added initial version of bia shared datamodels (#111)

* added initial version of bia shared datamodels

* switched to pydantic model only

* added dataset class as parent of annotation and image study components

* created process class and subclasses to cover annotation, post-processing, and imaging techniques

* added api models

* added class diagram

* updated semantic models and class diagram but not api models

* added models to indicate UUID connections

bia-shared-datamodels/.vscode/settings.json

@@ -0,0 +1,11 @@
+{
+    "python.testing.pytestArgs": [
+        "."
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnSave": true
+    }
+}

bia-shared-datamodels/Readme.md

@@ -0,0 +1,9 @@
+### First time setup
+Package containing the shared BIA models in link-ml yaml format, and the generate pydantic and readmes.
+
+Below shows the class diagram for the Shared BIA Models.
+
+<img src="./src/bia_models/Datamodel-class_diagram.svg">
+
+To edit the diagram, see: https://docs.google.com/drawings/d/1l0Yjy5bGBDlu6qoNfE7Mta7XdBmydRNCQTciY-KeztQ/edit
+

bia-shared-datamodels/pyproject.toml

@@ -0,0 +1,26 @@
+[tool.poetry]
+name = "bia-shared-datamodels"
+version = "0.1.0"
+description = "Schemas and models for working with the BioImage Archive's (Metadata, Incentives, Formats and Accessibility) metadata implementation"
+authors = ["Francois Sherwood <[email protected]>"]
+license = "Apache Software License 2.0"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.9"
+pydantic = {version = "^2", extras = ["email"]}
+pydantic-2-mermaid = "^0.7"
+pytest = "^7"
+
+[tool.poetry-dynamic-versioning]
+enable = true
+vcs = "git"
+style = "pep440"
+
+# [tool.poetry.group.dev.dependencies]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.extras]

bia-shared-datamodels/src/bia_models/bia_data_model.py

@@ -0,0 +1,135 @@
+from __future__ import annotations
+
+import semantic_models
+from pydantic import BaseModel, Field, AnyUrl
+from typing import List, Optional, Union
+from uuid import UUID
+
+from pydantic_core import Url
+
+
+class DocumentMixin(BaseModel):
+    uuid: UUID = Field(
+        description="""Unique ID (across the BIA database) used to refer to and identify a document."""
+    )
+
+
+class UserIdentifiedObject(BaseModel):
+    title_id: str = Field(
+        description="""User provided title, which is unqiue within a submission, used to identify a part of a submission."""
+    )
+
+
+class Study(
+    semantic_models.Study,
+    DocumentMixin,
+):
+    experimental_imaging_component: List[UUID] = Field()
+    annotation_component: List[UUID] = Field()
+
+
+class FileReference(
+    semantic_models.FileReference,
+    DocumentMixin,
+):
+    submission_dataset: UUID = Field()
+
+
+class ImageRepresentation(
+    semantic_models.ImageRepresentation,
+    DocumentMixin,
+):
+    original_file_reference: Optional[List[UUID]] = Field()
+
+
+class ExperimentalImagingDataset(
+    semantic_models.ExperimentalImagingDataset,
+    DocumentMixin,
+    UserIdentifiedObject,
+):
+    image: List[UUID] = Field()
+    file: List[UUID] = Field()
+    submitted_in_study: UUID = Field()
+    specimen_preparation_method: List[UUID] = Field()
+    acquisition_method: List[UUID] = Field()
+    biological_entity: List[UUID] = Field()
+    # we include image analysis and correlation
+
+
+class Specimen(semantic_models.Specimen):
+    preparation_method: List[UUID] = Field()
+    sample_of: List[UUID] = Field()
+
+
+class ExperimentallyCapturedImage(
+    semantic_models.ExperimentallyCapturedImage,
+    DocumentMixin,
+):
+    acquisition_process: List[UUID] = Field()
+    representation: List[UUID] = Field()
+    submission_dataset: UUID = Field()
+    subject: Specimen = Field()
+    # note Specimen is included in image document, but needs to be overriden to link to protocol & biosample via uuid.
+
+
+class ImageAcquisition(
+    semantic_models.ImageAcquisition,
+    DocumentMixin,
+    UserIdentifiedObject,
+):
+    pass
+
+
+class SpecimenPrepartionProtocol(
+    semantic_models.SpecimenPrepartionProtocol,
+    DocumentMixin,
+    UserIdentifiedObject,
+):
+    pass
+
+
+class BioSample(
+    semantic_models.BioSample,
+    DocumentMixin,
+    UserIdentifiedObject,
+):
+    pass
+
+
+class ImageAnnotationDataset(
+    semantic_models.ImageAnnotationDataset,
+    DocumentMixin,
+    UserIdentifiedObject,
+):
+    image: List[UUID] = Field()
+    file: List[UUID] = Field()
+    annotation_file: List[UUID] = Field()
+    submitted_in_study: UUID = Field()
+    annotation_method: UUID = Field()
+
+
+class AnnotationFileReference(
+    semantic_models.AnnotationFileReference,
+    DocumentMixin,
+):
+    source_image: List[UUID] = Field()
+    submission_dataset: UUID = Field()
+    creation_process: UUID = Field()
+
+
+class DerivedImage(
+    semantic_models.DerivedImage,
+    DocumentMixin,
+):
+    source_image: List[UUID] = Field()
+    submission_dataset: UUID = Field()
+    creation_process: UUID = Field()
+    representation: List[UUID] = Field()
+
+
+class AnnotationMethod(
+    semantic_models.AnnotationMethod,
+    DocumentMixin,
+    UserIdentifiedObject,
+):
+    source_dataset: List[Union[UUID, AnyUrl]]