plt.close()
# Plot unique MSAs with largest deviations
OGids = set()
outliers = sorted([
record for record in records
if record[0] < -1 and record[2] < a * record[0]**2
]) # Use -1 to exclude near-zero floating point rounding errors
for record in outliers:
# Unpack variables
OGid, msa, regions = record[3], record[4], record[5]
if OGid in OGids:
continue
OGids.add(OGid)
# Plot MSA with regions
msa = [seq for _, seq in sorted(msa, key=lambda x: tip_order[x[0]])
] # Re-order sequences and extract seq only
line = np.zeros(len(msa[0]))
for region in regions:
line[region] = 1
plot_msa_lines(msa, line, figsize=(16, 6))
plt.savefig(f'out/{len(OGids)-1}_{OGid}.png', bbox_inches='tight', dpi=400)
plt.close()
"""
DEPENDENCIES
../../ortho_tree/ctree_WAG/ctree_WAG.py
../../ortho_tree/ctree_WAG/out/100red_ni.txt
../realign_hmmer1/realign_hmmer1.py
../realign_hmmer1/out/*.mfa
"""
labels[state].append((int(start), int(stop)))
OGid2labels[OGid] = labels
if not os.path.exists('out/'):
os.mkdir('out/')
for OGid, labels in OGid2labels.items():
msa = trim_terminals(read_fasta(f'../../ortho_MSA/realign_hmmer1/out/{OGid}.mfa'))
if labels['0'] and labels['0'][0][0] == 0:
offset = labels['0'][0][1]
else:
offset = 0
lines = {}
for state in ['1A', '1B', '2', '3']:
line = np.zeros(len(msa[0][1]))
for start, stop in labels[state]:
line[slice(start-offset, stop-offset)] = 1
lines[state] = line
plot_msa_lines([seq[1].upper() for seq in msa], [lines['1A'], lines['2'], lines['3'], lines['1B']], figsize=(15, 6))
plt.savefig(f'out/{OGid}.png', bbox_inches='tight')
plt.close()
"""
DEPENDENCIES
../../ortho_MSA/realign_hmmer1/realign_hmmer1.py
../../ortho_MSA/realign_hmmer1/out/*.mfa
../config/segments.tsv
"""
emit1 = sum(col)
emits.append((emit0, emit1))
col0 = col
# Instantiate model
e_dists_rv = {
state: bernoulli_betabinom_frozen(p,
len(msa) - 1, a, b)
for state, (p, a, b) in params['e_dists'].items()
}
model = hmm.HMM(params['t_dists'], e_dists_rv, params['start_dist'])
# Decode states and plot
fbs = model.forward_backward(emits)
draw.plot_msa_lines([seq.upper() for _, seq in msa],
[fbs['1A'], fbs['2'], fbs['3'], fbs['1B']],
figsize=(15, 6))
plt.savefig(f'out/{OGid}_wide.png', bbox_inches='tight')
plt.close()
draw.plot_msa_lines([seq.upper() for _, seq in msa],
[fbs['1A'], fbs['2'], fbs['3'], fbs['1B']],
figsize=(8, 8))
plt.savefig(f'out/{OGid}_tall.png', bbox_inches='tight')
plt.close()
"""
DEPENDENCIES
../../ortho_MSA/realign_hmmer1/realign_hmmer1.py
../../ortho_MSA/realign_hmmer1/out/*.mfa
../config/segments.tsv
./fit.py
emits.append((j, 1))
else:
emits.append((j, 0))
# Instantiate model
e_dists_rv = {
'0': msaBernoulli(ps),
'1': msaBernoulli([params['e_param'] for _ in range(len(ps))])
}
model = hmm.HMM(params['t_dists'], e_dists_rv, params['start_dist'])
# Decode states and plot
fbs = model.forward_backward(emits)
draw.plot_msa_lines(
[seq.upper() for _, seq in msa],
fbs['1'],
msa_labels=[ppid if ppid in header else '' for header, _ in msa],
msa_labelsize=4,
figsize=(15, 6))
plt.savefig(f'out/{OGid}_{ppid}_wide.png', bbox_inches='tight')
plt.close()
draw.plot_msa_lines(
[seq.upper() for _, seq in msa],
fbs['1'],
msa_labels=[ppid if ppid in header else '' for header, _ in msa],
msa_labelsize=4,
figsize=(8, 8))
plt.savefig(f'out/{OGid}_{ppid}_tall.png', bbox_inches='tight')
plt.close()
"""
DEPENDENCIES
# Load decoded states
posterior = []
with open(f'../insertion_trim/out/{row.OGid}.tsv') as file:
header = file.readline().rstrip('\n').split('\t')
for line in file:
fields = {key: float(value) for key, value in zip(header, line.rstrip('\n').split('\t'))}
posterior.append(fields['2'] + fields['3'])
posterior = np.array(posterior)
gradient = np.gradient(posterior)
# Make trim plot
slices = get_slices(msa, posterior, gradient)
trims = np.zeros(len(posterior))
for s in slices:
trims[s] = 1
msa = [seq.upper() for _, seq in sorted(msa, key=lambda x: tip_order[x[0]])] # Re-order sequences and extract seq only
plot_msa_lines(msa, [posterior, trims], figsize=(15, 6))
plt.savefig(f'out/{label}/{i}_{row.OGid}.png', bbox_inches='tight')
plt.close()
"""
DEPENDENCIES
../../ortho_MSA/realign_hmmer2/realign_hmmer2.py
../../ortho_MSA/realign_hmmer2/out/*
../../ortho_tree/ctree_WAG/ctree_WAG.py
../../ortho_tree/ctree_WAG/out/100red_ni.txt
../insertion_trim/decode.py
./insertion_trim/out/*.tsv
"""