def listIntervals(operon,fastaindex):
intervals = []
operon = interval_filter.overlaps(operon,fastaindex,False)
operon = sorted(operon,key=lambda x:x[5])
toxins = [t for t in operon if t[1].split('.')[0]=='toxin']
starts,ends = zip(*toxins)[5:7]
gene = operon[0]
st,end = map(int,gene[5:7])
front = st
name = gene[0]
print "Functions",[gene[1].split('.')[0] for gene in operon ]
strand = fasta.strand(fasta.getFrame(gene[0]))
#if strand== "+":
# st,end = min(map(int,starts)),min(map(int,ends))
# front = min(st,end)
#else:
# st,end = max(map(int,starts)),max(map(int,ends))
# front = max(st,end)
for i in xrange(0,len(operon)):
gene = operon[i]
name = gene[0]
cluster = gene[1]
function = cluster.split('.')[0]
st,end = map(int,gene[5:7])
if st>end: st,end = end,st
intervals.append( (function,st-front,end-front) )
ints = []
for intv in intervals:
func,st,end = intv
interval = xrange(st,end)
funcs = [func]*len(interval)
ints+=zip(funcs,interval)
return ints
def countMidpoints(operon,fastaindex):
intervals = []
operon = interval_filter.overlaps(operon,fastaindex,backtran=False)
operon = sorted(operon,key=lambda x:x[5])
#toxins = [t for t in operon if t[1].split('.')[0]=='toxin']
#starts,ends = zip(*operon)[5:7]
gene = operon[0]
strand = fasta.strand(fasta.getFrame(gene[0]))
name = gene[0]
st,end = map(int,gene[5:7])
front = st
#if strand== "+":
# st,end = min(map(int,starts)),min(map(int,ends))
# front = min(st,end)
#else:
# st,end = max(map(int,starts)),max(map(int,ends))
# front = max(st,end)
#print "Operon",name,"Strand",strand
for i in xrange(1,len(operon)):
gene = operon[i]
name = gene[0]
cluster = gene[1]
function = cluster.split('.')[0]
st,end = map(int,gene[5:7])
mid = (st+end)/2 - front
#print function,'st',st,'end',end,'front',front,'mid',mid
intervals.append( (function,mid) )
return intervals
def test2(self):
#all_hits=sorted(self.queries,key=lambda x: x[6])
#all_hits=sorted(all_hits,key=lambda x: x[5])
#Sort by genome name
#all_hits=sorted(all_hits,key=lambda x: x[-1])
reduced = interval_filter.overlaps(self.queries,self.testfai)
self.assertItemsEqual(reduced,
[ ('CP002279.1','toxin.fa.cluster2.fa',0,0,100,25000,25100,
'Mesorhizobium opportunistum WSM2075, complete genome','-','AAQEIWJ.1'),
('CP002279.1','transport.fa.cluster2.fa',0,0,100,25200,25300,
'Mesorhizobium opportunistum WSM2075, complete genome','-','BAQEIWJ.1'),
('CP002279.1','modifier.fa.cluster2.fa',0,0,100,25400,25500,
'Mesorhizobium opportunistum WSM2075, complete genome','-','CAQEIWJ.1'),
('CP002279.1','regulator.fa.cluster2.fa',0,0,100,25600,25700,
'Mesorhizobium opportunistum WSM2075, complete genome','-','DAQEIWJ.1'),
('CP002279.1','immunity.fa.cluster2.fa',0,0,100,25800,26900,
'Mesorhizobium opportunistum WSM2075, complete genome','-','EAQEIWJ.1'),
('CP002279.1','immunity.fa.cluster2.fa',0,0,100, 740038, 740138,
'Mesorhizobium opportunistum WSM2075, complete genome','-','FAQEIWJ.1'),
('CP002279.1','transport.fa.cluster2.fa',0,0,100,35127,35356,
'Mesorhizobium opportunistum WSM2075, complete genome','-','GAQEIWJ.1'),
('CP002279.1','transport.fa.cluster2.fa',0,0,100,45127,45356,
'Mesorhizobium opportunistum WSM2075, complete genome','-','KAQEIWJ.1')])
