset >= reg.rlSRO and offset < reg.rlSRO + reg.len):
return (i, offset - reg.rlSRO);
@@ -608,7 +608,7 @@ class regionList:
if (not self.regList[rinx].ensureValid(0, roff)):
return False;
# Do whatever is left in the middle.
- for i in xrange(linx+1, rinx):
+ for i in range(linx+1, rinx):
if (not self.regList[i].ensureValid()):
return False;
return True;
@@ -622,7 +622,7 @@ class regionList:
(rinx, roff) = self.findOffset(offset + length, linx);
# Copy the regions of interest into a new list.
newRL = regionList();
- for i in xrange(linx, rinx+1):
+ for i in range(linx, rinx+1):
newreg = (self.regList[i].copy());
newRL.append(newreg);
# Do the cutting.
@@ -683,7 +683,7 @@ class regionList:
self.maybeMergeRegions(inx);
# Now we need to fix up the rlSROs
length = retregion.len;
- for i in xrange(inx, len(self.regList)):
+ for i in range(inx, len(self.regList)):
reg = self.regList[i];
reg.rlSRO -= length;
self.totlen -= length;
@@ -706,7 +706,7 @@ class regionList:
del self.regList[delstart:rinx+1];
self.maybeMergeRegions(linx);
# Fix up the trailing rlSROs
- for i in xrange(delstart, len(self.regList)):
+ for i in range(delstart, len(self.regList)):
reg = self.regList[i];
reg.rlSRO -= length;
self.totlen -= length;
@@ -756,7 +756,7 @@ class regionList:
if (len(self.regList) < 2):
return breakSet;
lreg = self.regList[0];
- for i in xrange(1, len(self.regList)):
+ for i in range(1, len(self.regList)):
rreg = self.regList[i];
if (self.checkMergeable(lreg, rreg)):
lreg = rreg;
@@ -791,7 +791,7 @@ class regionList:
if (GlobalOptions.leftonly):
endlen = 2;
lreg = self.regList[0];
- for i in xrange(1, endlen):
+ for i in range(1, endlen):
rreg = self.regList[i];
if (self.checkMergeable(lreg, rreg)):
lreg = rreg;
@@ -819,7 +819,7 @@ class regionList:
else:
(inx, off) = self.findOffset(soff);
curlen = 0;
- for i in xrange(inx, len(self.regList)):
+ for i in range(inx, len(self.regList)):
reg = self.regList[i];
reglen = reg.len - off;
# sys.stderr.write(str(reglen) + '\n');
@@ -853,16 +853,16 @@ class regionList:
addlen = len(newRL.regList);
selflen = len(self.regList);
# Expand the list so we can copy up.
- self.regList.extend(xrange(0,addlen)); # xrange gives bogus iterable as we don't care what the values are.
+ self.regList.extend(range(0,addlen)); # xrange gives bogus iterable as we don't care what the values are.
# We need to go backwards to allow the copy up without smashing.
- for i in xrange(selflen-1, inx-1, -1):
+ for i in range(selflen-1, inx-1, -1):
reg = self.regList[i];
reg.rlSRO += addbases;
self.regList[i+addlen] = reg;
self.totlen += addbases;
reflib.totalMutLength += addbases;
# Now do the insertions with rlSRO fixups as we go.
- for i in xrange(0, addlen):
+ for i in range(0, addlen):
reg = newRL.regList[i];
reg.rlSRO = currlSRO;
currlSRO += reg.len;
@@ -1026,7 +1026,7 @@ class simpleLocationEvent (object):
elocp = random.choice(EROlocs);
slocp = self.findClosest(elocp, SROlocs);
else:
- raise StandardError("Invalid endpoint select mode: " + GlobalOptions.select);
+ raise Exception("Invalid endpoint select mode: " + GlobalOptions.select);
(sloc, sinv) = slocp;
(eloc, einv) = elocp;
@@ -1082,7 +1082,7 @@ class simpleLocationEvent (object):
return True;
def performWGMEvent(self):
- chromorder = range(0, len(self.seqlist));
+ chromorder = list(range(0, len(self.seqlist)));
if (GlobalOptions.select != "F"):
random.shuffle(chromorder);
for i in chromorder:
@@ -1396,7 +1396,7 @@ def simulateSV():
if (GlobalOptions.reference is None):
myError("Reference File (-r) argument is Missing", parser);
reflib = refLib(GlobalOptions.reference, GlobalOptions.ploidy);
- print >>sys.stderr, "Input", reflib.seqcount, "sequences totaling", reflib.totalOrigLength, "bases";
+ print("Input", reflib.seqcount, "sequences totaling", reflib.totalOrigLength, "bases", file=sys.stderr);
# Set up the random number generator
random.seed(GlobalOptions.seed);
@@ -1423,7 +1423,7 @@ def simulateSV():
continue;
s = line.strip().split();
op = s[0];
- for i in xrange(0, GlobalOptions.repeat):
+ for i in range(0, GlobalOptions.repeat):
# Delete, Duplicate, InsertRandom and Invert all have the same arguments.
if (op == "DEL" or op == "DUP" or op == "INR" or op == "INV"):
startlen = int(s[1]);
@@ -1434,7 +1434,7 @@ def simulateSV():
if (len(s) >= 4):
inc = int(s[3]);
endlen = int(s[2]) + inc;
- for oplen in xrange(startlen, endlen, inc):
+ for oplen in range(startlen, endlen, inc):
if (op == "INR"):
e = insertEvent(op, oplen);
else:
@@ -1549,7 +1549,7 @@ def simulateSV():
chrom = e.performWGMEvent();
if (chrom == 0):
failCount += 1;
- print count, e.seqlist[0].name, e.rSRO, e.rERO, e.strand1, e.strand2, "Failed", failCount;
+ print(count, e.seqlist[0].name, e.rSRO, e.rERO, e.strand1, e.strand2, "Failed", failCount);
continue;
chromRL = e.seqlist[chrom-1].RL;
chromLen = chromRL.totlen;
@@ -1558,9 +1558,9 @@ def simulateSV():
numbreaks = len(breaks);
states = reflib.countCNstates();
numstates = len(states);
- print count, e.seqlist[0].name, e.type, e.rSRO, e.rERO, e.strand1, e.strand2, "Succeeded", failCount, chromLen, maxChromLen, numbreaks, numstates, states
+ print(count, e.seqlist[0].name, e.type, e.rSRO, e.rERO, e.strand1, e.strand2, "Succeeded", failCount, chromLen, maxChromLen, numbreaks, numstates, states)
chromRL.printDebug();
- print
+ print()
elif (GlobalOptions.loop == "P"):
# Loop for doing probability runs.
@@ -1570,7 +1570,7 @@ def simulateSV():
countsperbin = GlobalOptions.repeat;
binwidth = 1;
breakbins = [0] * totbins;
- for i in xrange(totbins-1,totbins):
+ for i in range(totbins-1,totbins):
# Use following for no failed events at the criteria.
while (totout < GlobalOptions.repeat):
# Use the following for correct number of breakpoints as the criteria.
@@ -1602,7 +1602,7 @@ def simulateSV():
# breakbins[binnum] = breakbins[binnum] + 1;
totout += 1;
states = reflib.countBigCNstates(GlobalOptions.minseg);
- print "\t".join([str(totout), str(binnum), str(totiter), str(len(breaks)), str(len(states)), str(failCount)]);
+ print("\t".join([str(totout), str(binnum), str(totiter), str(len(breaks)), str(len(states)), str(failCount)]));
sys.stdout.flush();
random.shuffle(eventList);
reflib.reset();
@@ -1619,8 +1619,8 @@ def simulateSV():
totbins = int(((len(eventList))/binwidth) + 0.5);
sys.stderr.write("Filling " + str(totbins) + " bins.\n");
breakbins = [0] * totbins;
- binrange = range(1,binwidth*totbins + 1, binwidth);
- for i in xrange(1,totbins):
+ binrange = list(range(1,binwidth*totbins + 1, binwidth));
+ for i in range(1,totbins):
while (breakbins[i] < countsperbin):
totiter += 1;
failCount = 0;
@@ -1640,7 +1640,7 @@ def simulateSV():
breakbins[binnum] = breakbins[binnum] + 1;
totout += 1;
states = reflib.countBigCNstates(GlobalOptions.minseg);
- print "\t".join([str(totout), str(binnum), str(totiter), str(numbreaks), str(len(states)), str(failCount), str(max(maxChromLen))]);
+ print("\t".join([str(totout), str(binnum), str(totiter), str(numbreaks), str(len(states)), str(failCount), str(max(maxChromLen))]));
sys.stdout.flush();
break;
if (max(maxChromLen) > GlobalOptions.maxchromlen):
@@ -1649,7 +1649,7 @@ def simulateSV():
random.shuffle(eventList);
reflib.reset();
else:
- raise StandardError("Invalid loop type: " + GlobalOptions.loop);
+ raise Exception("Invalid loop type: " + GlobalOptions.loop);
return;
@@ -1660,7 +1660,7 @@ def main():
except IOError as err:
sys.stderr.write("IOError " + str(err) + '\n');
return;
- except StandardError as err:
+ except Exception as err:
sys.stderr.write("StandardError\n");
handleException(err);
sys.exit(1);
diff --git a/svinterval.py b/svinterval.py
index 7632d976c09af744c3a2d92f113dd3d86ec10f49..0078b6b183c820a6092fda930b1426307f3d4dc1 100644
--- a/svinterval.py
+++ b/svinterval.py
@@ -1,8 +1,7 @@
#! /usr/bin/env python
-import argparse, sys
-import os.path
+import sys
from math import fabs
import numpy
diff --git a/svreader/__init__.py b/svreader/__init__.py
index a15e4ec073d0d9e76acd74825a341e822c295974..1bc14d6cf76d053edb71734edcc708528ce300ce 100644
--- a/svreader/__init__.py
+++ b/svreader/__init__.py
@@ -1,14 +1,11 @@
-import sys
import os
import re
-from subprocess import call
-
import vcf
from pybedtools import BedTool
from pybedtools import create_interval_from_list
-from pysam import VariantFile, tabix_compress, tabix_index
+from pysam import tabix_compress, tabix_index
from svreader.vcf_utils import get_template
from svrunner_utils import eprint, vcf_to_pybed
diff --git a/svreader/vcfwrapper.py b/svreader/vcfwrapper.py
index d49db5fc7be7c69a3b1457931703241be6abf98f..ce5bc9ee5600435c42f8a5f28a4fc756ad533bbf 100644
--- a/svreader/vcfwrapper.py
+++ b/svreader/vcfwrapper.py
@@ -1,8 +1,4 @@
-import logging
-import sys
-import os
-
-from pysam import VariantFile, tabix_compress, tabix_index
+from pysam import VariantFile
from svreader import SVRecord, SVReader, SVWriter