AnaPla: mallard

stdpopsim/catalog/AnaPla/__init__.py

@@ -0,0 +1,4 @@
+"""
+Catalog definitions for AnaPla (Ensembl ID='anas_platyrhynchos')
+"""
+from . import species  # noqa: F401

stdpopsim/catalog/AnaPla/genome_data.py

@@ -0,0 +1,48 @@
+# File autogenerated from Ensembl REST API. Do not edit.
+data = {
+    "assembly_accession": "GCA_008746955.1",
+    "assembly_name": "ASM874695v1",
+    "chromosomes": {
+        "1": {"length": 208326429, "synonyms": []},
+        "2": {"length": 162939446, "synonyms": []},
+        "3": {"length": 119723720, "synonyms": []},
+        "4": {"length": 77626585, "synonyms": []},
+        "5": {"length": 64988622, "synonyms": []},
+        "6": {"length": 39543408, "synonyms": []},
+        "7": {"length": 37812880, "synonyms": []},
+        "8": {"length": 33348632, "synonyms": []},
+        "9": {"length": 26742597, "synonyms": []},
+        "10": {"length": 22933227, "synonyms": []},
+        "11": {"length": 22193879, "synonyms": []},
+        "12": {"length": 22338721, "synonyms": []},
+        "13": {"length": 21714986, "synonyms": []},
+        "14": {"length": 20320564, "synonyms": []},
+        "15": {"length": 18227546, "synonyms": []},
+        "16": {"length": 16053328, "synonyms": []},
+        "17": {"length": 15319648, "synonyms": []},
+        "18": {"length": 13333155, "synonyms": []},
+        "19": {"length": 12198306, "synonyms": []},
+        "20": {"length": 12091001, "synonyms": []},
+        "21": {"length": 8553409, "synonyms": []},
+        "22": {"length": 16160689, "synonyms": []},
+        "23": {"length": 7977799, "synonyms": []},
+        "24": {"length": 7737077, "synonyms": []},
+        "25": {"length": 7574731, "synonyms": []},
+        "26": {"length": 6918023, "synonyms": []},
+        "27": {"length": 6270716, "synonyms": []},
+        "28": {"length": 5960150, "synonyms": []},
+        "29": {"length": 1456683, "synonyms": []},
+        "30": {"length": 1872559, "synonyms": []},
+        "Z": {"length": 81233375, "synonyms": []},
+        "31": {"length": 2637124, "synonyms": []},
+        "32": {"length": 3473573, "synonyms": []},
+        "33": {"length": 2151773, "synonyms": []},
+        "34": {"length": 7214884, "synonyms": []},
+        "35": {"length": 5548691, "synonyms": []},
+        "36": {"length": 3997205, "synonyms": []},
+        "37": {"length": 3148754, "synonyms": []},
+        "38": {"length": 2836164, "synonyms": []},
+        "39": {"length": 2018729, "synonyms": []},
+        "40": {"length": 1354177, "synonyms": []},
+    },
+}

stdpopsim/catalog/AnaPla/species.py

@@ -0,0 +1,193 @@
+import stdpopsim
+
+from . import genome_data
+
+_HuangEtAl2006 = stdpopsim.Citation(
+    author="Huang et al.",
+    year=2006,
+    doi="https://dx.doi.org/10.1534%2Fgenetics.105.053256",
+    reasons={stdpopsim.CiteReason.REC_RATE},
+)
+
+_LavretskyEtAl2019 = stdpopsim.Citation(
+    author="Lavretsky et al.",
+    year=2019,
+    doi="https://doi.org/10.1111/mec.15343",
+    reasons={stdpopsim.CiteReason.GEN_TIME, stdpopsim.CiteReason.MUT_RATE},
+)
+
+_GuoEtAl2020 = stdpopsim.Citation(
+    author="Guo et al.",
+    year=2020,
+    doi="https://doi.org/10.24272/j.issn.2095-8137.2020.133",
+    reasons={stdpopsim.CiteReason.POP_SIZE},
+)
+
+
+# def _print_recomb_rates():
+#     """
+#     Code to produce the following rates, which follows Lavretsky et al 2019
+#     in taking the total map lengths from chromosomes 1-7 from a microsat study
+#     (Huang et al 2006) to give average rates. This assumes the total lengths for
+#     chromsomes 1-7 is as in Huang et al, and applies the average per-bp rate to
+#     the rest of the chromosomes.
+#     """
+#     from genome_data import data as mallard
+#
+#     chroms = mallard["chromosomes"]
+#     # from Huang et al 2006
+#     huang_chroms = {
+#         "1": {"M": 3.17},
+#         "2": {"M": 2.26},
+#         "3": {"M": 1.12},
+#         "4": {"M": 0.93},
+#         "5": {"M": 0.79},
+#         "6": {"M": 1.20},
+#         "7": {"M": 0.98},
+#     }
+#     for c in huang_chroms:
+#         h = huang_chroms[c]
+#         h["bp"] = mallard["chromosomes"][c]["length"]
+#         h["rate"] = h["M"] / h["bp"]
+#     total_M = sum([x["M"] for x in huang_chroms.values()])
+#     total_bp = sum([x["bp"] for x in huang_chroms.values()])
+#     mean_rate = total_M / total_bp
+#     print(f"_default_recombination_rate = {mean_rate}")
+#     print("_recombination_rate = {")
+#     for c in chroms:
+#         if c in huang_chroms:
+#             print(f"\"{c}\": {huang_chroms[c]['rate']:.2e},")
+#         else:
+#             print(f'"{c}": _default_recombination_rate,')
+#     print("}")
+
+
+_default_recombination_rate = 1.47e-08
+
+
+_recombination_rate = {
+    "1": 1.52e-08,
+    "2": 1.39e-08,
+    "3": 9.35e-09,
+    "4": 1.20e-08,
+    "5": 1.22e-08,
+    "6": 3.03e-08,
+    "7": 2.59e-08,
+    "8": _default_recombination_rate,
+    "9": _default_recombination_rate,
+    "10": _default_recombination_rate,
+    "11": _default_recombination_rate,
+    "12": _default_recombination_rate,
+    "13": _default_recombination_rate,
+    "14": _default_recombination_rate,
+    "15": _default_recombination_rate,
+    "16": _default_recombination_rate,
+    "17": _default_recombination_rate,
+    "18": _default_recombination_rate,
+    "19": _default_recombination_rate,
+    "20": _default_recombination_rate,
+    "21": _default_recombination_rate,
+    "22": _default_recombination_rate,
+    "23": _default_recombination_rate,
+    "24": _default_recombination_rate,
+    "25": _default_recombination_rate,
+    "26": _default_recombination_rate,
+    "27": _default_recombination_rate,
+    "28": _default_recombination_rate,
+    "29": _default_recombination_rate,
+    "30": _default_recombination_rate,
+    "Z": _default_recombination_rate,
+    "31": _default_recombination_rate,
+    "32": _default_recombination_rate,
+    "33": _default_recombination_rate,
+    "34": _default_recombination_rate,
+    "35": _default_recombination_rate,
+    "36": _default_recombination_rate,
+    "37": _default_recombination_rate,
+    "38": _default_recombination_rate,
+    "39": _default_recombination_rate,
+    "40": _default_recombination_rate,
+}
+
+
+# value used in Lavretsky et al 2019, as obtained for nuclear genes in other
+# ducks by Peters, Zhuravlev, Fefelov, Humphries, & Omland, 2008
+_overall_mutation_rate = 4.83e-9  # per generation
+
+_mutation_rate = {
+    "1": _overall_mutation_rate,
+    "2": _overall_mutation_rate,
+    "3": _overall_mutation_rate,
+    "4": _overall_mutation_rate,
+    "5": _overall_mutation_rate,
+    "6": _overall_mutation_rate,
+    "7": _overall_mutation_rate,
+    "8": _overall_mutation_rate,
+    "9": _overall_mutation_rate,
+    "10": _overall_mutation_rate,
+    "11": _overall_mutation_rate,
+    "12": _overall_mutation_rate,
+    "13": _overall_mutation_rate,
+    "14": _overall_mutation_rate,
+    "15": _overall_mutation_rate,
+    "16": _overall_mutation_rate,
+    "17": _overall_mutation_rate,
+    "18": _overall_mutation_rate,
+    "19": _overall_mutation_rate,
+    "20": _overall_mutation_rate,
+    "21": _overall_mutation_rate,
+    "22": _overall_mutation_rate,
+    "23": _overall_mutation_rate,
+    "24": _overall_mutation_rate,
+    "25": _overall_mutation_rate,
+    "26": _overall_mutation_rate,
+    "27": _overall_mutation_rate,
+    "28": _overall_mutation_rate,
+    "29": _overall_mutation_rate,
+    "30": _overall_mutation_rate,
+    "Z": _overall_mutation_rate,
+    "31": _overall_mutation_rate,
+    "32": _overall_mutation_rate,
+    "33": _overall_mutation_rate,
+    "34": _overall_mutation_rate,
+    "35": _overall_mutation_rate,
+    "36": _overall_mutation_rate,
+    "37": _overall_mutation_rate,
+    "38": _overall_mutation_rate,
+    "39": _overall_mutation_rate,
+    "40": _overall_mutation_rate,
+}
+
+_genome = stdpopsim.Genome.from_data(
+    genome_data.data,
+    recombination_rate=_recombination_rate,
+    mutation_rate=_mutation_rate,
+    citations=[
+        _LavretskyEtAl2019,
+        _HuangEtAl2006,
+    ],
+)
+
+_species = stdpopsim.Species(
+    id="AnaPla",
+    ensembl_id="anas_platyrhynchos",
+    name="Anas platyrhynchos",
+    common_name="Mallard",
+    # description="The 'mallard' species complex consists of 14 hybridizing and "
+    # "recently diverged species living around the world, ranging from the holarctic "
+    # "mallard with >15M individuals today in North America alone to "
+    # "endangered endemics in Hawaii and New Zealand. The assembly, "
+    # "recombination rates, and default Ne were estimtaed with wild Chinese "
+    # "mallards.",
+    genome=_genome,
+    generation_time=4,
+    # choosing Ne based on theta = 4 Ne u from Guo et al 2020
+    # theta = 0.003 (Figure 1), u as above (the paper uses a rate from chicken)
+    population_size=156000,
+    citations=[
+        _LavretskyEtAl2019,
+        _GuoEtAl2020,
+    ],
+)
+
+stdpopsim.register_species(_species)

tests/test_AnaPla.py

@@ -0,0 +1,135 @@
+import pytest
+
+import stdpopsim
+from tests import test_species
+
+
+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 == -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("AnaPla").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,
+            "21": -1,
+            "22": -1,
+            "23": -1,
+            "24": -1,
+            "25": -1,
+            "26": -1,
+            "27": -1,
+            "28": -1,
+            "29": -1,
+            "30": -1,
+            "Z": -1,
+            "31": -1,
+            "32": -1,
+            "33": -1,
+            "34": -1,
+            "35": -1,
+            "36": -1,
+            "37": -1,
+            "38": -1,
+            "39": -1,
+            "40": -1,
+        }.items(),
+    )
+    def test_recombination_rate(self, name, rate):
+        assert pytest.approx(rate, 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,
+            "21": -1,
+            "22": -1,
+            "23": -1,
+            "24": -1,
+            "25": -1,
+            "26": -1,
+            "27": -1,
+            "28": -1,
+            "29": -1,
+            "30": -1,
+            "Z": -1,
+            "31": -1,
+            "32": -1,
+            "33": -1,
+            "34": -1,
+            "35": -1,
+            "36": -1,
+            "37": -1,
+            "38": -1,
+            "39": -1,
+            "40": -1,
+        }.items(),
+    )
+    def test_mutation_rate(self, name, rate):
+        assert pytest.approx(rate, self.genome.get_chromosome(name).mutation_rate)