class TestGenome(unittest.TestCase, test_species.GenomeTestMixin):
"""
Tests for the human genome.
"""
genome = stdpopsim.get_species("HomSap").genome
def test_basic_attributes(self):
self.assertEqual(len(self.genome.chromosomes), 25)
def test_recombination_rates(self):
# recompute recombination rates from HapMapII_GRCh37 map then
# compare the results to the current recombination rates for each chromosome
genetic_map = "HapMapII_GRCh37"
species = stdpopsim.get_species("HomSap")
for chrom in self.genome.chromosomes:
if chrom.id == "chrY":
with self.assertWarns(Warning):
contig = species.get_contig(chrom.id,
genetic_map=genetic_map)
else:
contig = species.get_contig(chrom.id, genetic_map=genetic_map)
self.assertAlmostEqual(
chrom.recombination_rate,
contig.recombination_map.mean_recombination_rate,
)
def main():
num_samples = 100
seed = 42
data = {
"species": [],
"model": [],
"cpu_time": [],
"ram": [],
"file_size": []
}
for species_id in ["PonAbe", "HomSap", "DroMel", "AraTha"]:
species = stdpopsim.get_species(species_id)
# Get the shortest chromosome
chrom = sorted(species.genome.chromosomes, key=lambda x: x.length)[0]
assert chrom.recombination_rate > 0
for model in species.demographic_models:
with tempfile.NamedTemporaryFile() as out:
cmd = (
f"{species_id} -d {model.id} -c {chrom.id} {num_samples} "
f"-s {seed} -o {out.name}")
cpu_time, ram = time_cmd(["stdpopsim"] + cmd.split())
file_size = os.path.getsize(out.name)
data["species"].append(species.id)
data["model"].append(model.id)
data["cpu_time"].append(cpu_time)
data["ram"].append(ram)
data["file_size"].append(file_size)
df = pd.DataFrame(data)
df.to_csv("data/benchmark.csv")
print(df)
def _twopop_IM(engine_id,
out_dir,
seed,
NA=1000,
N1=500,
N2=5000,
T=1000,
M12=0,
M21=0,
pulse=None,
**sim_kwargs):
species = stdpopsim.get_species("AraTha")
contig = species.get_contig("chr5", length_multiplier=0.01) # ~270 kb
model = stdpopsim.IsolationWithMigration(NA=NA,
N1=N1,
N2=N2,
T=T,
M12=M12,
M21=M21)
if pulse is not None:
model.demographic_events.append(pulse)
model.demographic_events.sort(key=lambda x: x.time)
model.generation_time = species.generation_time
samples = model.get_samples(50, 50, 0)
engine = stdpopsim.get_engine(engine_id)
t0 = time.perf_counter()
ts = engine.simulate(model, contig, samples, seed=seed, **sim_kwargs)
t1 = time.perf_counter()
out_file = out_dir / f"{seed}.trees"
ts.dump(out_file)
return out_file, t1 - t0
def homsap_composite_model(length, sample_counts, seed, model=hominin_composite()):
if "Nea" in sample_counts and sample_counts["Nea"] != 4:
raise RuntimeError(
"Must have one sample each for the Vindija and Altai Neanderthals"
)
species = stdpopsim.get_species("HomSap")
model = hominin_composite()
contig = random_autosomal_chunk(species, "HapMapII_GRCh37", length, seed)
samples = model.get_samples(
*[
sample_counts.get(p.id, 0)
if p.id != "Nea" and p.sampling_time is not None
else 0
for p in model.populations
]
)
if "Nea" in sample_counts:
# Altai and Vindija Neanderthal dates from Prüfer et al. 2017.
T_Altai = 115e3 / model.generation_time
T_Vindija = 55e3 / model.generation_time
pop = {p.id: i for i, p in enumerate(model.populations)}
samples.extend(
[
msprime.Sample(pop["Nea"], T_Altai),
msprime.Sample(pop["Nea"], T_Altai),
msprime.Sample(pop["Nea"], T_Vindija),
msprime.Sample(pop["Nea"], T_Vindija),
]
)
return species, model, contig, samples
def test_number_of_calls(self):
# Test that genetic map citations are converted.
species = stdpopsim.get_species("HomSap")
genetic_map = species.get_genetic_map("HapMapII_GRCh37")
contig = species.get_contig("chr22", genetic_map=genetic_map.id)
model = stdpopsim.PiecewiseConstantSize(species.population_size)
engine = stdpopsim.get_default_engine()
cites_and_cites = [
genetic_map.citations,
model.citations,
engine.citations,
species.genome.mutation_rate_citations,
species.genome.recombination_rate_citations,
species.genome.assembly_citations,
]
ncite = len(set([ref.doi for cites in cites_and_cites for ref in cites]))
# Patch out writing to a file, then
# ensure that the method is called
# the correct number of times.
with mock.patch("builtins.open", mock.mock_open()):
with open('tmp.bib', 'w') as bib:
with mock.patch.object(
stdpopsim.citations.Citation,
"fetch_bibtex") as mock_bib:
cli.write_bibtex(engine, model, contig, species, bib)
self.assertEqual(mock_bib.call_count, ncite)
def OutOfAfrica_3G09_with_DFE(seed):
"""
The Gutenkunst et al. HomSap/OutOfAfrica_3G09 model, simulated with a DFE.
"""
species = stdpopsim.get_species("HomSap")
model = species.get_demographic_model("OutOfAfrica_3G09")
contig = species.get_contig("chr1", length_multiplier=0.001)
samples = model.get_samples(100, 100, 100) # YRI, CEU, CHB
mutation_types = KimDFE()
# Simulate.
engine = stdpopsim.get_engine("slim")
ts = engine.simulate(
model,
contig,
samples,
seed=seed,
mutation_types=mutation_types,
slim_scaling_factor=10,
slim_burn_in=10,
# Set slim_script=True to print the script instead of running it.
# slim_script=True,
)
return ts
class TestGenomeData(test_species.GenomeTestBase):
genome = stdpopsim.get_species("AnoGam").genome
@pytest.mark.skip("Recombination rate QC not done yet")
@pytest.mark.parametrize(
["name", "rate"],
{
"2L": -1,
"2R": -1,
"3L": -1,
"3R": -1,
"X": -1,
"Mt": -1
}.items(),
)
def test_recombination_rate(self, name, rate):
assert rate == pytest.approx(
self.genome.get_chromosome(name).recombination_rate)
@pytest.mark.skip("Mutation rate QC not done yet")
@pytest.mark.parametrize(
["name", "rate"],
{
"2L": -1,
"2R": -1,
"3L": -1,
"3R": -1,
"X": -1,
"Mt": -1
}.items(),
)
def test_mutation_rate(self, name, rate):
assert rate == pytest.approx(
self.genome.get_chromosome(name).mutation_rate)
def test_recombination_rates(self, chr_id):
# We should recast this test and just hard code in the values.
# Tests should be *obvious* not clever.
# recompute recombination rates from HapMapII_GRCh37 map then
# compare the results to the current recombination rates for each chromosome
genetic_map = "HapMapII_GRCh37"
species = stdpopsim.get_species("HomSap")
chrom = species.genome.get_chromosome(chr_id)
if chr_id in ["X", "Y", "MT"]:
with pytest.warns(stdpopsim.NonAutosomalWarning):
contig = species.get_contig(chr_id, genetic_map=genetic_map)
elif chr_id in ["3", "5", "7", "11", "16", "17", "18", "20"]:
contig = species.get_contig(chr_id, genetic_map=genetic_map)
else:
# The rest of the chromosomes are currently emitting a warning about
# the mismatch in chromosome lengths because of the fact that we're
# on 37 for the map. This should be resolved when we start using the
# lifted over map.
with pytest.warns(UserWarning,
match="longer than chromosome length"):
contig = species.get_contig(chr_id, genetic_map=genetic_map)
assert pytest.approx(
chrom.recombination_rate,
contig.recombination_map.mean_rate,
)
def test_download_over_cache(self):
species = stdpopsim.get_species("DroMel")
gm = species.get_genetic_map("ComeronCrossover_dm6")
gm.download()
self.assertTrue(gm.is_cached())
gm.download()
self.assertTrue(gm.is_cached())
def test_bad_genetic_map(self):
species = stdpopsim.get_species("HomSap")
with mock.patch("stdpopsim.cli.exit", autospec=True) as mocked_exit:
cli.get_genetic_map_wrapper(species, "XXX")
available_maps = ", ".join([gm.id for gm in species.genetic_maps])
mocked_exit.assert_called_once_with(
f"GeneticMap 'HomSap/XXX' not in catalog ({available_maps})")
class TestGetChromosomeAnnotations(tests.CacheReadingTest):
"""
Tests if we get chromosome level annotations
using the Ensembl_GRCh38 human GFF.
"""
# TODO: The HomSap annotations are huge. Once we include a smaller
# annotation set, we should instead use that, so tests are faster.
species = stdpopsim.get_species("HomSap")
an = species.get_annotations("Ensembl_GRCh38_gff3")
def test_known_chromosome(self):
cm = self.an.get_chromosome_annotations("21")
self.assertIsInstance(cm, pandas.DataFrame)
def test_known_chromosome_prefix(self):
cm = self.an.get_chromosome_annotations("chr21")
self.assertIsInstance(cm, pandas.DataFrame)
def test_unknown_chromosome(self):
for bad_chrom in ["", "ABD", None]:
with self.assertRaises(ValueError):
self.an.get_chromosome_annotations(bad_chrom)
def test_get_genes(self):
g = self.an.get_genes_from_chromosome("21")
self.assertIsInstance(g, pandas.DataFrame)
def test_get_genes_full(self):
g = self.an.get_genes_from_chromosome("21", full_table=True)
self.assertIsInstance(g, pandas.DataFrame)
def test_bad_annot_type(self):
bad_annot = "foo"
with self.assertRaises(ValueError):
self.an.get_annotation_type_from_chromomosome(bad_annot, "21")
def test_bad_params(self):
engine = stdpopsim.get_engine("slim")
species = stdpopsim.get_species("HomSap")
contig = species.get_contig("chr1")
model = stdpopsim.PiecewiseConstantSize(species.population_size)
samples = model.get_samples(10)
for scaling_factor in (0, -1, -1e-6):
with self.assertRaises(ValueError):
engine.simulate(
demographic_model=model,
contig=contig,
samples=samples,
slim_scaling_factor=scaling_factor,
dry_run=True,
)
for burn_in in (-1, -1e-6):
with self.assertRaises(ValueError):
engine.simulate(
demographic_model=model,
contig=contig,
samples=samples,
slim_burn_in=burn_in,
dry_run=True,
)
class TestGetContig(unittest.TestCase):
"""
Tests for the get contig method.
"""
species = stdpopsim.get_species("HomSap")
def test_length_multiplier(self):
contig1 = self.species.get_contig("chr22")
for x in [0.125, 1.0, 2.0]:
contig2 = self.species.get_contig("chr22", length_multiplier=x)
self.assertEqual(contig1.recombination_map.get_positions()[-1] * x,
contig2.recombination_map.get_positions()[-1])
def test_length_multiplier_on_empirical_map(self):
with self.assertRaises(ValueError):
self.species.get_contig("chr1",
genetic_map="HapMapII_GRCh37",
length_multiplier=2)
def test_genetic_map(self):
# TODO we should use a different map here so we're not hitting the cache.
contig = self.species.get_contig("chr22",
genetic_map="HapMapII_GRCh37")
self.assertIsInstance(contig.recombination_map,
msprime.RecombinationMap)
def test_get_known_genetic_map(self):
good = ["HapmapII_GRCh37", "Decode_2010_sex_averaged"]
species = stdpopsim.get_species("homsap")
for name in good:
gmap = species.get_genetic_map(name)
self.assertIsInstance(gmap, stdpopsim.GeneticMap)
self.assertEqual(gmap.name, name)
def test_bad_model(self):
species = stdpopsim.get_species("HomSap")
with mock.patch("stdpopsim.cli.exit", autospec=True) as mocked_exit:
cli.get_model_wrapper(species, "XXX")
mocked_exit.assert_called_once_with(
"DemographicModel 'HomSap/XXX' not in catalog"
)
def test_known_chromosome(self):
species = stdpopsim.get_species("CanFam")
genetic_map = species.get_genetic_map("Campbell2016_CanFam3_1")
chrom = species.genome.get_chromosome("1")
cm = genetic_map.get_chromosome_map(chrom.id)
self.assertIsInstance(cm, msprime.RateMap)
self.assertEqual(chrom.length, cm.sequence_length)
def test_bad_genetic_map(self):
species = stdpopsim.get_species("HomSap")
with mock.patch("stdpopsim.cli.exit", autospec=True) as mocked_exit:
cli.get_genetic_map_wrapper(species, "XXX")
mocked_exit.assert_called_once_with(
"Genetic map 'HomSap/XXX' not in catalog"
)
def test_required_params(self):
species = stdpopsim.get_species("HomSap")
model = species.get_demographic_model("AshkSub_7G19")
contig = (species.get_contig("chr1"), )
for engine in stdpopsim.all_engines():
with self.assertRaises(TypeError):
engine.simulate(model, contig)
def setup_sample_file(args):
"""
Return a Thousand Genomes Project sample data file, the
corresponding recombination rate array, a prefix to use for files, and None
"""
filename = args.sample_file
map = args.genetic_map
if not filename.endswith(".samples"):
raise ValueError("Sample data file must end with '.samples'")
sd = tsinfer.load(filename)
inference_pos = sd.sites_position[:][sd.sites_inference[:]]
match = re.search(r'(chr\d+)', filename)
if match or map is not None:
if map is not None:
chr_map = msprime.RecombinationMap.read_hapmap(map)
else:
chr = match.group(1)
print(
f"Using {chr} from HapMapII_GRCh37 for the recombination map")
map = stdpopsim.get_species("HomSap").get_genetic_map(
id="HapMapII_GRCh37")
if not map.is_cached():
map.download()
chr_map = map.get_chromosome_map(chr)
inference_distances = physical_to_genetic(chr_map, inference_pos)
d = np.diff(inference_distances)
rho = np.concatenate(([0.0], d))
else:
inference_distances = inference_pos
d = np.diff(inference_distances)
rho = np.concatenate(([0.0], d / sd.sequence_length))
return sd, rho, filename[:-len(".samples")], None
class PiecewiseConstantSizeMixin:
"""
Mixin that sets up a simple demographic model.
"""
species = stdpopsim.get_species("HomSap")
contig = species.get_contig("chr22", length_multiplier=0.001) # ~50 kb
N0 = 1000 # size in the present
N1 = 500 # ancestral size
T = 500 # generations since size change occurred
T_mut = 300 # introduce a mutation at this generation
model = stdpopsim.PiecewiseConstantSize(N0, (T, N1))
model.generation_time = 1
samples = model.get_samples(100)
mutation_types = [
stdpopsim.ext.MutationType(convert_to_substitution=False)
]
mut_id = len(mutation_types)
def allele_frequency(self, ts):
"""
Get the allele frequency of the drawn mutation.
"""
# surely there's a simpler way!
assert ts.num_mutations == 1
samples = ts.samples()
mut = next(ts.mutations())
tree = ts.at(ts.site(mut.site).position)
have_mut = [u for u in samples if tree.is_descendant(u, mut.node)]
af = len(have_mut) / len(samples)
return af
def run(self):
species = stdpopsim.get_species(self.arguments[0])
sid = f"sec_catalog_{species.id}"
species_target = self.get_target(sid)
section = nodes.section(ids=[sid], names=[sid])
section += nodes.title(text=species.name)
section += self.species_summary(species)
genome_section = nodes.section(
ids=[f"sec_catalog_{species.id}_genome"])
genome_section += nodes.title(text="Genome")
genome_section += self.chromosomes_table(species)
section += genome_section
section += nodes.transition()
maps_section = nodes.section(
ids=[f"sec_catalog_{species.id}_genetic_maps"])
maps_section += nodes.title(text="Genetic Maps")
maps_section += self.genetic_maps_table(species)
for gmap in species.genetic_maps:
maps_section += self.genetic_map_section(species, gmap)
section += maps_section
section += nodes.transition()
models_section = nodes.section(
ids=[f"sec_catalog_{species.id}_models"])
models_section += nodes.title(text="Models")
models_section += self.models_table(species)
for model in species.demographic_models:
models_section += self.model_section(species, model)
section += models_section
return [species_target, section]
def test_get_known_genetic_map(self):
good = ["HapMapII_GRCh37", "DeCodeSexAveraged_GRCh36"]
species = stdpopsim.get_species("HomSap")
for name in good:
gmap = species.get_genetic_map(name)
self.assertIsInstance(gmap, stdpopsim.GeneticMap)
self.assertEqual(gmap.id, name)
def test_script_generation(self):
engine = stdpopsim.get_engine("slim")
species = stdpopsim.get_species("HomSap")
contig = species.get_contig("chr1")
model = stdpopsim.PiecewiseConstantSize(species.population_size)
samples = model.get_samples(10)
model.generation_time = species.generation_time
out, _ = capture_output(engine.simulate,
demographic_model=model,
contig=contig,
samples=samples,
slim_script=True)
self.assertTrue("sim.registerLateEvent" in out)
model = species.get_demographic_model("AncientEurasia_9K19")
samples = model.get_samples(1, 2, 3, 4, 5, 6, 7)
out, _ = capture_output(engine.simulate,
demographic_model=model,
contig=contig,
samples=samples,
slim_script=True)
self.assertTrue("sim.registerLateEvent" in out)
model = species.get_demographic_model("AmericanAdmixture_4B11")
samples = model.get_samples(10, 10, 10)
out, _ = capture_output(engine.simulate,
demographic_model=model,
contig=contig,
samples=samples,
slim_script=True)
self.assertTrue("sim.registerLateEvent" in out)
class TestGenomeData(test_species.GenomeTestBase):
genome = stdpopsim.get_species("AedAeg").genome
@pytest.mark.parametrize(
["name", "rate"],
{
"1": 0.306e-8,
"2": 0.249e-8,
"3": 0.291e-8,
"MT": 0.0
}.items(),
)
def test_recombination_rate(self, name, rate):
assert pytest.approx(
rate,
self.genome.get_chromosome(name).recombination_rate)
@pytest.mark.parametrize(["name", "rate"], {
"1": 3.5e-9,
"2": 3.5e-9,
"3": 3.5e-9,
"MT": 3.5e-9
}.items())
def test_mutation_rate(self, name, rate):
assert pytest.approx(rate,
self.genome.get_chromosome(name).mutation_rate)
def test_number_of_calls(self):
# Test that genetic map citations are converted.
species = stdpopsim.get_species("HomSap")
genetic_map = species.get_genetic_map("HapMapII_GRCh37")
contig = species.get_contig("chr20", genetic_map=genetic_map.id)
model = stdpopsim.PiecewiseConstantSize(species.population_size)
engine = stdpopsim.get_default_engine()
local_cites = stdpopsim.Citation.merge(
[stdpopsim.citations._stdpopsim_citation]
+ genetic_map.citations
+ model.citations
+ engine.citations
+ species.genome.citations
+ species.citations
)
dois = set([ref.doi for ref in local_cites])
ncite = len(dois)
assert ncite == len(local_cites)
cli_cites = cli.get_citations(engine, model, contig, species)
assert len(cli_cites) == len(local_cites)
# Patch out writing to a file, then
# ensure that the method is called
# the correct number of times.
with mock.patch("builtins.open", mock.mock_open()):
with open("tmp.bib", "w") as bib:
with mock.patch.object(
stdpopsim.citations.Citation, "fetch_bibtex", autospec=True
) as mock_bib:
cli.write_bibtex(engine, model, contig, species, bib)
assert mock_bib.call_count == ncite
def get_models_help(species_id, model_id):
"""
Generate help text for the specified species. If model_id is None, generate
help for all models. Otherwise, it must be a string with a valid model ID.
"""
species = stdpopsim.get_species(species_id)
if model_id is None:
models_text = f"\nAll simulation models for {species.name}\n\n"
models = [model.id for model in species.demographic_models]
else:
models = [model_id]
models_text = f"\nModel description\n\n"
# TODO improve this text formatting.
indent = " " * 4
wrapper = textwrap.TextWrapper(initial_indent=indent,
subsequent_indent=indent)
for model_id in models:
model = get_model_wrapper(species, model_id)
models_text += f"{model.id}: {model.description}\n"
models_text += wrapper.fill(textwrap.dedent(model.long_description))
models_text += "\n\n"
models_text += indent + "Populations:\n"
for population in model.populations:
if population.allow_samples:
models_text += indent * 2
models_text += f"{population.id}: {population.description}\n"
models_text += "\n"
return models_text
class TestGenome(test_species.GenomeTestBase):
genome = stdpopsim.get_species("HomSap").genome
def test_basic_attributes(self):
assert len(self.genome.chromosomes) == 25
@pytest.mark.parametrize("chr_id",
[chrom.id for chrom in genome.chromosomes])
def test_recombination_rates(self, chr_id):
# recompute recombination rates from HapMapII_GRCh37 map then
# compare the results to the current recombination rates for each chromosome
genetic_map = "HapMapII_GRCh37"
species = stdpopsim.get_species("HomSap")
chrom = species.genome.get_chromosome(chr_id)
if chr_id in ["X", "Y", "MT"]:
with pytest.warns(stdpopsim.NonAutosomalWarning):
contig = species.get_contig(chr_id, genetic_map=genetic_map)
elif chr_id in ["3", "5", "7", "11", "16", "17", "18", "20"]:
contig = species.get_contig(chr_id, genetic_map=genetic_map)
else:
# The rest of the chromosomes are currently emitting a warning about
# the mismatch in chromosome lengths because of the fact that we're
# on 37 for the map. This should be resolved when we start using the
# lifted over map.
with pytest.warns(UserWarning,
match="longer than chromosome length"):
contig = species.get_contig(chr_id, genetic_map=genetic_map)
assert pytest.approx(
chrom.recombination_rate,
contig.recombination_map.mean_rate,
)
class TestSpeciesData(test_species.SpeciesTestBase):
species = stdpopsim.get_species("AnaPla")
def test_ensembl_id(self):
assert self.species.ensembl_id == "anas_platyrhynchos"
def test_name(self):
assert self.species.name == "Anas platyrhynchos"
def test_common_name(self):
assert self.species.common_name == "Mallard"
# QC Tests. These tests are performed by another contributor
# independently referring to the citations provided in the
# species definition, filling in the appropriate values
# and deleting the pytest "skip" annotations.
# @pytest.mark.skip("Population size QC not done yet")
def test_qc_population_size(self):
assert self.species.population_size == 156000
# @pytest.mark.skip("Generation time QC not done yet")
def test_qc_generation_time(self):
assert self.species.generation_time == 4
class TestGenome(unittest.TestCase, test_species.GenomeTestMixin):
"""
Tests for the Pongo abelii genome.
"""
genome = stdpopsim.get_species("PonAbe").genome
def test_basic_attributes(self):
self.assertEqual(len(self.genome.chromosomes), 24)
def test_chromosome_lengths(self):
genome = self.genome
self.assertEqual(genome.get_chromosome("chr1").length, 229942017)
self.assertEqual(genome.get_chromosome("chr2a").length, 113028656)
self.assertEqual(genome.get_chromosome("chr2b").length, 135000294)
self.assertEqual(genome.get_chromosome("chr3").length, 202140232)
self.assertEqual(genome.get_chromosome("chr4").length, 198332218)
self.assertEqual(genome.get_chromosome("chr5").length, 183952662)
self.assertEqual(genome.get_chromosome("chr6").length, 174210431)
self.assertEqual(genome.get_chromosome("chr7").length, 157549271)
self.assertEqual(genome.get_chromosome("chr8").length, 153482349)
self.assertEqual(genome.get_chromosome("chr9").length, 135191526)
self.assertEqual(genome.get_chromosome("chr10").length, 133410057)
self.assertEqual(genome.get_chromosome("chr11").length, 132107971)
self.assertEqual(genome.get_chromosome("chr12").length, 136387465)
self.assertEqual(genome.get_chromosome("chr13").length, 117095149)
self.assertEqual(genome.get_chromosome("chr14").length, 108868599)
self.assertEqual(genome.get_chromosome("chr15").length, 99152023)
self.assertEqual(genome.get_chromosome("chr16").length, 77800216)
self.assertEqual(genome.get_chromosome("chr17").length, 73212453)
self.assertEqual(genome.get_chromosome("chr18").length, 94050890)
self.assertEqual(genome.get_chromosome("chr19").length, 60714840)
self.assertEqual(genome.get_chromosome("chr20").length, 62736349)
self.assertEqual(genome.get_chromosome("chr21").length, 48394510)
self.assertEqual(genome.get_chromosome("chr22").length, 46535552)
self.assertEqual(genome.get_chromosome("chrX").length, 156195299)
def get_rho(ancestors, filename):
inference_pos = ancestors.sites_position[:]
match = re.search(r'(chr\d+)', filename)
if match is None:
raise ValueError("chr must be in filename")
chr = match.group(1)
map = params.genetic_map
if match or map is not None:
if map is not None:
print(f"Using {chr} from GRCh38 for the recombination map")
chr_map = msprime.RecombinationMap.read_hapmap(map + chr + ".txt")
else:
print(
f"Using {chr} from HapMapII_GRCh37 for the recombination map")
map = stdpopsim.get_species("HomSap").get_genetic_map(
id="HapMapII_GRCh37")
if not map.is_cached():
map.download()
chr_map = map.get_chromosome_map(chr)
inference_distances = physical_to_genetic(chr_map, inference_pos)
d = np.diff(inference_distances)
rho = np.concatenate(([0.0], d))
else:
inference_distances = inference_pos
d = np.diff(inference_distances)
rho = np.concatenate(([0.0], d / sd.sequence_length))
if np.any(d == 0):
w = np.where(d == 0)
raise ValueError("Zero recombination rates at", w, inference_pos[w])
return rho