feat: add va spec pydantic models (#6)

close #3

.github/workflows/release.yaml

@@ -50,7 +50,7 @@ jobs:
     runs-on: ubuntu-latest
     environment:
       name: pypi
-      url: https://pypi.org/p/ga4gh-va-spec
+      url: https://pypi.org/p/ga4gh.va_spec
     permissions:
       id-token: write # IMPORTANT: mandatory for trusted publishing
     steps:

.gitmodules

@@ -0,0 +1,4 @@
+[submodule "submodules/va_spec"]
+	path = submodules/va_spec
+	url = https://github.com/ga4gh/va-spec
+	branch = 1.x

pyproject.toml

@@ -30,7 +30,11 @@ keywords = [
 ]
 requires-python = ">=3.10"
 dynamic = ["version"]
-dependencies = []
+dependencies = [
+    "ga4gh.vrs~=2.0.0a12",
+    "ga4gh.cat_vrs~=0.1.0",
+    "pydantic==2.*"
+]
 
 [project.optional-dependencies]
 dev = [
@@ -132,7 +136,9 @@ ignore = [
 # ANN102 - missing-type-cls
 # S101 - assert
 # B011 - assert-false
+# N815 - mixed-case-variable-in-class-scope
 "tests/*" = ["ANN001", "ANN2", "ANN102", "S101", "B011"]
+"src/ga4gh/va_spec/profiles/*" = ["ANN102", "N815"]
 
 [tool.setuptools.packages.find]
 where = ["src"]

src/ga4gh/va_spec/profiles/__init__.py

@@ -0,0 +1,44 @@
+"""Package for VA-Spec Python implementation"""
+
+from .assay_var_effect import (
+    AssayVariantEffectClinicalClassificationStatement,
+    AssayVariantEffectFunctionalClassificationStatement,
+    AssayVariantEffectMeasurementStudyResult,
+    AveClinicalClassification,
+    AveFunctionalClassification,
+)
+from .caf_study_result import CohortAlleleFrequencyStudyResult
+from .var_path_stmt import PenetranceQualifier, VariantPathogenicityStatement
+from .var_study_stmt import (
+    AlleleOriginQualifier,
+    AllelePrevalenceQualifier,
+    DiagnosticPredicate,
+    OncogenicPredicate,
+    PrognosticPredicate,
+    TherapeuticResponsePredicate,
+    VariantDiagnosticStudyStatement,
+    VariantOncogenicityStudyStatement,
+    VariantPrognosticStudyStatement,
+    VariantTherapeuticResponseStudyStatement,
+)
+
+__all__ = [
+    "AveFunctionalClassification",
+    "AveClinicalClassification",
+    "AssayVariantEffectFunctionalClassificationStatement",
+    "AssayVariantEffectClinicalClassificationStatement",
+    "AssayVariantEffectMeasurementStudyResult",
+    "CohortAlleleFrequencyStudyResult",
+    "PenetranceQualifier",
+    "VariantPathogenicityStatement",
+    "AlleleOriginQualifier",
+    "DiagnosticPredicate",
+    "OncogenicPredicate",
+    "PrognosticPredicate",
+    "TherapeuticResponsePredicate",
+    "AllelePrevalenceQualifier",
+    "VariantDiagnosticStudyStatement",
+    "VariantOncogenicityStudyStatement",
+    "VariantPrognosticStudyStatement",
+    "VariantTherapeuticResponseStudyStatement",
+]

src/ga4gh/va_spec/profiles/assay_var_effect.py

@@ -0,0 +1,134 @@
+"""VA Spec Assay Variant Effect statement and study result Profiles"""
+
+from __future__ import annotations
+
+from enum import Enum
+from typing import Literal
+
+from ga4gh.cat_vrs.core_models import CategoricalVariant
+from ga4gh.core.entity_models import (
+    IRI,
+    Coding,
+    DataSet,
+    Method,
+    StatementBase,
+    StudyGroup,
+    StudyResult,
+    StudyResultBase,
+)
+from ga4gh.vrs.models import MolecularVariation
+from pydantic import ConfigDict, Field
+
+
+class AveFunctionalClassification(str, Enum):
+    """The functional classification of the variant effect in the assay."""
+
+    NORMAL = "normal"
+    INDETERMINATE = "indeterminate"
+    ABNORMAL = "abnormal"
+
+
+class AveClinicalClassification(str, Enum):
+    """The clinical strength of evidence of the variant effect in the assay."""
+
+    PS3_STRONG = "PS3_Strong"
+    PS3_MODERATE = "PS3_Moderate"
+    PS3_SUPPORTING = "PS3_Supporting"
+    BS3_STRONG = "BS3_Strong"
+    BS3_MODERATE = "BS3_Moderate"
+    BS3_SUPPORTING = "BS3_Supporting"
+
+
+class AssayVariantEffectFunctionalClassificationStatement(StatementBase):
+    """A statement that assigns a functional classification to a variant effect from a functional assay."""
+
+    model_config = ConfigDict(use_enum_values=True)
+
+    type: Literal["AssayVariantEffectFunctionalClassificationStatement"] = Field(
+        "AssayVariantEffectFunctionalClassificationStatement",
+        description="MUST be 'AssayVariantEffectFunctionalClassificationStatement'.",
+    )
+    subjectVariant: MolecularVariation | CategoricalVariant | IRI = Field(
+        ...,
+        description="A protein or genomic contextual or canonical molecular variant.",
+    )
+    predicate: Literal["hasAssayVariantEffectFor"] = Field(
+        "hasAssayVariantEffectFor",
+        description="The relationship declared to hold between the subject and the object of the Statement.",
+    )
+    objectAssay: IRI | Coding = Field(
+        ...,
+        description="The assay that is evaluated for the variant effect. (e.g growth in haploid cell culture protein stability in fluorescence assay)",
+    )
+    classification: AveFunctionalClassification = Field(
+        ...,
+        description="The functional classification of the variant effect in the assay.",
+    )
+    specifiedBy: Method | IRI | None = Field(
+        None,
+        description="The method that specifies the functional classification of the variant effect in the assay.",
+    )
+
+
+class AssayVariantEffectClinicalClassificationStatement(StatementBase):
+    """A statement that assigns a clinical strength of evidence to a variant effect from a functional assay."""
+
+    model_config = ConfigDict(use_enum_values=True)
+
+    type: Literal["AssayVariantEffectClinicalClassificationStatement"] = Field(
+        "AssayVariantEffectClinicalClassificationStatement",
+        description="MUST be 'AssayVariantEffectClinicalClassificationStatement'.",
+    )
+    subjectVariant: MolecularVariation | CategoricalVariant | IRI = Field(
+        ...,
+        description="A protein or genomic contextual or canonical molecular variant.",
+    )
+    predicate: Literal["hasAssayVariantEffectFor"] = Field(
+        "hasAssayVariantEffectFor",
+        description="The relationship declared to hold between the subject and the object of the Statement.",
+    )
+    objectAssay: IRI | Coding = Field(
+        ...,
+        description="The assay that is evaluated for the variant effect. (e.g growth in haploid cell culture protein stability in fluorescence assay)",
+    )
+    classification: AveClinicalClassification = Field(
+        ...,
+        description="The clinical strength of evidence of the variant effect in the assay.",
+    )
+    specifiedBy: Method | IRI | None = Field(
+        None,
+        description="The method that specifies the clinical strength of evidence of the variant effect in the assay.",
+    )
+
+
+class AssayVariantEffectMeasurementStudyResult(StudyResultBase):
+    """A StudyResult that reports a variant effect score from a functional assay."""
+
+    model_config = ConfigDict(use_enum_values=True)
+
+    type: Literal["AssayVariantEffectMeasurementStudyResult"] = Field(
+        "AssayVariantEffectMeasurementStudyResult",
+        description="MUST be 'AssayVariantEffectMeasurementStudyResult'.",
+    )
+    componentResult: list[StudyResult] | None = Field(
+        None,
+        description="Another StudyResult comprised of data items about the same focus as its parent Result, but based on a more narrowly scoped analysis of the foundational data (e.g. an analysis based on data about a subset of the parent Results full study population) .",
+    )
+    studyGroup: StudyGroup | None = Field(
+        None,
+        description="A description of a specific group or population of subjects interrogated in the ResearchStudy that produced the data captured in the StudyResult.",
+    )
+    focusVariant: MolecularVariation | IRI | None = Field(
+        None,
+        description="The human mapped representation of the variant that is the subject of the Statement.",
+    )
+    score: float | None = Field(
+        None, description="The score of the variant effect in the assay."
+    )
+    specifiedBy: Method | IRI | None = Field(
+        None,
+        description="The assay that was used to measure the variant effect with all the various properties",
+    )
+    sourceDataSet: list[DataSet] | None = Field(
+        None, description="The full data set that this measurement is a part of"
+    )

src/ga4gh/va_spec/profiles/caf_study_result.py

@@ -0,0 +1,49 @@
+"""VA Spec Cohort Allele Frequency (population frequency) Study Result Standard Profile"""
+
+from __future__ import annotations
+
+from typing import Literal
+
+from ga4gh.core.entity_models import (
+    DataSet,
+    StudyResult,
+    StudyResultBase,
+)
+from ga4gh.vrs.models import Allele
+from pydantic import ConfigDict, Field
+
+
+class CohortAlleleFrequencyStudyResult(StudyResultBase):
+    """A StudyResult that reports measures related to the frequency of an Allele in a cohort"""
+
+    model_config = ConfigDict(use_enum_values=True)
+
+    type: Literal["CohortAlleleFrequencyStudyResult"] = Field(
+        "CohortAlleleFrequencyStudyResult",
+        description="MUST be 'CohortAlleleFrequencyStudyResult'.",
+    )
+    sourceDataSet: list[DataSet] | None = Field(
+        None,
+        description="The dataset from which the CohortAlleleFrequencyStudyResult was reported.",
+    )
+    focusAllele: Allele | str = Field(
+        ...,
+        description="The specific subject or experimental unit in a Study that data in the StudyResult object is about - e.g. a particular variant in a population allele frequency dataset like ExAC or gnomAD.",
+    )
+    focusAlleleCount: int = Field(
+        ..., description="The number of occurrences of the focusAllele in the cohort."
+    )
+    locusAlleleCount: int = Field(
+        ...,
+        description="The number of occurrences of all alleles at the locus in the cohort (sometimes referred to as 'allele number')",
+    )
+    focusAlleleFrequency: float = Field(
+        ..., description="The frequency of the focusAllele in the cohort."
+    )
+    cohort: list[StudyResult] = Field(
+        ..., description="The cohort from which the frequency was derived."
+    )
+    subCohortFrequency: list[CohortAlleleFrequencyStudyResult] | None = Field(
+        None,
+        description="A list of CohortAlleleFrequency objects describing subcohorts of the cohort currently being described. This creates a recursive relationship and subcohorts can be further subdivided into more subcohorts. This enables, for example, the description of different ancestry groups and sexes among those ancestry groups.",
+    )

src/ga4gh/va_spec/profiles/var_path_stmt.py

@@ -0,0 +1,54 @@
+"""VA Spec Variant Pathogenicity Statement Standard Profile"""
+
+from enum import Enum
+from typing import Literal
+
+from ga4gh.cat_vrs.core_models import CategoricalVariant
+from ga4gh.core.domain_models import Condition, Gene
+from ga4gh.core.entity_models import IRI, Coding, StatementBase
+from ga4gh.vrs.models import Variation
+from pydantic import ConfigDict, Field
+
+
+class PenetranceQualifier(str, Enum):
+    """Reports the penetrance of the pathogenic effect - i.e. the extent to which the
+    variant impact is expressed by individuals carrying it as a measure of the
+    proportion of carriers exhibiting the condition.
+    """
+
+    HIGH = "high"
+    LOW = "low"
+    RISK_ALLELE = "risk allele"
+
+
+class VariantPathogenicityStatement(StatementBase):
+    """A Statement describing the role of a variant in causing an inherited condition."""
+
+    model_config = ConfigDict(use_enum_values=True)
+
+    type: Literal["VariantPathogenicityStatement"] = Field(
+        "VariantPathogenicityStatement",
+        description="MUST be 'VariantPathogenicityStatement'.",
+    )
+    subjectVariant: Variation | CategoricalVariant | IRI = Field(
+        ..., description="A variant that is the subject of the Statement."
+    )
+    predicate: Literal["isCausalFor"] = Field(
+        "isCausalFor",
+        description="The relationship declared to hold between the subject and the object of the Statement.",
+    )
+    objectCondition: Condition | IRI = Field(
+        ..., description="The Condition for which the variant impact is stated."
+    )
+    penetranceQualifier: PenetranceQualifier | None = Field(
+        None,
+        description="Reports the penetrance of the pathogenic effect - i.e. the extent to which the variant impact is expressed by individuals carrying it as a measure of the proportion of carriers exhibiting the condition.",
+    )
+    modeOfInheritanceQualifier: list[Coding] | None = Field(
+        None,
+        description="Reports a pattern of inheritance expected for the pathogenic effect of the variant. Use HPO terms within the hierarchy of 'HP:0000005' (mode of inheritance) to specify.",
+    )
+    geneContextQualifier: Gene | IRI | None = Field(
+        None,
+        description="Reports the gene through which the pathogenic effect asserted for the variant is mediated (i.e. it is the variant's impact on this gene that is responsible for causing the condition).",
+    )