def test_make_seq(self):
"""test constructor utility function"""
_seq = "ACGGT"
seq = make_seq(_seq)
self.assertEqual(seq.moltype.label, "text")
seq = make_seq(_seq, moltype="dna")
self.assertEqual(seq.moltype.label, "dna")
self.assertEqual(str(seq), _seq)
def test_reverse_complement(self):
"""testing reversal and complementing of a sequence"""
seq = make_seq(moltype=DNA, seq="ACTGTAA")
rev = seq.reverse_complement()
self.assertEqual(str(rev), "TTACAGT")
seq = make_seq(moltype=DNA, seq="ACTG-TAA")
rev = seq.reverse_complement()
self.assertEqual(str(rev), "TTA-CAGT")
# try amigbuities
seq = make_seq(moltype=DNA, seq="ACHNRTAA")
rev = seq.reverse_complement()
self.assertEqual(str(rev), "TTAYNDGT")
def test_has_terminal_stop(self):
"""test check for terminal stop codons"""
seq = make_seq(moltype=DNA, seq="ACTTAA")
assert seq.has_terminal_stop() == True
seq = make_seq(moltype=DNA, seq="ACTTAT") == False
# for sequence not divisible by 3
seq = make_seq(moltype=DNA, seq="ACTTA")
# fail
self.assertRaises(ValueError, seq.has_terminal_stop)
# unless explicitly over-ride length issue using allow_partial
# in which case, returns False
self.assertFalse(seq.has_terminal_stop(allow_partial=True))
def test_without_terminal_stop_sodon(self):
"""testing deleting terminal stop"""
# for standard code
seq = make_seq(moltype=DNA, seq="ACTTAA")
seq2 = seq.trim_stop_codon()
self.assertEqual(str(seq2), "ACT")
# for sequence not divisible by 3
seq = make_seq(moltype=DNA, seq="ACTTA")
# fail
self.assertRaises(ValueError, seq.trim_stop_codon)
# unless explicitly over-ride length issue using allow_partial
seq2 = seq.trim_stop_codon(allow_partial=True)
def test_translate_incomplete(self):
"""test of translating seqs with incomplete codon"""
seq = make_seq("CGNTGNAC----", moltype=DNA)
aa = seq.get_translation(incomplete_ok=True)
self.assertEqual(str(aa), "RX?-")
with self.assertRaises(AlphabetError):
_ = seq.get_translation(incomplete_ok=False)
def test_to_regex(self):
"""creates a regex from aa seq to match a DNA sequence"""
import re
from cogent3 import make_seq
dna = "ACCGAACAGGGC"
aa = "TEQG"
pattern = DEFAULT.to_regex(aa)
self.assertTrue("".join(re.findall(pattern, dna)) == dna)
# note that Z is Q or E
aa = "TZQG"
pattern = DEFAULT.to_regex(aa)
self.assertTrue("".join(re.findall(pattern, dna)) == dna)
aa = make_seq(aa, moltype="protein")
pattern = DEFAULT.to_regex(aa)
self.assertTrue("".join(re.findall(pattern, dna)) == dna)
def test_ambig_translate(self):
"""test of translating seqs"""
seq = make_seq("CGNTGN???---", moltype=DNA).get_translation()
self.assertEqual(str(seq), "RX?-")
def test_translate(self):
"""test of translating seqs"""
seq = make_seq("ATGACGTTGCGTAGCATAGCTCGA", moltype=DNA).get_translation()
self.assertEqual(str(seq), "MTLRSIAR")
def setUp(self):
self.seq = make_seq("ATGACGTTGCGTAGCATAGCTCGA", "dna")
"""
Information analysis of an alignment
====================================
Information here is in the formal sense -- maximum entropy minus the entropy at a position. This is fast to compute and is an indicator of the variability at a position.
"""
#%%
# Illustrated with a simple example
# #################################
from cogent3 import load_aligned_seqs, make_aligned_seqs, make_seq
s1 = make_seq('TGATGTAAGGTAGTT', name='s1', moltype="dna")
s2 = make_seq('--CTGGAAGGGT---', name='s2', moltype="dna")
seqs = make_aligned_seqs(data=[s1, s2], array_align=False, moltype='dna')
draw = seqs.information_plot(window=2, include_gap=True)
draw.show(width=500, height=400)
#%%
# On a sample data set
# ********************
#
# Clicking on any of the legend items causes that to disappear from the plot.
aln = load_aligned_seqs('../../data/brca1.fasta', moltype='protein')
fig = aln.information_plot(stat='median')
# sphinx_gallery_thumbnail_number = 2
fig.show(width=500, height=400)
