Merge pull request #179 from ProteinsWebTeam/dev

Merge dev into master

Author: apolignano

config/elastic_mapping.json

@@ -81,6 +81,9 @@
       "protein_af_score": {
         "type": "float"
       },
+      "protein_bfvd_score": {
+        "type": "float"
+      },
       "proteome_acc": {
         "type": "keyword"
       },
@@ -105,6 +108,12 @@
       "structure_protein_acc": {
         "type": "keyword"
       },
+      "structure_protein_db": {
+        "type": "keyword"
+      },
+      "structure_protein_length": {
+        "type": "long"
+      },
       "structure_protein_locations": {
         "type": "object",
         "enabled": false

docs/README.md

@@ -21,8 +21,7 @@
 def get_uniprot_accessions(source_db, query):
     api_url = "https://www.ebi.ac.uk/interpro/api"
     url = f"{api_url}/protein/UniProt/entry/{source_db}/{query}/?"
-    url += urlencode({"has_model": True, "page_size": 100})
-
+    url += urlencode({"with": "alphafold", "page_size": 100})
     accessions = []
 
     while True:
@@ -38,10 +37,9 @@ def get_uniprot_accessions(source_db, query):
 
     return accessions
 
-
 def get_mem_db(query):
     url = f"https://www.ebi.ac.uk/interpro/api/utils/accession/{query}"
-    
+
     with urlopen(url) as res:
         if res.status != 200:
             sys.stderr.write(f"error: no results found for {query}\n")
@@ -53,8 +51,7 @@ def get_mem_db(query):
             sys.stderr.write(f"error: {query} is not an entry\n")
 
         return obj["source_database"]
-
-
+    
 def download_af_pdb(accession, outdir):
     url = f"https://alphafold.ebi.ac.uk/api/prediction/{accession}"
     with urlopen(url) as res:
@@ -69,8 +66,8 @@ def download_af_pdb(accession, outdir):
         for chunk in res:
             fh.write(chunk)
 
-
 def main():
+
     query = sys.argv[1]
     outdir = sys.argv[2]
 

docs/examples/fetch-alphafold-for-entry.py

@@ -196,10 +196,18 @@ Information on member database signatures integrated/unintegrated in InterPro en
 | `filter_by_entry=< InterPro accession >` | x                               | Selected taxon hierarchy and counters for the InterPro entry accession specified                      | https://www.ebi.ac.uk:443/interpro/api/taxonomy/uniprot/1?filter_by_entry=IPR001165   |
 | `filter_by_entry_db=< db name >`         | x                               | Selected taxon hierarchy and counters for the database name specified (e.g. interpro, pfam, smart...) | https://www.ebi.ac.uk:443/interpro/api/taxonomy/uniprot/1?filter_by_entry_db=interpro |
 
-## /api/protein/uniprot/entry/InterPro/< _interpro accession_ >
+## /api/protein/uniprot/entry/< _source database_ >/< _interpro accession_ >
 
 Proteins with an AlphaFold model.
 
 | Modifier                 | Compatible with other modifiers | Data returned                                                                         | Example                                                                                         |
 |--------------------------|---------------------------------|---------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
-| `has_model=[true,false]` | x                               | List of proteins with/without an AlphaFold prediction for the InterPro entry selected | https://www.ebi.ac.uk:443/interpro/api/protein/uniprot/entry/InterPro/IPR000001/?has_model=true |
+| `has_model=[true,false]` | x                               | List of proteins with/without an AlphaFold prediction for the <_ source database _> entry selected | https://www.ebi.ac.uk:443/interpro/api/protein/uniprot/entry/InterPro/IPR000001/?has_model=true |
+
+
+Proteins with an AlphaFold or BFVD model.
+
+| Modifier                 | Compatible with other modifiers | Data returned                                                                         | Example                                                                                         |
+|--------------------------|---------------------------------|---------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
+| `with=[alphafold,bfvd]` | x                               | List of proteins with an AlphaFold prediction or a BFVD prediction for the <_ source database _> entry selected | https://www.ebi.ac.uk:443/interpro/api/protein/uniprot/entry/InterPro/IPR000001/?with=alphafold|
+

docs/modifiers.md

@@ -1,6 +1,6 @@
 # remember to check the version is compatible with python 3.8
-Django==4.2.13
-djangorestframework==3.15.1
+Django==4.2.19
+djangorestframework==3.15.2
 PyYAML==6.0
 jsonfield2==4.0.0.post0
 pymysql==1.1.1

requirements.txt

@@ -0,0 +1,44 @@
+# Generated by Django 4.2.19 on 2025-02-24 14:11
+
+from django.db import migrations, models
+import django.db.models.deletion
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("webfront", "0034_set_wikipedia"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="InterProNMatches",
+            fields=[
+                ("match_id", models.AutoField(primary_key=True, serialize=False)),
+                ("in_interpro", models.BooleanField(db_column="in_interpro")),
+                ("is_preferred", models.BooleanField(db_column="is_preferred")),
+                ("locations", models.JSONField()),
+                (
+                    "entry",
+                    models.ForeignKey(
+                        db_column="entry_acc",
+                        null=True,
+                        on_delete=django.db.models.deletion.SET_NULL,
+                        to="webfront.entry",
+                    ),
+                ),
+                (
+                    "protein_acc",
+                    models.ForeignKey(
+                        db_column="protein_acc",
+                        null=True,
+                        on_delete=django.db.models.deletion.SET_NULL,
+                        to="webfront.protein",
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "webfront_interpro_n",
+            },
+        ),
+    ]

webfront/migrations/0035_interpronmatches.py

@@ -0,0 +1,39 @@
+# Generated by Django 4.2.19 on 2025-02-24 14:14
+
+from django.db import migrations
+import jsonfield.fields
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("webfront", "0035_interpronmatches"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="entry",
+            name="overlaps_with",
+            field=jsonfield.fields.JSONField(default=list),
+        ),
+        migrations.AlterField(
+            model_name="protein",
+            name="structure",
+            field=jsonfield.fields.JSONField(default=dict, null=True),
+        ),
+        migrations.AlterField(
+            model_name="set",
+            name="authors",
+            field=jsonfield.fields.JSONField(default=list),
+        ),
+        migrations.AlterField(
+            model_name="set",
+            name="literature",
+            field=jsonfield.fields.JSONField(default=list),
+        ),
+        migrations.AlterField(
+            model_name="set",
+            name="wikipedia",
+            field=jsonfield.fields.JSONField(default=list),
+        ),
+    ]

webfront/migrations/0036_default_value_lists_dicts.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.13 on 2025-03-11 09:46
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('webfront', '0036_default_value_lists_dicts'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='protein',
+            name='in_bfvd',
+            field=models.BooleanField(default=False),
+        ),
+    ]

webfront/migrations/0037_protein_in_bfvd.py

@@ -35,7 +35,7 @@ class Entry(models.Model):
     hierarchy = JSONField(null=True)
     cross_references = JSONField(null=True)
     entry_date = models.DateTimeField(null=True)
-    overlaps_with = JSONField(default=[])
+    overlaps_with = JSONField(default=list)
     is_public = models.BooleanField(default=False)
     deletion_date = models.DateTimeField(null=True)
     counts = JSONField(null=True)
@@ -86,9 +86,10 @@ class Protein(models.Model):
     source_database = models.CharField(
         max_length=20, default="unreviewed", db_index=True
     )
-    structure = JSONField(default={}, null=True)
+    structure = JSONField(default=dict, null=True)
     is_fragment = models.BooleanField(default=False)
     in_alphafold = models.BooleanField(default=False)
+    in_bfvd = models.BooleanField(default=False)
     tax_id = models.CharField(max_length=20, null=False, default="")
     ida_id = models.CharField(max_length=40, null=True)
     ida = models.TextField(null=True)
@@ -267,9 +268,9 @@ class Set(models.Model):
     source_database = models.CharField(max_length=20, db_index=True)
     relationships = JSONField(null=True)
     counts = JSONField(null=True)
-    authors = JSONField(null=True)
-    literature = JSONField(null=True)
-    wikipedia = JSONField(null=True)
+    authors = JSONField(default=list)
+    literature = JSONField(default=list)
+    wikipedia = JSONField(default=list)
 
 
 class Release_Note(models.Model):
@@ -296,7 +297,9 @@ class InterProNMatches(models.Model):
     entry = models.ForeignKey(
         Entry, db_column="entry_acc", on_delete=models.SET_NULL, null=True
     )
+    in_interpro = models.BooleanField(db_column="in_interpro", null=False)
+    is_preferred = models.BooleanField(db_column="is_preferred", null=False)
     locations = models.JSONField()
 
     class Meta:
-        db_table = "webfront_interpro_n"
+        db_table = "webfront_interpro_n"

webfront/models/interpro_new.py

@@ -216,9 +216,19 @@ def tune_counter_facet_for_entry(self, facet, endpoint, extra_counters):
 
     def tune_counter_facet_for_protein(self, facet, endpoint, extra_counters):
         if endpoint == "protein":
+            if self.queryset_manager.main_endpoint == "structure":
+                acc_field = "structure_protein_acc"
+                db_field = "structure_protein_db"
+            else:
+                acc_field = "protein_acc"
+                db_field = "protein_db"
+
+            facet["aggs"]["databases"]["terms"]["field"] = db_field
+            facet["aggs"]["databases"]["aggs"]["unique"]["cardinality"]["field"] = acc_field
+
             facet["aggs"]["uniprot"] = {
-                "filter": {"exists": {"field": "protein_acc"}},
-                "aggs": {"unique": {"cardinality": {"field": "protein_acc"}}},
+                "filter": {"exists": {"field": acc_field}},
+                "aggs": {"unique": {"cardinality": {"field": acc_field}}},
             }
             self.add_extra_counters(facet, "uniprot", extra_counters)
 
@@ -310,19 +320,26 @@ def get_group_obj_of_field_by_query(
 
         return output
 
+    def get_cardinality_field(self, endpoint):
+        filters = self.queryset_manager.filters
+        if endpoint == "protein" and filters.get("structure") and not filters.get("entry"):
+            return "structure_protein_acc"
+
+        return endpoint + "_acc"
+
     def get_list_of_endpoint(self, endpoint, query=None, rows=10, start=0, cursor=None):
         should_keep_elastic_order = False
         qs = self.queryset_manager.get_searcher_query() if query is None else query
         if qs == "":
             qs = "*:*"
         facet = {
             "aggs": {
-                "ngroups": {"cardinality": {"field": endpoint + "_acc"}},
+                "ngroups": {"cardinality": {"field": self.get_cardinality_field(endpoint)}},
                 "groups": {
                     "composite": {
                         "size": rows,
                         "sources": [
-                            {"source": {"terms": {"field": "{}_acc".format(endpoint)}}}
+                            {"source": {"terms": {"field": self.get_cardinality_field(endpoint)}}}
                         ],
                     }
                 },