def test_compute_of_two_gapped_seqs(self):
# setup
sequences = MSA(["-----", "-----"])
# results
expected = 0
result = Entropy(sequences).compute()
# check
self.assertEqual(expected, result)
def test_should_print_class_name(self):
# setup
sumofpairs = SumOfPairs().get_name()
star = Star().get_name()
entropy = Entropy().get_name()
# check
self.assertEqual("SumOfPairs", sumofpairs)
self.assertEqual("Star", star)
self.assertEqual("Entropy", entropy)
def test_compute_of_four_seqs_with_no_gaps(self):
# setup
sequences = MSA(["ACGT", "ACGT", "TGCA", "TGCA"])
# results
expected = -2.77
result = round(Entropy(sequences).compute(), 2)
# check
self.assertEqual(expected, result)
def test_compute_of_three_seqs_with_gaps(self):
# setup
sequences = MSA(["A-TGCAAT-G", "-CT-CCAT-A", "-TTAT-CTG-"])
# results
expected = -6.94
result = round(Entropy(sequences).compute(), 2)
# check
self.assertEqual(expected, result)
def test_get_entropy_of_a_column_with_gaps(self):
# setup
d = {"-": 0.8, "A": 0.2}
# results
result = round(Entropy.get_entropy(d), 1)
expected = -0.5
# check
self.assertEqual(expected, result)
def test_get_dictionary_of_a_gapped_column(self):
# setup
column = ["-", "-", "-", "-", "-"]
# results
expected = {"-": 1}
result = Entropy.get_words_frequencies(column)
# check
self.assertEqual(expected, result)
def test_get_entropy_of_a_gapped_column(self):
# setup
d = {"-": 1}
# results
expected = 0
result = Entropy.get_entropy(d)
# check
self.assertEqual(expected, result)
def test_get_dictionary_of_a_gapped_column(self):
# setup
column = ["-", "-", "-", "-", "-"]
# results
expected = {"-": 1}
result = Entropy.get_words_frequencies(column)
# check
self.assertEqual(expected, result)
def test_get_entropy_of_a_gapped_column(self):
# setup
d = {"-": 1}
# results
expected = 0
result = Entropy.get_entropy(d)
# check
self.assertEqual(expected, result)
def test_get_entropy_of_a_column_with_gaps(self):
# setup
d = {"-": 0.8, "A": 0.2}
# results
result = round(Entropy.get_entropy(d), 1)
expected = -0.5
# check
self.assertEqual(expected, result)
def test_get_dictionary_of_a_five_letter_column(self):
# setup
column = ["-", "A", "C", "G", "T"]
tot_seqs = len(column)
# results
expected = {"-": 1 / tot_seqs, "A": 1 / tot_seqs, "C": 1 / tot_seqs, "G": 1 / tot_seqs, "T": 1 / tot_seqs}
result = Entropy.get_words_frequencies(column)
# check
self.assertEqual(expected, result)
def test_get_dictionary_of_a_five_letter_column(self):
# setup
column = ["-", "A", "C", "G", "T"]
tot_seqs = len(column)
# results
expected = {
"-": 1 / tot_seqs,
"A": 1 / tot_seqs,
"C": 1 / tot_seqs,
"G": 1 / tot_seqs,
"T": 1 / tot_seqs
}
result = Entropy.get_words_frequencies(column)
# check
self.assertEqual(expected, result)
def run_all_scores(msa: list) -> None:
align_sequences = list(pair[1] for pair in msa)
sequences_id = list(pair[0] for pair in msa)
# Percentage of non-gaps and totally conserved columns
non_gaps = PercentageOfNonGaps()
totally_conserved_columns = PercentageOfTotallyConservedColumns()
percentage = non_gaps.compute(align_sequences)
conserved = totally_conserved_columns.compute(align_sequences)
print("Percentage of non-gaps: {0} %".format(percentage))
print("Percentage of totally conserved columns: {0}".format(conserved))
# Entropy
value = Entropy().compute(align_sequences=align_sequences)
print("Entropy score: {0}".format(value))
# Sum of pairs
value = SumOfPairs(Blosum62()).compute(align_sequences=align_sequences)
print("SumOfPairs score (Blosum62): {0}".format(value))
value = SumOfPairs(PAM250()).compute(align_sequences=align_sequences)
print("SumOfPairs score (PAM250): {0}".format(value))
value = SumOfPairs(FileMatrix('PAM380.txt')).compute(align_sequences=align_sequences)
print("SumOfPairs score (PAM380): {0}".format(value))
# Star
value = Star(Blosum62()).compute(align_sequences=align_sequences)
print("Star score (Blosum62): {0}".format(value))
value = Star(PAM250()).compute(align_sequences=align_sequences)
print("Star score (PAM250): {0}".format(value))
# STRIKE
value = Strike().compute(align_sequences=align_sequences,
sequences_id=sequences_id,
chains=['A', 'E', 'A', 'A'])
print("STRIKE score: {0}".format(value))
def setUp(self):
self.ent = Entropy()
class EntropyTestCases(unittest.TestCase):
def setUp(self):
self.ent = Entropy()
def test_get_entropy_of_a_column_with_gaps(self):
# setup
d = {"-": 0.8, "A": 0.2}
# results
result = round(self.ent.get_column_entropy(d), 1)
expected = -0.5
# check
self.assertEqual(expected, result)
def test_get_entropy_of_a_gapped_column(self):
# setup
d = {"-": 1}
# results
expected = 0
result = self.ent.get_column_entropy(d)
# check
self.assertEqual(expected, result)
def test_get_dictionary_of_a_five_letter_column(self):
# setup
column = ["-", "A", "C", "G", "T"]
tot_seqs = len(column)
# results
expected = {
"-": 1 / tot_seqs,
"A": 1 / tot_seqs,
"C": 1 / tot_seqs,
"G": 1 / tot_seqs,
"T": 1 / tot_seqs
}
result = self.ent.get_words_frequencies(column)
# check
self.assertEqual(expected, result)
def test_get_dictionary_of_a_gapped_column(self):
# setup
column = ["-", "-", "-", "-", "-"]
# results
expected = {"-": 1}
result = self.ent.get_words_frequencies(column)
# check
self.assertEqual(expected, result)
def test_compute_of_four_seqs_with_no_gaps(self):
# setup
sequences = ["ACGT", "ACGT", "TGCA", "TGCA"]
# results
expected = -2.77
result = round(self.ent.compute(sequences), 2)
# check
self.assertEqual(expected, result)
def test_compute_of_three_seqs_with_gaps(self):
# setup
sequences = ["A-TGCAAT-G", "-CT-CCAT-A", "-TTAT-CTG-"]
# results
expected = -6.94
result = round(self.ent.compute(sequences), 2)
# check
self.assertEqual(expected, result)
def test_compute_of_two_gapped_seqs(self):
# setup
sequences = ["-----", "-----"]
# results
expected = 0
result = self.ent.compute(sequences)
# check
self.assertEqual(expected, result)