def __init__(self):
genome = stdpopsim.Genome(chromosomes=[])
_species = stdpopsim.Species(
id="tesspe", name="Test species", genome=genome)
super().__init__(
species=_species,
name="test_map",
url="http://example.com/genetic_map.tar.gz",
file_pattern="prefix_{name}.txt")
def __init__(self):
genome = stdpopsim.Genome(chromosomes=[])
_species = stdpopsim.Species(id="TesSpe",
name="Test species",
common_name="Testy McTestface",
genome=genome)
super().__init__(species=_species,
id="test_annotation",
url="http://example.com/annotation.gff.gz",
zarr_url="http://example.com/annotation.zip",
file_name="annotation.gff.gz")
def __init__(self):
genome = stdpopsim.Genome(chromosomes=[])
_species = stdpopsim.Species(id="TesSpe",
name="Test species",
common_name="Testy McTestface",
genome=genome)
super().__init__(
species=_species,
id="test_map",
url="http://example.com/genetic_map.tar.gz",
sha256="1234", # url doesn't exist, so this will never be checked
file_pattern="prefix_{name}.txt")
def __init__(self):
genome = stdpopsim.Genome(chromosomes=[])
_species = stdpopsim.Species(id="TesSpe",
name="Test species",
common_name="Testy McTestface",
genome=genome)
super().__init__(
species=_species,
id="test_annotation",
url="http://example.com/annotation.gff.gz",
zarr_url="http://example.com/annotation.zip",
zarr_sha256="1234", # this shouldn't be checked anywhere
description="test annotation",
)
def __init__(self):
genome = stdpopsim.Genome(chromosomes=[])
_species = stdpopsim.Species(
id="TesSpe",
ensembl_id="test_species",
name="Test species",
common_name="Testy McTestface",
genome=genome,
)
super().__init__(
species=_species,
id="test_annotation",
url="http://example.com/annotation.gff.gz",
intervals_url="http://example.com/annotation.zip",
intervals_sha256="1234", # this shouldn't be checked anywhere
gff_sha256="6789",
description="test annotation",
file_pattern="yolo_{id}.txt",
annotation_source="your mom",
annotation_type="test",
)
length=4641652,
# Lapierre et al. (2016) refer to:
# Genomic adaptive mutation rate: 1e-5, Perfeito et al. (2007), and
# Genomic deleterious mutation rate: 2e−4, Kibota and Lynch (1996).
mutation_rate=1e-5+2e-4,
recombination_rate=0.0))
# mean_conversion_rate=8.9e-11 # not implemented yet!
# mean_conversion_length=542 # not implemented yet!
#: :class:`stdpopsim.Genome` definition for E. Coli.
# Chromosome length data is based on strain K-12.
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
mutation_rate_citations=[
_perfeito_et_al.because(stdpopsim.CiteReason.MUT_RATE),
_kibota_and_lynch.because(stdpopsim.CiteReason.MUT_RATE),
],
assembly_citations=[
_blattner_et_al.because(stdpopsim.CiteReason.ASSEMBLY)])
_species = stdpopsim.Species(
id="EscCol",
name="Escherichia coli",
common_name="E. coli",
genome=_genome,
generation_time=0.00003805175, # 1.0 / (525600 min/year / 20 min/gen)
generation_time_citations=[
_sezonov_et_al.because(stdpopsim.CiteReason.GEN_TIME)],
population_size=1.8e8,
population_size_citations=[
_lapierre_et_al.because(stdpopsim.CiteReason.POP_SIZE)])
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
# Harland et al. (2017), sex-averaged estimate per bp per generation.
mutation_rate=1.2e-8,
recombination_rate=_recombination_rate_data[name],
)
)
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
mutation_rate_citations=[
_HarlandEtAl.because(stdpopsim.CiteReason.MUT_RATE),
],
recombination_rate_citations=[_MaEtAl.because(stdpopsim.CiteReason.REC_RATE)],
assembly_citations=[_RosenEtAl.because(stdpopsim.CiteReason.ASSEMBLY)],
)
_species = stdpopsim.Species(
id="BosTau",
name="Bos Taurus",
common_name="Cattle",
genome=_genome,
generation_time=5,
generation_time_citations=[_MacLeodEtAl.because(stdpopsim.CiteReason.GEN_TIME)],
population_size=62000,
population_size_citations=[_MacLeodEtAl.because(stdpopsim.CiteReason.POP_SIZE)],
)
_chromosomes = []
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
# Harland et al. (2017), sex-averaged estimate per bp per generation.
mutation_rate=1.2e-8,
recombination_rate=_recombination_rate_data[name],
))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
citations=[
_HarlandEtAl.because(stdpopsim.CiteReason.MUT_RATE),
_MaEtAl.because(stdpopsim.CiteReason.REC_RATE),
_RosenEtAl.because(stdpopsim.CiteReason.ASSEMBLY),
],
)
_species = stdpopsim.Species(
id="BosTau",
ensembl_id="bos_taurus",
name="Bos Taurus",
common_name="Cattle",
genome=_genome,
generation_time=5,
population_size=62000,
citations=[_MacLeodEtAl],
)
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
# Nater et al. 2017 used mu=1.5e-8 per generation, based on the
# assumption that it's similar to humans and chimps.
mutation_rate=1.5e-8,
recombination_rate=_recombination_rate_data[name],
)
)
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
citations=[_nater2017],
)
_species = stdpopsim.Species(
id="PonAbe",
ensembl_id="pongo_abelii",
name="Pongo abelii",
common_name="Sumatran orangutan",
genome=_genome,
# generation time used by Locke et al. without further citation
generation_time=20,
# Locke et al. inferred ancestral Ne
population_size=1.79e4,
citations=[_locke2011],
)
name, length = line.split()[:2]
_chromosomes.append(stdpopsim.Chromosome(
id=name, length=int(length),
mutation_rate=7e-9,
recombination_rate=200 / 124000 / 2 / 1e6))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
mutation_rate_citations=[
stdpopsim.Citation(
author="Ossowski et al.",
year="2010",
doi="https://doi.org/10.1126/science.1180677",
reasons={stdpopsim.CiteReason.MUT_RATE})],
recombination_rate_citations=[
stdpopsim.Citation(
author="Huber et al.",
year="2014",
doi="https://doi.org/10.1093/molbev/msu247",
reasons={stdpopsim.CiteReason.REC_RATE})],
assembly_citations=[
stdpopsim.Citation(
doi="https://doi.org/10.1093/nar/gkm965",
year="2007",
author="Swarbreck et al.",
reasons={stdpopsim.CiteReason.ASSEMBLY})])
_species = stdpopsim.Species(
id="AraTha",
name="Arabidopsis thaliana",
common_name="A. thaliana",
genome=_genome,
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
# Nater et al. 2017 used mu=1.5e-8 per generation, based on the
# assumption that it's similar to humans and chimps.
mutation_rate=1.5e-8,
recombination_rate=_recombination_rate_data[name],
))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
mutation_rate_citations=[
_nater2017.because(stdpopsim.CiteReason.MUT_RATE)
],
)
_species = stdpopsim.Species(
id="PonAbe",
name="Pongo abelii",
common_name="Sumatran orangutan",
genome=_genome,
# generation time used by Locke et al. without further citation
generation_time=20,
generation_time_citations=[
_locke2011.because(stdpopsim.CiteReason.GEN_TIME)
],
# Locke et al. inferred ancestral Ne
synonyms=data["synonyms"],
# Wielgoss et al. (2011) calculated for strain REL606,
# from synonymous substitutions over 40,000 generations.
mutation_rate=8.9e-11,
recombination_rate=0.0,
)
)
# mean_conversion_rate=8.9e-11 # not implemented yet!
# mean_conversion_length=542 # not implemented yet!
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
mutation_rate_citations=[
_wielgoss_et_al.because(stdpopsim.CiteReason.MUT_RATE),
],
assembly_citations=[_blattner_et_al.because(stdpopsim.CiteReason.ASSEMBLY)],
)
_species = stdpopsim.Species(
id="EscCol",
name="Escherichia coli",
common_name="E. coli",
# We use the K-12 strain, because the parameters we're using more
# closely match this strain than the ensembl default (HUSEC2011).
ensembl_id="escherichia_coli_str_k_12_substr_mg1655_gca_000005845",
genome=_genome,
# E. coli K-12 strain MG1655 "doubling time during steady-state growth in
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
mutation_rate=5.49e-9, # _SchriderEtAl de novo mutation rate
recombination_rate=_recombination_rate_data[name],
)
)
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
citations=[
_SchriderEtAl.because(stdpopsim.CiteReason.MUT_RATE),
_DosSantosEtAl,
_HoskinsEtAl,
_ComeronEtAl.because(stdpopsim.CiteReason.REC_RATE),
],
)
_species = stdpopsim.Species(
id="DroMel",
ensembl_id="drosophila_melanogaster",
name="Drosophila melanogaster",
common_name="D. melanogaster",
genome=_genome,
generation_time=0.1,
population_size=1720600,
citations=[_LiAndStephan],
chr22 51304566 1.4445022767788226e-08
chrX 155270560 1.164662223273842e-08
chrY 59373566 0.0
"""
_chromosomes = []
for line in _chromosome_data.splitlines():
name, length, mean_rr = line.split()[:3]
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=int(length),
mutation_rate=1e-8, # WRONG!,
recombination_rate=float(mean_rr)))
_genome = stdpopsim.Genome(chromosomes=_chromosomes)
_species = stdpopsim.Species(
id="homsap",
name="H**o sapiens",
genome=_genome,
# TODO reference for these
generation_time=25,
population_size=10**4)
stdpopsim.register_species(_species)
###########################################################
#
# Genetic maps
#
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
mutation_rate=1.84e-9, # _Konrad et al. de-nove mutation rate,
# it's not uniform and it's much better to use a mutation map.
# mutation_rate=_mutation_rate_data[name],
recombination_rate=_recombination_rate_data[name],
))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
citations=[
_genome1998,
_KonradEtAl2019.because(stdpopsim.CiteReason.MUT_RATE),
_KonradEtAl2017.because(stdpopsim.CiteReason.MUT_RATE),
_Rockman2009.because(stdpopsim.CiteReason.REC_RATE),
],
)
_species = stdpopsim.Species(
id="CaeEle",
ensembl_id="",
name="Caenorhabditis elegans",
common_name="C. elegans",
genome=_genome,
generation_time=0.01, # the generation time in the lab ~150
# generation per year (0.00666), it should be less in the wild
population_size=10000,
for line in _chromosome_data.splitlines():
name, length, mean_rr = line.split()
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=int(length),
mutation_rate=4e-9, # based on non-CpG sites only
recombination_rate=float(mean_rr)))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
mutation_rate_citations=[
_SkoglundEtAl.because(stdpopsim.CiteReason.MUT_RATE),
_FranzEtAl.because(stdpopsim.CiteReason.MUT_RATE),
],
recombination_rate_citations=[
_CampbellEtAl.because(stdpopsim.CiteReason.REC_RATE)
],
assembly_citations=[
_LindbladTohEtAl.because(stdpopsim.CiteReason.ASSEMBLY)
],
)
_species = stdpopsim.Species(
id="CanFam",
name="Canis familiaris",
common_name="Dog",
genome=_genome,
generation_time=3,
generation_time_citations=[
# Everyone uses 3 years because everyone else uses it.
_chromosomes = []
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
mutation_rate=1.29e-8,
recombination_rate=_recombination_rate_data[name],
))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
mutation_rate_citations=[_tian2019.because(stdpopsim.CiteReason.MUT_RATE)],
recombination_rate_citations=[
_hapmap2007.because(stdpopsim.CiteReason.REC_RATE)
],
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
assembly_citations=[_genome2001],
)
_species = stdpopsim.Species(
id="HomSap",
name="H**o sapiens",
common_name="Human",
genome=_genome,
generation_time=30,
generation_time_citations=[
_tremblay2000.because(stdpopsim.CiteReason.GEN_TIME)
],
population_size=10**4,
author="Nater et al.",
year=2017,
doi="https://doi.org/10.1016/j.cub.2017.09.047")
_chromosomes = []
for line in _chromosome_data.splitlines():
name, length, mean_rr = line.split()[:3]
_chromosomes.append(
stdpopsim.Chromosome(id=name,
length=int(length),
mutation_rate=1.5e-8,
recombination_rate=float(mean_rr)))
_genome = stdpopsim.Genome(chromosomes=_chromosomes,
mutation_rate_citations=[
_nater2017.because(
stdpopsim.CiteReason.MUT_RATE)
])
_species = stdpopsim.Species(
id="PonAbe",
name="Pongo abelii",
common_name="Sumatran orangutan",
genome=_genome,
generation_time=20,
generation_time_citations=[
_locke2011.because(stdpopsim.CiteReason.GEN_TIME)
],
population_size=1.79e4,
population_size_citations=[
_locke2011.because(stdpopsim.CiteReason.POP_SIZE)
recombination_rate=_recombination_rate_data[name],
))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
citations=[
stdpopsim.Citation(
author="Ossowski et al.",
year=2010,
doi="https://doi.org/10.1126/science.1180677",
reasons={stdpopsim.CiteReason.MUT_RATE},
),
stdpopsim.Citation(
author="Huber et al.",
year=2014,
doi="https://doi.org/10.1093/molbev/msu247",
reasons={stdpopsim.CiteReason.REC_RATE},
),
stdpopsim.Citation(
doi="https://doi.org/10.1093/nar/gkm965",
year=2007,
author="Swarbreck et al.",
reasons={stdpopsim.CiteReason.ASSEMBLY},
),
],
)
stdpopsim.utils.append_common_synonyms(_genome)
_species = stdpopsim.Species(
_recombination_rate_data["mitochondrion_genome"] = 0
_chromosomes = []
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
mutation_rate=5.49e-9, # citation: _SchriderEtAl
recombination_rate=_recombination_rate_data[name]))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
mutation_rate_citations=[
_SchriderEtAl.because(stdpopsim.CiteReason.MUT_RATE)
],
assembly_citations=[_DosSantosEtAl])
_species = stdpopsim.Species(
id="DroMel",
name="Drosophila melanogaster",
common_name="D. melanogaster",
genome=_genome,
generation_time=0.1,
generation_time_citations=[
_LiAndStephan.because(stdpopsim.CiteReason.GEN_TIME)
],
population_size=1720600,
population_size_citations=[
for line in _chromosome_data.splitlines():
name, length = line.split()[:2]
_chromosomes.append(stdpopsim.Chromosome(
id=name, length=int(length),
mutation_rate=7e-9,
recombination_rate=8.1e-9))
_SwarbreckEtAl = stdpopsim.Citation(
doi="https://doi.org/10.1093/nar/gkm965",
year="2007",
author="Swarbreck et al.",
reasons={stdpopsim.CiteReason.ASSEMBLY}
)
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_citations=[
_SwarbreckEtAl])
_species = stdpopsim.Species(
id="AraTha",
name="Arabidopsis thaliana",
common_name="A. thaliana",
genome=_genome,
generation_time=1.0,
generation_time_citations=[stdpopsim.Citation(
doi="https://doi.org/10.1890/0012-9658(2002)083[1006:GTINSO]2.0.CO;2",
year="2002",
author="Donohue",
reasons={stdpopsim.CiteReason.GEN_TIME})],
population_size=10**4,
population_size_citations=[stdpopsim.Citation(
for line in _chromosome_data.splitlines():
name, length = line.split()[:2]
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=int(length),
mutation_rate=5.49e-9, # citation: _SchriderEtAl
recombination_rate=8.4e-9)) # WRONG, underestimate used in S&S!
# TODO need to port this documentation somewhere.
# class:`stdpopsim.Genome` definition for D. melanogaster. Chromosome length data is
# based on `dm6 <https://www.ncbi.nlm.nih.gov/assembly/GCF_000001215.4/>`_.
_genome = stdpopsim.Genome(chromosomes=_chromosomes,
mutation_rate_citations=[
_SchriderEtAl.because(
stdpopsim.CiteReason.MUT_RATE)
],
assembly_citations=[_DosSantosEtAl])
_species = stdpopsim.Species(
id="DroMel",
name="Drosophila melanogaster",
common_name="D. melanogaster",
genome=_genome,
generation_time=0.1,
generation_time_citations=[
_LiAndStephan.because(stdpopsim.CiteReason.GEN_TIME)
],
population_size=1720600,
population_size_citations=[
_LiAndStephan.because(stdpopsim.CiteReason.POP_SIZE)
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
# Harland et al. (2017), sex-averaged estimate per bp per generation.
mutation_rate=1.2e-8,
recombination_rate=_recombination_rate_data[name],
)
)
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
citations=[
_RosenEtAl,
_HarlandEtAl,
_MaEtAl,
],
)
_species = stdpopsim.Species(
id="BosTau",
ensembl_id="bos_taurus",
name="Bos taurus",
common_name="Cattle",
genome=_genome,
generation_time=5,
population_size=90, # most recent Ne in _MacLeodEtAl
citations=[_MacLeodEtAl],
)
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
mutation_rate=4e-9, # based on non-CpG sites only
recombination_rate=_recombination_rate_data[name],
))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
citations=[
_SkoglundEtAl.because(stdpopsim.CiteReason.MUT_RATE),
_FranzEtAl.because(stdpopsim.CiteReason.MUT_RATE),
_CampbellEtAl.because(stdpopsim.CiteReason.REC_RATE),
_LindbladTohEtAl.because(stdpopsim.CiteReason.ASSEMBLY),
],
)
_species = stdpopsim.Species(
id="CanFam",
ensembl_id="canis_familiaris",
name="Canis familiaris",
common_name="Dog",
genome=_genome,
population_size=13000, # ancestral dog size
generation_time=3,
citations=[
_chromosomes = []
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
mutation_rate=1.29e-8,
recombination_rate=_recombination_rate_data[name],
))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
citations=[
_genome2001,
_tian2019.because(stdpopsim.CiteReason.MUT_RATE),
_hapmap2007.because(stdpopsim.CiteReason.REC_RATE),
],
)
stdpopsim.utils.append_common_synonyms(_genome)
_species = stdpopsim.Species(
id="HomSap",
ensembl_id="homo_sapiens",
name="H**o sapiens",
common_name="Human",
genome=_genome,
generation_time=30,
population_size=10**4,
citations=[
