def main():
check_input(sys.argv[0])
seqs = []
for _, seq in read_fasta(sys.argv[1]):
seqs.append(seq)
graph = create_graph(seqs)
print(find_shortest_superstring(graph))
def main():
"""Calculate total number of different RNA strings for the input."""
check_input(sys.argv[0])
# Amino acids and # of codons that code for them
NUM_CODONS = {
"I": 3,
"L": 6,
"V": 4,
"F": 2,
"M": 1,
"C": 2,
"A": 4,
"G": 4,
"P": 4,
"T": 4,
"S": 6,
"Y": 2,
"W": 1,
"Q": 2,
"N": 2,
"H": 2,
"E": 2,
"D": 2,
"K": 2,
"R": 6,
"Stop": 3
}
with open(sys.argv[1]) as infile:
aa_seq = infile.readline().strip()
print(possible_mrnas(aa_seq, NUM_CODONS))
def main():
"""Calculate the size of the next population."""
check_input(sys.argv[0])
expected_offspring = {1: 1, 2: 1, 3: 1, 4: 0.75, 5: 0.5, 6: 0}
with open(sys.argv[1]) as infile:
data = infile.readline().strip().split(" ")
print(calculate_average(data, expected_offspring))
def main():
"""Calculate hamming distance for input file."""
check_input(sys.argv[0])
with open(sys.argv[1]) as infile:
string_1 = infile.readline().strip()
string_2 = infile.readline().strip()
print(hamming_distance(string_1, string_2))
def main():
"""Print enumerated kmers for input k and alphabet."""
check_input(sys.argv[0])
with open(sys.argv[1]) as infile:
alpha = infile.readline().strip().split(" ")
k = int(infile.readline().strip())
lexi(alpha, k)
def main():
"""Calculate and print probability."""
check_input(sys.argv[0])
with open(sys.argv[1]) as infile:
args = [int(i) for i in infile.readline().strip().split()]
print(calculate_lia(args[0], args[1]))
def main():
check_input(sys.argv[0])
seq = ""
with open(sys.argv[1]) as infile:
for line in infile:
seq += line.strip()
print(rna(seq))
def main():
"""Count total partial permutations for input."""
check_input(sys.argv[0])
with open(sys.argv[1]) as infile:
n = int(infile.readline().strip())
k = int(infile.readline().strip())
print(partial_permutations(n, k))
def main():
"""Find longest common subsequence of input sequences."""
check_input(sys.argv[0])
seqs = []
for _, seq in read_fasta(sys.argv[1]):
seqs.append(seq)
print(find_common_subsequence(seqs[0], seqs[1]))
def main():
"""Translate input string."""
check_input(sys.argv[0])
input_string = ""
with open(sys.argv[1]) as infile:
for line in infile:
input_string += line.strip()
print(translate(input_string))
def main():
"""Print distance matrix for input sequences."""
check_input(sys.argv[0])
sequences = []
for _, seq in read_fasta(sys.argv[1]):
sequences.append(seq)
for row in create_matrix(sequences):
print(" ".join([str(i) for i in row]))
def main():
"""Calculate probabilities for input."""
check_input(sys.argv[0])
with open(sys.argv[1]) as infile:
seq = infile.readline().strip()
prob = infile.readline().strip().split(" ")
print(" ".join([str(i) for i in find_log_probabilites(seq, prob)]))
def main():
"""Calculate mass of input protein sequence."""
check_input(sys.argv[0])
input_protein = ""
with open(sys.argv[1]) as infile:
for line in infile:
input_protein += line.strip()
print(calculate_weight(input_protein, aa_mass))
def main():
"""Print erroneous and correct reads."""
check_input(sys.argv[0])
reads = []
for _, seq in read_fasta(sys.argv[1]):
reads.append(seq)
corrected_reads = find_erroneous_reads(reads)
for pair in corrected_reads:
print("->".join(pair))
def main():
"""Print GC content for input sequence."""
check_input(sys.argv[0])
gc_content = {}
for header, seq in read_fasta(sys.argv[1]):
gc_content[get_gc(seq)] = header
max_gc = max(gc_content)
print(gc_content[max_gc])
print(max_gc)
def main():
check_input(sys.argv[0])
enum_list = []
with open(sys.argv[1]) as infile:
num = int(infile.readline().strip())
print((2**num) * factorial(num))
get_signs(num, enum_list)
for l in enum_list:
permHelper(l, 0, len(l) - 1)
def main():
"""Splice and translate input DNA string."""
check_input(sys.argv[0])
seqs = []
for _, seq in read_fasta(sys.argv[1]):
transcribed = rna(seq)
seqs.append(transcribed)
mrna = splice(seqs)
print(translate(mrna))
def main():
"""Find common substring in input sequences."""
check_input(sys.argv[0])
contigs = []
for _, seq in read_fasta(sys.argv[1]):
contigs.append(seq)
# Check shortest sequence against other sequences
checker = min(contigs, key=lambda x: len(x))
print(get_common(contigs, checker))
def main():
"""Print consensus sequence and profile matrix for a given set of sequences."""
check_input(sys.argv[0])
infile = sys.argv[1]
seqs = []
for _, seq in read_fasta(infile):
seqs.append(seq)
profile = generate_profile(seqs)
print(get_consensus(profile))
print_profile(profile)
def main():
"""Produce a tree."""
check_input(sys.argv[0])
with open(sys.argv[1]) as infile:
adj_list = []
nodes = int(infile.readline().strip())
for line in infile:
adj_list.append([int(i) for i in line.split()])
print(complete_tree(nodes, adj_list))
def main():
"""Find indices of a given subsequence in a given sequence."""
check_input(sys.argv[0])
i = 0
for _, seq in read_fasta(sys.argv[1]):
if i == 0:
sequence = seq
elif i == 1:
search = seq
i += 1
print(find_subsequence(sequence, search))
def main():
"""Load all sequences from the input fasta file and print graph."""
check_input(sys.argv[0])
sequences = {}
for header, seq in read_fasta(sys.argv[1]):
sequences[header] = seq
for header_1 in sequences:
for header_2 in sequences:
if sequences[header_1] != sequences[
header_2]: # Only compare different seqs
if suffix(sequences[header_1]) == prefix(sequences[header_2]):
print(header_1, header_2, file=sys.stdout)
def main():
"""Count transitions and transversions between two given DNA strings."""
check_input(sys.argv[0])
i = 0
for _, seq in read_fasta(sys.argv[1]):
if i == 0:
seq_1 = seq
elif i == 1:
seq_2 = seq
i += 1
transitions, transversions = count_mutations(seq_1, seq_2)
ratio = transitions / transversions
print(ratio)
def main():
"""Find all candidate protein strings."""
check_input(sys.argv[0])
for _, seq in read_fasta(sys.argv[1]):
inseq = seq
rna_reading_frames = find_all_rnas(inseq)
orfs = []
for rna in rna_reading_frames:
orfs.extend(to_mrna(rna))
unique_orfs = set(orfs)
for orf in unique_orfs:
peptide = translate(orf)
if len(peptide) > 0:
print(translate(orf), file=sys.stdout)
def main():
"""Reverse complement input DNA sequence."""
check_input(sys.argv[0])
with open(sys.argv[1]) as infile:
sequence = infile.readline().strip()
print(rev_comp(sequence))
def main():
"""Read file and print the failure array."""
check_input(sys.argv[0])
for _, seq in read_fasta(sys.argv[1]):
print(" ".join([str(x) for x in create_failure_array(seq)]))
def main():
"""Print 4-mer composition array."""
check_input(sys.argv[0])
for _, seq in read_fasta(sys.argv[1]):
count_composition(seq)
def main():
"""Count perfect matchings in input sequence."""
check_input(sys.argv[0])
for _, seq in read_fasta(sys.argv[1]):
print(str(perfect_matchings(seq)))
def main():
"""Print number of permutations and all possible permutations for input number."""
check_input(sys.argv[0])
with open(sys.argv[1]) as infile:
invalue = int(infile.readline().strip())
perm(invalue)
def main():
"""Count maximum matchings for the input sequence."""
check_input(sys.argv[0])
for _, seq in read_fasta(sys.argv[1]):
print(maximum_matchings(seq))
