nci-cidc-api-modules 1.2.18__py3-none-any.whl → 1.2.25__py3-none-any.whl

cidc_api/models/db/stage2/treatment_orm.py

@@ -0,0 +1,39 @@
+from typing import List, Optional
+
+from sqlalchemy import ForeignKey
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from cidc_api.models.db.base_orm import BaseORM
+from cidc_api.models.types import YNU, OffTreatmentReason
+
+
+class TreatmentORM(BaseORM):
+    __tablename__ = "treatment"
+    __repr_attrs__ = ["treatment_id", "participant_id", "treatment_description"]
+    __table_args__ = {"schema": "stage2"}
+
+    treatment_id: Mapped[int] = mapped_column(primary_key=True)
+    participant_id: Mapped[int] = mapped_column(ForeignKey("stage2.participant.participant_id", ondelete="CASCADE"))
+    arm_id: Mapped[Optional[int]] = mapped_column(ForeignKey("stage2.arm.arm_id", ondelete="CASCADE"))
+    cohort_id: Mapped[Optional[int]] = mapped_column(ForeignKey("stage2.cohort.cohort_id", ondelete="CASCADE"))
+
+    treatment_description: Mapped[str]
+    off_treatment: Mapped[YNU]
+    off_treatment_reason: Mapped[Optional[OffTreatmentReason]]
+    off_treatment_reason_other: Mapped[Optional[str]]
+
+    participant: Mapped["ParticipantORM"] = relationship(back_populates="treatments", cascade="all, delete")
+    arm: Mapped[Optional["ArmORM"]] = relationship(cascade="all, delete")
+    cohort: Mapped[Optional["CohortORM"]] = relationship(cascade="all, delete")
+    adverse_events: Mapped[List["AdverseEventORM"]] = relationship(back_populates="treatment", cascade="all, delete")
+
+    therapy_agent_doses: Mapped[List["TherapyAgentDoseORM"]] = relationship(
+        back_populates="treatment", cascade="all, delete"
+    )
+    radiotherapy_doses: Mapped[List["RadiotherapyDoseORM"]] = relationship(
+        back_populates="treatment", cascade="all, delete"
+    )
+    surgeries: Mapped[List["SurgeryORM"]] = relationship(back_populates="treatment", cascade="all, delete")
+    stem_cell_transplants: Mapped[List["StemCellTransplantORM"]] = relationship(
+        back_populates="treatment", cascade="all, delete"
+    )

cidc_api/models/db/stage2/trial_orm.py

@@ -0,0 +1,60 @@
+from datetime import datetime
+from typing import List, Optional
+
+from sqlalchemy import ForeignKey
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+from sqlalchemy.types import JSON
+
+from cidc_api.models.db.base_orm import BaseORM
+from cidc_api.models.types import TrialStatus, AssayType, TrialOrganization, TrialFundingAgency
+
+
+class TrialORM(BaseORM):
+    __tablename__ = "trial"
+    __repr_attrs__ = ["trial_id", "version"]
+    __table_args__ = {"schema": "stage2"}
+
+    trial_id: Mapped[str] = mapped_column(primary_key=True)
+    version: Mapped[str] = mapped_column(primary_key=True)
+
+    nct_id: Mapped[Optional[str]]
+    nci_id: Mapped[Optional[str]]
+    trial_name: Mapped[Optional[str]]
+    trial_type: Mapped[Optional[str]]
+    trial_description: Mapped[Optional[str]]
+    trial_organization: Mapped[Optional[TrialOrganization]]
+    grant_or_affiliated_network: Mapped[Optional[TrialFundingAgency]]
+    trial_status: Mapped[TrialStatus]
+    biobank_institution_id: Mapped[Optional[int]]
+    justification: Mapped[Optional[str]]
+    dates_of_conduct_start: Mapped[datetime]
+    dates_of_conduct_end: Mapped[Optional[datetime]]
+    schema_file_id: Mapped[Optional[int]]
+    biomarker_plan: Mapped[Optional[str]]
+    data_sharing_plan: Mapped[Optional[str]]
+    expected_assays: Mapped[Optional[List[AssayType]]] = mapped_column(JSON, nullable=True)
+    is_liquid_tumor_trial: Mapped[bool]
+    dbgap_study_accession: Mapped[Optional[str]]
+
+    biobank: Mapped["InstitutionORM"] = relationship(back_populates="trial")
+    schema: Mapped[Optional["FileORM"]] = relationship(back_populates="trial", viewonly=True)
+    administrative_role_assignments: Mapped[List["AdministrativeRoleAssignmentORM"]] = relationship(
+        back_populates="trial", cascade="all, delete", passive_deletes=True
+    )
+    arms: Mapped[List["ArmORM"]] = relationship(back_populates="trial", cascade="all, delete", passive_deletes=True)
+    cohorts: Mapped[List["CohortORM"]] = relationship(
+        back_populates="trial", cascade="all, delete", passive_deletes=True
+    )
+    participants: Mapped[List["ParticipantORM"]] = relationship(
+        back_populates="trial", cascade="all, delete", passive_deletes=True
+    )
+    shipments: Mapped[List["ShipmentORM"]] = relationship(
+        back_populates="trial", cascade="all, delete", passive_deletes=True
+    )
+    files: Mapped[List["FileORM"]] = relationship(back_populates="trial", cascade="all, delete", passive_deletes=True)
+    publications: Mapped[List["PublicationORM"]] = relationship(
+        back_populates="trial", cascade="all, delete", passive_deletes=True
+    )
+    consent_groups: Mapped[List["ConsentGroupORM"]] = relationship(
+        back_populates="trial", cascade="all, delete", passive_deletes=True
+    )

cidc_api/models/files/facets.py

@@ -439,6 +439,11 @@ assay_facets: Facets = {
             "Analysis files for all samples run on the Olink platform in the trial.",
         ),
     },
+    "Olink HT": {
+        "Batch-Level Combined File": FacetConfig(["/olink_ht/batch_level_combined_file.parquet"]),
+        "Study-Level Combined File": FacetConfig(["/olink_ht/study_level_combined_file.parquet"]),
+        "Npx Run File": FacetConfig(["/olink_ht/npx_run_file.parquet"]),
+    },
     "IHC": {
         "Images": FacetConfig(["/ihc/ihc_image."]),
         "Combined Markers": FacetConfig(["csv|ihc marker combined"]),

cidc_api/models/migrations.py

@@ -91,15 +91,11 @@ def migration_session():
         session.close()
 
 
-def run_metadata_migration(
-    metadata_migration: Callable[[dict], MigrationResult], use_upload_jobs_table: bool
-):
+def run_metadata_migration(metadata_migration: Callable[[dict], MigrationResult], use_upload_jobs_table: bool):
     """Migrate trial metadata, upload job patches, and downloadable files according to `metadata_migration`"""
     with migration_session() as (session, task_queue):
         try:
-            _run_metadata_migration(
-                metadata_migration, use_upload_jobs_table, task_queue, session
-            )
+            _run_metadata_migration(metadata_migration, use_upload_jobs_table, task_queue, session)
         except:
             traceback.print_exc()
             raise
@@ -122,9 +118,7 @@ class ManifestUploads(CommonColumns):
     __tablename__ = "manifest_uploads"
 
 
-def _select_successful_assay_uploads(
-    use_upload_jobs_table: bool, session: Session
-) -> List[UploadJobs]:
+def _select_successful_assay_uploads(use_upload_jobs_table: bool, session: Session) -> List[UploadJobs]:
     if use_upload_jobs_table:
         return (
             session.query(UploadJobs)
@@ -133,21 +127,12 @@ def _select_successful_assay_uploads(
             .all()
         )
 
-    return (
-        session.query(AssayUploads)
-        .filter_by(status=UploadJobStatus.MERGE_COMPLETED.value)
-        .with_for_update()
-        .all()
-    )
+    return session.query(AssayUploads).filter_by(status=UploadJobStatus.MERGE_COMPLETED.value).with_for_update().all()
 
 
-def _select_manifest_uploads(
-    use_upload_jobs_table: bool, session: Session
-) -> List[UploadJobs]:
+def _select_manifest_uploads(use_upload_jobs_table: bool, session: Session) -> List[UploadJobs]:
     if use_upload_jobs_table:
-        return (
-            session.query(UploadJobs).filter_by(multifile=False).with_for_update().all()
-        )
+        return session.query(UploadJobs).filter_by(multifile=False).with_for_update().all()
 
     return session.query(ManifestUploads).with_for_update().all()
 
@@ -188,21 +173,15 @@ def _run_metadata_migration(
 
             # Regenerate additional metadata from the migrated clinical trial
             # metadata object.
-            print(
-                f"Regenerating additional metadata for artifact with uuid {artifact['upload_placeholder']}"
-            )
+            print(f"Regenerating additional metadata for artifact with uuid {artifact['upload_placeholder']}")
             artifact_path = uuid_path_map[artifact["upload_placeholder"]]
-            df.additional_metadata = get_source(
-                migration.result, artifact_path, skip_last=True
-            )[1]
+            df.additional_metadata = get_source(migration.result, artifact_path, skip_last=True)[1]
 
             # If the GCS URI has changed, rename the blob
             # makes call to bucket.rename_blob
             new_gcs_uri = artifact["object_url"]
             if old_gcs_uri != new_gcs_uri:
-                print(
-                    f"Encountered GCS data bucket artifact URI to update: {old_gcs_uri}"
-                )
+                print(f"Encountered GCS data bucket artifact URI to update: {old_gcs_uri}")
                 renamer = PieceOfWork(
                     partial(
                         rename_gcs_blob,
@@ -220,9 +199,7 @@ def _run_metadata_migration(
                 gcs_tasks.schedule(renamer)
 
     # Migrate all assay upload successes
-    successful_assay_uploads = _select_successful_assay_uploads(
-        use_upload_jobs_table, session
-    )
+    successful_assay_uploads = _select_successful_assay_uploads(use_upload_jobs_table, session)
     for upload in successful_assay_uploads:
         print(f"Running metadata migration for assay upload: {upload.id}")
         if use_upload_jobs_table:
@@ -248,9 +225,7 @@ def _run_metadata_migration(
             if old_target_uri in migration.file_updates:
                 new_target_uri = migration.file_updates[old_target_uri]["object_url"]
                 if old_target_uri != new_target_uri:
-                    print(
-                        f"Encountered GCS upload bucket artifact URI to update: {old_upload_uri}"
-                    )
+                    print(f"Encountered GCS upload bucket artifact URI to update: {old_upload_uri}")
                     new_upload_uri = "/".join([new_target_uri, upload_timestamp])
                     renamer = PieceOfWork(
                         partial(
@@ -325,7 +300,5 @@ def republish_artifact_uploads():
     with migration_session() as (session, _):
         files = session.query(DownloadableFiles).all()
         for f in files:
-            print(
-                f"Publishing to 'artifact_upload' topic for downloadable file with in bucket url {f.object_url}"
-            )
+            print(f"Publishing to 'artifact_upload' topic for downloadable file with in bucket url {f.object_url}")
             publish_artifact_upload(f.object_url)

cidc_api/models/models.py

@@ -3415,6 +3415,15 @@ class PreprocessedFiles(CommonColumns):
 
         return query.filter(cls.job_id.is_(None))
 
+    @with_default_session
+    def category_description(self, session: Session):
+        category = (
+            session.query(JobFileCategories)
+            .filter(JobFileCategories.job_id == self.job_id, JobFileCategories.category == self.file_category)
+            .first()
+        )
+        return category.description if category else None
+
 
 INGESTION_JOB_STATUSES = [
     "DRAFT",
@@ -3546,6 +3555,7 @@ class JobFileCategories(CommonColumns):
     )
 
     category = Column(String)
+    description = Column(String)
     job_id = Column(Integer, nullable=False)
     type = Column(Enum("required", "optional", name="type"), nullable=False)
     is_custom = Column(Boolean, nullable=False, default=False, server_default="false")
@@ -3556,6 +3566,7 @@ class JobFileCategories(CommonColumns):
         category: str,
         job_id: int,
         type: str,
+        description: str = None,
         is_custom: bool = False,
         session: Session = None,
     ):
@@ -3563,6 +3574,7 @@ class JobFileCategories(CommonColumns):
             category=category,
             job_id=job_id,
             type=type,
+            description=description,
             is_custom=is_custom,
         )
         new_category.insert(session=session)

cidc_api/models/pydantic/stage2/__init__.py

@@ -0,0 +1,78 @@
+from .additional_treatment import AdditionalTreatment
+from .administrative_person import AdministrativePerson
+from .administrative_role_assignment import AdministrativeRoleAssignment
+from .adverse_event import AdverseEvent
+from .arm import Arm
+from .baseline_clinical_assessment import BaselineClinicalAssessment
+from .cohort import Cohort
+from .comorbidity import Comorbidity
+from .consent_group import ConsentGroup
+from .contact import Contact
+from .demographic import Demographic
+from .disease import Disease
+from .exposure import Exposure
+from .file import File
+from .gvhd_diagnosis_acute import GVHDDiagnosisAcute
+from .gvhd_diagnosis_chronic import GVHDDiagnosisChronic
+from .gvhd_organ_acute import GVHDOrganAcute
+from .gvhd_organ_chronic import GVHDOrganChronic
+from .institution import Institution
+from .medical_history import MedicalHistory
+from .other_clinical_endpoint import OtherClinicalEndpoint
+from .other_malignancy import OtherMalignancy
+from .participant import Participant
+from .prior_treatment import PriorTreatment
+from .publication import Publication
+from .radiotherapy_dose import RadiotherapyDose
+from .response import Response
+from .response_by_system import ResponseBySystem
+from .shipment import Shipment
+from .shipment_specimen import ShipmentSpecimen
+from .specimen import Specimen
+from .stem_cell_transplant import StemCellTransplant
+from .surgery import Surgery
+from .therapy_agent_dose import TherapyAgentDose
+from .treatment import Treatment
+from .trial import Trial
+
+
+__all__ = [
+    "AdditionalTreatment",
+    "AdministrativePerson",
+    "AdministrativeRoleAssignment",
+    "AdverseEvent",
+    "Arm",
+    "BaselineClinicalAssessment",
+    "Cohort",
+    "Comorbidity",
+    "ConsentGroup",
+    "Contact",
+    "Demographic",
+    "Disease",
+    "Exposure",
+    "File",
+    "GVHDDiagnosisAcute",
+    "GVHDOrganAcute",
+    "GVHDDiagnosisChronic",
+    "GVHDOrganChronic",
+    "Institution",
+    "MedicalHistory",
+    "OtherClinicalEndpoint",
+    "OtherMalignancy",
+    "Participant",
+    "PriorTreatment",
+    "Publication",
+    "RadiotherapyDose",
+    "Response",
+    "ResponseBySystem",
+    "Shipment",
+    "ShipmentSpecimen",
+    "Specimen",
+    "StemCellTransplant",
+    "Surgery",
+    "TherapyAgentDose",
+    "Treatment",
+    "Trial",
+]
+
+all_models = [globals()[cls_name] for cls_name in __all__]

cidc_api/models/pydantic/stage2/additional_treatment.py

@@ -0,0 +1,23 @@
+from pydantic import NonNegativeInt
+from .base import Base
+
+
+class AdditionalTreatment(Base):
+    __data_category__ = "additional_treatment"
+    __cardinality__ = "many"
+
+    # The unique internal identifier for the AdditionalTreatment record
+    additional_treatment_id: int | None = None
+
+    # The unique internal identifier for the associated Participant record
+    participant_id: int | None = None
+
+    # Number of days from the enrollment date to the first recorded administration or occurrence of the treatment modality.
+    days_to_start: NonNegativeInt | None = None
+
+    # Number of days from the enrollment date to the last recorded administration or occurrence of the treatment modality.
+    days_to_end: NonNegativeInt | None = None
+
+    # Description of the prior treatment such as its full generic name if it is a type of therapy agent, radiotherapy procedure
+    # name and location, or surgical procedure name and location.
+    description: str

cidc_api/models/pydantic/stage2/administrative_person.py

@@ -0,0 +1,30 @@
+from .base import Base
+
+
+class AdministrativePerson(Base):
+
+    # The unique internal identifier for the administrative person
+    administrative_person_id: int | None = None
+
+    # The internal identifier for the Institution the administrative person belongs to
+    institution_id: int | None = None
+
+    # The word or group of words indicating a person's first (personal or given) name, e.g. "John"
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=2179589%20and%20ver_nr=2
+    first_name: str
+
+    # The word or group of worlds indicating a person's middle name, e.g. "Alan"
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=2179590%20and%20ver_nr=2
+    middle_name: str | None = None
+
+    # The means of identifying an individual by using a word or group of words indicating a person's last (family) name, e.g. "Smith"
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=2179591%20and%20ver_nr=2
+    last_name: str
+
+    # The string of characters that represents the electronic mail address of a person.
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=2517550%20and%20ver_nr=1
+    email: str | None = None
+
+    # The string of digits that represent a telephone number that can be used to contact the person.
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=2179593%20and%20ver_nr=3
+    phone_number: str | None = None

cidc_api/models/pydantic/stage2/administrative_role_assignment.py

@@ -0,0 +1,16 @@
+from .base import Base
+from cidc_api.models.types import AdministrativeRole
+
+
+class AdministrativeRoleAssignment(Base):
+    # The unique identifier for the associated trial
+    trial_id: int | None = None
+
+    # The version number of the trial dataset
+    version: str | None = None
+
+    # The unique identifier for the associated administrative person
+    administrative_person_id: int
+
+    # The role the administrative_person is performing for the associated trial
+    administrative_role: AdministrativeRole

cidc_api/models/pydantic/stage2/adverse_event.py

@@ -0,0 +1,100 @@
+from typing import Self
+
+from pydantic import NonNegativeInt, model_validator
+
+from .base import Base
+from cidc_api.reference.ctcae import is_ctcae_other_term
+from cidc_api.models.types import (
+    CTCAEEventTerm,
+    CTCAEEventCode,
+    SeverityGradeSystem,
+    SeverityGradeSystemVersion,
+    SeverityGrade,
+    SystemOrganClass,
+    AttributionCause,
+    AttributionLikelihood,
+    YNU,
+)
+
+
+class AdverseEvent(Base):
+    __data_category__ = "adverse_event"
+    __cardinality__ = "many"
+
+    # The unique internal identifier of the adverse event
+    adverse_event_id: int | None = None
+
+    # The unique internal identifier of the associated participant
+    participant_id: int | None = None
+
+    # The unique internal identifier of the attributed treatment, if any
+    treatment_id: int | None = None
+
+    # Text that represents the Common Terminology Criteria for Adverse Events low level term name for an adverse event.
+    event_term: CTCAEEventTerm | None = None
+
+    # A MedDRA code mapped to a CTCAE low level name for an adverse event.
+    event_code: CTCAEEventCode | None = None
+
+    # System used to define and report adverse event severity grade.
+    severity_grade_system: SeverityGradeSystem
+
+    # The version of the adverse event grading system.
+    severity_grade_system_version: SeverityGradeSystemVersion
+
+    # Numerical grade indicating the severity of an adverse event.
+    severity_grade: SeverityGrade
+
+    # A brief description that sufficiently details the event.
+    event_other_specify: str | None = None
+
+    # The highest level of the MedDRA hierarchy, distinguished by anatomical or physiological system, etiology (disease origin) or purpose.
+    system_organ_class: SystemOrganClass | None = None
+
+    # Indicator to identify whether a participant exited the study prematurely due to the adverse event being described.
+    discontinuation_due_to_event: bool
+
+    # Days from enrollment date to date of onset of the adverse event.
+    days_to_onset_of_event: NonNegativeInt
+
+    # Days from enrollment date to date of resolution of the adverse event.
+    days_to_resolution_of_event: NonNegativeInt | None = None
+
+    # Indicates whether the adverse event was a serious adverse event (SAE).
+    serious_adverse_event: YNU
+
+    # Indicates whether the adverse event was a dose-limiting toxicity (DLT).
+    dose_limiting_toxicity: YNU
+
+    # Indicates if the adverse was attributable to the protocol as a whole or to an individual treatment.
+    attribution_cause: AttributionCause
+
+    # The code that indicates whether the adverse event is related to the treatment/intervention.
+    attribution_likelihood: AttributionLikelihood
+
+    # The individual therapy (therapy agent, radiotherapy, surgery, stem cell transplant) in the treatment that is attributed to the adverse event.
+    individual_therapy: str | None = None
+
+    @model_validator(mode="after")
+    def validate_term_and_code_cr(self) -> Self:
+        if not self.event_term and not self.event_code:
+            raise ValueError("Please provide event_term or event_code or both")
+        return self
+
+    @model_validator(mode="after")
+    def validate_event_other_specify_cr(self) -> Self:
+        if (
+            self.severity_grade_system == "CTCAE"
+            and is_ctcae_other_term(self.event_term)
+            and not self.event_other_specify
+        ):
+            raise ValueError(
+                'If severity_grade_system is "CTCAE" and the event_code or event_term are of type "Other, specify", please provide event_other_specify'
+            )
+        return self
+
+    @model_validator(mode="after")
+    def validate_system_organ_class_cr(self) -> Self:
+        if self.event_other_specify and not self.system_organ_class:
+            raise ValueError("If event_other_specify is provided, please provide system_organ_class.")
+        return self

cidc_api/models/pydantic/stage2/arm.py

@@ -0,0 +1,16 @@
+from .base import Base
+
+
+class Arm(Base):
+    # The unique internal identifier for the arm
+    arm_id: int | None = None
+
+    # The unique identifier for the associated trial
+    trial_id: int | None = None
+
+    # The version number of the trial dataset
+    version: str | None = None
+
+    # The name of the arm, e.g. "Arm A1"
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=2001626%20and%20ver_nr=3
+    name: str

cidc_api/models/pydantic/stage2/base.py

@@ -0,0 +1,30 @@
+from pydantic import BaseModel, ConfigDict
+from contextlib import contextmanager
+
+import copy
+
+
+class Base(BaseModel):
+
+    model_config = ConfigDict(validate_assignment=True, from_attributes=True)
+
+    # Validates the new state and updates the object if valid
+    def update(self, **kwargs):
+        self.model_validate(self.__dict__ | kwargs)
+        self.__dict__.update(kwargs)
+
+    # CM that delays validation until all fields are applied.
+    # If validation fails the original fields are restored and the ValidationError is raised.
+    @contextmanager
+    def delay_validation(self):
+        original_dict = copy.deepcopy(self.__dict__)
+        self.model_config["validate_assignment"] = False
+        try:
+            yield
+        finally:
+            self.model_config["validate_assignment"] = True
+        try:
+            self.model_validate(self.__dict__)
+        except:
+            self.__dict__.update(original_dict)
+            raise

cidc_api/models/pydantic/stage2/baseline_clinical_assessment.py

@@ -0,0 +1,23 @@
+from .base import Base
+from cidc_api.models.types import ECOGScore, KarnofskyScore
+
+
+class BaselineClinicalAssessment(Base):
+    __data_category__ = "baseline_clinical_assessment"
+    __cardinality__ = "one"
+
+    # A unique internal identifier for the baseline clinical assessment
+    baseline_clinical_assessment_id: int | None = None
+
+    # The unique identifier for the associated participant
+    participant_id: int | None = None
+
+    # The numerical score that represents the functional capabilities of a participant at the
+    # enrollment date using the Eastern Cooperative Oncology Group Performance Status assessment.
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=88%20and%20ver_nr=5.1
+    ecog_score: ECOGScore | None = None
+
+    # Score from the Karnofsky Performance status scale, representing the functional capabilities of a participant
+    # at the enrollment date.
+    # CDE: 	https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=2003853%20and%20ver_nr=4.2
+    karnofsky_score: KarnofskyScore | None = None

cidc_api/models/pydantic/stage2/cohort.py

@@ -0,0 +1,16 @@
+from .base import Base
+
+
+class Cohort(Base):
+    # A unique internal identifier for the cohort
+    cohort_id: int | None = None
+
+    # The unique identifier for the associated trial
+    trial_id: str | None = None
+
+    # The version number of the trial dataset
+    version: str | None = None
+
+    # The name of the cohort, e.g. "Cohort A"
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=7979585%20and%20ver_nr=1
+    name: str

cidc_api/models/pydantic/stage2/comorbidity.py

@@ -0,0 +1,36 @@
+from typing import Self
+
+from pydantic import model_validator
+
+from .base import Base
+from cidc_api.models.types import ICD10CMCode, ICD10CMTerm
+
+
+class Comorbidity(Base):
+    __data_category__ = "comorbidity"
+    __cardinality__ = "many"
+
+    # The unique internal identifier for the comorbidity record
+    comorbidity_id: int | None = None
+
+    # The unique internal identifier for the associated MedicalHistory record
+    medical_history_id: int | None = None
+
+    # The diagnosis, in humans, as captured in the tenth version of the
+    # International Classification of Disease (ICD-10-CM, the disease code subset of ICD-10).
+    comorbidity_code: ICD10CMCode | None = None
+
+    # The words from the tenth version of the International Classification of Disease (ICD-10-CM,
+    # the disease subset of ICD-10) used to identify the diagnosis in humans.
+    comorbidity_term: ICD10CMTerm | None = None
+
+    # A descriptive string that names or briefly describes the comorbidity.
+    comorbidity_other: str | None = None
+
+    @model_validator(mode="after")
+    def validate_code_or_term_or_other_cr(self) -> Self:
+        if not self.comorbidity_code and not self.comorbidity_term and not self.comorbidity_other:
+            raise ValueError(
+                'Please provide at least one of "comorbidity_code", "comorbidity_term" or "comorbidity_other".'
+            )
+        return self

cidc_api/models/pydantic/stage2/consent_group.py

@@ -0,0 +1,30 @@
+from pydantic import NonNegativeInt
+
+from .base import Base
+
+
+class ConsentGroup(Base):
+    __data_category__ = "consent_group"
+    __cardinality__ = "one"
+
+    # The unique internal identifier for the consent group record
+    consent_group_id: int | None = None
+
+    # The unique internal identifier for the associated Trial record
+    trial_id: int | None = None
+
+    # The version number of the trial dataset
+    version: str | None = None
+
+    # An abbreviated name for the consent group
+    consent_group_short_name: str
+
+    # The words or acronym which describe a set of study participants
+    # who have signed the same consent agreement and that will be included in the dbGaP repository.
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=14534329%20and%20ver_nr=1.00
+    consent_group_name: str
+
+    # A numeral or string of numerals used to identify the set of study participants who have signed the same consent
+    # agreement and that will be included in the dbGaP repository.
+    # CDE: https://cadsr.cancer.gov/onedata/dmdirect/NIH/NCI/CO/CDEDD?filter=CDEDD.ITEM_ID=14534330%20and%20ver_nr=1.00
+    consent_group_number: NonNegativeInt