'''
Generate a list of all pairwise comparisons of the exact matches
'''
import sys
import re
from phage import Phage
phage = Phage()
try:
f = sys.argv[1]
except:
sys.exit("Exact match file, probably phage.kmers.bacteria.rc.txt")
bg = phage.completeBacteriaIDs()
pg = phage.phageIDs()
matches = {}
for p in pg:
matches[p] = {}
for b in bg:
matches[p][b] = 0
with open(f, 'r') as fin:
for l in fin:
p = l.strip().split("\t")
m = re.findall('NC_\d+', l)
if len(m) != 2:
#sys.stderr.write("Error parsing two NC ids from " + l)
continue
from phage import Phage
phage = Phage()
try:
blastf = sys.argv[1]
except:
sys.exit(sys.argv[0] + "< blast file>")
# read the fasta file of phages to get the lengths
lens = phage.phageSequenceLengths()
sys.stderr.write("Found " + str(len(lens)) + " sequences\n")
# get the phage and bacteria so we can limit our data appropriately
bacteriaG = set(phage.completeBacteriaIDs())
phageG = set(phage.phageIDs())
hits = {}
for p in phageG:
hits[p] = {}
with open(blastf, 'r') as fin:
for l in fin:
p = l.strip().split("\t")
e = float(p[10])
if e > 0.001:
continue
m = re.findall('(NC_\d+)', p[0])
if m == []:
sys.stderr.write("WARNING: No phage found in " + p[0] + "\n")
continue
from phage import Phage
phage = Phage()
try:
f = sys.argv[1]
except:
sys.exit(
sys.argv[0] +
" <blast output file converted to NC/NC format. Probably phage.genomes.blastx"
)
count = {}
lens = phage.phageSequenceLengths()
bctG = set(phage.completeBacteriaIDs())
phgG = set(phage.phageIDs())
for p in phgG:
count[p] = {}
sys.stderr.write("Reading " + f + "\n")
with open(f, 'r') as bin:
for l in bin:
p = l.strip().split("\t")
if p[0] not in phgG:
continue
if p[1] not in bctG:
continue
if p[1] not in count[p[0]]:
count[p[0]][p[1]] = []
import sys
from phage import Phage
phage=Phage()
try:
f=sys.argv[1]
except:
sys.exit(sys.argv[0] + " <blast output file converted to NC/NC format. Probably phage.genomes.blastx")
count={}
lens=phage.phageSequenceLengths()
bctG = set(phage.completeBacteriaIDs())
phgG = set(phage.phageIDs())
for p in phgG:
count[p]={}
sys.stderr.write("Reading " + f + "\n")
with open(f, 'r') as bin:
for l in bin:
p=l.strip().split("\t")
if p[0] not in phgG:
continue
if p[1] not in bctG:
continue
if p[1] not in count[p[0]]:
count[p[0]][p[1]]=[]
'''
import sys
import re
from phage import Phage
phage = Phage()
try:
f = sys.argv[1]
except:
sys.exit("Exact match file, probably phage.kmers.bacteria.rc.txt")
bg = phage.completeBacteriaIDs()
pg = phage.phageIDs()
matches={}
for p in pg:
matches[p]={}
for b in bg:
matches[p][b] = 0
with open(f, 'r') as fin:
for l in fin:
p=l.strip().split("\t")
m=re.findall('NC_\d+', l)
if len(m) != 2:
#sys.stderr.write("Error parsing two NC ids from " + l)
continue
sys.stderr.write("No length for " + pnc + "\n")
continue
m = re.findall('(NC_\d+)', p[1])
if m == []:
sys.stderr.write("WARNING: No bacteria found in " + p[1] + "\n")
continue
bnc = m[0]
if bnc not in hits[pnc]:
hits[pnc][bnc] = []
for i in xrange(lens[pnc] + 1):
hits[pnc][bnc].append(0)
for i in range(int(p[6]), int(p[7]) + 1):
hits[pnc][bnc][i] = 1
# now print the table of phage and bacteria
bacteria = phage.completeBacteriaIDs()
phages = phage.phageIDs()
print "Bacteria\t" + "\t".join(phages)
for b in bacteria:
print b
for p in phages:
if hits[p][b]:
print "\t" + str(1.0 * sum(hits[p][b]) / lens[b])
else:
print "\t0"
print
import sys
from phage import Phage
phage=Phage()
try:
f=sys.argv[1]
except:
sys.exit(sys.argv[0] + " <blast output file converted to NC/NC format. Probably phage.genomes.blastx")
count={}
bctG = phage.completeBacteriaIDs()
phgG = phage.phageIDs()
for p in phgG:
count[p]={}
for b in bctG:
count[p][b]=0
with open(f, 'r') as bin:
for l in bin:
p=l.strip().split("\t")
if p[0] in count and p[1] in count[p[0]]:
count[p[0]][p[1]] = count[p[0]].get(p[1], 0) + 1
for p in count:
for b in count[p]:
print("\t".join([p, b, str(count[p][b])]))
phage=Phage()
try:
blastf=sys.argv[1]
except:
sys.exit(sys.argv[0] + "< blast file>")
# read the fasta file of phages to get the lengths
lens=phage.phageSequenceLengths()
sys.stderr.write("Found " + str(len(lens)) + " sequences\n")
# get the phage and bacteria so we can limit our data appropriately
bacteriaG = set(phage.completeBacteriaIDs())
phageG = set(phage.phageIDs())
hits = {}
for p in phageG:
hits[p]={}
with open(blastf, 'r') as fin:
for l in fin:
p=l.strip().split("\t")
e=float(p[10])
if e > 0.001:
continue
m=re.findall('(NC_\d+)', p[0])
if m == []:
sys.stderr.write("WARNING: No phage found in " + p[0] + "\n")
continue
