def phageSequences(self, fafile=datadir + 'phage_with_host.fna'):
'''Get the DNA sequences of the phages that we are interested in '''
if len(self.host) == 0:
self.phageHost()
fa = readFasta(fafile)
for i in fa:
m = re.findall('(NC_\d+)', i)
if m[0] not in self.host:
continue
self.fasta[m[0]] = fa[i]
return self.fasta
import os
import re
try:
orfF = sys.argv[1]
dir = sys.argv[2]
type = sys.argv[3]
except:
sys.exit(
sys.argv[0] +
" <orfs file> <dir to put them> <type must be one of phage or genome>")
if type not in ['phage', 'genome']:
sys.exit(type + " is not valid: must be either phage or genome\n")
fa = rob.readFasta(orfF)
if not os.path.exists(dir):
os.mkdir(dir)
for i in fa:
if type == 'genome':
m = re.findall('([\w\.\-]+)\s+\[(\w+)\]\s+\[(.*)\]', i)
if m == []:
continue
gene, genome, locus = m[0]
else:
x = i.replace(' COMPLEMENT', '')
m = x.split(' ')
gene, genome, locus = m
with open(os.path.sep.join([dir, genome]), 'a') as out:
out.write('>' + i + "\n" + fa[i] + "\n")
sys.path.append('/home3/redwards/bioinformatics/Modules')
import rob
import robseq
# this is a hash of all possible codons
codons = robseq.geneticCode().keys()
codons.sort()
try:
file = sys.argv[1]
except:
sys.exit(sys.argv[0] + " <fasta file of coding regions>")
fa = rob.readFasta(file)
count={}
cds={}
for id in fa:
if ((1.0 * len(fa[id])) / 3) != len(fa[id])/3:
sys.stderr.write("Sequence " + id + " does not appear to be a multiple of 3 nucleotides. Skipped\n")
continue
pieces = id.split(" ")
locus = pieces[1]
if locus not in count:
count[locus]=0
cds[locus]={}
for codon in codons:
cds[locus][codon]=0
p=0
while p<len(fa[id]):
complement = False
m = locationre.match(line)
if m:
start = m.group(1)
end = m.group(2)
else:
m = locationrerc.match(line)
if m:
complement = True
start = m.group(1)
end = m.group(2)
else:
sys.stderr.write("Can't parse an apparent location at : " + line + "\n")
fa = rob.readFasta(fnaf)
ncre = re.compile('.*ref\|(\w+)')
for id in fa:
m = ncre.match(id)
if not m:
sys.stderr.write("No apparent NC_ idenitifer in this sequence id: " + id + "\n")
continue
locus = m.group(1)
for l in locations[locus]:
[start, end, complement] = locations[locus][l]
if complement:
print ">" + l + " " + locus + " " + end + "_" + start + " COMPLEMENT"
print rob.rc(fa[id][int(start)-1:int(end)])
else:
import rob
import sys
# 1404927386.fasta analyzed_sequences.txt annotations.txt
#
faf = None
try:
faf = sys.argv[1]
except IndexError:
sys.stderr.write("Please provide a fasta file\n")
sys.exit(0)
fa = rob.readFasta(faf)
analyzed = []
with open('analyzed_sequences.txt', 'r') as asf:
for line in asf:
pieces = line.rstrip()
analyzed.append(pieces)
if pieces not in fa:
sys.stderr.write(pieces + " has been analyzed but is not in " +
faf + "\n")
for f in fa:
if f not in analyzed:
sys.stderr.write("NOT ANALYZED: " + f + "\n")
annotated = []
with open('annotations.txt', 'r') as asf:
import rob
import sys
import os
import re
try:
orfF = sys.argv[1]
dir = sys.argv[2]
type = sys.argv[3]
except:
sys.exit(sys.argv[0] + " <orfs file> <dir to put them> <type must be one of phage or genome>")
if type not in ['phage', 'genome']:
sys.exit(type + " is not valid: must be either phage or genome\n")
fa = rob.readFasta(orfF)
if not os.path.exists(dir):
os.mkdir(dir)
for i in fa:
if type == 'genome':
m = re.findall('([\w\.\-]+)\s+\[(\w+)\]\s+\[(.*)\]', i)
if m == []:
continue
gene, genome, locus = m[0]
else:
x=i.replace(' COMPLEMENT', '')
m=x.split(' ')
gene, genome, locus = m
with open(os.path.sep.join([dir, genome]), 'a') as out:
out.write('>' + i + "\n" + fa[i] + "\n")
m = locationre.match(line)
if m:
start = m.group(1)
end = m.group(2)
else:
m = locationrerc.match(line)
if m:
complement = True
start = m.group(1)
end = m.group(2)
else:
sys.stderr.write("Can't parse an apparent location at : " +
line + "\n")
fa = rob.readFasta(fnaf)
#ncre = re.compile('.*ref\|(\w+)')
ncre = re.compile('(NC_\d+)')
for id in fa:
m = ncre.match(id)
if not m:
sys.stderr.write("No apparent NC_ idenitifer in this sequence id: " +
id + "\n")
continue
locus = m.group(1)
for l in locations[locus]:
[start, end, complement] = locations[locus][l]
if complement:
print ">" + l + " " + locus + " " + end + "_" + start + " COMPLEMENT"
def longestCommonSubstring(s1, s2):
'''This is taken straight from the wikibooks page, and is creating a matrix to look up. Dynamic programming'''
m = [[0] * (1 + len(s2)) for i in xrange(1 + len(s1))]
longest, x_longest = 0, 0
for x in xrange(1, 1 + len(s1)):
for y in xrange(1, 1 + len(s2)):
if s1[x - 1] == s2[y - 1]:
m[x][y] = m[x - 1][y - 1] + 1
if m[x][y] > longest:
longest = m[x][y]
x_longest = x
else:
m[x][y] = 0
return s1[x_longest - longest: x_longest]
fa1=rob.readFasta(file1)
fa2=rob.readFasta(file2)
longest = ""
for id1 in fa1.keys():
for id2 in fa2.keys():
sys.stderr.write("Comparing " + id1 + " to " + id2 + "\n")
test = longestCommonSubstring(fa1[id1], fa2[id2])
if len(test) > len(longest):
longest = test
sys.stderr.write("Comparing rc " + id1 + " to " + id2 + "\n")
test = longestCommonSubstring(rob.rc(fa1[id1]), fa2[id2])
if len(test) > len(longest):
longest = test
print "\t".join([file1, file2, len(longest), longest])
import rob
import sys
# 1404927386.fasta analyzed_sequences.txt annotations.txt
#
faf=None
try:
faf=sys.argv[1]
except IndexError:
sys.stderr.write("Please provide a fasta file\n")
sys.exit(0)
fa = rob.readFasta(faf)
analyzed=[]
with open('analyzed_sequences.txt', 'r') as asf:
for line in asf:
pieces=line.rstrip()
analyzed.append(pieces)
if pieces not in fa:
sys.stderr.write(pieces + " has been analyzed but is not in " + faf + "\n")
for f in fa:
if f not in analyzed:
sys.stderr.write("NOT ANALYZED: " + f + "\n")