Remove different citation lists.

jeanrjc · Mar 10, 2021 · 5a0048a · 5a0048a
1 parent f295c1b
commit 5a0048a
Show file tree

Hide file tree

Showing 13 changed files with 96 additions and 108 deletions.
diff --git a/stdpopsim/catalog/AraTha/species.py b/stdpopsim/catalog/AraTha/species.py
@@ -28,29 +28,25 @@
     chromosomes=_chromosomes,
     assembly_name=genome_data.data["assembly_name"],
     assembly_accession=genome_data.data["assembly_accession"],
-    mutation_rate_citations=[
+    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},
-        )
+        ),
     ],
 )
 
@@ -61,22 +57,20 @@
     common_name="A. thaliana",
     genome=_genome,
     generation_time=1.0,
-    generation_time_citations=[
+    population_size=10 ** 4,
+    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(
             doi="https://doi.org/10.1016/j.cell.2016.05.063",
             year=2016,
             author="1001GenomesConsortium",
             reasons={stdpopsim.CiteReason.POP_SIZE},
-        )
+        ),
     ],
 )
 

diff --git a/stdpopsim/catalog/BosTau/species.py b/stdpopsim/catalog/BosTau/species.py
@@ -33,6 +33,7 @@
     doi="https://doi.org/10.1093/molbev/mst125",
     year="2013",
     author="MacLeod et al.",
+    reasons={stdpopsim.CiteReason.GEN_TIME, stdpopsim.CiteReason.POP_SIZE},
 )
 
 # Recombination rate has been derived from dairy cattle crossovers
@@ -66,11 +67,11 @@
 
 _genome = stdpopsim.Genome(
     chromosomes=_chromosomes,
-    mutation_rate_citations=[
+    citations=[
         _HarlandEtAl.because(stdpopsim.CiteReason.MUT_RATE),
+        _MaEtAl.because(stdpopsim.CiteReason.REC_RATE),
+        _RosenEtAl.because(stdpopsim.CiteReason.ASSEMBLY),
     ],
-    recombination_rate_citations=[_MaEtAl.because(stdpopsim.CiteReason.REC_RATE)],
-    assembly_citations=[_RosenEtAl.because(stdpopsim.CiteReason.ASSEMBLY)],
 )
 
 _species = stdpopsim.Species(
@@ -80,9 +81,8 @@
     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)],
+    citations=[_MacLeodEtAl],
 )
 
 stdpopsim.register_species(_species)
diff --git a/stdpopsim/catalog/CanFam/species.py b/stdpopsim/catalog/CanFam/species.py
@@ -95,12 +95,12 @@
     chromosomes=_chromosomes,
     assembly_name=genome_data.data["assembly_name"],
     assembly_accession=genome_data.data["assembly_accession"],
-    mutation_rate_citations=[
+    citations=[
         _SkoglundEtAl.because(stdpopsim.CiteReason.MUT_RATE),
         _FranzEtAl.because(stdpopsim.CiteReason.MUT_RATE),
+        _CampbellEtAl.because(stdpopsim.CiteReason.REC_RATE),
+        _LindbladTohEtAl.because(stdpopsim.CiteReason.ASSEMBLY),
     ],
-    recombination_rate_citations=[_CampbellEtAl.because(stdpopsim.CiteReason.REC_RATE)],
-    assembly_citations=[_LindbladTohEtAl.because(stdpopsim.CiteReason.ASSEMBLY)],
 )
 
 _species = stdpopsim.Species(
@@ -109,9 +109,10 @@
     name="Canis familiaris",
     common_name="Dog",
     genome=_genome,
+    population_size=13000,  # ancestral dog size
     generation_time=3,
-    generation_time_citations=[
-        # Everyone uses 3 years because everyone else uses it.
+    citations=[
+        # Everyone uses 3 years for generation time because everyone else uses it.
         # It's likely higher, at least in wolves:
         # https://academic.oup.com/mbe/article/35/6/1366/4990884
         # Reasoning behind a generation time of 3 years:
@@ -122,9 +123,8 @@
         # intervention in breeding. In case (2), you might want to match what other
         # studies have done (thus using 3 year generations), or you might want to
         # consider what is known about modern wolves.
+        _LindbladTohEtAl.because(stdpopsim.CiteReason.POP_SIZE)
     ],
-    population_size=13000,  # ancestral dog size
-    population_size_citations=[_LindbladTohEtAl.because(stdpopsim.CiteReason.POP_SIZE)],
 )
 
 stdpopsim.register_species(_species)
diff --git a/stdpopsim/catalog/DroMel/demographic_models.py b/stdpopsim/catalog/DroMel/demographic_models.py
@@ -40,7 +40,6 @@ def _afr_3epoch():
         )
     ]
     generation_time = _species.generation_time
-    citations.extend(_species.generation_time_citations)
 
     # Parameter values from "Simulating Data" section
     # these are assumptions, not estimates
@@ -95,7 +94,6 @@ def _ooa_2():
     populations = [_afr_population, _eur_population]
     citations = [_LiAndStephan.because(stdpopsim.CiteReason.DEM_MODEL)]
     generation_time = _species.generation_time
-    citations.extend(_species.generation_time_citations)
 
     # African Parameter values from "Demographic History of the African
     # Population" section

diff --git a/stdpopsim/catalog/DroMel/species.py b/stdpopsim/catalog/DroMel/species.py
@@ -5,7 +5,10 @@
 
 
 _LiAndStephan = stdpopsim.Citation(
-    author="Li et al.", year=2006, doi="https://doi.org/10.1371/journal.pgen.0020166"
+    author="Li et al.",
+    year=2006,
+    doi="https://doi.org/10.1371/journal.pgen.0020166",
+    reasons={stdpopsim.CiteReason.GEN_TIME, stdpopsim.CiteReason.POP_SIZE},
 )
 
 _SchriderEtAl = stdpopsim.Citation(
@@ -45,8 +48,7 @@
     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],
+    citations=[_SchriderEtAl.because(stdpopsim.CiteReason.MUT_RATE), _DosSantosEtAl],
 )
 
 _species = stdpopsim.Species(
@@ -56,9 +58,8 @@
     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)],
+    citations=[_LiAndStephan],
 )
 
 stdpopsim.register_species(_species)
diff --git a/stdpopsim/catalog/EscCol/species.py b/stdpopsim/catalog/EscCol/species.py
@@ -43,10 +43,10 @@
     chromosomes=_chromosomes,
     assembly_name=genome_data.data["assembly_name"],
     assembly_accession=genome_data.data["assembly_accession"],
-    mutation_rate_citations=[
+    citations=[
         _wielgoss_et_al.because(stdpopsim.CiteReason.MUT_RATE),
+        _blattner_et_al.because(stdpopsim.CiteReason.ASSEMBLY),
     ],
-    assembly_citations=[_blattner_et_al.because(stdpopsim.CiteReason.ASSEMBLY)],
 )
 
 
@@ -61,11 +61,13 @@
     # E. coli K-12 strain MG1655 "doubling time during steady-state growth in
     # Luria-Bertani broth was 20 min".
     generation_time=0.00003805175,  # 1.0 / (525600 min/year / 20 min/gen)
-    generation_time_citations=[_sezonov_et_al.because(stdpopsim.CiteReason.GEN_TIME)],
     # Hartl et al. calculated Ne for "natural isolates of E. coli",
     # assuming mu=5e-10 (from Drake 1991).
     population_size=1.8e8,
-    population_size_citations=[_hartl_et_al.because(stdpopsim.CiteReason.POP_SIZE)],
+    citations=[
+        _sezonov_et_al.because(stdpopsim.CiteReason.GEN_TIME),
+        _hartl_et_al.because(stdpopsim.CiteReason.POP_SIZE),
+    ],
 )
 
 

diff --git a/stdpopsim/catalog/HomSap/species.py b/stdpopsim/catalog/HomSap/species.py
@@ -79,11 +79,13 @@
 
 _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],
+    citations=[
+        _genome2001,
+        _tian2019.because(stdpopsim.CiteReason.MUT_RATE),
+        _hapmap2007.because(stdpopsim.CiteReason.REC_RATE),
+    ],
 )
 
 _species = stdpopsim.Species(
@@ -93,9 +95,11 @@
     common_name="Human",
     genome=_genome,
     generation_time=30,
-    generation_time_citations=[_tremblay2000.because(stdpopsim.CiteReason.GEN_TIME)],
     population_size=10 ** 4,
-    population_size_citations=[_takahata1993.because(stdpopsim.CiteReason.POP_SIZE)],
+    citations=[
+        _tremblay2000.because(stdpopsim.CiteReason.GEN_TIME),
+        _takahata1993.because(stdpopsim.CiteReason.POP_SIZE),
+    ],
 )
 
 stdpopsim.register_species(_species)
diff --git a/stdpopsim/catalog/PonAbe/species.py b/stdpopsim/catalog/PonAbe/species.py
@@ -34,11 +34,17 @@
 }
 
 _locke2011 = stdpopsim.Citation(
-    author="Locke et al.", year=2011, doi="http://doi.org/10.1038/nature09687"
+    author="Locke et al.",
+    year=2011,
+    doi="http://doi.org/10.1038/nature09687",
+    reasons={stdpopsim.CiteReason.GEN_TIME, stdpopsim.CiteReason.POP_SIZE},
 )
 
 _nater2017 = stdpopsim.Citation(
-    author="Nater et al.", year=2017, doi="https://doi.org/10.1016/j.cub.2017.09.047"
+    author="Nater et al.",
+    year=2017,
+    doi="https://doi.org/10.1016/j.cub.2017.09.047",
+    reasons={stdpopsim.CiteReason.MUT_RATE, stdpopsim.CiteReason.REC_RATE},
 )
 
 _chromosomes = []
@@ -59,7 +65,7 @@
     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)],
+    citations=[_nater2017],
 )
 
 _species = stdpopsim.Species(
@@ -70,10 +76,9 @@
     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
     population_size=1.79e4,
-    population_size_citations=[_locke2011.because(stdpopsim.CiteReason.POP_SIZE)],
+    citations=[_locke2011],
 )
 
 stdpopsim.register_species(_species)
diff --git a/stdpopsim/cli.py b/stdpopsim/cli.py
@@ -268,9 +268,8 @@ def get_citations(engine, model, contig, species):
     """
     citations = [stdpopsim.citations._stdpopsim_citation]
     citations.extend(engine.citations)
-    citations.extend(species.genome.assembly_citations)
-    citations.extend(species.genome.mutation_rate_citations)
-    citations.extend(species.genome.recombination_rate_citations)
+    citations.extend(species.citations)
+    citations.extend(species.genome.citations)
     if contig.genetic_map is not None:
         citations.extend(contig.genetic_map.citations)
     citations.extend(model.citations)
@@ -498,8 +497,10 @@ def run_simulation(args):
         if args.demographic_model is None:
             model = stdpopsim.PiecewiseConstantSize(species.population_size)
             model.generation_time = species.generation_time
-            model.citations.extend(species.population_size_citations)
-            model.citations.extend(species.generation_time_citations)
+            for citation in species.citations:
+                reasons = {stdpopsim.CiteReason.POP_SIZE, stdpopsim.CiteReason.GEN_TIME}
+                if len(citation.reasons & reasons) > 0:
+                    model.citations.append(citation)
             qc_complete = True
         else:
             model = get_model_wrapper(species, args.demographic_model)

diff --git a/stdpopsim/genomes.py b/stdpopsim/genomes.py
@@ -11,32 +11,23 @@ class Genome:
 
     :ivar chromosomes: A list of :class:`.Chromosome` objects.
     :vartype chromosomes: list
-    :ivar mutation_rate_citations: A list of :class:`.Citation` objects
-        providing justification for the mutation rate estimate.
-    :vartype mutation_rate_citations: list
-    :ivar recombination_rate_citations: A list of :class:`.Citation` objects
-        providing justification for the recombination rate estimate.
-    :vartype recombination_rate_citations: list
-    :ivar assembly_citations: A list of :class:`.Citation` objects
-        providing reference to the source of the genome assembly.
-    :vartype assembly_citations: list
+    :ivar citations: A list of :class:`.Citation` objects
+        providing the source for the genome assembly,
+        mutation rate and recombination rate estimates.
+    :vartype citations: list
     :ivar length: The total length of the genome.
     :vartype length: int
     """
 
+    # TODO document the assembly_name and accession
+
     chromosomes = attr.ib(factory=list)
     assembly_name = attr.ib(default=None, kw_only=True)
     assembly_accession = attr.ib(default=None, kw_only=True)
-    length = attr.ib(default=0, init=False)
-
-    # TODO these should all be combined into a single "citations" attr,
-    # since we already have a "reason" attribute in Citation.
-    mutation_rate_citations = attr.ib(factory=list, kw_only=True)
-    recombination_rate_citations = attr.ib(factory=list, kw_only=True)
-    assembly_citations = attr.ib(factory=list, kw_only=True)
+    citations = attr.ib(factory=list, kw_only=True)
 
     @staticmethod
-    def from_data(genome_data, *, recombination_rate, mutation_rate):
+    def from_data(genome_data, *, recombination_rate, mutation_rate, citations):
         """
         Construct a Genome object from the specified dictionary of
         genome information from Ensembl, recombination_rate and
@@ -62,11 +53,12 @@ def from_data(genome_data, *, recombination_rate, mutation_rate):
             chromosomes=chromosomes,
             assembly_name=genome_data["assembly_name"],
             assembly_accession=genome_data["assembly_accession"],
+            citations=citations,
         )
 
-    def __attrs_post_init__(self):
-        for chromosome in self.chromosomes:
-            self.length += chromosome.length
+    @property
+    def length(self):
+        return sum(chrom.length for chrom in self.chromosomes)
 
     def __str__(self):
         s = "Chromosomes:\n"
@@ -96,9 +88,10 @@ def mean_recombination_rate(self):
         """
         The length-weighted mean recombination rate across all chromosomes.
         """
+        length = self.length
         mean_recombination_rate = 0
         for chrom in self.chromosomes:
-            normalized_weight = chrom.length / self.length
+            normalized_weight = chrom.length / length
             cont = chrom.recombination_rate * normalized_weight
             mean_recombination_rate += cont
         return mean_recombination_rate
@@ -108,9 +101,10 @@ def mean_mutation_rate(self):
         """
         The length-weighted mean mutation rate across all chromosomes.
         """
+        length = self.length
         mean_mutation_rate = 0
         for chrom in self.chromosomes:
-            normalized_weight = chrom.length / self.length
+            normalized_weight = chrom.length / length
             cont = chrom.mutation_rate * normalized_weight
             mean_mutation_rate += cont
         return mean_mutation_rate