import BioLib
dna = BioLib.readFASTA(BioLib.getFile("grph"))
for x in dna:
for y in dna:
if (x.dna != y.dna and x.dna.endswith(y.dna[:3])):
print x.name, y.name
##Given: A collection of n (n≤10) DNA strings s1,…,sn of equal length (at most 1 kbp).
## Strings are given in FASTA format.
##
##Return: The matrix D corresponding to the p-distance dp on the given strings.
## As always, note that your answer is allowed an absolute error of 0.001.
import BioLib
dna = BioLib.readFASTA(BioLib.getFile("pdst"))
dmatrix = list()
length = len(dna[0].dna)
for x in dna:
dmatrix.append(map(lambda y: float(BioLib.hammingDistance(x,y))/length, dna))
for x in dmatrix:
for y in x:
print y,
print
import BioLib
file = open("C:\\Users\\Aaron\\Downloads\\rosalind_cons (1).txt","r")
NameDNA = BioLib.readFASTA(file)
pMatrix = {"A": list(), "C": list(), "G": list(), "T": list()}
consensus = str()
for i in range(len(NameDNA[0][1])):
a = c = g = t = 0
for x in NameDNA:
if(x[1][i]=="A"): a+=1
elif(x[1][i]=="C"): c+=1
elif(x[1][i]=="G"): g+=1
elif(x[1][i]=="T"): t+=1
pMatrix["A"].append(a)
pMatrix["C"].append(c)
pMatrix["G"].append(g)
pMatrix["T"].append(t)
if (a >= c and a >= g and a >=t): consensus+="A"
elif(c >= a and c >= g and c >=t): consensus+="C"
elif(g >= a and g >= c and g >=t): consensus+="G"
else: consensus+="T"
print consensus
for y in "ACGT":
print y+": ",
print " ".join(map(str,pMatrix[y]))
regex = str()
i = 0
while i < len(motif):
if(motif[i]=="{"):
regex+="[^"+motif[i+1]+"]"
i+=3
elif(motif[i]=="["):
regex+="("+motif[i+1]+"|"+motif[i+2]+")"
i+=4
else:
regex+=motif[i]
i+=1
return re.compile(regex)
s = motifToRegex("N{P}[ST]{P}")
proteins = BioLib.getFile("mprt").read().split()
for x in proteins:
urllib.urlretrieve("http://www.uniprot.org/uniprot/"+x+".fasta",x)
file = open(x,"r")
file.readline()
protein = file.read().replace("\n","")
match = s.search(protein)
matches = list()
if match:
print x
while match:
i = match.start()+1
matches.append(str(i))
match = s.search(protein, i)
print " ".join(matches)
import BioLib
dna = BioLib.readFASTA(BioLib.getFile("grph"))
for x in dna:
for y in dna:
if(x.dna != y.dna and x.dna.endswith(y.dna[:3])):
print x.name, y.name
import BioLib
def getCodonFrequencies():
strings = open("RNACodonTable.txt").read().split()
frequencies = dict()
for i in range(1, len(strings), 2):
if strings[i] not in frequencies:
frequencies[strings[i]] = 1
else:
frequencies[strings[i]] += 1
return frequencies
file = BioLib.getFile("mrna")
freq = getCodonFrequencies()
nums = 1
for x in file.readline():
for y in x:
if y != "\n":
nums *= freq[x]
nums *= freq["Stop"]
nums = nums % 1000000
print nums
import BioLib
def readSet(string):
newset = set()
for x in string:
if (x != "{" or x != "}" or x != " " or x != ","):
newset.add(x)
return newset
file = BioLib.getFile("seto")
n = int(file.readline())
a = readSet(file.readline())
b = readSet(file.readline())
print a
print b
import BioLib
def getMonoMassTable():
values = open("MonoIsoMassTable.txt", "r").read().split("\n")
monotable = list()
for x in values:
x = x.split()
monotable.append((float(x[1]), x[0]))
return monotable
def findFragment(monotable, weight):
for x in monotable:
if (x[0] - 0.001 < weight < x[0] + 0.001):
return x[1]
numbers = map(lambda x: float(x), BioLib.getFile("spec").read().split())
mono = getMonoMassTable()
protein = str()
for i in range(1, len(numbers)):
diff = numbers[i] - numbers[i - 1]
protein += findFragment(mono, diff)
print protein
import BioLib
basepairs = {"A":"T","C":"G","G":"C","T":"A"}
dna = BioLib.readFASTA(BioLib.getFile("revp"))[0].dna
results = list()
for i in range(len(dna)):
it = 1
while i - it >= 0 and i + it < len(dna) and dna[i+1-it] == basepairs[dna[i+it]]:
print dna[i+1-it], dna[i+it]
print it
it+=1
if 4 <= it*2 <= 12:
results.append((i-it+1, it*2))
#for x in results:
# print x[0], x[1], dna[x[0]:x[0]+x[1]]
import BioLib
import math
import itertools
file = BioLib.getFile("prob")
dna = file.readline()
cglist = map(lambda x: float(x), file.readline().split())
problist = list()
for x in cglist:
CG = math.log10(x / 2)
AT = math.log10((1 - x) / 2)
prob = 0
for y in dna:
if (y == "C" or y == "G"): prob += CG
elif (y == "A" or y == "T"): prob += AT
problist.append(prob)
s = reduce(lambda x, y: str(x) + " " + str(y), problist)
print s
i = 0
while i < len(motif):
if (motif[i] == "{"):
regex += "[^" + motif[i + 1] + "]"
i += 3
elif (motif[i] == "["):
regex += "(" + motif[i + 1] + "|" + motif[i + 2] + ")"
i += 4
else:
regex += motif[i]
i += 1
return re.compile(regex)
s = motifToRegex("N{P}[ST]{P}")
proteins = BioLib.getFile("mprt").read().split()
for x in proteins:
urllib.urlretrieve("http://www.uniprot.org/uniprot/" + x + ".fasta", x)
file = open(x, "r")
file.readline()
protein = file.read().replace("\n", "")
match = s.search(protein)
matches = list()
if match:
print x
while match:
i = match.start() + 1
matches.append(str(i))
match = s.search(protein, i)
print " ".join(matches)
import BioLib
def getCodonFrequencies():
strings = open("RNACodonTable.txt").read().split()
frequencies = dict()
for i in range(1,len(strings),2):
if strings[i] not in frequencies:
frequencies[strings[i]] = 1
else:
frequencies[strings[i]]+=1
return frequencies
file = BioLib.getFile("mrna")
freq = getCodonFrequencies()
nums = 1
for x in file.readline():
for y in x:
if y !="\n":
nums*=freq[x]
nums*=freq["Stop"]
nums = nums%1000000
print nums
import BioLib
file = BioLib.getFile("splc")
introns = map(lambda x: x.DNA, BioLib.readFASTA(file))
codons = BioLib.codonTable(True)
exon = introns.pop(0)
for x in introns:
if x in exon:
exon = exon.replace(x,"")
blocks = BioLib.DNAtoCodon(exon)
protein = str()
for x in blocks:
if(codons[x]=="Stop"):
break
protein+=codons[x]
print protein
import BioLib
def getMonoMassTable():
values = open("MonoIsoMassTable.txt","r").read().split("\n")
monotable = list()
for x in values:
x = x.split()
monotable.append((float(x[1]),x[0]))
return monotable
def findFragment(monotable, weight):
for x in monotable:
if(x[0]-0.001 < weight < x[0]+0.001):
return x[1]
numbers = map(lambda x: float(x), BioLib.getFile("spec").read().split())
mono = getMonoMassTable()
protein = str()
for i in range(1, len(numbers)):
diff = numbers[i]-numbers[i-1]
protein+=findFragment(mono,diff)
print protein
import BioLib
file = BioLib.getFile("orf")
fasta = BioLib.readFASTA(file)[0]
dnastrings = (fasta.reverseComplement(), fasta.DNA)
codons = BioLib.codonTable(True)
proteins = list()
it = 0
for x in dnastrings:
while("ATG" in x):
it = x.find("ATG", it)
x = x[it:]
protein = str()
for i in range(0, len(x),3):
if i+3 >= len(x):
break
elif codons[x[i:i+3]]=="Stop":
proteins.append(protein)
break;
else:
protein+=codons[x[i:i+3]]
it=+3
proteins = set(proteins)
for x in proteins:
print x
import BioLib
import itertools
file = BioLib.getFile("lexf")
alphabet = file.readline().split()
#n = int(file.readline())
lists = list()
n = 4
for x in itertools.product("TACG",repeat=n):
kmer = str()
for y in x:
kmer+=y
lists.append(kmer)
#print kmer
print len(lists)
import BioLib
file = BioLib.getFile("tree")
n = int(file.readline())
edges = 0
for x in file.readlines():
edges+=len(x.split())-1
print n-edges-1
import BioLib
def readSet(string):
newset = set()
for x in string:
if(x != "{" or x != "}" or x != " " or x != ","):
newset.add(x)
return newset
file = BioLib.getFile("seto")
n = int(file.readline())
a = readSet(file.readline())
b = readSet(file.readline())
print a
print b
import BioLib
file = BioLib.getFile("tree")
n = int(file.readline())
edges = 0
for x in file.readlines():
edges += len(x.split()) - 1
print n - edges - 1
import BioLib
s = BioLib.readFASTA(BioLib.getFile("kmp (1)")).pop().DNA
f = open("answer", "w")
j = 0
i = 1
failure = [0]
string = "0"
while i < len(s):
if s[i] == s[j]:
j += 1
failure.append(j)
string += " " + str(j)
i += 1
elif j > 0:
j = failure[j - 1]
else:
j = 0
i += 1
failure.append(j)
string += " 0"
f.write(string)
f.close()
print "end"
##Given: A collection of n (n≤10) DNA strings s1,…,sn of equal length (at most 1 kbp).
## Strings are given in FASTA format.
##
##Return: The matrix D corresponding to the p-distance dp on the given strings.
## As always, note that your answer is allowed an absolute error of 0.001.
import BioLib
dna = BioLib.readFASTA(BioLib.getFile("pdst"))
dmatrix = list()
length = len(dna[0].dna)
for x in dna:
dmatrix.append(
map(lambda y: float(BioLib.hammingDistance(x, y)) / length, dna))
for x in dmatrix:
for y in x:
print y,
print
import BioLib
import collections
dna = BioLib.readFASTA(BioLib.getFile("kmer"))[0].dna
kmers1 = BioLib.getKmers("ACGT",4)
kmers = dict(zip(kmers1,range(len(kmers1))))
kmercount = dict()
i = 0
while i+4 <= len(dna):
s = dna[i:i+4]
kmercount[kmers[s]] = kmercount.get(kmers[s],0)+1
i+=1
for i in range(len(kmers)):
print kmercount.get(i,0),
import BioLib
file = BioLib.getFile("iev")
couples = map(lambda x: int(x), file.readline().split())
probs = [1,1,1,0.75, 0.5,0]
ex = 0
for i in range(len(couples)):
ex+=couples[i]*probs[i]*2
print ex
import BioLib
dna = map(lambda x: x.dna, BioLib.readFASTA(BioLib.getFile("lcsm")))
dna1 = dna.pop(0)
substrings =
import BioLib
import math
import itertools
file = BioLib.getFile("prob")
dna = file.readline()
cglist = map(lambda x: float(x), file.readline().split())
problist = list()
for x in cglist:
CG = math.log10(x/2)
AT = math.log10((1-x)/2)
prob = 0
for y in dna:
if(y=="C" or y=="G"): prob+=CG
elif(y=="A" or y=="T"): prob+=AT
problist.append(prob)
s = reduce(lambda x,y: str(x)+" "+str(y), problist)
print s
import BioLib
basepairs = {"A": "T", "C": "G", "G": "C", "T": "A"}
dna = BioLib.readFASTA(BioLib.getFile("revp"))[0].dna
results = list()
for i in range(len(dna)):
it = 1
while i - it >= 0 and i + it < len(dna) and dna[i + 1 -
it] == basepairs[dna[i +
it]]:
print dna[i + 1 - it], dna[i + it]
print it
it += 1
if 4 <= it * 2 <= 12:
results.append((i - it + 1, it * 2))
#for x in results:
# print x[0], x[1], dna[x[0]:x[0]+x[1]]
import BioLib
s = BioLib.readFASTA(BioLib.getFile("kmp (1)")).pop().DNA
f = open("answer","w")
j = 0
i = 1
failure = [0]
string = "0"
while i < len(s):
if s[i]==s[j]:
j+=1
failure.append(j)
string+=" "+str(j)
i+=1
elif j > 0:
j = failure[j-1]
else:
j = 0
i+=1
failure.append(j)
string+=" 0"
f.write(string)
f.close()
print "end"
import BioLib
file = BioLib.getFile("orf")
fasta = BioLib.readFASTA(file)[0]
dnastrings = (fasta.reverseComplement(), fasta.DNA)
codons = BioLib.codonTable(True)
proteins = list()
it = 0
for x in dnastrings:
while ("ATG" in x):
it = x.find("ATG", it)
x = x[it:]
protein = str()
for i in range(0, len(x), 3):
if i + 3 >= len(x):
break
elif codons[x[i:i + 3]] == "Stop":
proteins.append(protein)
break
else:
protein += codons[x[i:i + 3]]
it = +3
proteins = set(proteins)
for x in proteins:
print x