Merge pull request #173 from BIH-CEI/170-change-datafield-to-work-wit…

…h-datanode

hierarchical datamodel

notebooks/hierarchical_data_model.ipynb

@@ -0,0 +1,196 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2024-10-14T21:21:45.314262Z",
+     "start_time": "2024-10-14T21:21:45.309299Z"
+    }
+   },
+   "source": [
+    "from phenopacket_mapper.data_standards import DataField\n",
+    "from phenopacket_mapper.data_standards import DataModel, ValueSet, DataSection, OrGroup"
+   ],
+   "outputs": [],
+   "execution_count": 4
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-10-14T21:21:45.340239Z",
+     "start_time": "2024-10-14T21:21:45.334880Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "genomic_interpretation = DataModel(\n",
+    "    data_model_name=\"Phenopacket schema Genomic Interpretation\",\n",
+    "    fields=(\n",
+    "        DataField(\n",
+    "            name=\"subject_or_biosample_id\",\n",
+    "            specification=str,\n",
+    "            required=True,\n",
+    "            description=\"The id of the patient or biosample that is the subject being interpreted. REQUIRED.\"\n",
+    "        ),\n",
+    "        \n",
+    "        DataField(\n",
+    "            name=\"interpretation_status\",\n",
+    "            specification=ValueSet(\n",
+    "                name=\"Interpretation Status Value Set\",\n",
+    "                elements=[\"UNKNOWN_STATUS\", \"REJECTED\", \"CANDIDATE\", \"CONTRIBUTORY\", \"CAUSATIVE\"],\n",
+    "            ),\n",
+    "            required=True,\n",
+    "            description=\"status of the interpretation. REQUIRED.\",\n",
+    "        ),\n",
+    "        \n",
+    "        OrGroup(\n",
+    "            name=\"call\",\n",
+    "            fields=(\n",
+    "                DataSection(\n",
+    "                    name=\"GeneDescriptor\",\n",
+    "                    fields=(\n",
+    "                        DataField(\n",
+    "                            name=\"value_id\",\n",
+    "                            specification=str,\n",
+    "                            required=True,\n",
+    "                            description=\"Official identifier of the gene. REQUIRED.\"\n",
+    "                        ),\n",
+    "\n",
+    "                        DataField(\n",
+    "                            name=\"symbol\",\n",
+    "                            specification=str,\n",
+    "                            required=True,\n",
+    "                            description=\"Official gene symbol. REQUIRED.\"\n",
+    "                        ),\n",
+    "\n",
+    "                        DataField(\n",
+    "                            name=\"description\",\n",
+    "                            specification=str,\n",
+    "                            required=False,\n",
+    "                            description=\"A free-text description of the gene\"\n",
+    "                        ),\n",
+    "                    ),\n",
+    "                ),\n",
+    "            ),\n",
+    "        ),\n",
+    "    )\n",
+    ")"
+   ],
+   "id": "2e979683ae450d9b",
+   "outputs": [],
+   "execution_count": 5
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-10-14T21:21:45.352293Z",
+     "start_time": "2024-10-14T21:21:45.347715Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "s = str(genomic_interpretation)\n",
+    "\n",
+    "print(s)"
+   ],
+   "id": "35a697d8b9b8236d",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "DataModel(\n",
+      "\tname: Phenopacket schema Genomic Interpretation\n",
+      "\tDataField(\n",
+      "\t\tid: subject_or_biosample_id,\n",
+      "\t\tname: subject_or_biosample_id,\n",
+      "\t\trequired: True\n",
+      "\t\tspecification: ValueSet(elements=[<class 'str'>], name='', description='')\n",
+      "\t\tcardinality: 1..n\n",
+      "\t)\n",
+      "\tDataField(\n",
+      "\t\tid: interpretation_status,\n",
+      "\t\tname: interpretation_status,\n",
+      "\t\trequired: True\n",
+      "\t\tspecification: ValueSet(elements=['UNKNOWN_STATUS', 'REJECTED', 'CANDIDATE', 'CONTRIBUTORY', 'CAUSATIVE'], name='Interpretation Status Value Set', description='')\n",
+      "\t\tcardinality: 1..n\n",
+      "\t)\n",
+      "\tOrGroup(\n",
+      "\t\tid: call,\n",
+      "\t\tname: call,\n",
+      "\t\trequired: False\n",
+      "\t\tcardinality: 0..n\n",
+      "\tDataSection(\n",
+      "\t\tid: genedescriptor,\n",
+      "\t\tname: GeneDescriptor,\n",
+      "\t\trequired: False\n",
+      "\t\tcardinality: 0..n\n",
+      "\tDataField(\n",
+      "\t\tid: value_id,\n",
+      "\t\tname: value_id,\n",
+      "\t\trequired: True\n",
+      "\t\tspecification: ValueSet(elements=[<class 'str'>], name='', description='')\n",
+      "\t\tcardinality: 1..n\n",
+      "\t)\n",
+      "\tDataField(\n",
+      "\t\tid: symbol,\n",
+      "\t\tname: symbol,\n",
+      "\t\trequired: True\n",
+      "\t\tspecification: ValueSet(elements=[<class 'str'>], name='', description='')\n",
+      "\t\tcardinality: 1..n\n",
+      "\t)\n",
+      "\tDataField(\n",
+      "\t\tid: description,\n",
+      "\t\tname: description,\n",
+      "\t\trequired: False\n",
+      "\t\tspecification: ValueSet(elements=[<class 'str'>], name='', description='')\n",
+      "\t\tcardinality: 0..n\n",
+      "\t)\n",
+      "\t)\n",
+      "\t)\n",
+      "---\n",
+      ")\n"
+     ]
+    }
+   ],
+   "execution_count": 6
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-10-14T21:21:45.378046Z",
+     "start_time": "2024-10-14T21:21:45.375530Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "",
+   "id": "4c78eb05ea58ff6c",
+   "outputs": [],
+   "execution_count": null
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

src/phenopacket_mapper/_api/__init__.py

@@ -2,12 +2,13 @@
 This package is intended to expose the PhenopacketMapper API to the user.
 """
 
-import abc
+from abc import ABCMeta, abstractmethod
 from typing import Tuple, Iterable, Iterator
-from dataclasses import dataclass
 
+from phenopacket_mapper.data_standards import Cardinality
 
-class DataModelDefiner(metaclass=abc.ABCMeta):
+
+class DataModelDefiner(metaclass=ABCMeta):
     """
     Take some data model definition and try to load it into :class:`DataModel`.
 
@@ -16,7 +17,7 @@ class DataModelDefiner(metaclass=abc.ABCMeta):
     pass
 
 
-class DataModel(metaclass=abc.ABCMeta):
+class DataModel(metaclass=ABCMeta):
     """
     Value class.
     The fields:
@@ -29,8 +30,7 @@ class DataModel(metaclass=abc.ABCMeta):
     pass
 
 
-@dataclass
-class DataNode(metaclass=abc.ABCMeta):
+class DataNode(metaclass=ABCMeta):
     """
     This is very much like Jackson (Java) `TreeNode`,
     because it can be many things.
@@ -41,16 +41,38 @@ class DataNode(metaclass=abc.ABCMeta):
 
     We want to be able to (de)serialize this.
     """
-    label: str
-    id: str
-    required: bool
+    @property
+    @abstractmethod
+    def name(self) -> str:
+        pass
+
+    @property
+    @abstractmethod
+    def id(self) -> str:
+        pass
+
+    @property
+    @abstractmethod
+    def required(self) -> bool:
+        pass
+
+
+    @property
+    @abstractmethod
+    def description(self) -> str:
+        pass
+
+    @property
+    @abstractmethod
+    def cardinality(self) -> Cardinality:
+        pass
 
 
 class DataInstance:
     pass
 
 
-class Transformation(metaclass=abc.ABCMeta):
+class Transformation(metaclass=ABCMeta):
     """
 
     """

src/phenopacket_mapper/data_standards/__init__.py

@@ -1,18 +1,19 @@
 """This submodule defines the data standards used in the project."""
-
+from .cardinality import Cardinality
 from .date import Date
 from .code_system import CodeSystem, SNOMED_CT, HPO, MONDO, OMIM, ORDO, LOINC
 from .code import Coding, CodeableConcept
-from .data_model import DataModel, DataField, DataModelInstance, DataFieldValue, DataSet
+from .data_model import DataModel, DataField, DataModelInstance, DataFieldValue, DataSet, DataSection, OrGroup
 from . import data_models
 from .value_set import ValueSet
 
 __all__ = [
+    "Cardinality",
     "Coding", "CodeableConcept",
-    "DataModel", "DataField", "DataModelInstance", "DataFieldValue", "DataSet",
+    "DataModel", "DataField", "DataModelInstance", "DataFieldValue", "DataSet", "DataSection", "OrGroup",
     "data_models",
     "CodeSystem",
     "SNOMED_CT", "HPO", "MONDO", "OMIM", "ORDO", "LOINC",
     "Date",
-    "ValueSet"
+    "ValueSet",
 ]

src/phenopacket_mapper/data_standards/cardinality.py

@@ -0,0 +1,22 @@
+from dataclasses import dataclass, field
+from typing import Union, Literal
+
+
+@dataclass(slots=True, frozen=True)
+class Cardinality:
+    min: int = field(default=0)
+    max: Union[int, Literal['n']] = field(default='n')
+
+    def __post_init__(self):
+        if not isinstance(self.min, int):
+            raise ValueError(f"Parameter min must be of type integer. (Not: {type(self.min)})")
+        elif self.min < 0:
+            raise ValueError(f"Parameter min must be a non-negative integer. (Not: {self.min})")
+        if not (isinstance(self.max, int) or self.max == 'n'):
+            raise ValueError(f"Parameter max must be of type or equal to the literal 'n'. "
+                             f"(Not: {self.min} ({type(self.min)}))")
+        elif self.max != 'n' and self.max < 1:  # has to be an integer
+            raise ValueError(f"Parameter max must be a positive integer. (Not: {self.min})")
+
+    def __str__(self):
+        return f"{self.min}..{self.max}"