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 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
