Add the first production-ready version of the external project overview

backend/fms_core/serializers.py

@@ -103,6 +103,8 @@
     "UserSerializer",
     "GroupSerializer",
     "ProjectSerializer",
+    "ParentProjectSerializer",
+    "ParentProjectReadsetSerializer",
     "ProjectExportSerializer",
     "SequenceSerializer",
     "TaxonSerializer",
@@ -123,7 +125,7 @@
     "SampleIdentityMatchSerializer",
     "SampleIdentitySerializer",
     "ProfileSerializer",
-    "DerivedSampleSerializer"
+    "DerivedSampleSerializer",
     "FreezemanPermissionSerializer",
 ]
 
@@ -616,6 +618,49 @@ class Meta:
         fields = '__all__'
 
 
+class ParentProjectReadsetSerializer(serializers.Serializer):
+    id = serializers.IntegerField()
+    name = serializers.CharField()
+    readset_sample_name = serializers.CharField()
+    biosample_id = serializers.IntegerField(allow_null=True)
+    external_id = serializers.CharField()
+    run_name = serializers.CharField()
+    lane = serializers.IntegerField()
+    reference_genome_id = serializers.IntegerField(allow_null=True,)
+    reference_genome_assembly_name = serializers.CharField(allow_null=True,)
+    sequencing_index_name = serializers.CharField(allow_null=True)
+    run_start_date = serializers.DateField()
+    alias = serializers.CharField(allow_null=True)
+    cohort = serializers.CharField(allow_blank=True,allow_null=True,)
+    library_type = serializers.CharField(allow_null=True,)
+    container_barcodes = serializers.ListField(child=serializers.CharField(allow_null=True),allow_empty=True,)
+    number_of_reads = serializers.IntegerField(allow_null=True,)
+    number_of_bases = serializers.IntegerField(allow_null=True,)
+    average_quality = serializers.DecimalField(
+        max_digits=40,
+        decimal_places=20,
+        allow_null=True,
+    )
+
+    pf_reads_aligned = serializers.DecimalField(
+        max_digits=40,
+        decimal_places=20,
+        allow_null=True,
+    )
+
+    duplicate_aligned = serializers.DecimalField(
+        max_digits=40,
+        decimal_places=20,
+        allow_null=True,
+    )
+    readset_files = serializers.ListField(
+        child=serializers.DictField(),
+        required=False,
+    )
+    run_validation_status = serializers.IntegerField(allow_null=True,)
+
+
+
 class IndexSetSerializer(serializers.ModelSerializer):
     index_count = serializers.SerializerMethodField()
 

backend/fms_core/viewsets/parent_project.py

@@ -1,9 +1,15 @@
+from django.db.models import F, Max, Q, Value
+from django.db.models.functions import JSONObject
+from django.contrib.postgres.aggregates import ArrayAgg
+
 from rest_framework import viewsets
+from rest_framework.decorators import action
 from rest_framework.permissions import IsAuthenticated
+from rest_framework.response import Response
 
-from fms_core.models import ParentProject
-from fms_core.serializers import ParentProjectSerializer
 
+from fms_core.models import ParentProject, Readset
+from fms_core.serializers import ParentProjectReadsetSerializer, ParentProjectSerializer
 from ._utils import _list_keys
 from ._constants import _parent_project_filterset_fields
 
@@ -21,4 +27,108 @@ class ParentProjectViewSet(viewsets.ModelViewSet):
         **_parent_project_filterset_fields,
     }
 
-    ordering = ["external_id"]
+    ordering = ["external_id"]
+
+    def _get_readsets_queryset(self, parent_project : ParentProject):
+
+        PARENT_PROJECT_READSET_ORDERING = [
+            "dataset__experiment_run__start_date",
+            "dataset__experiment_run__name",
+            "dataset__lane",
+            "id",
+        ]
+
+        PARENT_PROJECT_READSET_VALUE_FIELDS = [
+            "id",
+            "name",
+            "average_quality",
+            "pf_reads_aligned",
+            "duplicate_aligned",
+            "number_of_reads",
+            "number_of_bases",
+            "readset_files",
+            "container_barcodes",
+            "run_validation_status",
+        ]
+
+        PARENT_PROJECT_READSET_VALUE_ALIASES = {
+            "readset_sample_name": F("sample_name"),
+            "biosample_id": F("derived_sample__biosample_id"),
+            "external_id": F("dataset__project__parent_project__external_id"),
+            "run_name": F("dataset__experiment_run__name"),
+            "lane": F("dataset__lane"),
+            "reference_genome_id": F("derived_sample__biosample__individual__reference_genome_id"),
+            "reference_genome_assembly_name": F("derived_sample__biosample__individual__reference_genome__assembly_name"),
+            "sequencing_index_name": F("derived_sample__library__index__name"),
+            "run_validation_status": F("validation_status"),
+            "run_start_date": F("dataset__experiment_run__start_date"),
+            "alias": F("derived_sample__biosample__alias"),
+            "cohort": F("derived_sample__biosample__individual__cohort"),
+            "library_type": F("derived_sample__library__library_type__name"),
+
+        }
+
+        return (
+            Readset.objects.filter(
+                dataset__project__parent_project=parent_project,
+            )
+            .annotate(
+                average_quality=Max(
+                    "metrics__value_numeric",
+                    filter=Q(metrics__name="avg_qual"),
+                ),
+                pf_reads_aligned=Max(
+                    "metrics__value_numeric",
+                    filter=Q(metrics__name="pf_read_alignment_rate"),
+                ),
+                duplicate_aligned=Max(
+                    "metrics__value_numeric",
+                    filter=Q(metrics__name="duplicate_rate"),
+                ),
+                number_of_reads=Max(
+                    "metrics__value_numeric",
+                    filter=Q(metrics__name="nb_reads"),
+                ),
+                number_of_bases=Max(
+                    "metrics__value_numeric",
+                    filter=Q(metrics__name="yield"),
+                ),
+                readset_files=ArrayAgg(
+                    JSONObject(
+                        file_path=F("files__file_path"),
+                        size=F("files__size"),
+                    ),
+                    filter=Q(files__isnull=False),
+                    distinct=True,
+                    default=Value([]),
+                ),
+                container_barcodes=ArrayAgg(
+                    "derived_sample__derived_by_samples__sample__container__barcode",
+                    distinct=True,
+                ),
+            )
+            .order_by(*PARENT_PROJECT_READSET_ORDERING)
+            .values(
+                *PARENT_PROJECT_READSET_VALUE_FIELDS,
+                **PARENT_PROJECT_READSET_VALUE_ALIASES,
+            )
+
+        )
+
+
+    @action(detail=True, methods=["get"], url_path="readsets")
+    def overview_readsets(self, request, pk=None):
+        parent_project = self.get_object()
+
+        queryset = self._get_readsets_queryset(parent_project)
+        page = self.paginate_queryset(queryset)
+
+        if page is not None:
+            serializer = ParentProjectReadsetSerializer(page, many=True,)
+            return self.get_paginated_response(serializer.data)
+
+        else:
+
+            serializer = ParentProjectReadsetSerializer(queryset, many=True,)
+            return Response(serializer.data)
+