import simuPOP as sim
from simuPOP.utils import migrIslandRates
p = [0.2, 0.3, 0.5]
pop = sim.Population(size=[10000] * 3, loci=1, infoFields='migrate_to')
simu = sim.Simulator(pop, rep=2)
simu.evolve(
initOps=[sim.InitSex()] +
[sim.InitGenotype(prop=[p[i], 1 - p[i]], subPops=i) for i in range(3)],
preOps=sim.Migrator(rate=migrIslandRates(0.01, 3), reps=0),
matingScheme=sim.RandomMating(),
postOps=[
sim.Stat(alleleFreq=0, structure=0, vars='alleleFreq_sp', step=50),
sim.PyEval(
"'Fst=%.3f (%s)\t' % (F_st, ', '.join(['%.2f' % "
"subPop[x]['alleleFreq'][0][0] for x in range(3)]))",
step=50),
sim.PyOutput('\n', reps=-1, step=50),
],
gen=201)
# 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.
#
import simuPOP as sim
simu = sim.Simulator(sim.Population(100, loci=[20]), 5)
simu.evolve(
initOps=[sim.InitSex(), sim.InitGenotype(freq=[0.2, 0.8])],
matingScheme=sim.RandomMating(),
postOps=[
sim.Stat(alleleFreq=0, step=10),
sim.PyEval('gen', step=10, reps=0),
sim.PyEval(r"'\t%.2f' % alleleFreq[0][0]", step=10, reps=(0, 2, -1)),
sim.PyOutput('\n', step=10, reps=-1)
],
gen=30,
)
import simuOpt
simuOpt.setOptions(quiet=True, alleleType='long')
import simuPOP as sim
pop = sim.Population(size=[2500]*10, loci=1)
simu = sim.Simulator(pop, rep=2)
simu.evolve(
initOps=[
sim.InitSex(),
sim.InitGenotype(genotype=20),
],
preOps=[
sim.StepwiseMutator(rates=0.0001, reps=0),
sim.KAlleleMutator(k=10000, rates=0.0001, reps=1),
],
matingScheme=sim.RandomMating(),
postOps=[
# Use vars=['alleleFreq_sp'] to calculate allele frequency for
# each subpopulation
sim.Stat(alleleFreq=0, vars=['alleleFreq_sp'], step=200),
sim.PyEval('gen', step=200, reps=0),
sim.PyEval(r"'\t%.2f' % (sum([len(subPop[x]['alleleFreq'][0]) "
"for x in range(10)])/10.)", step=200),
sim.PyOutput('\n', reps=-1, step=200)
],
gen=601
)
p2 = inds[randint(0, len(inds) - 1)]
# return indexes of both parents
if s1 == sim.MALE:
yield p1, p2
else:
yield p2, p1
pop = sim.Population(size=2000, loci=1, infoFields='x')
# define VSPs x<1, 1<=x<2, 2<=x<3, 3<=x<4, ...
pop.setVirtualSplitter(sim.InfoSplitter(field='x', cutoff=range(1, 8)))
pop.evolve(
initOps=[
sim.InitSex(),
sim.InitInfo(lambda: uniform(0, 8), infoFields='x'),
# only individuals in the middle range has certain genotype
sim.InitGenotype(freq=[0.6, 0.4], subPops=[(0, 4)]),
],
matingScheme=VicinityMating(locationField='x',
vicinity=1,
varOfLocation=0.5),
postOps=[
sim.Stat(alleleFreq=0,
subPops=[(0, sim.ALL_AVAIL)],
vars='alleleFreq_sp'),
sim.PyEval(r"'%.3f ' % alleleFreq[0][1]",
subPops=[(0, sim.ALL_AVAIL)]),
sim.PyOutput('\n'),
],
gen=10)
pop.dvars((0,sp)).propOfAffected * 100.,
pop.dvars((0,sp)).popSize))
#
return True
pop.evolve(
initOps=[
sim.InitSex(),
# random assign age
sim.InitInfo(lambda: random.randint(0, 75), infoFields='age'),
# random genotype
sim.InitGenotype(freq=[0.5, 0.5]),
# assign an unique ID to everyone.
sim.IdTagger(),
sim.PyOutput('Prevalence of disease in each age group:\n'),
],
# increase the age of everyone by 1 before mating.
preOps=sim.InfoExec('age += 1'),
matingScheme=sim.HeteroMating([
# all individuals with age < 75 will be kept. Note that
# CloneMating will keep individual sex, affection status and all
# information fields (by default).
sim.CloneMating(subPops=[(0,0), (0,1), (0,2)], weight=-1),
# only individuals with age between 20 and 50 will mate and produce
# offspring. The age of offspring will be zero.
sim.RandomMating(ops=[
sim.IdTagger(), # give new born an ID
sim.PedigreeTagger(), # track parents of each individual
sim.MendelianGenoTransmitter(), # transmit genotype
],
import simuPOP as sim
# [100]*100 means a population with 100 subpopulations, each of size 100.
pop = sim.Population([100] * 100, loci=1)
pop.evolve(
initOps=[
sim.InitSex(),
sim.InitGenotype(freq=[0.5, 0.5]),
sim.PyOutput('gen: mean freq mean Ht (expected Ht)\n')
],
preOps=[
# Statistics in subpopulations are by default not calculated.
# This is changed by specifying variables with a '_sp' suffix.
sim.Stat(alleleFreq=0,
heteroFreq=0,
vars=['alleleFreq_sp', 'heteroFreq_sp'],
step=20),
# Variables in subpopulations are stored in dictionaries
# subPop[subPopID] where subPopID can be virtual.
sim.PyEval(
r'"%2d: %.4f %.4f (%.4f)\n" % (gen,'
'sum([subPop[x]["alleleFreq"][0][1] for x in range(100)])/100.,'
'sum([subPop[x]["heteroFreq"][0] for x in range(100)])/100.,'
'0.5*(1-1/200.)**gen)',
step=20)
],
matingScheme=sim.RandomMating(),
gen=100)
#
# 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.
#
import simuPOP as sim
pop = sim.Population(100, loci=[1] * 100)
pop.evolve(initOps=[
sim.InitSex(),
sim.InitGenotype(freq=[0.3, 0.7]),
sim.PyOutput('#all 0\t#seg sites\t#all 1\n'),
],
matingScheme=sim.RandomMating(),
postOps=[
sim.Stat(numOfSegSites=sim.ALL_AVAIL,
vars=['numOfSegSites', 'numOfFixedSites']),
sim.PyEval(
r'"%d\t%d\t%d\n" % (100-numOfSegSites-numOfFixedSites,'
'numOfSegSites, numOfFixedSites)',
step=50)
],
gen=500)
# output a list of segregating sites
sim.stat(pop, numOfSegSites=sim.ALL_AVAIL, vars='segSites')
print(pop.dvars().segSites)
# 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.
#
import simuPOP as sim
simu = sim.Simulator(sim.Population(size=1000, loci=2), rep=3)
simu.evolve(initOps=[sim.InitSex(),
sim.InitGenotype(genotype=[1, 2, 2, 1])],
matingScheme=sim.RandomMating(ops=sim.Recombinator(rates=0.01)),
postOps=[
sim.Stat(LD=[0, 1]),
sim.PyEval(r"'%.2f\t' % LD[0][1]", step=20, output='>>LD.txt'),
sim.PyOutput('\n', reps=-1, step=20, output='>>LD.txt'),
sim.PyEval(r"'%.2f\t' % R2[0][1]", output='R2.txt'),
sim.PyEval(r"'%.2f\t' % LD[0][1]",
step=20,
output="!'>>LD_%d.txt' % rep"),
],
gen=100)
print(open('LD.txt').read())
print(open('R2.txt').read()) # Only the last write operation succeed.
print(open('LD_2.txt').read()) # Each replicate writes to a different file.
# 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.
#
import simuPOP as sim
simu = sim.Simulator(sim.Population(size=[1000], loci=[100]), rep=2)
simu.evolve(
initOps=[sim.InitSex(),
sim.InitGenotype(genotype=[0] * 100 + [1] * 100)],
matingScheme=sim.RandomMating(ops=[
sim.Recombinator(rates=0.01, reps=0),
sim.Recombinator(rates=[0.01] * 10, loci=range(50, 60), reps=1),
]),
postOps=[
sim.Stat(LD=[[40, 55], [60, 70]]),
sim.PyEval(
r'"%d:\t%.3f\t%.3f\t" % (rep, LD_prime[40][55], LD_prime[60][70])'
),
sim.PyOutput('\n', reps=-1)
],
gen=5)
def simuRareVariants(regions,
N,
G,
mu,
selDist,
selCoef,
selModel='exponential',
recRate=0,
splitTo=[1],
splitAt=0,
migrRate=0,
steps=[100],
mutationModel='finite_sites',
initPop='',
extMutantFile='',
addMutantsAt=0,
postHook=None,
statFile='',
popFile='',
markerFile='',
mutantFile='',
genotypeFile='',
verbose=1,
logger=None):
'''
Please refer to simuRareVariants.py -h for a detailed description of all parameters.
Note that a user-defined function can be passed to parameter selDist to specify
arbitrary distribution of fitness. A script-only feature is that a Python function
can be provided through parameter postHook to process the population at each generation.
'''
#
# convert regions to start/end positions
ranges = []
chromTypes = []
for region in regions:
start, end = [int(x) for x in region.split(':')[1].split('..')]
ranges.append((start, end + 1))
if region.split(':')[0] == 'chrX':
chromTypes.append(sim.CHROMOSOME_X)
if len(regions) > 1:
raise ValueError(
'The current implementation only allows one region if it is on chromosome X'
)
logger.info('Chromosome {} is on chromosome X'.format(region))
elif region.split(':')[0] == 'chrY':
raise ValueError(
'The current implementation does not support chromosome Y')
chromTypes.append(sim.CHROMOSOME_Y)
logger.info('Chromosome {} is on chromosome Y'.format(region))
else:
chromTypes.append(sim.AUTOSOME)
if logger:
logger.info('%s regions with a total length of %d basepair.' %
(len(ranges), sum([x[1] - x[0] for x in ranges])))
#
# set default parameter
if selCoef is None:
# set default parameters
if selDist == 'mixed_gamma':
selCoef = [0.0186, 0.0001, 0.184, 0.160 * 2, 0.5, 0.0001, 0.1]
elif selDist == 'mixed_gamma1':
selCoef = [0, -1, 0.562341, 0.01, 0.5, 0.00001, 0.1]
elif selDist == 'gamma1':
selCoef = [0.23, 0.185 * 2, 0.5]
elif selDist == 'gamma2':
selCoef = [0.184, 0.160 * 2, 0.5]
elif selDist == 'gamma3':
selCoef = [0.206, 0.146 * 2, 0.5]
elif selDist == 'constant':
selCoef = [0.01, 0.5]
elif not isinstance(selDist, collections.Callable):
raise ValueError("Unsupported random distribution")
else:
# force to list type
selCoef = list(selCoef)
if len(steps) == 0:
# at the end of each stage
steps = G
elif len(steps) == 1:
# save step for each stage
steps = steps * len(G)
# use a right selection operator.
collector = fitnessCollector()
mode = {
'multiplicative': sim.MULTIPLICATIVE,
'additive': sim.ADDITIVE,
'exponential': sim.EXPONENTIAL
}[selModel]
#
if type(popFile) == str:
popFile = [popFile, -1]
#
if isinstance(selDist, collections.Callable):
mySelector = MutSpaceSelector(selDist=selDist,
mode=mode,
output=collector.getCoef)
elif selDist == 'mixed_gamma':
mySelector = MutSpaceSelector(selDist=mixedGamma(selCoef),
mode=mode,
output=collector.getCoef)
elif selDist == 'mixed_gamma1':
mySelector = MutSpaceSelector(selDist=mixedGamma1(selCoef),
mode=mode,
output=collector.getCoef)
elif selDist.startswith('gamma'):
mySelector = MutSpaceSelector(selDist=[sim.GAMMA_DISTRIBUTION] +
selCoef,
mode=mode,
output=collector.getCoef)
elif selDist == 'constant':
if selCoef == 0:
mySelector = sim.NoneOp()
else:
mySelector = MutSpaceSelector(selDist=[sim.CONSTANT] + selCoef,
mode=mode,
output=collector.getCoef)
#
# Evolve
if os.path.isfile(initPop):
if logger:
logger.info('Loading initial population %s...' % initPop)
pop = sim.loadPopulation(initPop)
if pop.numChrom() != len(regions):
raise ValueError(
'Initial population %s does not have specified regions.' %
initPop)
for ch, reg in enumerate(regions):
if pop.chromName(ch) != reg:
raise ValueError(
'Initial population %s does not have region %s' %
(initPop, reg))
pop.addInfoFields(['fitness', 'migrate_to'])
else:
pop = sim.Population(size=N[0],
loci=[10] * len(regions),
chromNames=regions,
infoFields=['fitness', 'migrate_to'],
chromTypes=chromTypes)
if logger:
startTime = time.clock()
#
progGen = []
# 0, G[0], G[0]+G[1], ..., sum(G)
Gens = [sum(G[:i]) for i in range(len(G) + 1)]
for i in range(len(Gens) - 1):
progGen += list(range(Gens[i], Gens[i + 1], steps[i]))
pop.evolve(
initOps=sim.InitSex(),
preOps=[
sim.PyOutput('''Statistics outputted are
1. Generation number,
2. population size (a list),
3. number of segregation sites,
4. average number of segregation sites per individual
5. average allele frequency * 100
6. average fitness value
7. minimal fitness value of the parental population
''', at = 0)] + \
[sim.PyOutput('Starting stage %d\n' % i, at = Gens[i]) for i in range(0, len(Gens))] + \
# add alleles from an existing population
[sim.IfElse(extMutantFile != '',
ifOps = [
sim.PyOutput('Loading and converting population %s' % extMutantFile),
sim.PyOperator(func=addMutantsFrom, param=(extMutantFile, regions, logger)),
], at = addMutantsAt),
# revert alleles at fixed loci to wildtype
MutSpaceRevertFixedSites(),
# mutate in a region at rate mu, if verbose > 2, save mutation events to a file
MutSpaceMutator(mu, ranges, {'finite_sites':1, 'infinite_sites':2}[mutationModel],
output='' if verbose < 2 else '>>mutations.lst'),
# selection on all loci
mySelector,
# output statistics in verbose mode
sim.IfElse(verbose > 0, ifOps=[
sim.Stat(popSize=True, meanOfInfo='fitness', minOfInfo='fitness'),
NumSegregationSites(),
sim.PyEval(r'"%5d %s %5d %.6f %.6f %.6f %.6f\n" '
'% (gen, subPopSize, numSites, avgSites, avgFreq*100, meanOfInfo["fitness"], minOfInfo["fitness"])',
output='>>' + statFile),
], at = progGen
),
sim.IfElse(len(splitTo) > 1,
sim.Migrator(rate=migrIslandRates(migrRate, len(splitTo)),
begin=splitAt + 1)
),
],
matingScheme=sim.RandomMating(ops=MutSpaceRecombinator(recRate, ranges),
subPopSize=multiStageDemoFunc(N, G, splitTo, splitAt)),
postOps = [
sim.NoneOp() if postHook is None else sim.PyOperator(func=postHook),
sim.SavePopulation(popFile[0], at=popFile[1]),
],
finalOps=[
# revert fixed sites so that the final population does not have fixed sites
MutSpaceRevertFixedSites(),
sim.IfElse(verbose > 0, ifOps=[
# statistics after evolution
sim.Stat(popSize=True),
NumSegregationSites(),
sim.PyEval(r'"%5d %s %5d %.6f %.6f %.6f %.6f\n" '
'% (gen+1, subPopSize, numSites, avgSites, avgFreq*100, meanOfInfo["fitness"], minOfInfo["fitness"])',
output='>>' + statFile),
sim.PyEval(r'"Simulated population has %d individuals, %d segregation sites.'
r'There are on average %.1f sites per individual. Mean allele frequency is %.4f%%.\n"'
r'% (popSize, numSites, avgSites, avgFreq*100)'),
]),
],
gen = Gens[-1]
)
# record selection coefficients to population
if len(collector.selCoef) == 0:
# this must be the neutral case where a NonOp has been used.
pop.dvars().selCoef = 0
else:
pop.dvars().selCoef = collector.selCoef
# re-save the file with the added selCoef
if popFile[-1] == -1:
pop.save(popFile[0])
#
if logger:
logger.info('Population simulation takes %.2f seconds' %
(time.clock() - startTime))
if markerFile or genotypeFile:
if logger:
logger.info('Saving marker information to file %s' % markerFile)
mutants = saveMarkerInfoToFile(pop, markerFile, logger)
if genotypeFile:
if logger:
logger.info('Saving genotype in .ped format to file %s' %
genotypeFile)
saveGenotypeToFile(pop, genotypeFile, mutants, logger)
if mutantFile:
if logger:
logger.info('Saving mutants to file %s' % mutantFile)
saveMutantsToFile(pop, mutantFile, logger=logger)
return pop
v = 0.03 # case of aaBb
elif geno[0] + geno[1] == 2 and geno[2] + geno[3] == 2:
v = 0.05 # case of aabb
else:
v = 0.01 # other cases
if smoking:
return v * 2
else:
return v
pop.evolve(
initOps=[
sim.InitSex(),
sim.InitGenotype(freq=[.5, .5]),
sim.PyOutput('Calculate prevalence in smoker and non-smokers\n'),
],
matingScheme=sim.RandomMating(),
postOps=[
# set smoking status randomly
sim.InitInfo(lambda: random.randint(0, 1), infoFields='smoking'),
# assign affection status
sim.PyPenetrance(loci=[0, 1], func=penet),
sim.Stat(numOfAffected=True,
subPops=[(0, sim.ALL_AVAIL)],
vars='propOfAffected_sp',
step=20),
sim.PyEval(
r"'Non-smoker: %.2f%%\tSmoker: %.2f%%\n' % "
"(subPop[(0,0)]['propOfAffected']*100, subPop[(0,1)]['propOfAffected']*100)",
step=20)
import simuPOP as sim
pop = sim.Population(size=10000, loci=2, infoFields='fitness')
a, b, c, d = 1, 1.5, 2.5, 4
r = 0.02
pop.evolve(initOps=[
sim.InitSex(),
sim.InitGenotype(freq=(0.5, 0.5)),
sim.PyOutput('LD, AB, Ab, aB, ab, avg fitness\n'),
],
preOps=[
sim.MaSelector(loci=[0, 1],
wildtype=0,
fitness=[a, b, a, c, d, c, a, b, a]),
sim.Stat(meanOfInfo='fitness'),
],
matingScheme=sim.RandomMating(ops=sim.Recombinator(rates=r)),
postOps=[
sim.Stat(haploFreq=[0, 1], LD=[0, 1], step=20),
sim.PyEval(
r"'%.3f %.2f %.2f %.2f %.2f %.2f\n' % (LD[0][1], "
"haploFreq[(0,1)][(0,0)], haploFreq[(0,1)][(0,1)],"
"haploFreq[(0,1)][(1,0)], haploFreq[(0,1)][(1,1)],"
"meanOfInfo['fitness'])",
step=20),
],
gen=100)
