mostly compound variants indexes

progenetix · Feb 21, 2024 · 6b9f444 · 6b9f444
1 parent aac4a08
commit 6b9f444
Show file tree

Hide file tree

Showing 5 changed files with 332 additions and 21 deletions.
diff --git a/bin/config/housekeeping.yaml b/bin/config/housekeeping.yaml
@@ -29,9 +29,7 @@ indexed_special_collections:
       db_key: id
 
 indexed_special_dbs:
-
   cellz:
-
     biosamples:
       location:
         db_key: provenance.geo_location.geometry
@@ -40,10 +38,32 @@ indexed_special_dbs:
       location:
         db_key: provenance.geo_location.geometry
         type: 2dsphere
-
+    variants:
+      variantbracketquery:
+        db_key:
+          variant_state.id: 1
+          location.sequence_id: 1
+          location.start: 1
+          location.end: 1
+          info.var_length: 1
+        type: compound
+      variantallelequery:
+        db_key:
+          location.sequence_id: 1
+          location.start: 1
+          sequence: 1
+          reference_sequence: 1
+        type: compound
+      variantrangequery:
+        db_key:
+          location.sequence_id: 1
+          location.start: 1
+          location.end: 1
+          variant_state.id: 1
+          sequence: 1
+        type: compound
 
   progenetix:
-
     biosamples:
       location:
         db_key: provenance.geo_location.geometry
@@ -52,6 +72,30 @@ indexed_special_dbs:
       location:
         db_key: provenance.geo_location.geometry
         type: 2dsphere
+    variants:
+      variantbracketquery:
+        db_key:
+          variant_state.id: 1
+          location.sequence_id: 1
+          location.start: 1
+          location.end: 1
+          info.var_length: 1
+        type: compound
+      variantallelequery:
+        db_key:
+          location.sequence_id: 1
+          location.start: 1
+          sequence: 1
+          reference_sequence: 1
+        type: compound
+      variantrangequery:
+        db_key:
+          location.sequence_id: 1
+          location.start: 1
+          location.end: 1
+          variant_state.id: 1
+          sequence: 1
+        type: compound
 
     publications:
       id:

diff --git a/bin/lib/mongodb_utils.py b/bin/lib/mongodb_utils.py
@@ -13,12 +13,10 @@ def mongodb_update_indexes(ds_id, byc):
     data_db = mongo_client[ds_id]
     coll_names = data_db.list_collection_names()
     for r_t, r_d in b_rt_s.items():
-
         collname = r_d.get("collection", False)
         if collname not in coll_names:
             print(f"¡¡¡ Collection {collname} does not exist in {ds_id} !!!")
             continue
-
         i_coll = data_db[ collname ]
         io_params = dt_m["definitions"][ r_t ]["parameters"]
 
@@ -51,7 +49,6 @@ def mongodb_update_indexes(ds_id, byc):
 ################################################################################
 
 def __index_by_colldef(ds_id, coll_defs):
-
     mongo_client = MongoClient(host=DB_MONGOHOST)
     i_db = mongo_client[ds_id]
     coll_names = i_db.list_collection_names()
@@ -61,14 +58,17 @@ def __index_by_colldef(ds_id, coll_defs):
             continue
 
         i_coll = i_db[ collname ]
-
         for p_k, p_v in io_params.items():
             special = p_v.get("type", "___none___")
             k = p_v["db_key"]
             if "2dsphere" in special:
                 print(f'Creating GEOSPHERE index "{k}" in {collname} from {ds_id}')
                 i_coll.create_index([(k, GEOSPHERE)])
                 pass
+            elif "compound" in special:
+                print(f'Creating compound index "{k}" in {collname} from {ds_id}')
+                i_coll.create_index(k)
+                pass
             else:
                 print(f'Creating index "{k}" in {collname} from {ds_id}')
                 try:
@@ -77,7 +77,3 @@ def __index_by_colldef(ds_id, coll_defs):
                 except Exception:
                     print(f'¡¡¡ Index "{k}" in {collname} from {ds_id} has one with same id !!!')
 
-
-
-
-
diff --git a/bin/pgxProbesPlotter.py b/bin/pgxProbesPlotter.py
@@ -18,9 +18,9 @@
 ################################################################################
 
 def main():
-
     pgx_probes_plotter()
 
+
 ################################################################################
 
 def pgx_probes_plotter():
@@ -34,7 +34,6 @@ def pgx_probes_plotter():
     if not input_file:
         print("No input file specified (-i, --inputfile) => read_probedata_file(filepath, byc):quitting ...")
         exit()
-
     if not "probe" in input_file:
         print('Only probe files are accepted (should have "...probes..." in name).')
         exit()
@@ -43,7 +42,6 @@ def pgx_probes_plotter():
 
     # TODO: method for multiple?
     cs_probes = pb.read_probedata_file(input_file)
-
     plot_data_bundle = {
         "callsets_probes_bundles": [ {"id": "TBD", "probes": cs_probes }]
     }