Added Papio Anubis genome, recombination map, and demographic model

stdpopsim/catalog/PapAnu/__init__.py

@@ -0,0 +1,5 @@
+"""
+Catalog definitions for PapAnu (Ensembl ID='papio_anubis')
+"""
+from . import species  # noqa: F401
+from . import demographic_models  # noqa: F401

stdpopsim/catalog/PapAnu/demographic_models.py

@@ -0,0 +1,78 @@
+import msprime
+import numpy as np
+import stdpopsim
+
+_species = stdpopsim.get_species("PapAnu")
+
+
+def _pap_anu():
+    # the size during the interval times[k] to times[k+1] = sizes[k]
+    times = np.array(
+        [
+            0.0000,
+            221.2812,
+            463.8092,
+            15027.7847,
+            39328.5751,
+            71092.5441,
+            110830.9203,
+            186053.2682,
+        ]
+    )
+    sizes = np.array(
+        [
+            335505.4808,
+            120758.1302,
+            51822.58297,
+            41841.54229,
+            30714.33863,
+            72998.86202,
+            55968.42221,
+            93362.02606,
+        ]
+    )
+
+    demographic_events = []
+    for sz, t in zip(sizes, times):
+        demographic_events.append(
+            msprime.PopulationParametersChange(time=t, initial_size=sz, population_id=0)
+        )
+    populations = [
+        stdpopsim.Population(
+            id="PAnubis_SNPRC",
+            description="Papio Anubis population from SNPRC",
+        )
+    ]
+
+    return stdpopsim.DemographicModel(
+        id="SinglePopSMCpp_1W22",
+        description="SMC++ estimates of N(t) for Papio Anubis individuals",
+        long_description="""
+        These estimates were obtained from a sample of Papio Anubis
+        individuals from the colony housed at the Southwest National
+        Primate Research Center (SNPRC). SMC++ was run with a subset of
+        36 individuals from the population.
+        """,
+        populations=populations,
+        citations=[
+            stdpopsim.Citation(
+                doi="https://doi.org/10.1093/gbe/evac040",
+                year=2022,
+                author="Wall et. al.",
+                reasons={stdpopsim.CiteReason.DEM_MODEL},
+            )
+        ],
+        # citations for generation time and mutation rate can be
+        # found in species.py
+        generation_time=11,
+        mutation_rate=5.7 * 10e-9,
+        demographic_events=demographic_events,
+        population_configurations=[
+            msprime.PopulationConfiguration(
+                initial_size=335505, metadata=populations[0].asdict()
+            )
+        ],
+    )
+
+
+_species.add_demographic_model(_pap_anu())

stdpopsim/catalog/PapAnu/genetic_maps.py

@@ -0,0 +1,30 @@
+import stdpopsim
+
+
+_species = stdpopsim.get_species("PapAnu")
+
+_gm = stdpopsim.GeneticMap(
+    species=_species,
+    id="Pyrho_PAnubis1.0",
+    description="Pyrho inferred genetic map for Papio Anubis",
+    long_description="""
+        These estimates were obtained from a sample of Papio Anubis
+        individuals from the colony housed at the Southwest National
+        Primate Research Center (SNPRC).
+        """,
+    url=(
+        "https://stdpopsim.s3-us-west-2.amazonaws.com/genetic_maps/"
+        "PapAnu/papio_anubis_genetic_map.tar.gz"
+    ),
+    sha256="",
+    file_pattern="Pyrho_PAnubis1.0_chr{id}.txt",
+    citations=[
+        stdpopsim.Citation(
+            year=2022,
+            author="Wall et. al.",
+            doi="https://doi.org/10.1093/gbe/evac040",
+            reasons={stdpopsim.CiteReason.GEN_MAP},
+        ),
+    ],
+)
+_species.add_genetic_map(_gm)

stdpopsim/catalog/PapAnu/genome_data.py

@@ -0,0 +1,29 @@
+# File autogenerated from Ensembl REST API. Do not edit.
+data = {
+    "assembly_accession": "GCA_008728515.1",
+    "assembly_name": "Panubis1.0",
+    "chromosomes": {
+        "1": {"length": 218172882, "synonyms": []},
+        "2": {"length": 193660750, "synonyms": []},
+        "3": {"length": 184919515, "synonyms": []},
+        "4": {"length": 182120902, "synonyms": []},
+        "5": {"length": 173900761, "synonyms": []},
+        "6": {"length": 167138247, "synonyms": []},
+        "7": {"length": 161768468, "synonyms": []},
+        "8": {"length": 140274886, "synonyms": []},
+        "9": {"length": 127591819, "synonyms": []},
+        "10": {"length": 126462689, "synonyms": []},
+        "11": {"length": 125913696, "synonyms": []},
+        "12": {"length": 123343450, "synonyms": []},
+        "13": {"length": 106849001, "synonyms": []},
+        "14": {"length": 106654974, "synonyms": []},
+        "15": {"length": 91985775, "synonyms": []},
+        "16": {"length": 91184193, "synonyms": []},
+        "17": {"length": 74525926, "synonyms": []},
+        "18": {"length": 72894408, "synonyms": []},
+        "19": {"length": 72123344, "synonyms": []},
+        "20": {"length": 50021108, "synonyms": []},
+        "X": {"length": 142711496, "synonyms": []},
+        "Y": {"length": 8309886, "synonyms": []},
+    },
+}

stdpopsim/catalog/PapAnu/species.py

@@ -0,0 +1,97 @@
+import stdpopsim
+
+from . import genome_data
+
+# recombination rates for autosomes are obtained from
+# Wall et. al. 2022 GBE
+# Recombination for X chromosome has not been estimated
+# and is assigned the mean value of other chromosomes
+_recombination_rate = {
+    "1": 9.926379e-09,
+    "2": 9.605435e-09,
+    "3": 9.022377e-09,
+    "4": 9.825128e-09,
+    "5": 9.579804e-09,
+    "6": 1.049788e-08,
+    "7": 1.118884e-08,
+    "8": 1.108988e-08,
+    "9": 1.132883e-08,
+    "10": 1.175322e-08,
+    "11": 1.184026e-08,
+    "12": 1.082400e-08,
+    "13": 1.246772e-08,
+    "14": 1.274188e-08,
+    "15": 1.260836e-08,
+    "16": 1.476158e-08,
+    "17": 1.524101e-08,
+    "18": 1.368410e-08,
+    "19": 1.303735e-08,
+    "20": 1.677201e-08,
+    "X": 1.18898e-08,
+    "Y": 0.0,
+}
+
+
+_batra2020 = stdpopsim.Citation(
+    author="Batra et. al.",
+    year=2020,
+    doi="https://doi.org/10.1093/gigascience/giaa134",
+    reasons={stdpopsim.CiteReason.ASSEMBLY},
+)
+
+_wall2022 = stdpopsim.Citation(
+    author="Wall et. al.",
+    year=2022,
+    doi="https://doi.org/10.1093/gbe/evac040",
+    reasons={stdpopsim.CiteReason.REC_RATE},
+)
+
+_wu2020 = stdpopsim.Citation(
+    author="Wu et. al.",
+    year=2020,
+    doi="https://doi.org/10.1371/journal.pbio.3000838",
+    reasons={stdpopsim.CiteReason.MUT_RATE},
+)
+
+# mutation rate from Wu et. al. 2020 PLoS Biology
+# recombination rates from Wall et. al. 2022 GBE
+_chromosomes = []
+for name, data in genome_data.data["chromosomes"].items():
+    _chromosomes.append(
+        stdpopsim.Chromosome(
+            id=name,
+            length=data["length"],
+            synonyms=data["synonyms"],
+            mutation_rate=5.7 * 10e-9,
+            recombination_rate=_recombination_rate[name],
+        )
+    )
+
+_genome = stdpopsim.Genome(
+    chromosomes=_chromosomes,
+    assembly_name=genome_data.data["assembly_name"],
+    assembly_accession=genome_data.data["assembly_accession"],
+    citations=[
+        _batra2020.because(stdpopsim.CiteReason.ASSEMBLY),
+        _wall2022.because(stdpopsim.CiteReason.REC_RATE),
+        _wu2020.because(stdpopsim.CiteReason.MUT_RATE),
+    ],
+)
+
+_species = stdpopsim.Species(
+    id="PapAnu",
+    ensembl_id="papio_anubis",
+    name="Papio anubis",
+    common_name="Olive baboon",
+    genome=_genome,
+    generation_time=11,  # Generation time from Wu et al section
+    # "Inferring split times of humans and baboons"
+    population_size=335505,  # Most recent from Wall et al demographic model
+    # included in demographic_models.py in this directory
+    citations=[
+        _wall2022.because(stdpopsim.CiteReason.POP_SIZE),
+        _wu2020.because(stdpopsim.CiteReason.GEN_TIME),
+    ],
+)
+
+stdpopsim.register_species(_species)

tests/test_PapAnu.py

@@ -0,0 +1,99 @@
+import pytest
+
+import stdpopsim
+from tests import test_species
+
+
+class TestSpeciesData(test_species.SpeciesTestBase):
+
+    species = stdpopsim.get_species("PapAnu")
+
+    def test_ensembl_id(self):
+        assert self.species.ensembl_id == "papio_anubis"
+
+    def test_name(self):
+        assert self.species.name == "Papio anubis"
+
+    def test_common_name(self):
+        assert self.species.common_name == "Olive baboon"
+
+    # 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 == -1
+
+    @pytest.mark.skip("Generation time QC not done yet")
+    def test_qc_generation_time(self):
+        assert self.species.generation_time == -1
+
+
+class TestGenomeData(test_species.GenomeTestBase):
+
+    genome = stdpopsim.get_species("PapAnu").genome
+
+    @pytest.mark.skip("Recombination rate QC not done yet")
+    @pytest.mark.parametrize(
+        ["name", "rate"],
+        {
+            "1": -1,
+            "2": -1,
+            "3": -1,
+            "4": -1,
+            "5": -1,
+            "6": -1,
+            "7": -1,
+            "8": -1,
+            "9": -1,
+            "10": -1,
+            "11": -1,
+            "12": -1,
+            "13": -1,
+            "14": -1,
+            "15": -1,
+            "16": -1,
+            "17": -1,
+            "18": -1,
+            "19": -1,
+            "20": -1,
+            "X": -1,
+            "Y": -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"],
+        {
+            "1": -1,
+            "2": -1,
+            "3": -1,
+            "4": -1,
+            "5": -1,
+            "6": -1,
+            "7": -1,
+            "8": -1,
+            "9": -1,
+            "10": -1,
+            "11": -1,
+            "12": -1,
+            "13": -1,
+            "14": -1,
+            "15": -1,
+            "16": -1,
+            "17": -1,
+            "18": -1,
+            "19": -1,
+            "20": -1,
+            "X": -1,
+            "Y": -1,
+        }.items(),
+    )
+    def test_mutation_rate(self, name, rate):
+        assert rate == pytest.approx(self.genome.get_chromosome(name).mutation_rate)