def generate_f_one(self, pop: sim.Population):
"""
A very basic implementation of the F_1 cross between pairs of individuals. Relies on
pre-formatting of desired mating pairs into an ordered list.
[1, 3, 5, 11, 12, 9, 22, 2]
The mating pattern would be:
1x3, 5x11, 12x9, 22x2. Rearranging the order of the indices would change the mating
pairs.
:param pop:
:type pop:
:return:
:rtype:
"""
pop.dvars().generations[1] = 'F_1'
pop.dvars().gen = 1
pairs_of_founders = int(pop.popSize() / 2)
self.odd_to_even(pop)
print("Creating the F_one population from selected founders.")
return pop.evolve(
preOps=[
sim.PyEval(r'"Generation: %d\n" % gen'),
operators.CalcTripletFrequencies(),
sim.PyExec('triplet_freq[gen]=tripletFreq'),
sim.SplitSubPops(sizes=[2] * pairs_of_founders, randomize=False),
],
matingScheme=sim.RandomMating(subPopSize=[1] * pairs_of_founders,
ops=[sim.Recombinator(rates=0.01), sim.IdTagger(), sim.PedigreeTagger()]),
gen=1,
)
def _assertSize(self, sizes, initSize=[], startGen=0):
'''This function is provided for testing purpose.
'''
self.intended_size = sizes
pop = Population(size=initSize if initSize else self.init_size,
infoFields=self.info_fields)
pop.dvars().gen = startGen
pop.evolve(matingScheme=RandomSelection(subPopSize=self),
postOps=PyOperator(self._checkSize, param=startGen),
finalOps=PyOperator(self._checkSize, param=startGen),
gen=self.num_gens)
def plot(self, filename='', title='', initSize=[]):
'''Evolve a haploid population using a ``RandomSelection`` mating scheme
using the demographic model. Print population size changes duringe evolution.
An initial population size could be specified using parameter ``initSize``
for a demographic model with dynamic initial population size. If a filename
is specified and if matplotlib is available, this function draws a figure
to depict the demographic model and save it to ``filename``. An optional
``title`` could be specified to the figure. Note that this function can
not be plot demographic models that works for particular mating schemes
(e.g. genotype dependent).'''
if not self.init_size:
if initSize:
self.init_size = initSize
else:
raise ValueError(
'Specific self does not have a valid initial population size'
)
if filename and not has_plotter:
raise RuntimeError(
'This function requires module numpy and matplotlib')
self.draw_figure = filename and has_plotter
self.pop_regions = OrderedDict()
self.pop_base = OrderedDict()
#
self._reset()
if title:
print(title)
pop = Population(self.init_size, infoFields=self.info_fields, ploidy=1)
pop.evolve(matingScheme=RandomSelection(subPopSize=self),
postOps=PyOperator(self._recordPopSize),
gen=self.num_gens)
self._recordPopSize(pop)
#
if self.draw_figure:
fig = plt.figure()
ax = fig.add_subplot(111)
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_ticks_position('left')
for name, region in self.pop_regions.items():
region = region.reshape(region.size / 4, 4)
points = np.append(region[:, 0:2], region[::-1, 2:4], axis=0)
plt.fill(points[:, 0],
points[:, 1],
label=name,
linewidth=0,
edgecolor='w')
leg = plt.legend(loc=2)
leg.draw_frame(False)
if title:
plt.title(title)
plt.savefig(filename)
plt.close()
def _assertSize(self, sizes, initSize=[], startGen=0):
'''This function is provided for testing purpose.
'''
self.intended_size = sizes
pop = Population(size=initSize if initSize else self.init_size,
infoFields=self.info_fields)
pop.dvars().gen = startGen
pop.evolve(
matingScheme=RandomSelection(subPopSize=self),
postOps=PyOperator(self._checkSize, param=startGen),
finalOps=PyOperator(self._checkSize, param=startGen),
gen=self.num_gens
)
def plot(self, filename='', title='', initSize=[]):
'''Evolve a haploid population using a ``RandomSelection`` mating scheme
using the demographic model. Print population size changes duringe evolution.
An initial population size could be specified using parameter ``initSize``
for a demographic model with dynamic initial population size. If a filename
is specified and if matplotlib is available, this function draws a figure
to depict the demographic model and save it to ``filename``. An optional
``title`` could be specified to the figure. Note that this function can
not be plot demographic models that works for particular mating schemes
(e.g. genotype dependent).'''
if not self.init_size:
if initSize:
self.init_size = initSize
else:
raise ValueError('Specific self does not have a valid initial population size')
if filename and not has_plotter:
raise RuntimeError('This function requires module numpy and matplotlib')
self.draw_figure = filename and has_plotter
self.pop_regions = OrderedDict()
self.pop_base = OrderedDict()
#
self._reset()
if title:
print(title)
pop = Population(self.init_size, infoFields=self.info_fields, ploidy=1)
pop.evolve(
matingScheme=RandomSelection(subPopSize=self),
postOps=PyOperator(self._recordPopSize),
gen=self.num_gens
)
self._recordPopSize(pop)
#
if self.draw_figure:
fig = plt.figure()
ax = fig.add_subplot(111)
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_ticks_position('left')
for name, region in self.pop_regions.items():
region = region.reshape(region.size / 4, 4)
points = np.append(region[:, 0:2],
region[::-1, 2:4], axis=0)
plt.fill(points[:,0], points[:,1], label=name, linewidth=0, edgecolor='w')
leg = plt.legend(loc=2)
leg.draw_frame(False)
if title:
plt.title(title)
plt.savefig(filename)
plt.close()
def calculate_additive_trait(pop: sim.Population, trait_information_field: str,
allele_effects_array: np.ndarray):
"""
Calculates additive trait ``trait_information_field`` by summing allele
effects at each qtl.
:param pop:
:param trait_information_field:
:param allele_effects_array:
:return:
"""
for ind in pop.individuals():
ind.setInfo(
sum(allele_effects_array[range(pop.totNumLoci()),
np.asarray(ind.genotype(ploidy=0))] +
allele_effects_array[range(pop.totNumLoci()),
np.asarray(ind.genotype(ploidy=1))]),
trait_information_field)
def meta_population_information_writer(meta_pop: sim.Population,
info_field_list: list, filename: str):
"""
Writes information equivalent to a simuPOP.utils Exporter; however, this function is much more
flexible. I am uncertain of what information will be necessary in the future.
:param info_field_list: List of information fields to be included in output file.
:param filename: Name of output file.
:return: CSV File 'filename'
"""
for i in range(meta_pop.numSubPop()):
full_filename = filename + "_" + str(i) + ".txt"
with open(full_filename, 'w') as info:
info_writer = csv.writer(info, delimiter=',')
info_writer.writerow(info_field_list)
for ind in meta_pop.individuals(i):
info_writer.writerow(
[ind.ind_id, ind.mother_id, ind.father_id, ind.ge, ind.pe])
def _generate_f_two(self, pop: sim.Population) -> sim.Population:
"""
Creates an F2 subpopulations generation by selfing the individuals of 'pop'. Works on a population with one
or more subpopulations.
"""
pop.vars()['generations'][2] = 'F_2'
self.odd_to_even(pop)
num_sub_pops = pop.numSubPop()
progeny_per_individual = int(self.selected_population_size/2)
print("Creating the F_two population.")
return pop.evolve(
preOps=[
sim.MergeSubPops(),
sim.PyEval(r'"Generation: %d\n" % gen'),
operators.CalcTripletFreq(),
sim.PyExec('triplet_freq[gen]=tripletFreq'),
sim.SplitSubPops(sizes=[1]*num_sub_pops, randomize=False),
],
matingScheme=sim.SelfMating(subPopSize=[progeny_per_individual] * num_sub_pops,
numOffspring=progeny_per_individual,
ops=[sim.Recombinator(rates=0.01), sim.IdTagger(), sim.PedigreeTagger()],
),
gen=1,
)
def _mate_and_merge(self, pop: sim.Population):
starting_gen = pop.vars()['gen']
print("Initiating recombinatorial convergence at generation: %d" % pop.dvars().gen)
while pop.numSubPop() > 1:
pop.vars()['generations'][pop.vars()['gen']] = 'IG'+str(pop.vars()['gen'] - starting_gen)
self.pop_halver(pop)
self.odd_to_even(pop)
self.pairwise_merge_protocol(pop)
sub_pop_sizes = list(pop.subPopSizes())
pop.evolve(
preOps=[
sim.MergeSubPops(),
sim.PyEval(r'"Generation: %d\n" % gen'),
operators.CalcTripletFreq(),
sim.PyExec('triplet_freq[gen]=tripletFreq'),
sim.SplitSubPops(sizes=sub_pop_sizes, randomize=False),
],
matingScheme=sim.RandomMating(ops=[sim.Recombinator(rates=0.01),
sim.IdTagger(), sim.PedigreeTagger()]),
gen=1,
)
def find_minor_alleles(pop: sim.Population):
minor_allele_frequencies = col.OrderedDict()
minor_alleles = np.empty(pop.totNumLoci())
for locus in range(pop.totNumLoci()):
if len(list(pop.dvars().alleleFreq[locus].keys())) >= 2:
minor_allele_frequencies[locus] = min(
pop.dvars().alleleFreq[locus].values())
for k in pop.dvars().alleleFreq[locus].keys():
if pop.dvars(
).alleleFreq[locus][k] == minor_allele_frequencies[locus]:
minor_alleles[locus] = k
elif len(list(pop.dvars().alleleFreq[locus].keys())) == 1:
# If an allele is at fixation then we want to show a zero for the MAC format.
minor_alleles[locus] = 7
return minor_alleles
def population_information_writer(pop: sim.Population, info_field_list: list,
filename: str):
"""
Writes information equivalent to a simuPOP.utils Exporter; however, this function is much more
flexible. I am uncertain of what information will be necessary in the future.
:param pop: sim.Population
:param info_field_list: List of information fields to be included in output file.
:param filename: Name of output file.
:return: CSV File 'filename'
"""
with open(filename, 'w') as info:
info_writer = csv.writer(info, delimiter=',')
info_writer.writerow(info_field_list)
for ind in pop.individuals():
info_writer.writerow([
ind.ind_id, ind.mother_id, ind.father_id, ind.ge, ind.pe,
ind.fitness,
ind.genotype()
])
def write_info_fields_to_file(pop: sim.Population, info_fields: list,
output_filename: str, fmt_string):
"""
Utilize numpy's simple numpy.savetxt function to write various types of pop.IndInfo(info_string) to files.
Superior solution to using csv.writer's for simple .txt output.
+ Example
----------
pop.infoFields() = ('ind_id', 'ge', 'pe')
info_fields = ['ind_id', 'ge', 'pe']
info_array = np.array([pop.indInfo(info) for info in info_fields])
np.savetxt(output_filename, info_array, delimiter='\t', newline='\n', header=">Generation: pop.dvars().gen",
comments='')
"""
info_array = np.array([pop.indInfo(info) for info in info_fields]).T
np.savetxt(output_filename,
info_array,
fmt='%d\t%.2f\t%.2f',
delimiter='\t',
newline='\n',
header=">Generation: 0\nID\tG\tP",
comments='')
# Copyright (C) 2004 - 2010 Bo Peng ([email protected]) # # This program is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see <http://www.gnu.org/licenses/>. # # This script is an example in the simuPOP user's guide. Please refer to # the user's guide (http://simupop.sourceforge.net/manual) for a detailed # description of this example. # from simuPOP import InitGenotype, Population def initGenotype(pop, *args, **kwargs): InitGenotype(*args, **kwargs).apply(pop) pop = Population(1000, loci=[2, 3]) initGenotype(pop, freq=[.2, .3, .5])
def table_for_development(prefounders: sim.Population, founders: list,
pop: sim.Population, replicate_type: str):
"""
Function to generate a summary data table for population subjected to either drift or selection.
:param prefounders: Population from which all populations are derived
:param founders: List of integers specifying which prefounders to use in making a population
:param pop: Population subjected to either drift or selection
:param replicate_type: String either 'drift' or 'selection' reflecting whether 'pop' is subjected to drift or
selection
:return: hierarchically indexed pandas.DataFrame with frequency and effect data for all qtl
"""
data = []
columns = [
'QTL', 'Chromosome', 'cM_Position', 'Singlet', 'SingletEffect',
'SingletFrequency', 'Triplet', 'TripletEffect', 'NumberOfFounders'
]
generational_columns = [
pop.dvars().generations[i] for i in range(pop.dvars().gen)
]
columns.extend(generational_columns)
chromosomes, relative_positions = chromosome_abs_and_rel(pop)
qtls = []
stf = test_subloci_calc_freq(prefounders, pop)
for i in range(len(pop.dvars().properQTL)):
qtls.append(prefounders.dvars().properQTL[i] - 1)
qtls.append(prefounders.dvars().properQTL[i])
qtls.append(prefounders.dvars().properQTL[i] + 1)
for qtl in pop.dvars().properQTL:
for trip in sorted(list(pop.vars()['triplet_freq'][0][qtl].keys())):
for i in range(3):
datarow = [
qtl, # locus
chromosomes[qtl], # chromosome of locus
relative_positions[qtl] + index_to_cM(i), # position in cM
trip[i], # singlet
pop.dvars().alleleEffects[qtl + i - 1,
int(trip[i])], # singlet effect
stf[qtl, qtl + i - 1][trip[i]], # singlet frequency
trip, # triplet
sum([
pop.dvars().alleleEffects[
qtl - 1, int(trip[0])], # triplet effect
pop.dvars().alleleEffects[qtl, int(trip[1])],
pop.dvars().alleleEffects[qtl + 1,
int(trip[2])]
]),
len(founders)
] # number of founders selected from prefounders
frq_per_gen = [
pop.vars()['triplet_freq'][j][qtl][trip] for j in range(8)
]
rep_frq_per_gen = [
pop.vars()[replicate_type + '_triplet_freq'][k][qtl][trip]
for k in range(8,
pop.dvars().gen)
]
frq_per_gen.extend(rep_frq_per_gen)
datarow.extend(frq_per_gen)
data.append(datarow)
s = pd.DataFrame(data, columns=columns)
for i in range(8, 13):
for term in pop.dvars().mav_terms:
s.set_value(term,
pop.dvars().generations[i],
pop.dvars().mavs[i, term])
return s.fillna(0)