Merge f3ba9ad into 234ae8d

HISTORY.rst

@@ -2,6 +2,32 @@
 History / Changelog
 ===================
 
+-----------------
+v1.2.3 (anthenea)
+-----------------
+
+End-User Summary
+================
+
+- Create single result row even if multiple clinvar entries (#565).
+- Warning in the case of truncated displayed results (#641).
+- Improving Clinvar filter performance (#635).
+- Fixing clinvar filter (#296).
+  **This will require an import of the updated Clinvar ``20210728c`` data (#296).**
+- Warning in the case of truncated displayed results (#641).
+- Improving Clinvar record aggregation (#640).
+
+Full Change List
+================
+
+- Create single result row even if multiple clinvar entries (#565).
+- Warning in the case of truncated displayed results (#641).
+- Improving Clinvar filter performance (#635).
+  Database indices were missing, assumedly because of a Django ``makemigrations`` bug.
+- Fixing clinvar filter (#296).
+  **This will require an import of the updated Clinvar ``20210728c`` data (#296).**
+- Improving Clinvar record aggregation (#640).
+
 -----------------
 v1.2.2 (anthenea)
 -----------------
@@ -13,7 +39,6 @@ End-User Summary
 - Extra annotations in export completed and tested (#495).
 - Fixed bug where Exac and thousand genomes settings were not shown in frequency tab for GRCh37 (#597).
 - Form template reports error if genomebuild variable is not set (#607).
-- Create single result row even if multiple clinvar entries (#565).
 
 Full Change List
 ================
@@ -22,7 +47,6 @@ Full Change List
 - Fixing issue with sync-from-remote when no remote is defined (#570).
 - Fixed bug where Exac and thousand genomes settings were not shown in frequency tab for GRCh37 (#597).
 - Form template reports error if genomebuild variable is not set (#607).
-- Create single result row even if multiple clinvar entries (#565).
 
 -----------------
 v1.2.1 (anthenea)
@@ -52,8 +76,6 @@ End-User Summary
 - Fixed smallvariant flags filter query (#502).
 - Added flags `segregates`, `doesnt_segregate` and `no_disease_association` to file export (#502).
 - Adding feature to enable and configure link-out to HGMD (#576).
-- Warning in the case of truncated displayed results (#641).
-- Improving Clinvar filter performance (#635).
 
 Full Change List
 ================
@@ -78,9 +100,6 @@ Full Change List
 - Added flags `segregates`, `doesnt_segregate` and `no_disease_association` to file export (#502).
 - Converted not cooperative tooltip to standard title on Filter & Display button (#508).
 - Adding feature to enable and configure link-out to HGMD (#576).
-- Warning in the case of truncated displayed results (#641).
-- Improving Clinvar filter performance (#635).
-  Database indices were missing, assumedly because of a Django ``makemigrations`` bug.
 
 ------
 v1.2.0

Makefile

@@ -47,7 +47,7 @@ celery:
 
 .PHONY: geticons
 geticons:
-	python manage.py geticons -c cil gridicons octicon
+	python manage.py geticons -c cil gridicons octicon icon-park-outline
 
 .PHONY: collectstatic
 collectstatic: geticons

clinvar/migrations/0008_auto_20220829_1132.py

@@ -0,0 +1,28 @@
+# Generated by Django 3.2.12 on 2022-08-29 11:32
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("clinvar", "0007_alter_clinvar_details"),
+    ]
+
+    operations = [
+        migrations.RenameField(
+            model_name="clinvar", old_name="point_rating", new_name="gold_stars",
+        ),
+        migrations.RemoveField(model_name="clinvar", name="pathogenicity_summary",),
+        migrations.AddField(
+            model_name="clinvar", name="origin", field=models.CharField(max_length=32, null=True),
+        ),
+        migrations.AddField(
+            model_name="clinvar", name="rcv", field=models.CharField(max_length=32, null=True),
+        ),
+        migrations.AddField(
+            model_name="clinvar",
+            name="variation_id",
+            field=models.CharField(max_length=32, null=True),
+        ),
+    ]

clinvar/migrations/0009_auto_20220908_1430.py

@@ -0,0 +1,72 @@
+# Generated by Django 3.2.15 on 2022-09-08 14:30
+
+import django.contrib.postgres.fields
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("clinvar", "0008_auto_20220829_1132"),
+    ]
+
+    operations = [
+        migrations.RemoveField(model_name="clinvar", name="gold_stars",),
+        migrations.RemoveField(model_name="clinvar", name="origin",),
+        migrations.RemoveField(model_name="clinvar", name="pathogenicity",),
+        migrations.RemoveField(model_name="clinvar", name="rcv",),
+        migrations.RemoveField(model_name="clinvar", name="review_status",),
+        migrations.RemoveField(model_name="clinvar", name="variation_id",),
+        migrations.AddField(
+            model_name="clinvar",
+            name="clinvar_version",
+            field=models.CharField(max_length=512, null=True),
+        ),
+        migrations.AddField(
+            model_name="clinvar", name="set_type", field=models.CharField(max_length=32, null=True),
+        ),
+        migrations.AddField(
+            model_name="clinvar",
+            name="summary_clinvar_gold_stars",
+            field=models.IntegerField(null=True),
+        ),
+        migrations.AddField(
+            model_name="clinvar",
+            name="summary_clinvar_pathogenicity",
+            field=django.contrib.postgres.fields.ArrayField(
+                base_field=models.CharField(max_length=32), null=True, size=None
+            ),
+        ),
+        migrations.AddField(
+            model_name="clinvar",
+            name="summary_clinvar_pathogenicity_label",
+            field=models.CharField(max_length=512, null=True),
+        ),
+        migrations.AddField(
+            model_name="clinvar",
+            name="summary_clinvar_review_status_label",
+            field=models.CharField(max_length=512, null=True),
+        ),
+        migrations.AddField(
+            model_name="clinvar",
+            name="summary_paranoid_gold_stars",
+            field=models.IntegerField(null=True),
+        ),
+        migrations.AddField(
+            model_name="clinvar",
+            name="summary_paranoid_pathogenicity",
+            field=django.contrib.postgres.fields.ArrayField(
+                base_field=models.CharField(max_length=32), null=True, size=None
+            ),
+        ),
+        migrations.AddField(
+            model_name="clinvar",
+            name="summary_paranoid_pathogenicity_label",
+            field=models.CharField(max_length=512, null=True),
+        ),
+        migrations.AddField(
+            model_name="clinvar",
+            name="summary_paranoid_review_status_label",
+            field=models.CharField(max_length=512, null=True),
+        ),
+    ]

clinvar/migrations/0010_clinvarpathogenicgenes.py

@@ -0,0 +1,54 @@
+# -*- coding: utf-8 -*-
+# Generated by Django 1.11.20 on 2019-04-16 14:00
+from __future__ import unicode_literals
+
+from django.conf import settings
+from django.db import migrations
+
+operations = []
+
+
+if not settings.IS_TESTING:
+    operations.append(
+        migrations.RunSQL(
+            """
+            DROP MATERIALIZED VIEW IF EXISTS clinvar_clinvarpathogenicgenes;
+
+            CREATE MATERIALIZED VIEW clinvar_clinvarpathogenicgenes
+            AS
+                SELECT
+                    ROW_NUMBER() OVER () AS id,
+                    symbol,
+                    geneinfo_hgnc.ensembl_gene_id,
+                    geneinfo_refseqtohgnc.entrez_id,
+                    pathogenic_count,
+                    likely_pathogenic_count
+                FROM (
+                    SELECT
+                        unnest(symbols) as symbol,
+                        SUM(CASE WHEN summary_clinvar_pathogenicity @> ARRAY['pathogenic'::varchar] THEN 1 ELSE 0 END) AS pathogenic_count,
+                        SUM(CASE WHEN summary_clinvar_pathogenicity @> ARRAY['likely pathogenic'::varchar] THEN 1 ELSE 0 END) AS likely_pathogenic_count
+                    FROM clinvar_clinvar
+                    GROUP BY symbol
+                    HAVING
+                        SUM(CASE WHEN summary_clinvar_pathogenicity @> ARRAY['pathogenic'::varchar] THEN 1 ELSE 0 END) > 0 OR
+                        SUM(CASE WHEN summary_clinvar_pathogenicity @> ARRAY['likely pathogenic'::varchar] THEN 1 ELSE 0 END) > 0
+                ) AS clinvar_pathogenic_counts
+                LEFT OUTER JOIN geneinfo_hgnc USING (symbol)
+                LEFT OUTER JOIN geneinfo_refseqtohgnc USING (hgnc_id)
+            WITH DATA;
+            """,
+            """
+            DROP MATERIALIZED VIEW clinvar_clinvarpathogenicgenes;
+            """,
+        )
+    )
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("clinvar", "0009_auto_20220908_1430"),
+        ("geneinfo", "0005_auto_20190104_1554"),
+        ("geneinfo", "0007_refseqtohgnc"),
+    ]
+    operations = operations

clinvar/models.py

@@ -28,6 +28,10 @@ class Clinvar(models.Model):
     reference = models.CharField(max_length=512)
     #: Variant coordinates - alternative
     alternative = models.CharField(max_length=512)
+    #: ClinVar version
+    clinvar_version = models.CharField(max_length=512, null=True)
+    #: Type of the set
+    set_type = models.CharField(max_length=32, null=True)
     #: Type of variation
     variation_type = models.CharField(max_length=16)
     #: The symbols.
@@ -36,14 +40,26 @@ class Clinvar(models.Model):
     hgnc_ids = ArrayField(base_field=models.CharField(max_length=32), size=None)
     #: The variant accession
     vcv = models.CharField(max_length=32)
-    #: The point_rating
-    point_rating = models.IntegerField()
-    #: The pathogenicity.
-    pathogenicity = models.CharField(max_length=128)
-    #: The review_status.
-    review_status = models.CharField(max_length=128)
-    #: The pathogenicity summary.
-    pathogenicity_summary = models.CharField(max_length=128)
+    #: Summary (ClinVar style) - review status label
+    summary_clinvar_review_status_label = models.CharField(max_length=512, null=True)
+    #: Summary (ClinVar style) - pathogenicity label
+    summary_clinvar_pathogenicity_label = models.CharField(max_length=512, null=True)
+    #: Summary (ClinVar style) - pathogenicities
+    summary_clinvar_pathogenicity = ArrayField(
+        base_field=models.CharField(max_length=32), size=None, null=True
+    )
+    #: Summary (ClinVar style) - gold stars for VCV
+    summary_clinvar_gold_stars = models.IntegerField(null=True)
+    #: Summary (paranoid style) - review status label
+    summary_paranoid_review_status_label = models.CharField(max_length=512, null=True)
+    #: Summary (paranoid style) - pathogenicity label
+    summary_paranoid_pathogenicity_label = models.CharField(max_length=512, null=True)
+    #: Summary (paranoid style) - pathogenicities
+    summary_paranoid_pathogenicity = ArrayField(
+        base_field=models.CharField(max_length=32), size=None, null=True
+    )
+    #: Summary (paranoid style) - gold stars for VCV
+    summary_paranoid_gold_stars = models.IntegerField(null=True)
     #: The structured Details information.
     details = JSONField()
 

clinvar/templatetags/clinvar_tags.py

@@ -0,0 +1,27 @@
+from django import template
+
+register = template.Library()
+
+PATHO_MAP = {
+    "benign": -2,
+    "likely benign": -1,
+    "uncertain significance": 0,
+    "likely pathogenic": 1,
+    "pathogenic": 2,
+}
+
+
+@register.filter
+def clinvar_patho_rank(entry):
+    if entry.summary_pathogenicity_label:
+        return PATHO_MAP.get(entry.summary_pathogenicity_label, -1) + 1
+    else:
+        return 0
+
+
+@register.filter
+def clinvar_gold_stars(entry):
+    if entry.summary_gold_stars:
+        return entry.summary_gold_stars + 1
+    else:
+        return 0

clinvar/tests/factories.py

@@ -21,14 +21,20 @@ class Meta:
     bin = 0
     reference = factory.Iterator("ACGT")
     alternative = factory.Iterator("CGTA")
+    clinvar_version = "99991122.1"
     variation_type = "snv"
+    set_type = "variant"
     symbols = factory.Sequence(lambda n: ["SYMBOL%d" % n])
     hgnc_ids = factory.Sequence(lambda n: ["HGNC:%d" % n])
     vcv = factory.Sequence(lambda n: "VCV%d" % (12345 + n))
-    point_rating = factory.Iterator([0, 1, 2, 3])
-    pathogenicity = ""
-    review_status = "practice guideline"
-    pathogenicity_summary = "uncertain significance"
+    summary_clinvar_review_status_label = "criteria provided, single committer"
+    summary_clinvar_pathogenicity_label = "likely pathogenic"
+    summary_clinvar_pathogenicity = ["likely pathogenic"]
+    summary_clinvar_gold_stars = 1
+    summary_paranoid_review_status_label = "criteria provided, single committer"
+    summary_paranoid_pathogenicity_label = "likely pathogenic"
+    summary_paranoid_pathogenicity = ["likely pathogenic"]
+    summary_paranoid_gold_stars = 1
     details = []
 
     @factory.post_generation

docker/Dockerfile

@@ -112,7 +112,7 @@ RUN cd /usr/src/app && \
     DJANGO_SECRET_KEY=for-build-only \
     DJANGO_SETTINGS_MODULE=config.settings.production \
     DATABASE_URL=postgres://sodar:sodar@fake/sodar \
-    python manage.py geticons -c mdi bi cil fa-regular fa-solid fluent gridicons octicon
+    python manage.py geticons -c mdi bi cil fa-regular fa-solid fluent gridicons octicon icon-park-outline
 
 # Prepare static files
 RUN cd /usr/src/app && \