import argparse
import os
import time
from helpers import read_strings
from snp import Trie
if __name__=='__main__':
start = time.time()
parser = argparse.ArgumentParser('BA9B Implement TrieMatching')
parser.add_argument('--sample', default=False, action='store_true', help='process sample dataset')
parser.add_argument('--extra', default=False, action='store_true', help='process extra dataset')
parser.add_argument('--rosalind', default=False, action='store_true', help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
trie = Trie(['ATCG','GGGT'])
print (trie.MatchAll('AATCGGGTTCAATCGGGGT'))
if args.extra:
Input,Expected = read_strings('data/TrieMatching.txt',init=0)
trie = Trie(Input[1:])
Actual = trie.MatchAll(Input[0])
Expected = [int(e) for e in Expected[0].split()]
print (len(Expected),len(Actual))
diffs = [(e,a) for e,a in zip(Expected,Actual) if e!=a]
print (diffs)
elapsed = time.time()-start
minutes = int(elapsed/60)
seconds = elapsed-60*minutes
print (f'Elapsed Time {minutes} m {seconds:.2f} s')
if __name__ == '__main__':
start = time.time()
parser = argparse.ArgumentParser(
'BA10G Perform a Multiple Sequence Alignment with a Profile HMM ')
parser.add_argument('--sample',
default=False,
action='store_true',
help='process sample dataset')
parser.add_argument('--rosalind',
default=False,
action='store_true',
help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
pass
if args.rosalind:
Input = read_strings(
f'data/rosalind_{os.path.basename(__file__).split(".")[0]}.txt')
Result = None
print(Result)
with open(f'{os.path.basename(__file__).split(".")[0]}.txt', 'w') as f:
for line in Result:
f.write(f'{line}\n')
elapsed = time.time() - start
minutes = int(elapsed / 60)
seconds = elapsed - 60 * minutes
print(f'Elapsed Time {minutes} m {seconds:.2f} s')
action='store_true',
help='process sample dataset')
parser.add_argument('--extra',
default=False,
action='store_true',
help='process extra dataset')
parser.add_argument('--rosalind',
default=False,
action='store_true',
help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
pass
if args.extra:
Input, Expected = read_strings('data/....txt', init=0)
trie = Trie(Input)
Actual = None
Expected.sort()
print(len(Expected), len(Actual))
diffs = [(e, a) for e, a in zip(Expected, Actual) if e != a]
print(diffs)
if args.rosalind:
Input = read_strings(
f'data/rosalind_{os.path.basename(__file__).split(".")[0]}.txt')
Result = None
print(Result)
with open(f'{os.path.basename(__file__).split(".")[0]}.txt', 'w') as f:
for line in Result:
if args.banana:
r, p, LCP = SuffixArray('panamabananas$', auxiliary=True, padLCP=True)
for edge, _ in SuffixArray2Tree('panamabananas$',
r,
LCP,
trace=args.trace):
print(edge)
if args.sample:
for edge, _ in SuffixArray2Tree('GTAGT$', [5, 2, 3, 0, 4, 1],
[0, 0, 0, 2, 0, 1],
trace=args.trace):
print(edge)
if args.extra:
Input, Expected = read_strings('data/SuffixTreeFromSuffixArray.txt',
init=0)
Result = [
edge for edge, _ in
SuffixArray2Tree(Input[0], [int(s) for s in Input[1].split(',')],
[int(s) for s in Input[2].split(',')],
trace=args.trace)
]
print(f'Expected {len(Expected)} Edges, actual = {len(Result)}')
Result.sort(key=lambda x: f'{len(x):04}{x}')
Expected.sort(key=lambda x: f'{len(x):04}{x}')
i = 0
j = 0
while i < len(Expected) and j < len(Result):
if Expected[i] == Result[j]:
i += 1
def FindApproximateMatches(Text,Patterns,d):
pass
if __name__=='__main__':
start = time.time()
parser = argparse.ArgumentParser('BA9O Find All Approximate Occurrences of a Collection of Patterns in a String ')
parser.add_argument('--sample', default=False, action='store_true', help='process sample dataset')
parser.add_argument('--extra', default=False, action='store_true', help='process extra dataset')
parser.add_argument('--rosalind', default=False, action='store_true', help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
print (FindApproximateMatches('ACATGCTACTTT', ['ATT', 'GCC', 'GCTA', 'TATT'], 1))
if args.extra:
Input,Expected = read_strings('data/MultipleApproximatePatternMatching.txt',init=0)
Result = FindApproximateMatches(Input[0],int(Input[1:-1],int(Input[-1])))
for a,b in Result:
print (a,b)
if args.rosalind:
Input = read_strings(f'data/rosalind_{os.path.basename(__file__).split(".")[0]}.txt')
Result = FindApproximateMatches(Input[0],int(Input[1:-1],int(Input[-1])))
print (Result)
with open(f'{os.path.basename(__file__).split(".")[0]}.txt','w') as f:
for line in Result:
f.write(f'{line}\n')
elapsed = time.time() - start
minutes = int(elapsed/60)
#pass
#else:
#pass
if __name__=='__main__':
start = time.time()
parser = argparse.ArgumentParser('BA9E Find the Longest Substring Shared by Two Strings')
parser.add_argument('--sample', default=False, action='store_true', help='process sample dataset')
parser.add_argument('--extra', default=False, action='store_true', help='process extra dataset')
parser.add_argument('--rosalind', default=False, action='store_true', help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
print (FindLongestRepeat('TCGGTAGATTGCGCCCACTC',
'AGGGGCTCGCAGTGTAAGAA'))
if args.extra:
sys.setrecursionlimit(2000)
Input,Expected = read_strings('data/LongestSharedSubstring.txt',init=0)
#print (Input[0])
Actual = FindLongestRepeat(Input[0],Input[1])
print (len(Expected[0]),len(Actual))
print (Expected[0])
print (Actual)
if args.rosalind:
pass
elapsed = time.time()-start
minutes = int(elapsed/60)
seconds = elapsed-60*minutes
print (f'Elapsed Time {minutes} m {seconds:.2f} s')
action='store_true',
help='process sample dataset')
parser.add_argument('--extra',
default=False,
action='store_true',
help='process extra dataset')
parser.add_argument('--rosalind',
default=False,
action='store_true',
help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
print(FindShortestNonShared('CCAAGCTGCTAGAGG', 'CATGCTGGGCTGGCT'))
if args.extra:
Input, Expected = read_strings('data/ShortestNonSharedSubstring.txt',
init=0)
print(Expected[0])
Actual = FindShortestNonShared(Input[0], Input[1])
print(len(Expected[0]), len(Actual))
print(Expected[0])
print(Actual)
if args.rosalind:
Input = read_strings(
f'data/rosalind_{os.path.basename(__file__).split(".")[0]}.txt')
Result = FindShortestNonShared(Input[0], Input[1])
print(Result)
with open(f'{os.path.basename(__file__).split(".")[0]}.txt', 'w') as f:
f.write(f'{Result}\n')
elapsed = time.time() - start
default=False,
action='store_true',
help='process extra dataset')
parser.add_argument('--rosalind',
default=False,
action='store_true',
help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
tree = SuffixTree()
tree.build('ATAAATG$')
for edge in tree.collectEdges():
print(edge)
if args.extra:
Input, Expected = read_strings('data/SuffixTreeConstruction.txt',
init=0)
tree = SuffixTree()
tree.build(Input[0])
#tree.print()
Edges = tree.collectEdges()
compare_edges(Edges, Expected)
if args.rosalind:
Input = read_strings(r'data/rosalind_ba9c.txt')
tree = SuffixTree()
tree.build(Input[0])
Edges = tree.collectEdges()
for e in Edges:
print(e)
help='Controls display of probabilities')
args = parser.parse_args()
if args.sample:
Transitions, Emissions = EstimateParameters('yzzzyxzxxx',
['x', 'y', 'z'],
'BBABABABAB',
['A', 'B', 'C'])
for row in formatTransition(Transitions, ['A', 'B', 'C'],
precision=args.precision):
print(row)
for row in formatEmission(Emissions, ['A', 'B', 'C'], ['x', 'y', 'z'],
precision=args.precision):
print(row)
if args.extra:
Input, Expected = read_strings(f'data/HMMParameterEstimation.txt',
init=0)
Transitions, Emissions = EstimateParameters(Input[0], Input[2].split(),
Input[4], Input[6].split())
for row in formatTransition(Transitions,
Input[6].split(),
precision=args.precision):
print(row)
print('--------')
for row in formatEmission(Emissions,
Input[6].split(),
Input[2].split(),
precision=args.precision):
print(row)
if args.rosalind:
Input = read_strings(
DOWNRIGHT = 2
LinearSpaceAlignment(0,len(v)+1,0,len(w)+1)
if __name__=='__main__':
start = time.time()
parser = argparse.ArgumentParser('BA5L.py Align Two Strings Using Linear Space')
parser.add_argument('--sample', default=False, action='store_true', help='process sample dataset')
parser.add_argument('--extra', default=False, action='store_true', help='process extra dataset')
parser.add_argument('--rosalind', default=False, action='store_true', help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
print (alignUsingLinearSpace('PLEASANTLY','MEANLY'))
if args.extra:
Input,Expected = read_strings(f'data/linear_space_alignment.txt',init=0)
print (alignUsingLinearSpace(Input[0],Input[1]))
if args.rosalind:
Input = read_strings(f'data/rosalind_{os.path.basename(__file__).split(".")[0]}.txt')
Result = None
print (Result)
with open(f'{os.path.basename(__file__).split(".")[0]}.txt','w') as f:
for line in Result:
f.write(f'{line}\n')
elapsed = time.time() - start
minutes = int(elapsed/60)
seconds = elapsed - 60*minutes
action='store_true',
help='process sample dataset')
parser.add_argument('--extra',
default=False,
action='store_true',
help='process extra dataset')
parser.add_argument('--rosalind',
default=False,
action='store_true',
help='process Rosalind dataset')
args = parser.parse_args()
if args.sample:
print(FindLongestRepeat('ATATCGTTTTATCGTT'))
if args.extra:
Input, Expected = read_strings('data/LongestRepeat.txt', init=0)
print(Input[0])
Actual = FindLongestRepeat(Input[0])
print(len(Expected[0]), len(Actual))
print(Expected[0])
print(Actual)
if args.rosalind:
Input = read_strings('data/rosalind_ba9d.txt')
Result = FindLongestRepeat(Input[0])
print(Result)
with open('ba9d.txt', 'w') as f:
f.write(f'{Result}\n')
elapsed = time.time() - start
minutes = int(elapsed / 60)
