def test_score_threshold_rule(kmer_alphabet, ref_kmer, threshold):
"""
Test if the similar k-mers given by :class:`ScoreThresholdRule`
are equal to k-mers generated by a brute-force approach.
"""
matrix = align.SubstitutionMatrix.std_protein_matrix()
ref_kmer_sequence = seq.ProteinSequence()
ref_kmer_sequence.code = kmer_alphabet.split(ref_kmer)
ref_sim_kmer_set = set()
# Iterate through all possible k-mers
for kmer in range(len(kmer_alphabet)):
kmer_sequence = seq.ProteinSequence()
kmer_sequence.code = kmer_alphabet.split(kmer)
score = align.align_ungapped(
ref_kmer_sequence, kmer_sequence, matrix, score_only=True
)
# Add k-mer to list if the threshold score is reached
if score >= threshold:
ref_sim_kmer_set.add(kmer)
test_rule = align.ScoreThresholdRule(matrix, threshold)
test_sim_kmer_set = set(test_rule.similar_kmers(kmer_alphabet, ref_kmer))
assert test_sim_kmer_set == ref_sim_kmer_set
def test_align_ungapped():
seq1 = seq.NucleotideSequence("ACCTGA")
seq2 = seq.NucleotideSequence("ACTGGT")
matrix = align.SubstitutionMatrix.std_nucleotide_matrix()
ali = align.align_ungapped(seq1, seq2, matrix)
assert ali.score == 3
assert str(ali) == "ACCTGA\nACTGGT"
consensus_sequence.code = consensus_code
return consensus_sequence
drug_type_consensus = create_consensus(
[sequences[strain] for strain in (1, 10, 13, 20, 53, 54)]
)
fiber_type_consensus = create_consensus(
[sequences[strain] for strain in (9, 5, 11, 45, 66, 68, 78)]
)
# Create an alignment for visualization purposes
# No insertion/deletions -> Align ungapped
matrix = align.SubstitutionMatrix.std_protein_matrix()
alignment = align.align_ungapped(
drug_type_consensus, fiber_type_consensus, matrix=matrix
)
# A colormap for hightlighting sequence dissimilarity:
# At low similarity the symbols are colored red,
# at high similarity the symbols are colored white
cmap = LinearSegmentedColormap.from_list(
"custom", colors=[(1.0, 0.3, 0.3), (1.0, 1.0, 1.0)]
# ^ reddish ^ white
)
fig = plt.figure(figsize=(8.0, 6.0))
ax = fig.add_subplot(111)
graphics.plot_alignment_similarity_based(
ax, alignment, matrix=matrix, symbols_per_line=50,