queriesTester and multi_variants modification

beaconplusWeb/src/components/searchResults/DatasetResultBox.js

@@ -179,7 +179,7 @@ export function DatasetResultBox({ data: responseSet, responseMeta, query }) {
           ) : null}
         </div>
         <div className="column is-one-third">
-          {info.counts.variants > 0 ? (
+          {info.counts.variants > 0 && query.referenceName ? (
             <div>
               <UCSCRegion query={query} />
             </div>

beaconplusWeb/src/config/beaconSearchParameters.yaml

@@ -23,7 +23,7 @@ parameters:
   geneId:
     label: Gene Symbol
     placeholder: MYCN
-    infoText: One or more comma concatenated gene symbols (HUGO), e.g. "TP53,CDKN2A".
+    infoText: A gene symbol (HUGO), e.g. "TP53" or "CDKN2A".
     isHidden: true
   aminoacidChange:
     label: Aminoacid alteration
@@ -209,7 +209,8 @@ parameters:
       create bracket requests or (experimentally) fusion requests (where the 2nd
       region denotes the "mateName" chromosome of the fusion partner).
       Example here would be the use of "8q24,14q32" to search for fusion events
-      involving MYC and IGH (_i.e._ the typical "Burkitt lymphoma fusion").
+      involving MYC and IGH (_i.e._ the typical "Burkitt lymphoma fusion").</br>
+      This is *not* a standard Beacon option.
     isHidden: true
   variantQueryDigests:
     label: Variation Shorthand(s)
@@ -220,7 +221,8 @@ parameters:
       * define a variant request in a concatenated `referenceName:start--end:variantType`
         or `referenceName:start:referenceBases>alternateBases` format
       * optionally comma-concatenate 2 or more of such strings, to identify samples
-        carrying matches for all of these variations
+        carrying matches for all of these variations</br>
+      This is *not* a standard Beacon option.
     isHidden: true
   variantMinLength:
     label: Min Variant Length

beaconplusWeb/src/site-specific/searchExamples.yaml

@@ -155,8 +155,6 @@
   description: |
     This example shows a short form version of the CDKN2A deletion example.
   parameters:
-    cytoBands:
-      isHidden: true
     variantQueryDigests:
       isHidden: false
       defaultValue: "9:21000001-21975098--21967753-24000000:DEL"

bycon/config/argument_definitions.yaml

@@ -260,10 +260,8 @@ $defs:
       The maximum variant length in bases e.g. for CNV queries.
 
   gene_id:
-    type: array
-    items:
-      type: string
-      pattern: '^\w+?(\w+?(\-\w+?)?)?$'
+    type: string
+    pattern: '^\w+?(\w+?(\-\w+?)?)?$'
     db_key: Null
     cmdFlags:
       - --geneId
@@ -328,9 +326,9 @@ $defs:
       - --variantInternalId
     description: 'An id value used for all variant instances of the same composition; a kind of `digest`'
 
-  ################################################################################
+  ##############################################################################
   # non-standard parameters
-  ################################################################################
+  ##############################################################################
 
   accessid:
     type: string

bycon/config/variant_request_definitions.yaml

@@ -17,12 +17,12 @@ request_pars:
   - mate_end
   - variant_min_length
   - variant_max_length
-
-# BeaconPlus
-multi_request_pars:
   - gene_id
   - aminoacid_change
   - genomic_allele_short_form
+
+# BeaconPlus
+multi_request_pars:
   - cyto_bands
   - variant_query_digests
 
@@ -109,8 +109,9 @@ request_types:
       # - assembly_id
       - start
       - reference_name
-      - reference_bases
       - alternate_bases
+    optional:
+      - reference_bases
 
   variantTypeFilteredRequest:
     description: >-

bycon/lib/query_execution.py

@@ -119,7 +119,7 @@ def __run_multi_variants_query(self):
         if len(queries) < 1:
             return
 
-        prdbug(f' ====== {BYC["response_entity"]} =====')
+        prdbug(f' ====== {BYC.get("response_entity_id", "biosample")} =====')
         res_e_id = BYC.get("response_entity_id", "biosample")
         res_e_coll = BYC["response_entity"].get("collection", "biosamples")
         id_k = f'{res_e_id}_id'

bycon/lib/query_generation.py

@@ -185,33 +185,25 @@ def __query_from_variant_pars(self):
     # -------------------------------------------------------------------------#
 
     def __preprocess_variant_pars(self):
-        self.variant_multi_pars = BYC_PARS.get("variant_multi_pars", [])
-        v_p_s = self.variant_request_definitions.get("request_pars", [])
-        v_mp_s = self.variant_request_definitions.get("multi_request_pars", [])
-
-        vips = []
+        v_m_ps = BYC_PARS.get("variant_multi_pars", [])
 
+        v_p_s = self.variant_request_definitions.get("request_pars", [])
         # standard pars
         s_q_p_0 = {}
         if (v_s_s := v_p_s & BYC_PARS.keys()):
             for v_p in v_s_s:
-                v_v = BYC_PARS.get(v_p)
-                s_q_p_0.update({ v_p: v_v })
-                BYC_VARGS.update({ v_p: v_v })
-                prdbug(f'...__preprocess_variant_pars: {v_p} {v_v}')
-
-        for v_mp in v_mp_s:
-            if len(v_mp_vs := BYC_PARS.get(v_mp, [])) > 0:
-                for v in v_mp_vs:
-                    if len(s_q_p_0.keys()) > 0:
-                        t_p = s_q_p_0.copy()
-                        t_p.update({v_mp: v})
-                        vips.append(self.__parse_variant_parameters(t_p))
-                    else:
-                        vips.append({v_mp: v})
-        if (len(vips)) < 1:
-            if len(s_q_p_0.keys()) > 0:
-                vips.append(self.__parse_variant_parameters(s_q_p_0))
+                s_q_p_0.update({ v_p: BYC_PARS.get(v_p) })
+        if len(s_q_p_0.keys()) > 0:
+            v_m_ps.append(s_q_p_0)
+
+        vips = []
+        for v in v_m_ps:
+            vp = {}
+            if (v_s_s := v_p_s & v.keys()):
+                for v_p in v_s_s:
+                    vp.update({ v_p: v.get(v_p) })
+                if len(vp.keys()) > 0:
+                    vips.append(self.__parse_variant_parameters(vp))
 
         self.variant_multi_pars = vips
 
@@ -225,17 +217,17 @@ def __parse_variant_parameters(self, variant_pars):
 
         # value checks
         v_p_c = { }
-
         for p_k, v_p in variant_pars.items():
-            v_p = variant_pars[ p_k ]
             v_p_k = humps.decamelize(p_k)
             if "variant_type" in v_p_k:
                 v_s_c = VariantTypes().variantStateChildren(v_p)
-                v_p_c[ v_p_k ] = { "$in": v_s_c }
-            elif "reference_name" in v_p_k or "mate_name" in v_p_k:
-                v_p_c[ v_p_k ] = self.ChroNames.refseq(v_p)
-            else:
-                v_p_c[ v_p_k ] = v_p
+                v_p_c.update({v_p_k: { "$in": v_s_c }})
+                continue
+            if "reference_name" in v_p_k or "mate_name" in v_p_k:
+                v_p_c.update({v_p_k: self.ChroNames.refseq(v_p)})
+                continue
+
+            v_p_c.update({v_p_k: v_p})
 
         return v_p_c
 
@@ -388,10 +380,10 @@ def __create_geneVariantRequest_query(self, v_pars):
             "end": [ gene.get("end", 1) ]
         }
         # TODO: global variant parameters by definition file
-        g_p_s = ["variant_type", "variant_min_length", "variant_max_length"]
-        for g_p in g_p_s:
-            if g_p in BYC_VARGS:
-                v_pars.update( { g_p: BYC_VARGS[g_p] } )
+        # g_p_s = ["variant_type", "variant_min_length", "variant_max_length"]
+        # for g_p in g_p_s:
+        #     if g_p in BYC_VARGS:
+        #         v_pars.update( { g_p: BYC_VARGS[g_p] } )
         q_t = self.__create_variantRangeRequest_query(v_pars)
         prdbug(f'...geneVariantRequest query result: {q_t}')
 
@@ -477,10 +469,10 @@ def __create_cytoBandRequest_query(self, v_pars):
         } )
         # TODO: other global parameters (length etc.)
         # TODO: global variant parameters by definition file
-        g_p_s = ["variant_type", "variant_min_length", "variant_max_length"]
-        for g_p in g_p_s:
-            if g_p in BYC_VARGS:
-                v_pars.update( { g_p: BYC_VARGS[g_p] } )
+        # g_p_s = ["variant_type", "variant_min_length", "variant_max_length"]
+        # for g_p in g_p_s:
+        #     if g_p in BYC_VARGS:
+        #         v_pars.update( { g_p: BYC_VARGS[g_p] } )
         self.variant_request_type = "variantRangeRequest"
         q = self.__create_variantRangeRequest_query(v_pars)
         return q
@@ -722,10 +714,14 @@ def __query_from_filters(self):
             # TODO: needs a general solution; so far for the iso age w/
             #       pre-calculated days field...
             if "alphanumeric" in f_info.get("ft_type", "ontology"):
-                f_class, comp, val = re.match(r'^(\w+):([<>=]+?)(\w[\w.]+?)$', f_info["id"]).group(1, 2, 3)
-                if "iso8601duration" in f_info.get("format", "___none___"):
-                    val = days_from_iso8601duration(val)
-                f_lists[f_entity][f_field].append(self.__mongo_comparator_query(comp, val))
+                prdbug(f'__query_from_filters ... alphanumeric: {f_info["id"]}')
+                if re.match(r'^(\w+):([<>=]+?)?(\w[\w.]+?)$', f_info["id"]):
+                    f_class, comp, val = re.match(r'^(\w+):([<>=]+?)?(\w[\w.]+?)$', f_info["id"]).group(1, 2, 3)
+                    if "iso8601duration" in f_info.get("format", "___none___"):
+                        val = days_from_iso8601duration(val)
+                    f_lists[f_entity][f_field].append(self.__mongo_comparator_query(comp, val))
+                else:
+                    f_lists[f_entity][f_field].append(f_info["id"])
             elif f_desc is True:
                 if f_neg is True:
                     f_lists[f_entity][f_field].append({'$nin': f_info["child_terms"]})

docs/generated/argument_definitions.md

@@ -218,10 +218,8 @@ The minimal variant length in bases e.g. for CNV queries.
 The maximum variant length in bases e.g. for CNV queries.    
 
 #### `gene_id` 
-**type:** array    
-**items:**  
-    - `type`: `string`      
-    - `pattern`: `^\w+?(\w+?(\-\w+?)?)?$`    
+**type:** string    
+**pattern:** `^\w+?(\w+?(\-\w+?)?)?$`    
 **db_key:** None    
 **cmdFlags:** `--geneId`    
 **description:**

housekeepers/config/mongodb_indexer.yaml

@@ -99,7 +99,13 @@ indexed_special_dbs:
           location.start: 1
           location.end: 1
           variant_state.id: 1
+        type: compound
+      variantallelerangequery:
+        db_key:
+          location.sequence_id: 1
+          location.start: 1
           sequence: 1
+          location.end: 1
         type: compound
 
   _byconHousekeepingDB:

housekeepers/queriesTester.py

@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+
+from bycon import *
+from pymongo import MongoClient
+
+from bycon import byconServiceLibs
+from service_helpers import assertSingleDatasetOrExit
+
+
+"""
+"""
+
+################################################################################
+################################################################################
+################################################################################
+
+ds_id = assertSingleDatasetOrExit()
+BYC_PARS.update({"response_entity_path_id":"analyses"})
+set_entities()
+for qek, qev in BYC.get("test_queries", {}).items():
+    for p, v in qev.items():
+        if p == "filters":
+            f_l = []
+            for f in v:
+                f_l.append({"id": f})
+            if len(f_l) > 0:
+                BYC.update({"BYC_FILTERS":f_l})
+        else:
+            BYC_PARS.update({p: v})
+
+    # print(f'... getting data for {qek}')
+    BRS = ByconResultSets()
+    r_c = BRS.get_record_queries()
+    ds_results = BRS.datasetsResults()
+    # print(f'... got it')
+
+    # clean out those globals for next run
+    # filters are tricky since they have a default `[]` value
+    # and have been pre-parsed into BYC_FILTERS at the stage of
+    # `ByconResultSets()` (_i.e._ embedded `ByconQuery()`)
+    for p, v in qev.items():
+        if p == "filters":
+            BYC_PARS.update({"filters": []})
+        else:
+            BYC_PARS.pop(p)
+    BYC.update({"BYC_FILTERS": []})
+
+    if not (ds := ds_results.get(ds_id)):
+        print(f'ERROR - no {qek} data for {ds_id}')
+        prjsonnice(r_c)
+        continue
+    if BYC.get("DEBUG_MODE"):
+        print(f'############################### {qek} ###############################')
+        prjsonnice(r_c)
+
+    print(f'==> {qek} with {ds["analyses.id"].get("target_count")} analysis hits')
+

local/test_queries.yaml

@@ -5,29 +5,35 @@ CDKN2AcnvQuery:
   start: [21000001,21975098]
   end: [21967753,23000000]
   variant_type: EFO:0030067
+
 EIF4A1snvQuery:
   reference_name: refseq:NC_000017.11
   start: [7577120]
   variant_type: SO:0001059
   alternate_bases: A
   reference_bases: G
+
 EIF4A1rangeQuery:
   reference_name: refseq:NC_000017.11
   start: [7572825]
   end: [7579005]
   variant_type: SO:0001059
+
 geneMatchQuery:
   gene_id: CDK2
   variant_min_length: 100000
   variant_max_length: 2000000
   variant_type: EFO:0030070
+
 HeLaIdentifierQuery:
   filters:
     - cellosaurus:CVCL_0030
+
 CDKN2AshortFormExample:
   filters:
     - NCIT:C3058
-  variant_query_digests: 9:21000001-21975098--21967753-24000000:DEL
+  variant_query_digests: [9:21000001-21975098--21967753-24000000:DEL]
+
 fusionExample:
   variant_type: SO:0000806
   reference_name: refseq:NC_000008.11
@@ -36,10 +42,34 @@ fusionExample:
   end: [47300000]
   mate_start: [26200000]
   mate_end: [35600000]
+
 ClinicalFiltersQuery:
   filters:
     - NCIT:C48786
     - NCIT:C20197
+
 AgeAtDXquery:
   filters:
-    - ageAtDiagnosis:<=P18Y
+    - ageAtDiagnosis:>=P65Y
+    - ageAtDiagnosis:<=P69Y
+
+MultiAlleleCNVquery:
+  variant_multi_pars:
+    - reference_name: refseq:NC_000017.11
+      start: [7673801]
+      alternate_bases: A
+    - reference_name: refseq:NC_000017.11
+      start: [5000000, 7687480]
+      end: [7668422, 9000000]
+      variant_type: EFO:0030067
+
+DoubleGeneDeletion:
+  variant_multi_pars:
+    - reference_name: refseq:NC_000009.12
+      start: [21500001, 21975098]
+      end: [21967753, 22500000]
+      variant_type: EFO:0030067
+    - reference_name: refseq:NC_000017.11
+      start: [5000000, 7687480]
+      end: [7668422, 9000000]
+      variant_type: EFO:0030067