def finalize():
if GC.random_number_seed is not None:
from warnings import warn
warn(
"random_number_seed specified, but Pyvolve does not support seeding its random generator"
)
makedirs("pyvolve_output", exist_ok=True)
label_to_node = MF.modules['TreeNode'].label_to_node()
for root, treestr in GC.pruned_newick_trees:
# run Pyvolve
treestr = treestr.strip()
label = root.get_label()
rootseq = root.get_seq()
if GC.VERBOSE:
print('[%s] Pyvolve evolving sequences on tree: %s' %
(datetime.now(), treestr),
file=stderr)
print('[%s] Pyvolve root sequence: %s' %
(datetime.now(), rootseq),
file=stderr)
if treestr != '(':
treestr = '(%s);' % treestr[:-1]
try:
tree = pyvolve.read_tree(tree=treestr)
partition = pyvolve.Partition(models=GC.pyvolve_model,
root_sequence=rootseq)
evolver = pyvolve.Evolver(partitions=partition, tree=tree)
except NameError:
import pyvolve
tree = pyvolve.read_tree(tree=treestr)
partition = pyvolve.Partition(models=GC.pyvolve_model,
root_sequence=rootseq)
evolver = pyvolve.Evolver(partitions=partition, tree=tree)
except AssertionError:
assert False, "Error setting up Pyvolve. Tree: %s" % treestr
ratefile = "pyvolve_output/%s_ratefile.txt" % label # set each to None to not generate these files
infofile = "pyvolve_output/%s_infofile.txt" % label
seqfile = "pyvolve_output/%s_seqfile.fasta" % label
evolver(ratefile=ratefile, infofile=infofile, seqfile=seqfile)
seqs = evolver.get_sequences(
) # use anc=True to get internal sequences as well
# store leaf sequences in GlobalContext
if not hasattr(
GC, 'final_sequences'
): # GC.final_sequences[cn_node][t] = set of (label,seq) tuples
GC.final_sequences = {}
for leaf in seqs:
seq = seqs[leaf]
virus_label, cn_label, sample_time = leaf.split('|')
sample_time = float(sample_time)
if cn_label not in GC.final_sequences:
GC.final_sequences[cn_label] = {}
if sample_time not in GC.final_sequences[cn_label]:
GC.final_sequences[cn_label][sample_time] = []
GC.final_sequences[cn_label][sample_time].append((leaf, seq))
def run_u(self, tree_file, sequences_folder):
with open(tree_file) as f:
line = f.readline().strip()
if "(" not in line or line == ";":
return None
else:
my_tree = ete3.Tree(line, format=1)
root = my_tree.get_tree_root()
root.name = "Root"
# in this case we need to read the multipliers
# First we apply the multipliers per family
# Second, the multipliers per species tree branch
gf_multiplier = self.gf_multipliers[tree_file.split("_")[-2].split("/")[-1]]
for node in my_tree.traverse():
node.dist = node.dist * gf_multiplier * self.st_multipliers[node.name.split("_")[0]]
tree = pyvolve.read_tree(tree=my_tree.write(format=5), scale_tree = self.parameters["SCALING"])
name_mapping = self.get_mapping_internal_names(tree, my_tree)
partition = pyvolve.Partition(models=self.model, size=self.size)
evolver = pyvolve.Evolver(tree=tree, partitions=partition)
fasta_file = tree_file.split("/")[-1].replace("_completetree.nwk", "_") + "complete.fasta"
evolver(seqfile=os.path.join(sequences_folder, fasta_file), ratefile=None, infofile=None, write_anc=True)
# Correct the names
self.correct_names(os.path.join(sequences_folder, fasta_file), name_mapping)
def get_random_tree(filename, tree_string, L, kappa):
# strains = read_in_strains(filename)
# # L = genome_length(strains)
# min_m = get_min_m(strains, L)
# scaled_tree_string = scale_newick_format_tree(strains, L, min_m, tree_string)
phylogeny = pyvolve.read_tree(tree = tree_string)
# pyvolve.print_tree(phylogeny)
freqs = [0.25,0.25,0.25,0.25]
nuc_model = pyvolve.Model('nucleotide', {'kappa':kappa, 'state_freqs':freqs})
ancestor = generate_ancestor(L)
print(ancestor)
my_partition = pyvolve.Partition(models = nuc_model, root_sequence = ancestor)
my_evolver = pyvolve.Evolver(partitions = my_partition, tree = phylogeny)
my_evolver()
# my_evolver(write_anc = True)
simulated_strains = my_evolver.get_sequences()
# strains = my_evolver.get_sequences(anc = True)
# strain_names = list(strains.keys())
pi = pi_value(simulated_strains)
theta = theta_value(simulated_strains)
# print('pi: ' + str(pi))
# print('theta: ' + str(theta))
return {'pi': pi, 'theta': theta}
def test_OnSimulatedData(self):
random.seed(1)
divpressuresites = random.sample(range(self.nsites), 5)
partitions = phydmslib.simulate.pyvolvePartitions(self.model,
(200.0, divpressuresites))
evolver = pyvolve.Evolver(partitions=partitions,
tree=pyvolve.read_tree(file=self.tree))
simulateprefix = os.path.join(self.outdir, self.modelname)
simulatedalignment = simulateprefix + '_simulatedalignment.fasta'
info = simulateprefix + '_temp_info.txt'
rates = simulateprefix + '_temp_ratefile.txt'
evolver(seqfile=simulatedalignment, infofile=info, ratefile=rates)
subprocess.check_call(['phydms', simulatedalignment, self.tree,
self.modelarg, simulateprefix, '--omegabysite',
'--brlen', 'scale'])
omegabysitefile = simulateprefix + '_omegabysite.txt'
omegas = pandas.read_csv(omegabysitefile, sep='\t', comment='#')
divpressureomegas = omegas[omegas['site'].isin(divpressuresites)]
self.assertTrue(len(divpressureomegas) == len(divpressuresites))
self.assertTrue((divpressureomegas['omega'].values > 2).all(),
"Not all divpressure sites have omega > 2:\n{0}".format(
divpressureomegas))
self.assertTrue((divpressureomegas['P'].values < 0.08).all(),
"Not all divpressure sites have P < 0.08:\n{0}".format(
divpressureomegas))
nspurious = len(omegas[(omegas['omega'] > 2) & (omegas['P'] < 0.05)
& (~omegas['site'].isin(divpressuresites))])
self.assertTrue(nspurious <= 1, "{0} spurious sites".format(nspurious))
for f in ["custom_matrix_frequencies.txt"]:
if os.path.isfile(f):
os.remove(f)
def evolve(newicks, sequence_size, scale_tree):
temp = "temporary_sequences.fasta"
phy_files = []
my_model = pyvolve.Model("nucleotide")
partition = pyvolve.Partition(models = my_model, size = sequence_size)
for i in range(0, len(newicks)):
newick = newicks[i]
tree = pyvolve.read_tree(tree = newick, scale_tree = scale_tree)
my_evolver = pyvolve.Evolver(tree = tree, partitions = partition)
fasta_seqfile = "temp" + str(i) + ".fasta"
phylip_seqfile = "temp" + str(i) + ".phyl"
phy_files.append(phylip_seqfile)
my_evolver(seqfile=fasta_seqfile, seqfmt = "fasta", ratefile = None, infofile = None)
fasta_to_phyl(fasta_seqfile, phylip_seqfile)
os.remove(fasta_seqfile)
phyl_output = "temp_seq.phyl"
with open(phyl_output, 'w') as outfile:
for fname in phy_files:
with open(fname) as infile:
outfile.write(infile.read())
outfile.write("\n")
os.remove(fname)
return phyl_output
def simulate_genomes(model, tree, asize, outdir, number):
path = mkdir(os.path.join(outdir, str(number)))
partition = pyvolve.Partition(models=model, size=asize)
evolver = pyvolve.Evolver(tree=tree, partitions=partition)
evolver(
seqfile=None, # ,
ratefile=os.path.join(path, "rate_{}.fasta".format(number)),
infofile=None)
return evolver.get_sequences()
def setUp(self):
"""Set up parameters for test."""
random.seed(1)
scipy.random.seed(1)
self.underflowfreq = 1
# define tree
self.newick = ('((node1:0.2,node2:0.3)node4:0.3,node3:0.5)node5:0.04;')
tempfile = '_temp.tree'
with open(tempfile, 'w') as f:
f.write(self.newick)
self.tree = Bio.Phylo.read(tempfile, 'newick')
os.remove(tempfile)
# amino-acid preferences
self.nsites = 50
prefs = []
minpref = 0.02
g = scipy.random.dirichlet([5] * N_NT)
for r in range(self.nsites):
rprefs = scipy.random.dirichlet([0.5] * N_AA)
rprefs[rprefs < minpref] = minpref
rprefs /= rprefs.sum()
prefs.append(dict(zip(sorted(AA_TO_INDEX.keys()), rprefs)))
# simulate alignment with pyvolve
pyvolvetree = pyvolve.read_tree(tree=self.newick)
self.nseqs = self.tree.count_terminals()
expcm = phydmslib.models.ExpCM(prefs)
partitions = phydmslib.simulate.pyvolvePartitions(expcm)
alignment = '_temp_simulatedalignment.fasta'
info = '_temp_info.txt'
rates = '_temp_ratefile.txt'
evolver = pyvolve.Evolver(partitions=partitions, tree=pyvolvetree)
evolver(seqfile=alignment, infofile=info, ratefile=rates)
self.alignment = [(s.description, str(s.seq))
for s in Bio.SeqIO.parse(alignment, 'fasta')]
for f in [alignment, info, rates]:
os.remove(f)
assert len(self.alignment[0][1]) == self.nsites * 3
assert len(self.alignment) == self.nseqs
# define model
if self.MODEL == phydmslib.models.ExpCM:
self.model = phydmslib.models.ExpCM(prefs)
else:
raise ValueError("Invalid MODEL: {0}".format(self.MODEL))
if self.DISTRIBUTIONMODEL is None:
pass
elif (self.DISTRIBUTIONMODEL ==
phydmslib.models.GammaDistributedOmegaModel):
self.model = self.DISTRIBUTIONMODEL(self.model, ncats=4)
else:
raise ValueError("Invalid DISTRIBUTIONMODEL: {0}".format(
self.DISTRIBUTIONMODEL))
def test_OnSimulatedData(self):
"""Run ``phydms`` on the simulated data."""
random.seed(1)
numpy.random.seed(1)
partitions = phydmslib.simulate.pyvolvePartitions(self.model)
evolver = pyvolve.Evolver(partitions=partitions,
tree=pyvolve.read_tree(file=self.tree))
simulateprefix = os.path.join(self.outdir, self.modelname)
simulatedalignment = simulateprefix + '_simulatedalignment.fasta'
info = simulateprefix + '_temp_info.txt'
rates = simulateprefix + '_temp_ratefile.txt'
evolver(seqfile=simulatedalignment, infofile=info, ratefile=rates)
prefsbymethod = {}
for fitprefsmethod in ['1', '2']:
outprefix = simulateprefix + '_fitprefsmethod{0}'.format(
fitprefsmethod)
subprocess.check_call(['phydms', simulatedalignment, self.tree,
self.modelarg, outprefix,
'--diffprefsbysite', '--brlen', 'scale',
'--ncpus', '-1', '--diffprefsprior',
'invquadratic,150,0.5'] +
self.gammaomega_arg +
['--fitprefsmethod', fitprefsmethod])
diffprefsbysitefile = outprefix + '_diffprefsbysite.txt'
aas = ['dpi_{0}'.format(INDEX_TO_AA[a]) for a in range(N_AA)]
diffprefs = pandas.read_csv(diffprefsbysitefile, sep='\t',
comment='#')
diffprefs['total'] = diffprefs[aas].abs().sum(axis=1)
for (site, a) in self.targetaas.items():
siteentry = diffprefs[diffprefs['site'] == site]
self.assertTrue(len(siteentry) == 1, str(len(siteentry)))
self.assertTrue((siteentry['dpi_{0}'.format(a)] > 0).all())
prefsbymethod[fitprefsmethod] = diffprefs
for (i, (method1, prefs1)) in enumerate(sorted(prefsbymethod.items())):
total1 = prefs1['total'].values
for (method2, prefs2) in sorted(prefsbymethod.items())[i + 1:]:
total2 = prefs2['total'].values
(r, p) = scipy.stats.pearsonr(total1, total2)
plt.scatter(total1, total2)
plt.xlabel('fitprefsmethod{0}'.format(method1))
plt.ylabel('fitprefsmethod{0}'.format(method2))
plotfile = os.path.join(self.outdir, '{0}_vs_{1}.pdf'.format(
method1, method2))
plt.savefig(plotfile)
self.assertTrue(r > 0.98, "Low correlation between "
"fitprefsmethods: {0}\nSee {1}"
.format(r, plotfile))
for f in ["custom_matrix_frequencies.txt"]:
if os.path.isfile(f):
os.remove(f)
def get_random_tree(L, species, scaled_tree_string, kappa, iteration):
# strains = read_in_strains(filename)
# L = genome_length(strains)
# min_m = get_min_m(strains, L)
# max_m = get_max_m(strains, L, tree_string)
# pis = []
# thetas = []
# scaled_trees = []
# for x in range(min_m,max_m+1):
# scaled_tree_string = scale_newick_format_tree(strains, L, x, tree_string, increment)
# scaled_trees.append(scaled_tree_string)
# for tree in scaled_trees:
phylogeny = pyvolve.read_tree(tree=scaled_tree_string)
print('read in the tree')
pyvolve.print_tree(phylogeny)
freqs = [0.25, 0.25, 0.25, 0.25]
nuc_model = pyvolve.Model('nucleotide', {
'kappa': kappa,
'state_freqs': freqs
})
ancestor = generate_ancestor(L)
print('generated an ancestor')
# # print(ancestor)
my_partition = pyvolve.Partition(models=nuc_model, root_sequence=ancestor)
my_evolver = pyvolve.Evolver(partitions=my_partition, tree=phylogeny)
my_evolver(ratefile=None,
infofile=None,
seqfile="simulated_alignment_" + str(species[:-1]) +
"_universal_" + str(iteration + 1) + ".fasta")
# # my_evolver()
print('evolved the sequences')
# # my_evolver(write_anc = True)
simulated_strains = my_evolver.get_sequences()
# # strains = my_evolver.get_sequences(anc = True)
# # strain_names = list(strains.keys())
pi = pi_value(simulated_strains)
theta = theta_value(simulated_strains)
# pis.append(pi)
# thetas.append(theta)
# # print('pi: ' + str(pi))
# # print('theta: ' + str(theta))
# return {'pi': pis, 'theta': thetas}
return pi, theta
def simulateAlignment(model, treeFile, alignmentPrefix, randomSeed=False):
"""
Simulate an alignment given a model and tree (units = subs/site).
Simulations done using `pyvolve`.
Args:
`model` (`phydmslib.models.Models` object)
The model used for the simulations. Only
models that can be passed to `pyvolve.Partitions`
are supported.
`treeFile` (str)
Name of newick file used to simulate the sequences.
The branch lengths should be in substitutions per site,
which is the default units for all `phydms` outputs.
`alignmentPrefix`
Prefix for the files created by `pyvolve`.
The result of this function is a simulated FASTA alignment
file with the name having the prefix giving by `alignmentPrefix`
and the suffix `'_simulatedalignment.fasta'`.
"""
if randomSeed == False:
pass
else:
random.seed(randomSeed)
#Transform the branch lengths by dividing by the model `branchScale`
tree = Bio.Phylo.read(treeFile, 'newick')
for node in tree.get_terminals() + tree.get_nonterminals():
if (node.branch_length == None) and (node == tree.root):
node.branch_length = 1e-06
else:
node.branch_length /= model.branchScale
fd, temp_path = mkstemp()
Bio.Phylo.write(tree, temp_path, 'newick')
os.close(fd)
pyvolve_tree = pyvolve.read_tree(file=temp_path)
os.remove(temp_path)
#Make the `pyvolve` partition
partitions = pyvolvePartitions(model)
#Simulate the alignment
alignment = '{0}_simulatedalignment.fasta'.format(alignmentPrefix)
info = '_temp_{0}info.txt'.format(alignmentPrefix)
rates = '_temp_{0}_ratefile.txt'.format(alignmentPrefix)
evolver = pyvolve.Evolver(partitions=partitions, tree=pyvolve_tree)
evolver(seqfile=alignment, infofile=info, ratefile=rates)
for f in [rates, info, "custom_matrix_frequencies.txt"]:
if os.path.isfile(f):
os.remove(f)
assert os.path.isfile(alignment)
def simulate(f, seqfile, tree, mu_dict, length):
''' Simulate single partition according homogeneous mutation-selection model.
'''
try:
my_tree = pyvolve.read_tree(file=tree)
except:
my_tree = pyvolve.read_tree(tree=tree)
model = pyvolve.Model("MutSel", {'state_freqs': f, 'mu': mu_dict})
part = pyvolve.Partition(size=length, models=model)
e = pyvolve.Evolver(partitions=part, tree=my_tree)
e(seqfile=seqfile, ratefile=None, infofile=None)
def get_accurate_c(L, kappa):
ancestor = generate_ancestor(L)
print(ancestor)
# phylogeny = pyvolve.read_tree(tree = '( (t1:0.5,t2:0.5)i1:0.5, (t3:0.5,t4:0.5)i2:0.5 , (t5:0.5,t6:0.5)i3:0.5, (t7:0.5,t8:0.5)i4:0.5 ) root;')
phylogeny = pyvolve.read_tree(
tree=
'( ((t7:0.5,t8:0.5)i4:0.5,(t5:0.5,t6:0.5)i3:0.5)i1:0.5, (t3:0.5,t4:0.5)i2:0.5 ) root;'
)
pyvolve.print_tree(phylogeny)
freqs = [0.25, 0.25, 0.25, 0.25]
nuc_model = pyvolve.Model('nucleotide', {
'kappa': 1.86836732388,
'state_freqs': freqs
})
my_partition = pyvolve.Partition(models=nuc_model, root_sequence=ancestor)
my_evolver = pyvolve.Evolver(partitions=my_partition, tree=phylogeny)
# my_evolver()
my_evolver(write_anc=True)
# strains = my_evolver.get_sequences()
strains = my_evolver.get_sequences(anc=True)
strain_names = list(strains.keys()) # pre-order traversal of the tree
n = len(strain_names)
print(strain_names)
c_sites = {}
for key in strain_names:
c_sites[key] = []
site_counts = L * [
None
] # list of dictionaries to keep track of which nucleotides are at each convergent site; index = site; key = nucleotide, value = number of strains with that nucleotide
strains_with_site = L * [
None
] # list of the strains that have a convergent mutation at each site; index = site
for x in range(L):
site_counts[x] = {'A': 0, 'T': 0, 'G': 0, 'C': 0}
strains_with_site[x] = []
# c_list_matrix = [[{} for x in range(n)] for y in range(n)] # matrix of the convergent mutation sites; the (i,j) entry is a dictionary of the convergent mutation sites between strain i and strain j; key = site, value = nucleotide
c = 0
strain_names
def execute(tree, model, length, out, numSim):
# read in model, tree, and define partition
pyvolveModel = pyvolve.Model(model)
pyvolveTree = pyvolve.read_tree(file=tree)
pyvolvePartition = pyvolve.Partition(models=pyvolveModel, size=int(length))
# create evolver
my_evolver = pyvolve.Evolver(tree=pyvolveTree, partitions=pyvolvePartition)
my_evolver()
print("Simulating sequences...")
# create simluated sequences
for i in range(int(numSim)):
print(str(out) + "." + str(i) + ".fa")
my_evolver(seqfile=str(out) + "." + str(model) + "-" + str(i) + ".fa")
def run(self, tree_file, sequences_folder):
with open(tree_file) as f:
line = f.readline().strip()
if "(" not in line or line == ";":
return None
else:
my_tree = ete3.Tree(line, format=1)
tree = pyvolve.read_tree(tree=my_tree.write(format=5), scale_tree = self.parameters["SCALING"])
name_mapping = self.get_mapping_internal_names(tree, my_tree)
partition = pyvolve.Partition(models=self.model, size=self.size)
evolver = pyvolve.Evolver(tree=tree, partitions=partition)
fasta_file = tree_file.split("/")[-1].replace("_completetree.nwk", "_complete") + ".fasta"
evolver(seqfile=os.path.join(sequences_folder, fasta_file), ratefile=None, infofile=None, write_anc=True)
# Correct the names
self.correct_names(os.path.join(sequences_folder, fasta_file), name_mapping)
def exampleFastaGenerator(nwkFile, fastaOutputLocation, seqLength, rate=1):
# Tree.
treeName = nwkFile[nwkFile.rindex('/'):]
treeName = treeName.split('.')[0]
phylogony = pyvolve.read_tree(file=nwkFile)
# Rates.
mutationRates = {
"AC": rate,
"AG": rate,
"AT": rate,
"CG": rate,
"CT": rate,
"GT": rate
}
# Model.
model = pyvolve.Model("nucleotide", {"mu": mutationRates})
partition = pyvolve.Partition(models=model, size=seqLength)
# Evolver.
evolver = pyvolve.Evolver(partitions=[partition], tree=phylogony)
evolver(seqfile=fastaOutputLocation, ratefile=None, infofile=None)
def evolve_nonconvergent_partition(g):
if (g['num_convergent_site'] == 0):
site_start = 1
else:
site_start = g['num_simulated_site'] - g['num_convergent_site'] + 1
site_end = g['num_simulated_site']
print('Codon site {}-{}; Non-convergent codons'.format(
site_start, site_end))
num_nonconvergent_site = g['num_simulated_site'] - g['num_convergent_site']
q_matrix = copy.copy(g['background_Q'])
with suppress_stdout_stderr():
model = pyvolve.Model(model_type='custom',
name='root',
parameters={'matrix': q_matrix})
partition = pyvolve.Partition(models=model, size=num_nonconvergent_site)
evolver = pyvolve.Evolver(partitions=partition, tree=g['background_tree'])
evolver(ratefile='tmp.csubst.simulate_nonconvergent_ratefile.txt',
infofile='tmp.csubst.simulate_nonconvergent_infofile.txt',
seqfile='tmp.csubst.simulate_nonconvergent.fa',
write_anc=False)
def simulate_single_sequence(self, name, gene_length, tree_file, sequences_folder):
my_tree = "(A:1,B:1);".replace("A",name)
tree = pyvolve.read_tree(tree=my_tree)
partition = pyvolve.Partition(models=self.model, size=gene_length)
evolver = pyvolve.Evolver(tree=tree, partitions=partition)
fasta_file = tree_file.split("/")[-1].replace("_completetree.nwk", "_complete") + ".fasta"
evolver(seqfile=os.path.join(sequences_folder, fasta_file), ratefile=None, infofile=None, write_anc=True)
# Select single sequence
entries = list()
for n, v in af.fasta_reader(os.path.join(sequences_folder, fasta_file)):
if n[1:] != name:
continue
else:
entries.append((n,v))
af.fasta_writer(os.path.join(sequences_folder, fasta_file), entries)
def generateTree(tns, ntaxa, seqlen):
#Construct the tree and save as newick file
t = dendropy.simulate.treesim.birth_death_tree(birth_rate=1.0, death_rate=0, taxon_namespace=tns, num_extant_tips=ntaxa)
t.write(path='/tmp/pyvt', schema='newick', suppress_rooting=True, suppress_internal_node_labels=True)
#Set pyvolve data type
m1 = pyvolve.Model("nucleotide")
p1 = pyvolve.Partition(models=m1, size=seqlen)
#Read tree from dendropy
pot = pyvolve.read_tree(file='/tmp/pyvt')
#Simulate evolution with no save file
e1 = pyvolve.Evolver(tree=pot, partitions=p1)
e1(seqfile=None)
seqs = e1.get_sequences()
ds=dendropy.DnaCharacterMatrix.from_dict(seqs, taxon_namespace=tns)
ds.write(path="evolvedsequences.fasta", schema="fasta")
#print ds
return t
def simulate(tree_index,length):
"""
Inputs: tree (integer 0-2)
Outputs: array of 4 sequences, using the tree from above
"""
tree_map = ["alpha","beta","charlie"]
tree = tree_map[tree_index]
my_tree = pyvolve.read_tree(file = "trees/"+tree+".tre")
#Idk weird pyvolve paramets
parameters_omega = {"omega": 0.65}
parameters_alpha_beta = {"beta": 0.65, "alpha": 0.98} # Corresponds to dN/dS = 0.65 / 0.98
my_model = pyvolve.Model("MG", parameters_alpha_beta)
# Assign the model to a pyvolve.Partition. The size argument indicates to evolve 250 positions (for a codon alignment, this means 250 codons, i.e. 750 nucleotide sites)
my_partition = pyvolve.Partition(models = my_model, size = length)
# Evolve!
my_evolver = pyvolve.Evolver(partitions = my_partition, tree = my_tree, ratefile = None, infofile = None)
my_evolver(ratefile = None, infofile = None)
#Extract the sequences
simulated_sequences = list(my_evolver.get_sequences().values())
return simulated_sequences
def setUp(self):
"""Set up for tests."""
scipy.random.seed(1)
random.seed(1)
nsites = 1
minpref = 0.001
self.prefs = []
self.realprefs = []
for r in range(nsites):
rprefs = scipy.random.dirichlet([0.5] * N_AA)
rprefs[rprefs < minpref] = minpref
rprefs /= rprefs.sum()
self.prefs.append(dict(zip(sorted(AA_TO_INDEX.keys()), rprefs)))
scipy.random.shuffle(rprefs)
self.realprefs.append(dict(zip(sorted(AA_TO_INDEX.keys()),
rprefs)))
self.kappa = 3.0
self.omega = 3.0
self.phi = scipy.random.dirichlet([5] * N_NT)
self.model = self.MODEL(self.prefs,
prior=None,
kappa=self.kappa,
omega=self.omega,
phi=self.phi)
self.realmodel = phydmslib.models.ExpCM(self.realprefs,
kappa=self.kappa,
omega=self.omega,
mu=10.0,
phi=self.phi)
treefile = os.path.abspath(
os.path.join(os.path.dirname(__file__),
'./NP_data/NP_tree.newick'))
self.tree = Bio.Phylo.read(treefile, 'newick')
self.tree.root_at_midpoint()
# simulate alignment using realmodel
evolver = pyvolve.Evolver(
partitions=phydmslib.simulate.pyvolvePartitions(self.realmodel),
tree=pyvolve.read_tree(file=treefile))
alignmentfile = '_temp_fitprefs_simulatedalignment.fasta'
info = '_temp_info.txt'
rates = '_temp_ratefile.txt'
evolver(seqfile=alignmentfile, infofile=info, ratefile=rates)
self.alignment = phydmslib.file_io.ReadCodonAlignment(
alignmentfile, True)
assert len(self.alignment[0][1]) == nsites * 3
for f in [alignmentfile, info, rates]:
os.remove(f)
self.codoncounts = dict([(r,
dict([(INDEX_TO_CODON[c], 0)
for c in range(N_CODON)]))
for r in range(nsites)])
self.aacounts = dict([(r, dict([(a, 0) for a in range(N_AA)]))
for r in range(nsites)])
for (head, seq) in self.alignment:
self.codoncounts[r][seq] += 1
self.aacounts[r][CODON_TO_AA[CODON_TO_INDEX[seq]]] += 1
self.tl = phydmslib.treelikelihood.TreeLikelihood(
self.tree, self.alignment, self.model)
def main():
"""Main body of script."""
codons = pyvolve.genetics.Genetics().codons
codon_dict = pyvolve.genetics.Genetics().codon_dict
pyrims = pyvolve.genetics.Genetics().pyrims
purines = pyvolve.genetics.Genetics().purines
args = vars(ParseArguments().parse_args())
print("Read the following command line arguments:")
print("\n\t{0}".format("\n\t".join(
["{0} = {1}".format(key, value) for (key, value) in args.items()])))
print("\nPerforming simulation with pyvolve version {0}".format(
pyvolve.__version__))
print("\nReading model params from {0}".format(args['modelparams']))
params = ReadParams(args['modelparams'])
for (param, paramvalue) in params.items():
print("The value of {0} is {1}".format(param, paramvalue))
print("\nReading preferences from {0}".format(args['prefs']))
tup = dms_tools.file_io.ReadPreferences(args['prefs'])
(sites, pis) = (tup[0], tup[2])
print("\nRead amino-acid preferences for {0} sites".format(len(pis)))
tree = pyvolve.read_tree(file=args['tree'])
# create models for simulation
partitions = []
for r in sites:
if params['diversifyingsitesA'] and (int(r)
in params['diversifyingsitesA']):
omega = params['diversifyingomegaA']
print r, omega
elif params['diversifyingsitesB'] and (
int(r) in params['diversifyingsitesB']):
omega = params['diversifyingomegaB']
print r, omega
else:
omega = 1.0
matrix = [] # matrix[x][y] is rate of substitution from x to y
for (xi, x) in enumerate(codons):
row = []
for (yi, y) in enumerate(codons):
ntdiffs = [(x[j], y[j]) for j in range(3) if x[j] != y[j]]
if len(ntdiffs) == 0:
assert x == y
row.append(
0) # will later be adjusted to make row sum to zero
elif len(ntdiffs) > 1:
# multi-nucleotide codon change
row.append(0)
else:
# single nucleotide change
(xnt, ynt) = ntdiffs[0]
if (xnt in purines) == (ynt in purines):
# transition
qxy = params['kappa'] * params['phi{0}'.format(ynt)]
else:
# transversion
qxy = params['phi{0}'.format(ynt)]
(xaa, yaa) = (codon_dict[x], codon_dict[y])
if xaa == yaa:
fxy = 1.0
else:
pix = pis[r][xaa]**params['stringencyparameter']
piy = pis[r][yaa]**params['stringencyparameter']
if abs(pix - piy) < 1e-6:
fxy = omega
else:
fxy = omega * math.log(
piy / pix) / (1.0 - pix / piy)
row.append(qxy * fxy * params['scalerate'])
assert len(row) == len(codons)
row[xi] = -sum(row)
matrix.append(row)
model = pyvolve.Model("custom", {"matrix": matrix})
partitions.append(pyvolve.Partition(models=model, size=1))
print("\nSimulating evolution, writing to {0}...".format(
args['simulatedalignment']))
basename = os.path.splitext(args['simulatedalignment'])[0]
evolver = pyvolve.Evolver(partitions=partitions, tree=tree)
evolver(
seqfile=args['simulatedalignment'],
infofile='{0}_infofile.txt'.format(basename),
ratefile='{0}_ratefile.txt'.format(basename),
)
print("Finished simulation")
uniqueseqs = set([])
uniquealignment = []
ninitial = 0
for seq in Bio.SeqIO.parse(args['simulatedalignment'], 'fasta'):
ninitial += 1
seqstr = str(seq.seq)
if seqstr not in uniqueseqs:
uniqueseqs.add(seqstr)
uniquealignment.append(seq)
print(
"\nAfter removing redundant sequences, we have shrunk {0} from {1} to {2} sequences"
.format(args['simulatedalignment'], ninitial, len(uniquealignment)))
Bio.SeqIO.write(uniquealignment, args['simulatedalignment'], 'fasta')
# This example script demonstrates how to evolve according to a nucleotide model with several partitions.
# In this example, the first partition has gamma-distributedsitewise rate heterogeneity, the second partition is homogenous, and the third partition has custom sitewise rate heterogeneity.
# All models use default mutation-rate parameters
import pyvolve
# Define a phylogeny, from a file containing a newick tree
my_tree = pyvolve.read_tree(file="file_with_tree.tre")
# Define first model and partition. This partition has a length of 50 positions
model1 = pyvolve.Model("nucleotide", alpha=0.7, num_categories=4)
part1 = pyvolve.Partition(models=model1, size=50)
# Define second model and partition. This partition has a length of 20 positions
model2 = pyvolve.Model("nucleotide")
part2 = pyvolve.Partition(models=model2, size=20)
# Define second model and partition. This partition has a length of 100 positions
model3 = pyvolve.Model("nucleotide",
rate_factors=[0.5, 1.6, 4.1],
rate_probs=[0.75, 0.2, 0.05])
part3 = pyvolve.Partition(models=model3, size=100)
# Provide all partitions *in the order in which they should be evolved* to Evolver and evolve
my_evolver = pyvolve.Evolver(partitions=[part1, part2, part3], tree=my_tree)
my_evolver()
usage ='''
python pyvolve-genseq.py <tree.nwk> <seq-size> [<scale> default=1 (no scale)]
'''
if len(sys.argv) < 3:
sys.exit(usage)
tree_f = sys.argv[1]
outfiles = tree_f
size = sys.argv[2]
scale = 1
scale = float(sys.argv[3]) if len(sys.argv) > 3 else None
print("Reading tree..")
my_tree = pyvolve.read_tree(file = tree_f, scale_tree=scale)
my_model = pyvolve.Model("nucleotide")
my_partition = pyvolve.Partition(models = my_model, size = int(size))
print("Simulating sequences..")
my_evolver = pyvolve.Evolver(tree = my_tree, partitions = my_partition)
my_evolver(ratefile = "%s.%s.ratefile.txt" % (outfiles, size),
infofile = "%s.%s.infofile.txt" % (outfiles, size),
seqfile = "%s.%s.seqfile.fasta" % (outfiles, size) )
print("Tree info..")
tree_distances_info(tree_f, scale, int(size))
print("Running ANI on sequences..")
pyani_seq("%s.%s.seqfile.fasta" % (outfiles, size))
def setUp(self):
"""Set up parameters for test."""
random.seed(1)
scipy.random.seed(1)
self.underflowfreq = 1
# define tree
self.newick = ('((node1:0.2,node2:0.3)node4:0.3,node3:0.5)node5:0.04;')
tempfile = '_temp.tree'
with open(tempfile, 'w') as f:
f.write(self.newick)
self.tree = Bio.Phylo.read(tempfile, 'newick')
os.remove(tempfile)
# simulate alignment with pyvolve
pyvolvetree = pyvolve.read_tree(tree=self.newick)
self.nsites = 50
self.nseqs = self.tree.count_terminals()
e_pw = scipy.ndarray((3, N_NT), dtype='float')
e_pw.fill(0.25)
yngkp_m0 = phydmslib.models.YNGKP_M0(e_pw, self.nsites)
partitions = phydmslib.simulate.pyvolvePartitions(yngkp_m0)
alignment = '_temp_simulatedalignment.fasta'
info = '_temp_info.txt'
rates = '_temp_ratefile.txt'
evolver = pyvolve.Evolver(partitions=partitions, tree=pyvolvetree)
evolver(seqfile=alignment, infofile=info, ratefile=rates)
self.alignment = [(s.description, str(s.seq))
for s in Bio.SeqIO.parse(alignment, 'fasta')]
for f in [alignment, info, rates]:
os.remove(f)
assert len(self.alignment[0][1]) == self.nsites * 3
assert len(self.alignment) == self.nseqs
# define model
prefs = []
minpref = 0.02
g = scipy.random.dirichlet([5] * N_NT)
for r in range(self.nsites):
rprefs = scipy.random.dirichlet([0.5] * N_AA)
rprefs[rprefs < minpref] = minpref
rprefs /= rprefs.sum()
prefs.append(dict(zip(sorted(AA_TO_INDEX.keys()), rprefs)))
if self.MODEL == phydmslib.models.ExpCM:
self.model = phydmslib.models.ExpCM(prefs)
elif self.MODEL == phydmslib.models.ExpCM_empirical_phi:
self.model = phydmslib.models.ExpCM_empirical_phi(prefs, g)
elif self.MODEL == phydmslib.models.ExpCM_empirical_phi_divpressure:
divpressure = scipy.random.uniform(-1, 5, self.nsites)
divpressure /= max(abs(divpressure))
self.model = phydmslib.models.ExpCM_empirical_phi_divpressure(
prefs, g, divpressure)
elif self.MODEL == phydmslib.models.YNGKP_M0:
e_pw = scipy.random.uniform(0.2, 0.8, size=(3, N_NT))
e_pw = e_pw / e_pw.sum(axis=1, keepdims=True)
self.model = phydmslib.models.YNGKP_M0(e_pw, self.nsites)
else:
raise ValueError("Invalid MODEL: {0}".format(self.MODEL))
if self.DISTRIBUTIONMODEL is None:
pass
elif (self.DISTRIBUTIONMODEL ==
phydmslib.models.GammaDistributedOmegaModel):
self.model = self.DISTRIBUTIONMODEL(self.model, ncats=4)
else:
raise ValueError("Invalid DISTRIBUTIONMODEL: {0}".format(
self.DISTRIBUTIONMODEL))
def setUp(self):
"""Set up parameters for test."""
random.seed(1)
scipy.random.seed(1)
# define tree
self.newick = ('((node1:0.2,node2:0.3)node4:0.3,node3:0.5)node5:0.04;')
tempfile = '_temp.tree'
with open(tempfile, 'w') as f:
f.write(self.newick)
self.tree = Bio.Phylo.read(tempfile, 'newick')
os.remove(tempfile)
self.brlen = {}
for (name,
brlen) in re.findall(r'(?P<name>node\d):(?P<brlen>\d+\.\d+)',
self.newick):
if name != self.tree.root.name:
i = name[-1] # node number
self.brlen[int(i)] = float(brlen)
# simulate alignment with pyvolve
pyvolvetree = pyvolve.read_tree(tree=self.newick)
self.nsites = 60
self.nseqs = self.tree.count_terminals()
e_pw = scipy.ndarray((3, N_NT), dtype='float')
e_pw.fill(0.25)
yngkp_m0 = phydmslib.models.YNGKP_M0(e_pw, self.nsites)
partitions = phydmslib.simulate.pyvolvePartitions(yngkp_m0)
alignment = '_temp_simulatedalignment.fasta'
info = '_temp_info.txt'
rates = '_temp_ratefile.txt'
evolver = pyvolve.Evolver(partitions=partitions, tree=pyvolvetree)
evolver(seqfile=alignment, infofile=info, ratefile=rates)
self.alignment = [(s.description, str(s.seq))
for s in Bio.SeqIO.parse(alignment, 'fasta')]
for f in [alignment, info, rates]:
os.remove(f)
assert len(self.alignment[0][1]) == self.nsites * 3
assert len(self.alignment) == self.nseqs
self.codons = {} # indexed by node, site, gives codon index
for node in self.tree.get_terminals():
node = node.name
i = int(node[-1])
self.codons[i] = {}
seq = [seq for (head, seq) in self.alignment if node == head][0]
for r in range(self.nsites):
codon = seq[3 * r:3 * r + 3]
self.codons[i][r] = CODON_TO_INDEX[codon]
# define model
prefs = []
minpref = 0.02
g = scipy.random.dirichlet([5] * N_NT)
g[g < 0.1] = 0.1
g /= g.sum()
for r in range(self.nsites):
rprefs = scipy.random.dirichlet([0.5] * N_AA)
rprefs[rprefs < minpref] = minpref
rprefs /= rprefs.sum()
prefs.append(dict(zip(sorted(AA_TO_INDEX.keys()), rprefs)))
if self.MODEL == phydmslib.models.ExpCM:
self.model = phydmslib.models.ExpCM(prefs)
elif self.MODEL == phydmslib.models.ExpCM_empirical_phi:
self.model = phydmslib.models.ExpCM_empirical_phi(prefs, g)
elif self.MODEL == phydmslib.models.ExpCM_empirical_phi_divpressure:
divpressure = scipy.random.uniform(-1, 5, self.nsites)
divpressure /= max(abs(divpressure))
self.model = phydmslib.models.ExpCM_empirical_phi_divpressure(
prefs, g, divpressure)
elif self.MODEL == phydmslib.models.YNGKP_M0:
e_pw = scipy.random.uniform(0.2, 0.8, size=(3, N_NT))
e_pw = e_pw / e_pw.sum(axis=1, keepdims=True)
self.model = phydmslib.models.YNGKP_M0(e_pw, self.nsites)
else:
raise ValueError("Invalid MODEL: {0}".format(self.MODEL))
if self.DISTRIBUTIONMODEL is None:
pass
elif (self.DISTRIBUTIONMODEL ==
phydmslib.models.GammaDistributedOmegaModel):
self.model = self.DISTRIBUTIONMODEL(self.model, ncats=4)
elif (self.DISTRIBUTIONMODEL ==
phydmslib.models.GammaDistributedBetaModel):
self.model = self.DISTRIBUTIONMODEL(self.model, ncats=4)
else:
raise ValueError("Invalid DISTRIBUTIONMODEL: {0}".format(
self.DISTRIBUTIONMODEL))
import sys, os
import pyvolve
import glob
from mungo.fasta import FastaReader
from collections import defaultdict
input_fasta = sys.argv[1]
input_tree_txt = sys.argv[2]
output_seqs = sys.argv[3]
#f = pyvolve.ReadFrequencies("amino_acid", file = "/Users/fengqian/Downloads/UniMelb_shared-master/project/mosaic_data/Protein_translateable_pilot_upper_centroids.fasta")
#f = pyvolve.ReadFrequencies("amino_acid", file = "/data/cephfs/punim0609/qian_feng/snake_pipeline/data/Protein_translateable_pilot_upper_centroids.fasta")
f = pyvolve.ReadFrequencies("amino_acid", file=input_fasta)
frequencies = f.compute_frequencies()
my_tree_1 = pyvolve.read_tree(file=input_tree_txt, scale_tree=0.5)
my_model_1 = pyvolve.Model("MTMAM", {"state_freqs": frequencies})
my_partition_1 = pyvolve.Partition(models=my_model_1, size=200)
my_evolver_1 = pyvolve.Evolver(partitions=my_partition_1, tree=my_tree_1)
my_evolver_1(ratefile=None, infofile=None, seqfile=output_seqs)
seqs = {}
seq_list = []
count = 0
for h, s in FastaReader(output_seqs):
seqs["seq" + str(count)] = s
seq_list.append("seq" + str(count))
count += 1
##organize the seq ID name
with open(output_seqs, 'w') as outfile:
for s in seq_list:
outfile.write(">" + s + "\n" + seqs[s] + "\n")
# Define a phylogeny, from a file containing a newick tree
my_tree = pyvolve.read_tree(file="file_with_tree.tre")
# Define a nucleotide model, as a pyvolve.Model object. For this example, we'll use default parameters, but see the example script custom_aminoacid.py for other options
# To implement rate heterogeneity, do either of these:
## 1) Custom rates: Provide a list of rate_factors when defining a Model object. These rate factors will be assigned to sites with equal probability by default. To change this, provide probabilities with the argument `rate_probs`.
## 2) Gamma rates: Provide the keyword arguments num_categories and alpha when defining a Model object. <num_categories> rates will be drawn from a gamma distribution with shape and scale parameter each equal to <alpha>. These rates will be equiprobable, unless overridden by `rate_probs`.
# Several model definitions are shown below (first argument can be a different model, as desired).
# custom rates
my_model1 = pyvolve.Model(
"WAG", rate_factors=[0.3, 0.8, 1.5,
2.45]) # 25% of sites will have each factor.
my_model2 = pyvolve.Model(
"WAG",
rate_factors=[0.3, 0.8, 1.5, 2.45],
rate_probs=[0.7, 0.2, 0.05, 0.05]
) # 70% of sites evolve with rate of 0.3, 20% with a rate of 0.8, 5% with a rate of 1.5, and 5% with a rate of 2.45
# gamma rates
my_model3 = pyvolve.Model("WAG", alpha=0.6, num_categories=5)
# Assign the model to a pyvolve.Partition. The size argument indicates to evolve 250 positions
my_partition = pyvolve.Partition(models=my_model2, size=250)
# Evolve!
my_evolver = pyvolve.Evolver(partitions=my_partition, tree=my_tree)
my_evolver()
def get_c(L, kappa):
ancestor = generate_ancestor(L)
print(ancestor)
phylogeny = pyvolve.read_tree(
tree='((t1:0.5,t2:0.5)i1:0.5,(t3:0.5,t4:0.5)i2:0.5)root;')
# '(t4:0.785,(t3:0.380,(t2:0.806,(t5:0.612,t1:0.660)i1:0.762)i2:0.921)i3:0.207)root;')
# ((s1,s2)n1,(s3,s4)n2)n3
pyvolve.print_tree(phylogeny)
freqs = [0.25, 0.25, 0.25, 0.25]
nuc_model = pyvolve.Model('nucleotide', {
'kappa': 1.86836732388,
'state_freqs': freqs
})
my_partition = pyvolve.Partition(models=nuc_model, root_sequence=ancestor)
my_evolver = pyvolve.Evolver(partitions=my_partition, tree=phylogeny)
my_evolver()
# my_evolver(write_anc = True)
strains = my_evolver.get_sequences()
# strains = my_evolver.get_sequences(anc = True)
strain_names = list(strains.keys())
n = len(strain_names)
site_counts = L * [
None
] # list of dictionaries to keep track of which nucleotides are at each convergent site; index = site; key = nucleotide, value = number of strains with that nucleotide
strains_with_site = L * [
None
] # list of the strains that have a convergent mutation at each site; index = site
for x in range(L):
site_counts[x] = {'A': 0, 'T': 0, 'G': 0, 'C': 0}
strains_with_site[x] = []
# c_list_matrix = [[{} for x in range(n)] for y in range(n)] # matrix of the convergent mutation sites; the (i,j) entry is a dictionary of the convergent mutation sites between strain i and strain j; key = site, value = nucleotide
for s1 in range(n):
strain1 = strains[strain_names[s1]]
for s2 in range(s1, n):
strain2 = strains[strain_names[s2]]
for site in range(L):
if strain1[site] == strain2[
site] and strain1[site] != ancestor[site]:
if strain1 not in strains_with_site[
site]: # avoids double counting strain1 as convergent at that site
strains_with_site[site].append(strain1)
site_counts[site][strain1[site]] += 1
if strain2 not in strains_with_site[
site]: # avoids double counting strain2 as convergent at that site
strains_with_site[site].append(strain2)
site_counts[site][strain2[site]] += 1
c_q = (n - 1) * [
None
] # list of the number of convergent mutations between q strains; index = q - 2
nucleotides = ['A', 'T', 'G', 'C']
for x in range(n - 1):
c_q[x] = 0
for site in site_counts:
for base in nucleotides:
for q in range(2, n + 1):
if site[base] == (q):
c_q[q - 2] += 1
c = sum(c_q)
print(c)
return c
def test_branchScale(self):
"""Simulate evolution, ensure scaled branches match number of subs."""
scipy.random.seed(1)
random.seed(1)
# define model, only free parameter is mu for testing simulations
nsites = 50
prefs = []
minpref = 0.01
for r in range(nsites):
rprefs = scipy.random.dirichlet([1] * N_AA)
rprefs[rprefs < minpref] = minpref
rprefs /= rprefs.sum()
prefs.append(dict(zip(sorted(AA_TO_INDEX.keys()), rprefs)))
kappa = 4.2
omega = 0.4
beta = 1.5
mu = 0.3
if self.MODEL == phydmslib.models.ExpCM:
phi = scipy.random.dirichlet([7] * N_NT)
model = phydmslib.models.ExpCM(prefs,
kappa=kappa,
omega=omega,
beta=beta,
mu=mu,
phi=phi,
freeparams=['mu'])
partitions = phydmslib.simulate.pyvolvePartitions(model)
elif self.MODEL == phydmslib.models.ExpCM_empirical_phi:
g = scipy.random.dirichlet([7] * N_NT)
model = phydmslib.models.ExpCM_empirical_phi(prefs,
g,
kappa=kappa,
omega=omega,
beta=beta,
mu=mu,
freeparams=['mu'])
partitions = phydmslib.simulate.pyvolvePartitions(model)
elif self.MODEL == phydmslib.models.YNGKP_M0:
e_pw = scipy.asarray(
[scipy.random.dirichlet([7] * N_NT) for i in range(3)])
model = phydmslib.models.YNGKP_M0(e_pw, nsites)
partitions = phydmslib.simulate.pyvolvePartitions(model)
else:
raise ValueError("Invalid MODEL: {0}".format(type(self.MODEL)))
# tree is two sequences separated by a single branch
t = 0.04 / model.branchScale
newicktree = '(tip1:{0},tip2:{0});'.format(t / 2.0)
pyvolvetree = pyvolve.read_tree(tree=newicktree)
temptree = '_temp.tree'
with open(temptree, 'w') as f:
f.write(newicktree)
biotree = Bio.Phylo.read(temptree, 'newick')
os.remove(temptree)
# Simulate evolution of two sequences separated by a long branch.
# Then estimate subs per site in a heuristic way that will be
# roughly correct for short branches. Do this all several times
# and average results to get better accuracy.
alignment = '_temp_branchScale_simulatedalignment.fasta'
info = '_temp_info.txt'
rates = '_temp_ratefile.txt'
evolver = pyvolve.Evolver(partitions=partitions, tree=pyvolvetree)
nsubs = 0 # subs in simulated seqs (estimate from Hamming distance)
treedist = 0.0 # distance inferred by `TreeLikelihood`
nreplicates = 100
for i in range(nreplicates):
evolver(seqfile=alignment, infofile=info, ratefile=rates)
a = [(s.description, str(s.seq))
for s in Bio.SeqIO.parse(alignment, 'fasta')]
assert len(a[0][1]) == len(a[1][1]) == nsites * 3
for f in [alignment, info, rates]:
if os.path.isfile(f):
os.remove(f)
for r in range(nsites):
codon1 = a[0][1][3 * r:3 * r + 3]
codon2 = a[1][1][3 * r:3 * r + 3]
nsubs += len([j for j in range(3) if codon1[j] != codon2[j]])
tl = phydmslib.treelikelihood.TreeLikelihood(biotree, a, model)
tl.maximizeLikelihood()
treedist += sum([n.branch_length for n in tl.tree.get_terminals()])
nsubs /= float(nsites * nreplicates)
treedist /= float(nreplicates)
# We expect nsubs = branchScale * t, but build in some tolerance
# with rtol since we simulated finite number of sites.
self.assertTrue(
scipy.allclose(nsubs, model.branchScale * t, rtol=0.2),
("Simulated subs per site of {0} is not close "
"to expected value of {1} (branchScale = {2}, t = {3})").format(
nsubs, t * model.branchScale, model.branchScale, t))
self.assertTrue(
scipy.allclose(treedist, nsubs, rtol=0.2),
("Simulated subs per site of {0} is not close to inferred "
"branch length of {1}").format(nsubs, treedist))
def main(strain, seedFilepath, gffFilepath):
for record in SeqIO.parse(seedFilepath, "fasta"):
seedRec = record
break
gff_df = read_gff(gffFilepath)
#get all the shuffle region
prv = 0
pos_lst = []
for _, row in gff_df.iterrows():
pos_lst.append(("nc", prv, row["start"] - 1, "+"))
pos_lst.append(("c", row["start"] - 1, row["end"], row["strand"]))
prv = row["end"]
pos_lst.append(("nc", prv, len(seedRec), "+"))
# configuration for evolution
treeFilepath = "tmp.tree"
mytree = pyvolve.read_tree(file=treeFilepath)
ncm = pyvolve.Model("nucleotide") # non-coding model
cm = pyvolve.Model("ECMrest") # coding model
outputSeq_lst = [Seq("") for _ in range(4)] # assuming tree has 4 nodes
for pos in pos_lst:
category, start, end, strand = pos
# get rootSeq according to start, end, strand info
rootSeq = seedRec.seq[start:end]
if strand == "-":
rootSeq = rootSeq.reverse_complement()
rootSeq = str(rootSeq)
# get simulated sequences
if category == "nc":
# partition = pyvolve.Partition(models = ncm, root_sequence = rootSeq)
# evolver = pyvolve.Evolver(partition = partition, tree = mytree)
# rec_lst = get_evolved(evolver)
rec_lst = [SeqRecord(Seq(rootSeq)) for _ in range(4)]
elif category == "c":
partition = pyvolve.Partition(
models=cm,
root_sequence=rootSeq[3:-3]) #remove start & stop codon
evolver = pyvolve.Evolver(partition=partition, tree=mytree)
rec_lst = get_evolved(evolver)
for rec in rec_lst:
rec.seq = rootSeq[:3] + rec.seq + rootSeq[
-3:] #add last stop codon back
assert len(rec_lst) == len(outputSeq_lst)
# concat to outputSeq_lst
for i, rec in enumerate(rec_lst):
simSeq = rec.seq
if strand == "-":
simSeq = simSeq.reverse_complement()
outputSeq_lst[i] += simSeq
for i, outputSeq in enumerate(outputSeq_lst):
genomeId = "{}_sim{}".format(strain, i + 1)
outFilepath = "../data/dnaseq/{}.dnaseq".format(genomeId)
with open(outFilepath, "w") as f:
seqname = "{}:seq".format(genomeId)
rec = SeqRecord(outputSeq, id=seqname, description="")
SeqIO.write(rec, f, "fasta")
print("DONE: output {}".format(outFilepath))