year=2011,
doi="http://doi.org/10.1038/nature09687")
_nater2017 = stdpopsim.Citation(
author="Nater et al.",
year=2017,
doi="https://doi.org/10.1016/j.cub.2017.09.047")
_chromosomes = []
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(
reasons={stdpopsim.CiteReason.ASSEMBLY})
_genome_wide_estimate = 8.4e-9 # WRONG, underestimate used in S&S!
_recombination_rate_data = collections.defaultdict(
lambda: _genome_wide_estimate)
# Set some exceptions for non-recombining chrs.
_recombination_rate_data["Y"] = 0
_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",
"2R": 2.23458641776e-08,
"3L": 1.79660308862e-08,
"3R": 1.71642045777e-08,
"4": 2.00579550709e-08,
"X": 2.89650687913e-08,
"Y": 0,
"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, # _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),
],
)
_locke2011 = stdpopsim.Citation(author="Locke et al.",
year=2011,
doi="http://doi.org/10.1038/nature09687")
_nater2017 = stdpopsim.Citation(
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=[
chr21 34683425 0.95e-8
chr22 35308119 0.95e-8
chrX 151242693 0.95e-8
"""
_locke2011 = stdpopsim.Citation(
author="Locke et al.",
year=2011,
doi="http://doi.org/10.1038/nature09687"
)
_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=2.0e-8,
recombination_rate=float(mean_rr)))
_genome = stdpopsim.Genome(
chromosomes=_chromosomes,
mutation_rate_citations=[
_locke2011.because(stdpopsim.CiteReason.MUT_RATE)])
_species = stdpopsim.Species(
id="PonPyg",
name="Pongo pygmaeus",
common_name="Bornean orangutan",
genome=_genome,
generation_time=20,
generation_time_citations=[
_locke2011.because(stdpopsim.CiteReason.GEN_TIME)],
_kibota_and_lynch = stdpopsim.Citation(
author="Kibota and Lynch",
year="1996",
doi="https://doi.org/10.1038/381694a0")
_blattner_et_al = stdpopsim.Citation(
author="Blattner et al.",
year="1997",
doi="10.1126/science.277.5331.1453")
_chromosomes = []
_chromosomes.append(stdpopsim.Chromosome(
id=None,
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),
],
_kibota_and_lynch = stdpopsim.Citation(author="Kibota and Lynch",
year="1996",
doi="https://doi.org/10.1038/381694a0")
_blattner_et_al = stdpopsim.Citation(author="Blattner et al.",
year="1997",
doi="10.1126/science.277.5331.1453")
_chromosomes = []
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
# 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,
assembly_name=genome_data.data["assembly_name"],
assembly_accession=genome_data.data["assembly_accession"],
_chromosome_data = """\
chr1 30427671
chr2 19698289
chr3 23459830
chr4 18585056
chr5 26975502
"""
# mutation rate from Ossowski 2010 Science
# recombination value from Huber et al 2014 MBE
# rho=200/Mb, assume Ne=124,000, rho=2*Ne*r
_chromosomes = []
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=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",
"II": 3.999342e-11,
"III": 4.484974e-11,
"IV": 2.417689e-11,
"V": 2.722476e-11,
"X": 3.447911e-11,
"MtDNA": 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=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),
],
_chromosome_data = """\
chr1 30427671
chr2 19698289
chr3 23459830
chr4 18585056
chr5 26975502
"""
# mutation rate from Ossowski 2010 Science
# recombination value from Huber et al 2014 MBE
# rho=200/Mb, assume Ne=124,000, rho=2*Ne*r
_chromosomes = []
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(
chr2L 23513712
chr2R 25286936
chr3L 28110227
chr3R 32079331
chr4 1348131
chrY 3667352
chrM 19524
"""
_chromosomes = []
for line in _chromosome_data.splitlines():
name, length = line.split()[:2]
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=int(length),
mutation_rate=8.4e-9, # WRONG!, underestimate used in S&S
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)
_species = stdpopsim.Species(
id="dromel",
name="Drosophila melanogaster",
genome=_genome,
# TODO reference for these
generation_time=0.1,
year=2016,
doi="https://doi.org/10.1126/science.aaf3161")
_CampbellEtAl = stdpopsim.Citation(
# A Pedigree-Based Map of Recombination in the Domestic Dog Genome.
author="Campbell et al.",
year=2016,
doi="https://doi.org/10.1534/g3.116.034678")
_chromosomes = []
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)
],
_recombination_rate_data = {
str(j): _mean_recombination_rate for j in range(1, 6)
}
_recombination_rate_data["Mt"] = 0
_recombination_rate_data["Pt"] = 0 # JK Is this correct??
# mutation rate from Ossowski 2010 Science
# recombination value from Huber et al 2014 MBE
# rho=200/Mb, assume Ne=124,000, rho=2*Ne*r
_chromosomes = []
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(stdpopsim.Chromosome(
id=name,
length=data["length"],
synonyms=data["synonyms"],
mutation_rate=7e-9,
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=[
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(
_wielgoss_et_al = stdpopsim.Citation(
author="Wielgoss et al.", year="2011", doi="https://doi.org/10.1534/g3.111.000406"
)
_blattner_et_al = stdpopsim.Citation(
author="Blattner et al.", year="1997", doi="10.1126/science.277.5331.1453"
)
_chromosomes = []
for name, data in genome_data.data["chromosomes"].items():
_chromosomes.append(
stdpopsim.Chromosome(
id=name,
length=data["length"],
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),
)
_tremblay2000 = stdpopsim.Citation(
doi="https://doi.org/10.1086/302770",
year=2000,
author="Tremblay and Vézina",
reasons={stdpopsim.CiteReason.GEN_TIME},
)
_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)
author="Schrider et al.",
year=2013,
doi="https://doi.org/10.1534/genetics.113.151670")
_DosSantosEtAl = stdpopsim.Citation(doi="https://doi.org/10.1093/nar/gku1099",
year="2015",
author="dos Santos et al.",
reasons={stdpopsim.CiteReason.ASSEMBLY})
_chromosomes = []
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(
# 24.35 / 2628394923 = 9.26e-9 per bp per generation.
_genome_wide_recombination_rate = 9.26e-9
_recombination_rate_data = collections.defaultdict(
lambda: _genome_wide_recombination_rate
)
# Set some exceptions for non-recombining chrs.
_recombination_rate_data["MT"] = 0
_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,
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(
)
_CampbellEtAl = stdpopsim.Citation(
# A Pedigree-Based Map of Recombination in the Domestic Dog Genome.
author="Campbell et al.",
year=2016,
doi="https://doi.org/10.1534/g3.116.034678",
)
_chromosomes = []
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),
],
)
#
###########################################################
_lapierre_et_al = stdpopsim.Citation(
author="Lapierre et al.",
year="2016",
doi="https://doi.org/10.1093/molbev/msw048")
_sezonov_et_al = stdpopsim.Citation(author="Sezonov et al.",
year="2007",
doi="https://doi.org/10.1128/JB.01368-07")
_chromosomes = []
_chromosomes.append(
stdpopsim.Chromosome(id=None,
length=4641652,
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)
_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)
