Feat/experiments ga4gh structure

chord_metadata_service/chord/ingest/experiments.py

@@ -4,6 +4,7 @@
 from structlog.stdlib import BoundLogger
 
 from chord_metadata_service.chord.models import Dataset
+from chord_metadata_service.experiments.descriptions import DEFAULT_GA4GH_TEMPLATE_ID
 from chord_metadata_service.experiments import models as em
 from chord_metadata_service.experiments.schemas import EXPERIMENT_SCHEMA, EXPERIMENT_RESULT_SCHEMA
 from chord_metadata_service.phenopackets import models as pm
@@ -89,18 +90,25 @@ def ingest_experiment(
     new_experiment_id = experiment_data.get("id", str(uuid.uuid4()))
     study_type = experiment_data.get("study_type")
     experiment_type = experiment_data["experiment_type"]
-    experiment_ontology = experiment_data.get("experiment_ontology", [])
+    experiment_ontology = experiment_data.get("experiment_ontology", {})
     molecule = experiment_data.get("molecule")
-    molecule_ontology = experiment_data.get("molecule_ontology", [])
+    molecule_ontology = experiment_data.get("molecule_ontology", {})
     library_strategy = experiment_data.get("library_strategy")
     library_source = experiment_data.get("library_source")
     library_selection = experiment_data.get("library_selection")
     library_layout = experiment_data.get("library_layout")
+    library_id = experiment_data.get("library_id")
+    library_extract_id = experiment_data.get("library_extract_id")
+    insert_size = experiment_data.get("insert_size")
+    description = experiment_data.get("description")
+    protocol_url = experiment_data.get("protocol_url")
+    library_description = experiment_data.get("library_description")
     extraction_protocol = experiment_data.get("extraction_protocol")
     reference_registry_id = experiment_data.get("reference_registry_id")
     qc_flags = experiment_data.get("qc_flags", [])
     biosample_id = experiment_data.get("biosample")
     experiment_results = experiment_data.get("experiment_results", [])
+    ga4gh_template_id = experiment_data.get("ga4gh_template_id", DEFAULT_GA4GH_TEMPLATE_ID)
     instrument = experiment_data.get("instrument", {})
     extra_properties = experiment_data.get("extra_properties", {})
 
@@ -132,10 +140,17 @@ def ingest_experiment(
         library_source=library_source,
         library_selection=library_selection,
         library_layout=library_layout,
+        library_id=library_id,
+        library_extract_id=library_extract_id,
+        insert_size=insert_size,
+        description=description,
+        protocol_url=protocol_url,
+        library_description=library_description,
         extraction_protocol=extraction_protocol,
         reference_registry_id=reference_registry_id,
         qc_flags=qc_flags,
         biosample=biosample,
+        ga4gh_template_id=ga4gh_template_id,
         instrument=instrument_db,
         extra_properties=extra_properties,
         dataset=Dataset.objects.get(identifier=dataset_id)

chord_metadata_service/chord/tests/example_experiment.json

@@ -5,24 +5,23 @@
       "biosample": "sample1",
       "study_type": "Epigenomics",
       "experiment_type": "Other",
-      "experiment_ontology": [
-        {
+      "experiment_ontology": {
           "id": "http://www.ebi.ac.uk/efo/EFO_0002692",
           "label": "ChIP-seq"
-        }
-      ],
+      },
       "library_strategy": "ChIP-Seq",
       "library_source": "Genomic",
       "library_selection": "Random",
       "library_layout": "Single",
+      "library_id": "lib_id_01", 
+      "ga4gh_template_id": "v1.0",
+      "insert_size": 400,
       "extraction_protocol": "NGS",
       "molecule": "genomic DNA",
-      "molecule_ontology": [
-        {
+      "molecule_ontology": {
           "id": "SO:0000991",
           "label": "genomic DNA"
-        }
-      ],
+      },
       "experiment_results": [
         {
           "identifier": "sample1_01",
@@ -72,24 +71,22 @@
       "biosample": "sample2",
       "study_type": "Epigenomics",
       "experiment_type": "Other",
-      "experiment_ontology": [
-        {
+      "experiment_ontology": {
           "id": "http://www.ebi.ac.uk/efo/EFO_0002692",
           "label": "ChIP-seq"
-        }
-      ],
+      },
       "library_strategy": "ChIP-Seq",
       "library_source": "Genomic",
       "library_selection": "Random",
       "library_layout": "Single",
+      "library_id": "lib_id_02",
+      "ga4gh_template_id": "v1.0",
       "extraction_protocol": "NGS",
       "molecule": "genomic DNA",
-      "molecule_ontology": [
-        {
+      "molecule_ontology": {
           "id": "SO:0000991",
           "label": "genomic DNA"
-        }
-      ],
+      },
       "instrument": {
         "identifier": "instrument:02",
         "model": "Illumina",

chord_metadata_service/chord/tests/example_experiment_bad_biosample.json

@@ -5,24 +5,20 @@
       "biosample": "sample1ohno!",
       "study_type": "Epigenomics",
       "experiment_type": "Other",
-      "experiment_ontology": [
-        {
+      "experiment_ontology": {
           "id": "http://www.ebi.ac.uk/efo/EFO_0002692",
           "label": "ChIP-seq"
-        }
-      ],
+      },
       "library_strategy": "ChIP-Seq",
       "library_source": "Genomic",
       "library_selection": "Random",
       "library_layout": "Single",
       "extraction_protocol": "NGS",
       "molecule": "genomic DNA",
-      "molecule_ontology": [
-        {
+      "molecule_ontology": {
           "id": "SO:0000991",
           "label": "genomic DNA"
-        }
-      ],
+      },
       "experiment_results": [
         {
           "identifier": "sample1_01",

chord_metadata_service/chord/tests/example_invalid_experiment.json

@@ -5,24 +5,20 @@
       "biosample": "sample1",
       "study_type": "Epigenomics",
       "experiment_type": "Other",
-      "experiment_ontology": [
-        {
+      "experiment_ontology": {
           "id": "http://www.ebi.ac.uk/efo/EFO_0002692",
           "label": "ChIP-seq"
-        }
-      ],
+      },
       "library_strategy": "ChIP-Seq",
       "library_source": "Genomic",
       "library_selection": "Random",
       "library_layout": "Single",
       "extraction_protocol": "NGS",
       "molecule": "genomic DNA",
-      "molecule_ontology": [
-        {
+      "molecule_ontology": {
           "id": "SO:0000991",
           "label": "genomic DNA"
-        }
-      ],
+      },
       "experiment_results": [
         {
           "identifier": "sample1_01",

chord_metadata_service/experiments/descriptions.py

@@ -5,6 +5,8 @@
 
 from chord_metadata_service.restapi.description_utils import EXTRA_PROPERTIES, ontology_class
 
+DEFAULT_GA4GH_TEMPLATE_ID = "v1.0"
+
 EXPERIMENT = {
     "description": "Experiment related metadata.",
     "properties": {
@@ -15,14 +17,14 @@
                            "Histone H3K4me1, etc.).",
         "experiment_ontology": {
             "description": "Links to experiment ontology information (e.g. via the OBI ontology.).",
-            "items": ontology_class("describing the experiment"),
+            **ontology_class("describing the experiment"),
         },
         "molecule": "(Controlled Vocabulary) The type of molecule that was extracted from the biological material."
                     "Include one of the following: total RNA, polyA RNA, cytoplasmic RNA, nuclear RNA, small RNA, "
                     "genomic DNA, protein, or other.",
         "molecule_ontology": {
             "description": "Links to molecule ontology information (e.g. via the SO ontology.).",
-            "items": ontology_class("describing a molecular property"),
+            **ontology_class("describing a molecular property"),
         },
         "library_strategy": "(Controlled Vocabulary) The assay used. These are defined within the SRA metadata "
                             "specifications with a controlled vocabulary (e.g. Bisulfite-Seq, RNA-Seq, ChIP-Seq)."
@@ -33,6 +35,12 @@
         "library_selection": "Method used to enrich the target in the sequence library preparation. "
                              "E.g. Random, PCR, Random PCR, RT-PCR, MF and other.",
         "library_layout": "The library layout. E.g. Single, Paired.",
+        "library_id": "The identifier associated with the sequencing library.",
+        "library_extract_id": "Optional identifier for a given specific extraction.",
+        "insert_size": "The size of the DNA fragment inserted into the vector (Integer).",
+        "description": "Free-text experimental design description.",
+        "protocol_url": "URL to the sequencing protocol.",
+        "library_description": "Specific free-text details about library construction.",
         "extraction_protocol": "The protocol used to isolate the extract material.",
         "reference_registry_id": "The IHEC EpiRR ID for this dataset, only for IHEC Reference Epigenome datasets. "
                                  "Otherwise leave empty.",
@@ -42,6 +50,7 @@
         },
         "experiment_results": "Related files containing the analysis of sequencing data.",
         "instrument": "The instrument used to sequence the biological specimens.",
+        "ga4gh_template_id": "An ID referring to the GA4GH template used for this experiment (e.g. v1.0).",
         "biosample": "Biosample on which this experiment was done.",
         **EXTRA_PROPERTIES
     }

chord_metadata_service/experiments/migrations/0014_align_experiment_metadata_to_standar_models.py

@@ -0,0 +1,109 @@
+# Generated by Django 5.1.15 on 2026-01-14 15:46
+
+from django.db import migrations, models
+import chord_metadata_service.restapi.validators
+
+# --- DATA MIGRATION FUNCTIONS ---
+
+def convert_list_to_object(apps, schema_editor):
+    """
+    Iterates through all experiments. If ontology fields are lists,
+    converts them to a single object (the first item) or an empty dict.
+    """
+    # retrieve the historical version of the model
+    Experiment = apps.get_model('experiments', 'Experiment')
+
+    for exp in Experiment.objects.all():
+        # fix molecule_ontology
+        mol_data = exp.molecule_ontology
+        if isinstance(mol_data, list):
+            # Take the first element if exists, otherwise empty dict
+            exp.molecule_ontology = mol_data[0] if len(mol_data) > 0 else {}
+
+        # fix experiment_ontology
+        exp_data = exp.experiment_ontology
+        if isinstance(exp_data, list):
+            exp.experiment_ontology = exp_data[0] if len(exp_data) > 0 else {}
+
+        exp.save()
+
+def reverse_object_to_list(apps, schema_editor):
+    """
+    Reverse logic: wraps the single object back into a list 
+    to restore the legacy schema structure if needed.
+    """
+    Experiment = apps.get_model('experiments', 'Experiment')
+
+    for exp in Experiment.objects.all():
+        # Revert molecule_ontology
+        mol_data = exp.molecule_ontology
+        if isinstance(mol_data, dict):
+            exp.molecule_ontology = [mol_data] if mol_data else []
+
+        # Revert experiment_ontology
+        exp_data = exp.experiment_ontology
+        if isinstance(exp_data, dict):
+            exp.experiment_ontology = [exp_data] if exp_data else []
+
+        exp.save()
+
+# --- MIGRATION CLASS ---
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('experiments', '0013_experiment_fts_extra_experimentresult_fts_extra'),
+    ]
+
+    operations = [
+        # Add new fields
+        migrations.AddField(
+            model_name='experiment',
+            name='description',
+            field=models.TextField(blank=True, help_text='Free-text experimental design description.', null=True),
+        ),
+        migrations.AddField(
+            model_name='experiment',
+            name='ga4gh_template_id',
+            field=models.CharField(blank=True, default='v1.0', help_text='An ID referring to the GA4GH template used for this experiment (e.g. v1.0).', max_length=200, null=True),
+        ),
+        migrations.AddField(
+            model_name='experiment',
+            name='insert_size',
+            field=models.IntegerField(blank=True, help_text='The size of the DNA fragment inserted into the vector (Integer).', null=True),
+        ),
+        migrations.AddField(
+            model_name='experiment',
+            name='library_description',
+            field=models.TextField(blank=True, help_text='Specific free-text details about library construction.', null=True),
+        ),
+        migrations.AddField(
+            model_name='experiment',
+            name='library_extract_id',
+            field=models.CharField(blank=True, help_text='Optional identifier for a given specific extraction.', max_length=200, null=True),
+        ),
+        migrations.AddField(
+            model_name='experiment',
+            name='library_id',
+            field=models.CharField(blank=True, help_text='The identifier associated with the sequencing library.', max_length=200, null=True),
+        ),
+        migrations.AddField(
+            model_name='experiment',
+            name='protocol_url',
+            field=models.URLField(blank=True, help_text='URL to the sequencing protocol.', max_length=500, null=True),
+        ),
+
+        # transform Lists [] into Dicts
+        migrations.RunPython(convert_list_to_object, reverse_object_to_list),
+
+        migrations.AlterField(
+            model_name='experiment',
+            name='experiment_ontology',
+            field=models.JSONField(blank=True, default=dict, help_text='An ontology term describing the experiment.', validators=[chord_metadata_service.restapi.validators.JsonSchemaValidator(formats=None, schema_ref='ONTOLOGY_CLASS')]),
+        ),
+        migrations.AlterField(
+            model_name='experiment',
+            name='molecule_ontology',
+            field=models.JSONField(blank=True, default=dict, help_text='An ontology term describing a molecular property.', validators=[chord_metadata_service.restapi.validators.JsonSchemaValidator(formats=None, schema_ref='ONTOLOGY_CLASS')]),
+        ),
+    ]