phylogenie 2.0.1__tar.gz → 2.0.3__tar.gz

{phylogenie-2.0.1 → phylogenie-2.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: phylogenie
-Version: 2.0.1
+Version: 2.0.3
 Summary: Generate phylogenetic datasets with minimal setup effort
 Author: Gabriele Marino
 Author-email: gabmarino.8601@gmail.com
@@ -23,7 +23,7 @@ Description-Content-Type: text/markdown
 ---
 
 [![AliSim](https://img.shields.io/badge/Powered%20by-AliSim-orange?style=flat-square)](https://iqtree.github.io/doc/AliSim)
-[![PyPI package](https://badge.fury.io/py/phylogenie.svg)](https://pypi.org/project/phylogenie/)
+[![PyPI version](https://img.shields.io/pypi/v/phylogenie)](https://pypi.org/project/phylogenie/)
 [![PyPI downloads](https://shields.io/pypi/dm/phylogenie)](https://pypi.org/project/phylogenie/)
 
 Phylogenie is a [Python](https://www.python.org/) package designed to easily simulate phylogenetic datasets—such as trees and multiple sequence alignments (MSAs)—with minimal setup effort. Simply specify the distributions from which your parameters should be sampled, and Phylogenie will handle the rest!
@@ -53,9 +53,6 @@ Phylogenie comes packed with useful features, including:
 - **Arithmetic operations on parameters** 🧮  
   Perform flexible arithmetic operations between parameters directly within the config file.
 
-- **Modular and extendible architecture** 🧩  
-  Easily add new simulation backends as needed.
-
 ## 📦 Installation
 Phylogenie requires [Python](https://www.python.org/) 3.10 to be installed on your system. There are several ways to install Python and managing different Python versions. One popular option is to use [pyenv](https://github.com/pyenv/pyenv).
 
@@ -83,7 +80,7 @@ It includes a collection of thoroughly commented configuration files, organized
 
 For quick start, pick your favorite config file and run Phylogenie with:
 ```bash
-phylogenie examples/<config_file>.yaml
+phylogenie examples/config_file.yaml
 ```
 This command will create the output dataset in the folder specified inside the configuration file, including data directories and metadata files for each dataset split defined in the config.
 

{phylogenie-2.0.1 → phylogenie-2.0.3}/README.md

@@ -5,7 +5,7 @@
 ---
 
 [![AliSim](https://img.shields.io/badge/Powered%20by-AliSim-orange?style=flat-square)](https://iqtree.github.io/doc/AliSim)
-[![PyPI package](https://badge.fury.io/py/phylogenie.svg)](https://pypi.org/project/phylogenie/)
+[![PyPI version](https://img.shields.io/pypi/v/phylogenie)](https://pypi.org/project/phylogenie/)
 [![PyPI downloads](https://shields.io/pypi/dm/phylogenie)](https://pypi.org/project/phylogenie/)
 
 Phylogenie is a [Python](https://www.python.org/) package designed to easily simulate phylogenetic datasets—such as trees and multiple sequence alignments (MSAs)—with minimal setup effort. Simply specify the distributions from which your parameters should be sampled, and Phylogenie will handle the rest!
@@ -35,9 +35,6 @@ Phylogenie comes packed with useful features, including:
 - **Arithmetic operations on parameters** 🧮  
   Perform flexible arithmetic operations between parameters directly within the config file.
 
-- **Modular and extendible architecture** 🧩  
-  Easily add new simulation backends as needed.
-
 ## 📦 Installation
 Phylogenie requires [Python](https://www.python.org/) 3.10 to be installed on your system. There are several ways to install Python and managing different Python versions. One popular option is to use [pyenv](https://github.com/pyenv/pyenv).
 
@@ -65,7 +62,7 @@ It includes a collection of thoroughly commented configuration files, organized
 
 For quick start, pick your favorite config file and run Phylogenie with:
 ```bash
-phylogenie examples/<config_file>.yaml
+phylogenie examples/config_file.yaml
 ```
 This command will create the output dataset in the folder specified inside the configuration file, including data directories and metadata files for each dataset split defined in the config.
 

phylogenie-2.0.3/phylogenie/__init__.py

@@ -0,0 +1,72 @@
+from phylogenie.generators import (
+    AliSimDatasetGenerator,
+    BDEITreeDatasetGenerator,
+    BDSSTreeDatasetGenerator,
+    BDTreeDatasetGenerator,
+    CanonicalTreeDatasetGenerator,
+    DatasetGenerator,
+    DatasetGeneratorConfig,
+    EpidemiologicalTreeDatasetGenerator,
+    FBDTreeDatasetGenerator,
+    TreeDatasetGeneratorConfig,
+)
+from phylogenie.io import load_fasta, load_newick
+from phylogenie.msa import MSA
+from phylogenie.skyline import (
+    SkylineMatrix,
+    SkylineMatrixCoercible,
+    SkylineParameter,
+    SkylineParameterLike,
+    SkylineVector,
+    SkylineVectorCoercible,
+    SkylineVectorLike,
+    skyline_matrix,
+    skyline_parameter,
+    skyline_vector,
+)
+from phylogenie.tree import Tree
+from phylogenie.treesimulator import (
+    Event,
+    get_BD_events,
+    get_BDEI_events,
+    get_BDSS_events,
+    get_canonical_events,
+    get_epidemiological_events,
+    get_FBD_events,
+    simulate_tree,
+)
+
+__all__ = [
+    "AliSimDatasetGenerator",
+    "BDEITreeDatasetGenerator",
+    "BDSSTreeDatasetGenerator",
+    "BDTreeDatasetGenerator",
+    "CanonicalTreeDatasetGenerator",
+    "DatasetGenerator",
+    "DatasetGeneratorConfig",
+    "EpidemiologicalTreeDatasetGenerator",
+    "FBDTreeDatasetGenerator",
+    "SkylineMatrix",
+    "SkylineMatrixCoercible",
+    "skyline_matrix",
+    "SkylineParameter",
+    "SkylineParameterLike",
+    "skyline_parameter",
+    "SkylineVector",
+    "SkylineVectorCoercible",
+    "SkylineVectorLike",
+    "skyline_vector",
+    "Tree",
+    "TreeDatasetGeneratorConfig",
+    "Event",
+    "get_BD_events",
+    "get_BDEI_events",
+    "get_BDSS_events",
+    "get_canonical_events",
+    "get_epidemiological_events",
+    "get_FBD_events",
+    "simulate_tree",
+    "load_fasta",
+    "load_newick",
+    "MSA",
+]

phylogenie-2.0.3/phylogenie/generators/__init__.py

@@ -0,0 +1,32 @@
+from typing import Annotated
+
+from pydantic import Field
+
+from phylogenie.generators.alisim import AliSimDatasetGenerator
+from phylogenie.generators.dataset import DatasetGenerator
+from phylogenie.generators.trees import (
+    BDEITreeDatasetGenerator,
+    BDSSTreeDatasetGenerator,
+    BDTreeDatasetGenerator,
+    CanonicalTreeDatasetGenerator,
+    EpidemiologicalTreeDatasetGenerator,
+    FBDTreeDatasetGenerator,
+    TreeDatasetGeneratorConfig,
+)
+
+DatasetGeneratorConfig = Annotated[
+    TreeDatasetGeneratorConfig | AliSimDatasetGenerator,
+    Field(discriminator="data_type"),
+]
+
+__all__ = [
+    "DatasetGeneratorConfig",
+    "DatasetGenerator",
+    "AliSimDatasetGenerator",
+    "CanonicalTreeDatasetGenerator",
+    "EpidemiologicalTreeDatasetGenerator",
+    "FBDTreeDatasetGenerator",
+    "BDTreeDatasetGenerator",
+    "BDEITreeDatasetGenerator",
+    "BDSSTreeDatasetGenerator",
+]

{phylogenie-2.0.1 → phylogenie-2.0.3}/phylogenie/generators/configs.py

@@ -38,4 +38,6 @@ SkylineParameterConfig = ScalarConfig | SkylineParameterModel
 SkylineVectorConfig = (
     str | pgt.Scalar | list[SkylineParameterConfig] | SkylineVectorModel
 )
-SkylineMatrixConfig = str | pgt.Scalar | list[SkylineVectorConfig] | SkylineMatrixModel
+SkylineMatrixConfig = (
+    str | pgt.Scalar | list[SkylineVectorConfig] | SkylineMatrixModel | None
+)

{phylogenie-2.0.1 → phylogenie-2.0.3}/phylogenie/generators/factories.py

@@ -148,7 +148,10 @@ def one_or_many_2D_scalars(
 
 def skyline_matrix(
     x: cfg.SkylineMatrixConfig, data: dict[str, Any]
-) -> SkylineMatrixCoercible:
+) -> SkylineMatrixCoercible | None:
+    if x is None:
+        return None
+
     if isinstance(x, str):
         e = _eval_expression(x, data)
         if tg.is_one_or_many_2D_scalars(e):

{phylogenie-2.0.1 → phylogenie-2.0.3}/phylogenie/generators/trees.py

@@ -89,8 +89,8 @@ class CanonicalTreeDatasetGenerator(TreeDatasetGenerator):
     birth_rates: cfg.SkylineVectorConfig = 0
     death_rates: cfg.SkylineVectorConfig = 0
     removal_probabilities: cfg.SkylineVectorConfig = 0
-    migration_rates: cfg.SkylineMatrixConfig = 0
-    birth_rates_among_states: cfg.SkylineMatrixConfig = 0
+    migration_rates: cfg.SkylineMatrixConfig = None
+    birth_rates_among_states: cfg.SkylineMatrixConfig = None
     states: list[str] | None = None
 
     def _get_events(self, rng: Generator, data: dict[str, Any]) -> list[Event]:
@@ -116,8 +116,8 @@ class EpidemiologicalTreeDatasetGenerator(TreeDatasetGenerator):
     become_uninfectious_rates: cfg.SkylineVectorConfig = 0
     sampling_proportions: cfg.SkylineVectorConfig = 1
     removal_probabilities: cfg.SkylineVectorConfig = 1
-    migration_rates: cfg.SkylineMatrixConfig = 0
-    reproduction_numbers_among_states: cfg.SkylineMatrixConfig = 0
+    migration_rates: cfg.SkylineMatrixConfig = None
+    reproduction_numbers_among_states: cfg.SkylineMatrixConfig = None
 
     def _get_events(self, rng: Generator, data: dict[str, Any]) -> list[Event]:
         return get_epidemiological_events(
@@ -142,8 +142,8 @@ class FBDTreeDatasetGenerator(TreeDatasetGenerator):
     turnover: cfg.SkylineVectorConfig = 0
     sampling_proportions: cfg.SkylineVectorConfig = 1
     removal_probabilities: cfg.SkylineVectorConfig = 0
-    migration_rates: cfg.SkylineMatrixConfig = 0
-    diversification_between_types: cfg.SkylineMatrixConfig = 0
+    migration_rates: cfg.SkylineMatrixConfig = None
+    diversification_between_types: cfg.SkylineMatrixConfig = None
 
     def _get_events(self, rng: Generator, data: dict[str, Any]) -> list[Event]:
         return get_FBD_events(

{phylogenie-2.0.1 → phylogenie-2.0.3}/phylogenie/io.py

@@ -85,7 +85,7 @@ def load_fasta(
             else:
                 try:
                     time = float(id.split("|")[-1])
-                except ValueError:
+                except:
                     time = None
             chars = next(f).strip()
             sequences.append(Sequence(id, chars, time))

{phylogenie-2.0.1 → phylogenie-2.0.3}/phylogenie/skyline/matrix.py

@@ -159,9 +159,13 @@ class SkylineMatrix:
     @overload
     def __getitem__(self, item: slice) -> "SkylineMatrix": ...
     @overload
-    def __getitem__(
-        self, item: tuple[int | slice, int | slice]
-    ) -> Union[SkylineParameter, SkylineVector, "SkylineMatrix"]: ...
+    def __getitem__(self, item: tuple[int, int]) -> SkylineParameter: ...
+    @overload
+    def __getitem__(self, item: tuple[int, slice]) -> SkylineVector: ...
+    @overload
+    def __getitem__(self, item: tuple[slice, int]) -> SkylineVector: ...
+    @overload
+    def __getitem__(self, item: tuple[slice, slice]) -> "SkylineMatrix": ...
     def __getitem__(
         self, item: int | slice | tuple[int | slice, int | slice]
     ) -> Union[SkylineParameter | SkylineVector, "SkylineMatrix"]:

{phylogenie-2.0.1 → phylogenie-2.0.3}/phylogenie/treesimulator/events.py

@@ -55,7 +55,7 @@ class DeathEvent(Event):
 
 
 class MigrationEvent(Event):
-    def __init__(self, state: str, target_state: str, rate: SkylineParameterLike):
+    def __init__(self, rate: SkylineParameterLike, state: str, target_state: str):
         super().__init__(rate, state)
         self.target_state = target_state
 
@@ -68,8 +68,8 @@ class SamplingEvent(Event):
     def __init__(
         self,
         rate: SkylineParameterLike,
-        removal_probability: SkylineParameterLike,
         state: str | None = None,
+        removal_probability: SkylineParameterLike = 0,
     ):
         super().__init__(rate, state)
         self.removal_probability = skyline_parameter(removal_probability)
@@ -85,8 +85,8 @@ def get_canonical_events(
     birth_rates: SkylineVectorCoercible = 0,
     death_rates: SkylineVectorCoercible = 0,
     removal_probabilities: SkylineVectorCoercible = 0,
-    migration_rates: SkylineMatrixCoercible = 0,
-    birth_rates_among_states: SkylineMatrixCoercible = 0,
+    migration_rates: SkylineMatrixCoercible | None = None,
+    birth_rates_among_states: SkylineMatrixCoercible | None = None,
     states: list[str] | None = None,
 ) -> list[Event]:
     N = 1 if states is None else len(states)
@@ -95,31 +95,32 @@ def get_canonical_events(
     death_rates = skyline_vector(death_rates, N)
     sampling_rates = skyline_vector(sampling_rates, N)
     removal_probabilities = skyline_vector(removal_probabilities, N)
-    if migration_rates and N == 1:
-        raise ValueError(f"Migration rates require multiple states (got {states}).")
-    if birth_rates_among_states and N == 1:
-        raise ValueError(
-            f"Birth rates among states require multiple states (got {states})."
-        )
 
     events: list[Event] = []
     for i in range(N):
         state = None if states is None else states[i]
         events.append(BirthEvent(birth_rates[i], state, state))
         events.append(DeathEvent(death_rates[i], state))
-        events.append(SamplingEvent(sampling_rates[i], removal_probabilities[i], state))
-        if N > 1:
-            migration_rates = skyline_matrix(migration_rates, N, N - 1)
-            birth_rates_among_states = skyline_matrix(
-                birth_rates_among_states, N, N - 1
-            )
-            assert states is not None
-            assert state is not None
+        events.append(SamplingEvent(sampling_rates[i], state, removal_probabilities[i]))
+
+    if states is not None and migration_rates is not None:
+        migration_rates = skyline_matrix(migration_rates, N, N - 1)
+        for i, state in enumerate(states):
+            for j, other_state in enumerate([s for s in states if s != state]):
+                events.append(MigrationEvent(migration_rates[i, j], state, other_state))
+    elif migration_rates is not None:
+        raise ValueError(f"Migration rates require states to be provided.")
+
+    if states is not None and birth_rates_among_states is not None:
+        birth_rates_among_states = skyline_matrix(birth_rates_among_states, N, N - 1)
+        for i, state in enumerate(states):
             for j, other_state in enumerate([s for s in states if s != state]):
-                events.append(MigrationEvent(state, other_state, migration_rates[i][j]))
                 events.append(
-                    BirthEvent(birth_rates_among_states[i][j], state, other_state)
+                    BirthEvent(birth_rates_among_states[i, j], state, other_state)
                 )
+    elif birth_rates_among_states is not None:
+        raise ValueError(f"Birth rates among states require states to be provided.")
+
     return [event for event in events if event.rate]
 
 
@@ -128,8 +129,8 @@ def get_epidemiological_events(
     reproduction_numbers: SkylineVectorCoercible = 0,
     become_uninfectious_rates: SkylineVectorCoercible = 0,
     removal_probabilities: SkylineVectorCoercible = 1,
-    migration_rates: SkylineMatrixCoercible = 0,
-    reproduction_numbers_among_states: SkylineMatrixCoercible = 0,
+    migration_rates: SkylineMatrixCoercible | None = None,
+    reproduction_numbers_among_states: SkylineMatrixCoercible | None = None,
     states: list[str] | None = None,
 ) -> list[Event]:
     N = 1 if states is None else len(states)
@@ -138,20 +139,20 @@ def get_epidemiological_events(
     become_uninfectious_rates = skyline_vector(become_uninfectious_rates, N)
     sampling_proportions = skyline_vector(sampling_proportions, N)
     removal_probabilities = skyline_vector(removal_probabilities, N)
-    if N == 1 and reproduction_numbers_among_states:
-        raise ValueError(
-            f"Reproduction numbers among states require multiple states (got {states})."
-        )
-    reproduction_numbers_among_states = (
-        skyline_matrix(reproduction_numbers_among_states, N, N - 1) if N > 1 else 0
-    )
 
     birth_rates = reproduction_numbers * become_uninfectious_rates
     sampling_rates = become_uninfectious_rates * sampling_proportions
-    birth_rates_among_states = (
-        reproduction_numbers_among_states * become_uninfectious_rates
-    )
     death_rates = become_uninfectious_rates - removal_probabilities * sampling_rates
+    birth_rates_among_states = None
+    if states is None and reproduction_numbers_among_states is not None:
+        raise ValueError(
+            f"Reproduction numbers among states require states to be provided."
+        )
+    elif reproduction_numbers_among_states is not None:
+        birth_rates_among_states = (
+            skyline_matrix(reproduction_numbers_among_states, N, N - 1)
+            * become_uninfectious_rates
+        )
 
     return get_canonical_events(
         states=states,
@@ -169,32 +170,30 @@ def get_FBD_events(
     turnover: SkylineVectorCoercible = 0,
     sampling_proportions: SkylineVectorCoercible = 1,
     removal_probabilities: SkylineVectorCoercible = 0,
-    migration_rates: SkylineMatrixCoercible = 0,
-    diversification_between_types: SkylineMatrixCoercible = 0,
+    migration_rates: SkylineMatrixCoercible | None = None,
+    diversification_between_types: SkylineMatrixCoercible | None = None,
     states: list[str] | None = None,
-):
+) -> list[Event]:
     N = 1 if states is None else len(states)
 
     diversification = skyline_vector(diversification, N)
     turnover = skyline_vector(turnover, N)
     sampling_proportions = skyline_vector(sampling_proportions, N)
     removal_probabilities = skyline_vector(removal_probabilities, N)
-    if N == 1 and diversification_between_types:
-        raise ValueError(
-            f"Diversification rates among states require multiple states (got {states})."
-        )
-    diversification_between_types = (
-        skyline_matrix(diversification_between_types, N, N - 1) if N > 1 else 0
-    )
 
     birth_rates = diversification / (1 - turnover)
     death_rates = turnover * birth_rates
-    sampling_rates = (
-        sampling_proportions
-        * death_rates
-        / (1 - removal_probabilities * sampling_proportions)
-    )
-    birth_rates_among_states = diversification_between_types + death_rates
+    sampling_rates_dividend = 1 - removal_probabilities * sampling_proportions
+    sampling_rates = sampling_proportions * death_rates / sampling_rates_dividend
+    birth_rates_among_states = None
+    if states is None and diversification_between_types is not None:
+        raise ValueError(
+            f"Diversification rates among states require states to be provided."
+        )
+    elif diversification_between_types is not None:
+        birth_rates_among_states = (
+            skyline_matrix(diversification_between_types, N, N - 1) + death_rates
+        )
 
     return get_canonical_events(
         states=states,

{phylogenie-2.0.1 → phylogenie-2.0.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "phylogenie"
-version = "2.0.1"
+version = "2.0.3"
 description = "Generate phylogenetic datasets with minimal setup effort"
 authors = ["Gabriele Marino <gabmarino.8601@gmail.com>"]
 readme = "README.md"

phylogenie-2.0.1/phylogenie/generators/__init__.py

@@ -1,14 +0,0 @@
-from typing import Annotated
-
-from pydantic import Field
-
-from phylogenie.generators.alisim import AliSimDatasetGenerator
-from phylogenie.generators.dataset import DatasetGenerator
-from phylogenie.generators.trees import TreeDatasetGeneratorConfig
-
-DatasetGeneratorConfig = Annotated[
-    TreeDatasetGeneratorConfig | AliSimDatasetGenerator,
-    Field(discriminator="data_type"),
-]
-
-__all__ = ["DatasetGeneratorConfig", "DatasetGenerator"]