read library selection, add doc

README.md

@@ -67,6 +67,21 @@ Katsu Metadata Service is a service to store epigenomic metadata.
 7. Rest api service handles all generic functionality shared among other services
 
 
+## Schemas
+### Clinical Data
+
+Katsu implements the [Phenopacket V1.0.0](https://phenopacket-schema.readthedocs.io/en/1.0.0/) schema for clinical data.
+
+The schema definition for the phenopacket object is located in [chord_metadata_service/phenopackets/schemas.py](https://github.com/bento-platform/katsu/blob/4ab3c55d6052994ef69b188fb872261c47de24e0/chord_metadata_service/phenopackets/schemas.py#L336).
+
+### Experiments
+
+Katsu's experiments schemas are based on the IHEC [schema](https://github.com/IHEC/ihec-ecosystems/blob/master/docs/metadata/2.0/Ihec_metadata_specification.md#experiments), which is based on EBI/SRA schemas.
+
+The value options for `library_strategy` and `library_selection` are read from [chord_metadata_service/ontologies/xsd/SRA.experiment.xsd.xml](./chord_metadata_service/ontologies/xsd/SRA.experiment.xsd.xml), downloaded from the EBI's [SRA v1.5 database](http://ftp.ebi.ac.uk/pub/databases/ena/doc/xsd/sra_1_5/).
+
+The `SRA.experiment.xsd.xml` file is licensed under Apache License V2.0, the full copyright text is included in the file's header.
+
 ## REST API highlights
 
 * Swagger schema docs can be found 

chord_metadata_service/experiments/migrations/0009_v4_1_0.py

@@ -1,17 +1,38 @@
+from typing import List
 from django.db import migrations
 
+LIB_STRATEGY_CONVERSIONS: List[tuple[str, str]] = [
+    # Convert WES -> WXS ...
+    ("WES", "WXS"),
+    ("Other", "OTHER")
+]
 
-def set_experiment_library_strategy(apps, _schema_editor):
+LIB_SELECTION_CONVERIONS: List[tuple[str, str]] = [
+    ("Random", "RANDOM"),
+    ("Random PCR", "RANDOM PCR"),
+    ("Exome capture", "other"), # 'Exome capture' no longer supported
+    ("Other", "other"),
+]
+
+def set_experiment_library(apps, _schema_editor):
     Experiment = apps.get_model("experiments", "Experiment")
-    for exp in Experiment.objects.filter(library_strategy="WES"):
-        exp.library_strategy = "WXS"
-        exp.save()
+    for (old_val, new_val) in LIB_STRATEGY_CONVERSIONS:
+        # Modify library_strategy if necessary
+        for exp in Experiment.objects.filter(library_strategy=old_val):
+            exp.library_strategy = new_val
+            exp.save()
+
+    for (old_val, new_val) in LIB_SELECTION_CONVERIONS:
+        # Modify library_selection if necessary
+        for exp in Experiment.objects.filter(library_selection=old_val):
+            exp.library_selection = new_val
+            exp.save()
 
 class Migration(migrations.Migration):
     dependencies = [
         ('experiments', '0007_v4_0_0'),
     ]
 
     operations = [
-        migrations.RunPython(set_experiment_library_strategy)
+        migrations.RunPython(set_experiment_library)
     ]

chord_metadata_service/experiments/schemas.py

@@ -1,14 +1,21 @@
 from .descriptions import EXPERIMENT, EXPERIMENT_RESULT, INSTRUMENT
 from chord_metadata_service.restapi.schemas import ONTOLOGY_CLASS_LIST, KEY_VALUE_OBJECT
 from chord_metadata_service.restapi.schema_utils import tag_ids_and_describe
-from chord_metadata_service.ontologies import read_xsd_simple_type_values
-
+from chord_metadata_service.ontologies import read_xsd_simple_type_values, SRA_EXPERIMENT_FILE_NAME
 
 __all__ = ["EXPERIMENT_SCHEMA", "EXPERIMENT_RESULT_SCHEMA", "INSTRUMENT_SCHEMA"]
 
+# Experiment library strategy options are read from the EBI xsd file
 LIBRARY_STRATEGIES = read_xsd_simple_type_values(
-    'chord_metadata_service/ontologies/xsd/SRA.experiment.xsd.xml',
-    'typeLibraryStrategy',
+    SRA_EXPERIMENT_FILE_NAME,
+    "typeLibraryStrategy",
+)
+
+
+# Experiment library selection options are read from the EBI xsd file
+LIBRARY_SELECTION = read_xsd_simple_type_values(
+    SRA_EXPERIMENT_FILE_NAME,
+    "typeLibrarySelection",
 )
 
 EXPERIMENT_RESULT_SCHEMA = tag_ids_and_describe({
@@ -118,7 +125,7 @@
         },
         "library_selection": {
             "type": "string",
-            "enum": ["Random", "PCR", "Random PCR", "RT-PCR", "MF", "Exome capture", "Other"]
+            "enum": LIBRARY_SELECTION
         },
         "library_layout": {
             "type": "string",

chord_metadata_service/ontologies/__init__.py

@@ -1,5 +1,6 @@
-from .utils import read_xsd_simple_type_values
+from .utils import read_xsd_simple_type_values, SRA_EXPERIMENT_FILE_NAME
 
 __all__ = [
     "read_xsd_simple_type_values",
+    "SRA_EXPERIMENT_FILE_NAME",
 ]

chord_metadata_service/ontologies/utils.py

@@ -1,14 +1,21 @@
+import os
 from typing import List
 import xmltodict
+from pathlib import Path
 
+XSD_ONTOLOGIES_PATH = Path("chord_metadata_service/ontologies/xsd/")
+SRA_EXPERIMENT_FILE_NAME = "SRA.experiment.xsd.xml"
 
-def read_xsd_simple_type_values(xsd_file_path: str, type_name: str) -> List[str]:
+
+def read_xsd_simple_type_values(xsd_file_name: str, type_name: str) -> List[str]:
     """Reads an XML Schema Definition (XSD) file and returns a type's values.
     The XSD file is parsed using xmltodict following this spec:
     https://www.xml.com/pub/a/2006/05/31/converting-between-xml-and-json.html
     """
+    xsd_file_path = os.path.join(XSD_ONTOLOGIES_PATH, xsd_file_name)
     with open(xsd_file_path, 'r') as file:
         xsd_file = file.read()
+
     xsd_data = xmltodict.parse(xsd_file, namespaces={'xs': None})
     simple_types = {sp["@name"]: sp for sp in xsd_data["schema"]["simpleType"]}
     target_type = simple_types[type_name]

pyproject.toml

@@ -21,6 +21,7 @@ include = [
     "chord_metadata_service/chord/tests/*.json",
     "chord_metadata_service/dats/*",
     "chord_metadata_service/mcode/tests/*.json",
+    "chord_metadata_service/ontologies/xsd/*.xml",
     "chord_metadata_service/restapi/tests/*.json",
 ]
 repository = "https://github.com/bento-platform/katsu"