feat: add general internal boilerplate/stubs (#15)

Author: jsstevenson

.gitignore

@@ -214,3 +214,6 @@ __marimo__/
 
 # Streamlit
 .streamlit/secrets.toml
+
+# uv
+uv.lock

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "tests/data/ga4gh-service-info"]
+	path = tests/data/ga4gh-service-info
+	url = https://github.com/ga4gh-discovery/ga4gh-service-info

pyproject.toml

@@ -17,11 +17,15 @@ classifiers = [
     "Operating System :: OS Independent",
 ]
 dependencies = [
+    "ga4gh.va_spec",
+    "biocommons.anyvar@git+https://github.com/biocommons/anyvar.git@storage-refactor-epic",
     "fastapi>=0.95.0",
     "python-multipart",  # required for fastapi file uploads
     "uvicorn",
-    "python-dotenv",
+    "click",
     "anyio",
+    "python-dotenv",
+    "pydantic-settings",
 ]
 dynamic = ["version"]
 
@@ -37,6 +41,7 @@ dev = [
     "ruff==0.12.8",
     "pre-commit>=4.2.0",
     "ipykernel",
+    "fastapi[standard]",
 ]
 
 [project.urls]
@@ -46,6 +51,9 @@ Changelog = "https://github.com/genomicmedlab/vlm_in_a_box/releases"
 Source = "https://github.com/genomicmedlab/vlm_in_a_box/"
 "Bug Tracker" = "https://github.com/genomicmedlab/vlm_in_a_box/issues"
 
+[project.scripts]
+vlm = "vlm.cli:_cli"
+
 
 [build-system]
 requires = [
@@ -57,33 +65,10 @@ build-backend = "setuptools.build_meta"
 [tool.setuptools_scm]
 
 [tool.pytest.ini_options]
-addopts = "--cov=anyvar --cov-report term-missing"
+addopts = "--cov=vlm --cov-report term-missing"
 testpaths = ["tests"]
 pythonpath = ["src"]
 
-[tool.coverage.run]
-branch = true
-source = ["biocommons.example"]
-omit = ["*_test.py", "*/test/*", "*/tests/*"]
-
-[tool.coverage.report]
-show_missing = true
-exclude_lines = [
-    # Have to re-enable the standard pragma
-    "pragma: no cover",
-
-    # Don't complain about missing debug-only code:
-    "def __repr__",
-    "if self.debug",
-
-    # Don't complain if tests don't hit defensive assertion code:
-    "raise AssertionError",
-    "raise NotImplementedError",
-
-    # Don't complain if non-runnable code isn't run:
-    "if __name__ == .__main__.:",
-]
-
 [tool.ruff]
 src = ["src"]
 include = ["src/**/*.py", "tests/**/*.py"]

src/vlm/__init__.py

@@ -1 +1,10 @@
 """Off-the-shelf solution for adding local aggregate-level variant information to a VLM network"""
+
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("vlm")
+except PackageNotFoundError:
+    __version__ = "unknown"
+finally:
+    del version, PackageNotFoundError

src/vlm/anyvar/__init__.py

@@ -0,0 +1 @@
+"""Provide client to interact with an AnyVar instance."""

src/vlm/anyvar/base_client.py

@@ -0,0 +1,43 @@
+"""Provide abstraction for a VLM-to-AnyVar connection."""
+
+import abc
+
+from anyvar.utils.types import VrsObject
+
+from vlm.schemas.domain import AlleleFrequencyAnnotation
+
+
+class BaseAnyVarClient(abc.ABC):
+    """Interface elements for an AnyVar client"""
+
+    @abc.abstractmethod
+    def put_objects(self, objects: list[VrsObject]) -> None:
+        """Register objects with AnyVar
+
+        :param objects: variation objects to register
+        """
+
+    @abc.abstractmethod
+    def put_af_annotation(self, key: str, af: AlleleFrequencyAnnotation) -> None:
+        """Add an allele frequency annotation to a variation
+
+
+        :param key: VRS ID for variation being annotated
+        :param af: frequency data for for annotation
+        """
+
+    @abc.abstractmethod
+    def search_by_interval(
+        self, accession: str, start: int, end: int
+    ) -> list[VrsObject]:
+        """Get all variation IDs located within the specified range
+
+        :param accession: sequence accession
+        :param start: start position for genomic region
+        :param end: end position for genomic region
+        :return: list of matching variant objects
+        """
+
+    @abc.abstractmethod
+    def close(self) -> None:
+        """Clean up AnyVar connection."""

src/vlm/cli.py

@@ -0,0 +1,17 @@
+"""CLI for interacting with VLM instance"""
+
+import click
+
+import vlm
+
+
+@click.version_option(vlm.__version__)
+@click.group()
+def _cli() -> None:
+    """Manage VLM data."""
+
+
+@_cli.command()
+def ingest_vcf() -> None:
+    """Deposit variants and allele frequencies from VCF into VLM instance"""
+    raise NotImplementedError

src/vlm/config.py

@@ -0,0 +1,35 @@
+"""Define app settings."""
+
+from functools import cache
+
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+from vlm.schemas.common import ServiceEnvironment
+
+
+class Settings(BaseSettings):
+    """Create app settings
+
+    This is not a singleton, so every new call to this class will re-compute
+    configuration settings, defaults, etc.
+    """
+
+    model_config = SettingsConfigDict(
+        env_prefix="vlm_",
+        env_file=".env",
+        env_file_encoding="utf-8",
+        extra="ignore",
+    )
+
+    env: ServiceEnvironment = ServiceEnvironment.LOCAL
+
+
+@cache
+def get_config() -> Settings:
+    """Get runtime configuration.
+
+    This function is cached, so the config object only gets created/calculated once.
+
+    :return: Settings instance
+    """
+    return Settings()

src/vlm/functions/__init__.py

@@ -0,0 +1 @@
+"""Provide actions to be performed by the orchestration layer, interacting with services to assemble data response."""

src/vlm/functions/get_caf.py

@@ -0,0 +1,19 @@
+"""Perform search against variant(s) contained by an AnyVar node, and construct cohort allele frequency model(s)"""
+
+from ga4gh.va_spec.base.core import CohortAlleleFrequencyStudyResult
+
+from vlm.anyvar.base_client import BaseAnyVarClient
+
+
+def get_caf(
+    av: BaseAnyVarClient, accession_id: str, start: int, end: int
+) -> list[CohortAlleleFrequencyStudyResult]:
+    """Retrieve Cohort Allele Frequency data for all known variants matching provided search params
+
+    :param av: AnyVar client
+    :param accession_id: ID for sequence to search upon
+    :param start: start of range search
+    :param end: end of range to search
+    :return: list of CAFs contained in search interval
+    """
+    raise NotImplementedError