def calculate_tt_ratio(fasta_data: List[str]) -> float:
"""
:param fasta_data: Two equal length DNA sequences in FASTA format
:return: Transition/transversion ratio, rounded to 4th digit
"""
strands = parse_fasta(fasta_data)
first, second = strands
transitions, transversions = first.transitions_transversions(second)
tt_ratio = transitions / transversions
return round(tt_ratio, 4)
def test_parse_fasta():
"""
Checks proper parsing of fasta files
:return:
"""
data = [">Tag1", "ATGC", "CGTA", "GGCC", ">Tag2", "ATGC", "AATT"]
output = parse_fasta(data)
output = [(line.sequence, line.tag) for line in output]
expected = [("ATGCCGTAGGCC", "Tag1"), ("ATGCAATT", "Tag2")]
assert output == expected
def calculate_max_gc_content(fasta_data: List[str]) -> Tuple[str, float]:
"""
:param fasta_data: - a list of DNA sequences in FASTA format
:return: the tag and gc content of DNA strand with highest GC content
"""
strands = parse_fasta(fasta_data)
gc_content_values = [(strand.tag, strand.gc_content())
for strand in strands]
max_tag, max_gc_content = max(gc_content_values,
key=lambda value: value[1])
return max_tag, max_gc_content
def get_possible_proteins(fasta_data: List[str]) -> str:
"""
:param fasta_data: A DNA sequence in FASTA format
:return: a formatted set of possible proteins encoded in DNA
"""
strands = parse_fasta(fasta_data)
# there should be only one sequence
strand, = strands
orfs = strand.search_for_orf()
proteins = {
orf.transcribe().translate_to_protein().sequence
for orf in orfs
}
return '\n'.join(proteins)
def splice_and_translate(fasta_data: List[str]) -> str:
"""
:param fasta_data: A DNA sequence of gene, followed by several intron sequences, in FASTA format
:return: A protein sequence obtained after translating spliced RNA
"""
dna_strands = parse_fasta(fasta_data)
# sequences are DNA, so we need to transcribe them
rna_strands = [strand.transcribe() for strand in dna_strands]
# first sequence is
matrix, *introns = rna_strands
for intron in introns:
matrix = matrix.splice(intron)
# we need protein sequence from spliced RNA
protein = matrix.translate_to_protein()
return protein.sequence
from rps.sequence_problems.parsing import parse_fasta
import rps.sequence_problems.consensus_and_profile as problem
dataset = [
">Rosalind_1", "ATCCAGCT", ">Rosalind_2", "GGGCAACT", ">Rosalind_3",
"ATGGATCT", ">Rosalind_4", "AAGCAACC", ">Rosalind_5", "TTGGAACT",
">Rosalind_6", "ATGCCATT", ">Rosalind_7", "ATGGCACT"
]
sequences = parse_fasta(dataset)
def test_get_profile_matrix():
profile_matrix = problem.get_profile_matrix(sequences)
expected_a = [5, 1, 0, 0, 5, 5, 0, 0]
expected_c = [0, 0, 1, 4, 2, 0, 6, 1]
expected_g = [1, 1, 6, 3, 0, 1, 0, 0]
expected_t = [1, 5, 0, 0, 0, 1, 1, 6]
assert profile_matrix.A == expected_a
assert profile_matrix.C == expected_c
assert profile_matrix.G == expected_g
assert profile_matrix.T == expected_t
def test_get_consensus_string():
matrix = problem.get_profile_matrix(sequences)
result = problem.get_consensus_string(matrix)
expected_string = 'ATGCAACT'
assert result == expected_string