def create_standard_fragments(self, profile_db):
reference_profile = profile_db.gats[0]
ref_frags = []
# get the basic details
for frag_number in reference_profile.orientationless_fragments():
f = Fragment([],
number=frag_number,
operon_forward_start=False,
dna_A=False,
dif=False)
if str(frag_number) == str(profile_db.dnaA_fragment_number):
f.dna_A = True
if str(frag_number) == str(profile_db.dif_fragment_number):
f.dif = True
ref_frags.append(f)
# reorientate to dnaA
dna_start_frags = self.reorientate_ori(ref_frags)
dnaa_index = self.find_dnaa(dna_start_frags)
dif_index = self.find_dif(dna_start_frags)
if dnaa_index == -1 or dif_index == -1:
return []
# forward walk (reverse is already set )
for i in range(dnaa_index, dif_index):
if i >= dif_index:
# we have reached the end
continue
else:
dna_start_frags[i].operon_forward_start = True
return dna_start_frags
def calc_fragment_coords(self, boundries):
genome_length = len(self.chromosome.seq)
fragments = []
start_coord = 0
end_coord = genome_length
# check to see if one of the fragments goes over the end
end_frag = [b for b in boundries if b[0] > b[1]]
if len(end_frag) > 0:
self.is_circular = False
del boundries[-1]
start_coord = end_frag[0][1]
end_coord = end_frag[0][0]
if self.is_circular:
# first - we assume its circular
f = Fragment([[boundries[-1][1], genome_length],
[0, boundries[0][0]]])
fragments.append(f)
else:
f = Fragment([[boundries[-1][1], end_coord]])
fragments.append(f)
f = Fragment([[start_coord, boundries[0][0]]])
fragments.append(f)
for i in range(0, len(boundries) - 1):
fragments.append(Fragment([[boundries[i][1],
boundries[i + 1][0]]]))
return fragments
def test_plot_profile_some_reversed(self):
fragments = []
fragments.append(
Fragment([],
sequence="AAAA",
number=1,
reversed_frag=True,
dna_A=True))
fragments.append(
Fragment([],
sequence="AAA",
number=3,
reversed_frag=False,
dna_A=False))
fragments.append(
Fragment([],
sequence="AAAAAAAAAA",
number=2,
reversed_frag=True,
dna_A=False))
fragments.append(
Fragment([],
sequence="A",
number=4,
reversed_frag=False,
dna_A=False))
p = PlotProfile(fragments, 'plot2.pdf', False)
p.create_plot()
self.assertTrue(os.path.exists('plot2.pdf'))
os.remove('plot2.pdf')
def create_fragments(self, input_profile, standard_fragments):
frags = []
# get the basic details
reversed_frags = input_profile.orientation_array()
for i, frag_number in enumerate(
input_profile.orientationless_fragments()):
f = Fragment([],
number=frag_number,
operon_forward_start=False,
dna_A=False,
dif=False,
reversed_frag=not reversed_frags[i])
if str(frag_number) == str(input_profile.dnaA_fragment_number):
f.dna_A = True
if str(frag_number) == str(input_profile.dif_fragment_number):
f.dif = True
frags.append(f)
# loop over the standard and set the direction (if inverted, then invert)
for f in frags:
for s in standard_fragments:
if f.number == s.number:
f.operon_forward_start = s.operon_forward_start
#if f.dna_A:
# f.operon_forward_start = True
#if f.dif:
# f.operon_forward_start = False
if f.reversed_frag:
f.operon_forward_start = not f.operon_forward_start
return frags
def calc_fragment_coords(self, boundries):
genome_length = len(self.chromosome.seq)
fragments = []
if not boundries:
return []
start_coord = 0
end_coord = genome_length
# check to see if one of the fragments goes over the end
end_frag = [b for b in boundries if b.start > b.end]
if len(end_frag) > 0:
self.is_circular = False
del boundries[-1]
start_coord = end_frag[0].end
end_coord = end_frag[0].start
if self.is_circular:
# first - we assume its circular
f = Fragment(
[[boundries[-1].end, genome_length], [0, boundries[0].start]],
operon_forward_start=boundries[-1].direction,
operon_forward_end=boundries[0].direction)
fragments.append(f)
else:
f = Fragment([[boundries[-1].end, end_coord]],
operon_forward_start=boundries[-1].direction)
fragments.append(f)
f = Fragment([[start_coord, boundries[0].start]],
operon_forward_end=boundries[0].direction)
fragments.append(f)
for i in range(0, len(boundries) - 1):
fragments.append(
Fragment([[boundries[i].end, boundries[i + 1].start]],
operon_forward_start=boundries[i].direction,
operon_forward_end=boundries[i + 1].direction))
return fragments
def test_term_first_valid(self):
# --> 1'(Ter) <-- 6' <-- 3 <-- 4 <-- 5(Ori) --> 2'
fragments = []
fragments.append(Fragment([], number = 1, operon_forward_start = False, dna_A = False, dif = True))
fragments.append(Fragment([], number = 6, operon_forward_start = False, dna_A = False, dif = False))
fragments.append(Fragment([], number = 3, operon_forward_start = False, dna_A = False, dif = False))
fragments.append(Fragment([], number = 4, operon_forward_start = False, dna_A = False, dif = False))
fragments.append(Fragment([], number = 5, operon_forward_start = True, dna_A = True, dif = False))
fragments.append(Fragment([], number = 2, operon_forward_start = True, dna_A = False, dif = False))
vf = ValidateFragments(fragments)
self.assertTrue(vf.validate())
def test_fragment_seq_name_one_coord(self):
f = Fragment([[10, 123]])
self.assertEqual(str(f), '0 10_123')
def test_fragment_seq_name_two_coords(self):
f = Fragment([[10, 123], [555, 999]])
self.assertEqual(str(f), '0 10_123__555_999')