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():
"""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():
"""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():
"""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():
"""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():
"""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():
"""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():
"""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():
"""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():
"""Count maximum matchings for the input sequence."""
check_input(sys.argv[0])
for _, seq in read_fasta(sys.argv[1]):
print(maximum_matchings(seq))
def main():
"""Find reverse palindromes in input."""
check_input(sys.argv[0])
for _, seq in read_fasta(sys.argv[1]):
for pair in find_revp(seq):
print(*pair, sep=" ")