add ids to export

hawc/apps/animal/exports.py

@@ -109,10 +109,15 @@ def _get_header_row(self):
 
     def _get_data_rows(self):
         rows = []
+        identifiers_df = Study.identifiers_df(self.queryset, "animal_group__experiment__study_id")
         for obj in self.queryset:
             ser = obj.get_json(json_encode=False)
             row = []
-            row.extend(Study.flat_complete_data_row(ser["animal_group"]["experiment"]["study"]))
+            row.extend(
+                Study.flat_complete_data_row(
+                    ser["animal_group"]["experiment"]["study"], identifiers_df
+                )
+            )
             row.extend(models.Experiment.flat_complete_data_row(ser["animal_group"]["experiment"]))
             row.extend(models.AnimalGroup.flat_complete_data_row(ser["animal_group"]))
             ser_dosing_regime = ser["animal_group"]["dosing_regime"]

hawc/apps/epi/exports.py

@@ -19,10 +19,13 @@ def _get_header_row(self):
 
     def _get_data_rows(self):
         rows = []
+        identifiers_df = Study.identifiers_df(self.queryset, "study_population__study_id")
         for obj in self.queryset:
             ser = obj.get_json(json_encode=False)
             row = []
-            row.extend(Study.flat_complete_data_row(ser["study_population"]["study"]))
+            row.extend(
+                Study.flat_complete_data_row(ser["study_population"]["study"], identifiers_df)
+            )
             row.extend(models.StudyPopulation.flat_complete_data_row(ser["study_population"]))
             row.extend(models.Outcome.flat_complete_data_row(ser))
             for res in ser["results"]:

hawc/apps/epimeta/exports.py

@@ -19,10 +19,11 @@ def _get_header_row(self):
 
     def _get_data_rows(self):
         rows = []
+        identifiers_df = Study.identifiers_df(self.queryset, "protocol__study_id")
         for obj in self.queryset:
             ser = obj.get_json(json_encode=False)
             row = []
-            row.extend(Study.flat_complete_data_row(ser["protocol"]["study"]))
+            row.extend(Study.flat_complete_data_row(ser["protocol"]["study"], identifiers_df))
             row.extend(models.MetaProtocol.flat_complete_data_row(ser["protocol"]))
             row.extend(models.MetaResult.flat_complete_data_row(ser))
 

hawc/apps/epiv2/exports.py

@@ -24,9 +24,14 @@ def _get_header_row(self):
 
     def _get_data_rows(self):
         rows = []
+        identifiers_df = Study.identifiers_df(self.queryset, "design__study_id")
         for obj in self.queryset:
             row = []
-            row.extend(Study.flat_complete_data_row(obj.design.study.get_json(json_encode=False)))
+            row.extend(
+                Study.flat_complete_data_row(
+                    obj.design.study.get_json(json_encode=False), identifiers_df
+                )
+            )
             row.extend(obj.design.flat_complete_data_row())
             row.extend(obj.exposure_level.chemical.flat_complete_data_row())
             row.extend(obj.exposure_level.exposure_measurement.flat_complete_data_row())

hawc/apps/invitro/exports.py

@@ -4,6 +4,7 @@
 
 from ..common.helper import FlatFileExporter
 from ..materialized.models import FinalRiskOfBiasScore
+from ..study.models import Study
 
 
 def getDose(ser, tag):
@@ -36,6 +37,9 @@ def _get_header_row(self):
 
         header = [
             "study id",
+            "study hero_id",
+            "study pubmed_id",
+            "study doi",
             "study name",
             "study identifier",
             "study published",
@@ -107,6 +111,8 @@ def _get_header_row(self):
     def _get_data_rows(self):
         rows = []
 
+        identifiers_df = Study.identifiers_df(self.queryset, "experiment__study_id")
+
         for obj in self.queryset:
             ser = obj.get_json(json_encode=False)
 
@@ -129,14 +135,17 @@ def _get_data_rows(self):
             bm_types = [bm["benchmark"] for bm in ser["benchmarks"]]
             bm_values = [bm["value"] for bm in ser["benchmarks"]]
 
+            study_id = ser["experiment"]["study"]["id"]
             row = [
-                ser["experiment"]["study"]["id"],
+                study_id,
+                identifiers_df["hero_id"].get(study_id),
+                identifiers_df["pubmed_id"].get(study_id),
+                identifiers_df["doi"].get(study_id),
                 ser["experiment"]["study"]["short_citation"],
                 ser["experiment"]["study"]["study_identifier"],
                 ser["experiment"]["study"]["published"],
             ]
 
-            study_id = ser["experiment"]["study"]["id"]
             study_robs = [
                 self.rob_data[(study_id, metric_id)] for metric_id in self.rob_headers.keys()
             ]

hawc/apps/lit/serializers.py

@@ -102,15 +102,12 @@ def create(self, validated_data):
 
 
 class IdentifiersSerializer(serializers.ModelSerializer):
-    def to_representation(self, instance):
-        ret = super().to_representation(instance)
-        ret["database"] = instance.get_database_display()
-        ret["url"] = instance.get_url()
-        return ret
+    database = serializers.CharField(source="get_database_display")
+    url = serializers.CharField(source="get_url")
 
     class Meta:
         model = models.Identifiers
-        fields = "__all__"
+        fields = ["id", "unique_id", "database", "url"]
 
 
 class ReferenceTagsSerializer(serializers.ModelSerializer):

hawc/apps/riskofbias/api.py

@@ -47,7 +47,6 @@ class RiskOfBiasAssessmentViewset(
     lookup_value_regex = re_digits
 
     def get_queryset(self):
-
         perms = self.get_obj_perms()
         if not perms["edit"]:
             return self.model.objects.published(self.assessment)

hawc/apps/study/models.py

@@ -1,6 +1,8 @@
 import logging
 import os
+from typing import Optional
 
+import pandas as pd
 from django.apps import apps
 from django.core.exceptions import MultipleObjectsReturned, ObjectDoesNotExist
 from django.db import models
@@ -197,6 +199,9 @@ def get_study_type(self):
     def flat_complete_header_row():
         return (
             "study-id",
+            "study-hero_id",
+            "study-pubmed_id",
+            "study-doi",
             "study-url",
             "study-short_citation",
             "study-full_citation",
@@ -216,9 +221,19 @@ def flat_complete_header_row():
         )
 
     @staticmethod
-    def flat_complete_data_row(ser):
+    def flat_complete_data_row(ser, identifiers_df: Optional[pd.DataFrame] = None) -> tuple:
+        try:
+            ident_row = (
+                identifiers_df.loc[ser["id"]] if isinstance(identifiers_df, pd.DataFrame) else None
+            )
+        except KeyError:
+            ident_row = None
         return (
             ser["id"],
+            # IDs can come from identifiers data frame if exists, else check study serializer
+            ident_row.hero_id if ident_row is not None else ser.get("hero_id", None),
+            ident_row.pubmed_id if ident_row is not None else ser.get("pubmed_id", None),
+            ident_row.doi if ident_row is not None else ser.get("doi", None),
             ser["url"],
             ser["short_citation"],
             ser["full_citation"],
@@ -237,6 +252,22 @@ def flat_complete_data_row(ser):
             ser["published"],
         )
 
+    @classmethod
+    def identifiers_df(cls, qs: models.QuerySet, relation: str) -> pd.DataFrame:
+        """Returns a data frame with reference identifiers for each study in the QuerySet
+
+        Args:
+            qs (models.QuerySet): A QuerySet of an model with a relation to the study
+            relation (str): The relation string to the `Study.study_id` for this QuerySet
+
+        Returns:
+            pd.DataFrame: A data frame an index of study/reference id, and columns for identifiers
+        """
+        study_ids = qs.values_list(relation, flat=True)
+        studies = cls.objects.filter(id__in=study_ids)
+        identifiers_df = Reference.objects.identifiers_dataframe(studies)
+        return identifiers_df.set_index("reference_id")
+
     @classmethod
     def delete_caches(cls, ids):
         SerializerHelper.delete_caches(cls, ids)

hawc/apps/study/serializers.py

@@ -1,3 +1,5 @@
+from typing import Optional, Union
+
 from django.core.exceptions import ObjectDoesNotExist, ValidationError
 from django.db import transaction
 from rest_framework import exceptions, serializers
@@ -83,6 +85,21 @@ class VerboseStudySerializer(StudySerializer):
     identifiers = IdentifiersSerializer(many=True)
     tags = ReferenceTagsSerializer()
 
+    def _get_identifier(
+        self, identifiers: list, key: str, to_int: bool
+    ) -> Optional[Union[int, str]]:
+        for identifier in identifiers:
+            if identifier["database"] == key:
+                value = identifier["unique_id"]
+                return int(value) if to_int else value
+
+    def to_representation(self, instance):
+        ret = super().to_representation(instance)
+        ret["hero_id"] = self._get_identifier(ret["identifiers"], "HERO", True)
+        ret["pubmed_id"] = self._get_identifier(ret["identifiers"], "PubMed", True)
+        ret["doi"] = self._get_identifier(ret["identifiers"], "DOI", False)
+        return ret
+
     def get_riskofbiases(self, study):
         return FinalRiskOfBiasSerializer(study.get_final_qs(), many=True).data