1.8.6

Author: mbaudis

bycon/definitions/datatable_mappings.yaml

@@ -48,7 +48,6 @@ h->o_types:
       id: 'pgx:HO.biosamplestable'
       label: "Biosamples Table"
     note: "retrieve data of the biosamples matched by the query as tab-delimited table"
-    output: datatable
     paginated_entities:
       - biosample
       - analysis
@@ -106,7 +105,6 @@ h->o_types:
       id: 'pgx:HO.pgxseg'
       label: "Found Variants (.pgxseg)"
     note: "retrieve variants matched by the query as .pgxseg download"
-    output: pgxseg
     paginated_entities:
       - all
     h->o_key: 'variants._id'
@@ -128,7 +126,6 @@ h->o_types:
       id: 'pgx:HO.bedfile2ucsc'
       label: "Show Found Variants in the UCSC browser"
     note: "map variants matched by the query to the UCSC browser"
-    output: ucscbrowser
     paginated_entities:
       - all
     h->o_key: 'variants._id'

bycon/definitions/handover_definitions.yaml

@@ -297,3 +297,16 @@ SO:0001413:
   cnv_dummy_value: Null
   child_terms:
     - SO:0001413
+    - SO:0000806
+
+SO:0000806:
+  variant_state:
+    id: SO:0000806
+    label: fusion
+  variant_type_id: SO:0000806
+  variant_type: BND
+  VRS_type: Null
+  VCF_symbolic_allele: <BND>
+  cnv_dummy_value: Null
+  child_terms:
+    - SO:0000806

bycon/definitions/variant_type_definitions.yaml

@@ -1,6 +1,7 @@
 import base36, humps, json, re, time
 
 from isodate import parse_duration
+from datetime import datetime
 from os import environ
 from pymongo import MongoClient
 
@@ -284,9 +285,7 @@ def assign_nested_value(parent, dotted_key, v, parameter_definitions={}):
 ################################################################################
 
 def get_nested_value(parent, dotted_key, parameter_type="string"):
-
-    ps = dotted_key.split('.')
-
+    ps = str(dotted_key).split('.')
     v = ""
 
     if len(ps) == 1:
@@ -342,11 +341,25 @@ def decamelize_words(j_d):
 
 def prdbughead(this=""):
     BYC.update({"DEBUG_MODE": True})
+    prtexthead()
+    print(this)
+
+################################################################################
+
+def prtexthead():
     if not "local" in ENV:
         print('Content-Type: text/plain')
         print('status: 302')
         print()
-        print(this)
+
+################################################################################
+
+def prdlhead(filename="download.txt"):
+    if not "local" in ENV:
+        print('Content-Type: text/tsv')
+        print(f'Content-Disposition: attachment; filename={filename}')
+        print('status: 200')
+        print()
 
 ################################################################################
 
@@ -366,5 +379,18 @@ def prjsonnice(this):
 def prjsoncam(this):
     prjsonnice(humps.camelize(this))
 
+################################################################################
+
+def isotoday():
+    return str(datetime.today().strftime('%Y-%m-%d'))
+
+################################################################################
+
+def isonow():
+    return str(datetime.datetime.now().isoformat())
+
+
+
+
 
 

bycon/lib/bycon_helpers.py

@@ -9,23 +9,22 @@
 ################################################################################
 
 def select_dataset_ids():
-    if ds_id_from_rest_path_value() is not False:
+    if ds_id_from_rest_path_value():
         return
-    if ds_id_from_accessid() is not False:
+    if ds_id_from_accessid():
         return
-    if ds_id_from_record_id() is not False:
+    if ds_id_from_record_id():
         return
-    if ds_ids_from_form() is not False:
+    if ds_ids_from_form():
         return
-    if ds_id_from_default() is not False:
+    if ds_id_from_default():
         return
 
 
 ################################################################################
 
 def ds_id_from_rest_path_value():
-    ds_p_id = rest_path_value("datasets")
-    if not ds_p_id:
+    if not (ds_p_id := rest_path_value("datasets")):
         return False
 
     ds_ids = []
@@ -44,7 +43,7 @@ def ds_id_from_rest_path_value():
 
 def ds_id_from_record_id():
     """
-    For data retrieval associated with a single record by its path id siuch as
+    For data retrieval associated with a single record by its path id such as
     `biosamples/{id}` the default Beacon model does not provide any way to provide
     the associated dataset id with the request. The assumption is that any record
     id is unique across all datasets.
@@ -62,18 +61,15 @@ def ds_id_from_accessid():
     # TODO: This is very verbose. In principle there should be an earlier
     # test of existence...
 
-    accessid = BYC_PARS.get("accessid", False)
-    if any(x is False for x in [accessid]):
+    if not (accessid := BYC_PARS.get("accessid")):
         return False
 
     ho_client = MongoClient(host=DB_MONGOHOST)
     h_o = ho_client[HOUSEKEEPING_DB][HOUSEKEEPING_HO_COLL].find_one({"id": accessid})
     if not h_o:
         return False
     ds_id = h_o.get("source_db", False)
-    if ds_id is False:
-        return False
-    if ds_id not in BYC["DATABASE_NAMES"]:
+    if (ds_id := str(h_o.get("source_db"))) not in BYC["DATABASE_NAMES"]:
         return False
     BYC.update({"BYC_DATASET_IDS":  [ds_id]})
     return True
@@ -82,26 +78,21 @@ def ds_id_from_accessid():
 ################################################################################
 
 def ds_ids_from_form():
-    f_ds_ids = BYC_PARS.get("dataset_ids", False)
-    if f_ds_ids is False:
-        return False
-    ds_ids = []
-    for ds_id in f_ds_ids:
-        if ds_id in BYC["DATABASE_NAMES"]:
-            ds_ids.append(ds_id)
-
-    if len(ds_ids) < 1:
+    
+    if not (f_ds_ids := BYC_PARS.get("dataset_ids")):
         return False
-    BYC.update({"BYC_DATASET_IDS":  ds_ids})
-    return True
+    ds_ids = [ds for ds in f_ds_ids if ds in BYC.get("DATABASE_NAMES",[])]
+    if len(ds_ids) > 0:
+        BYC.update({"BYC_DATASET_IDS":  ds_ids})
+        return True
+    return False
 
 
 ################################################################################
 
 def ds_id_from_default():
-    defaults: object = BYC["beacon_defaults"].get("defaults", {})
-    ds_id = defaults.get("default_dataset_id", "___undefined___")
-    if ds_id not in BYC["DATABASE_NAMES"]:
+    defaults: object = BYC["beacon_defaults"].get("defaults", {})  
+    if (ds_id := str(defaults.get("default_dataset_id"))) not in BYC["DATABASE_NAMES"]:
         return False
     BYC.update({"BYC_DATASET_IDS": [ ds_id ]})
     return True

bycon/lib/dataset_parsing.py

@@ -49,7 +49,7 @@ def refseqAliases(self):
     # -------------------------------------------------------------------------#
 
     def chro(self, s_id="___none___"):
-        return self.chro_aliases.get(s_id, "___none___")
+        return self.chro_aliases.get(s_id)
 
 
     # -------------------------------------------------------------------------#

bycon/lib/genome_utils.py

@@ -57,13 +57,9 @@ def remap_variants(r_s_res):
         }
         for d_v in d_vs:
             c_l_v = {}
-            for c_k in ("id", "biosample_id", "info"):
-                c_v = d_v.get(c_k)
-                if c_v:
+            for c_k in ("id", "biosample_id", "analysis_id", "individual_id", "info"):
+                if (c_v := d_v.get(c_k)):
                     c_l_v.update({c_k: c_v})
-            a_id = d_v.get("analysis_id")
-            if a_id:
-                c_l_v.update({"analysis_id": a_id})
             v["case_level_data"].append(c_l_v)
 
         # TODO: Keep legacy pars?
@@ -130,15 +126,16 @@ def remap_runs(r_s_res):
         return r_s_res
 
     runs = []
-    for cs_i, cs_r in enumerate(r_s_res):
+    for ana in r_s_res:
         r = {
-            "id": cs_r.get("id", ""),
-            "analysis_id": cs_r.get("id", ""),
-            "biosample_id": cs_r.get("biosample_id", ""),
-            "individual_id": cs_r.get("individual_id", ""),
+            "id": ana.get("id", ""),
+            "individual_id": ana.get("individual_id", ""),
             "run_date": datetime.datetime.fromisoformat(
-                cs_r.get("updated", datetime.datetime.now().isoformat())).isoformat()
+                ana.get("updated", datetime.datetime.now().isoformat())).isoformat()
         }
+        for p in ["biosample_id", "individual_id", "platform_model"]:
+            if (v := ana.get(p)):
+                r.update({p: v})
         runs.append(r)
 
     return runs
@@ -203,7 +200,12 @@ def remap_individuals(r_s_res):
     if not "individual" in BYC["response_entity_id"]:
         return r_s_res
 
-    return r_s_res
+    ind_s = []
+    for ind_i, ind in enumerate(r_s_res):
+        individual_remap_pgx_diseases(ind)
+        ind_s.append(ind)
+
+    return ind_s
 
 
 ################################################################################
@@ -264,7 +266,6 @@ def phenopack_individual(ind, data_db):
         ind.pop(k, None)
 
     individual_remap_pgx_diseases(ind)
-
     for d_i, d in enumerate(ind["diseases"]):
         for k in ["followup_state", "followup_time"]:
             ind["diseases"][d_i].pop(k, None)

bycon/lib/response_remapping.py

@@ -64,7 +64,9 @@ def byconVariant(self, variant={}):
 
     # -------------------------------------------------------------------------#
 
-    def pgxVariant(self, variant={}):
+    def pgxVariant(self, variant=None):
+        if not variant:
+            return self.pgx_variant
         self.byc_variant = variant
         self.__create_canonical_variant()
         var_keys = self.pgx_variant.keys()

bycon/lib/variant_mapping.py

@@ -1,12 +1,13 @@
 $schema: https://json-schema.org/draft/2020-12/schema
-$id: https://progenetix.org/services/schemas/analysis/v2021-11-01
+$id: https://progenetix.org/services/schemas/analysis/v2024-07-08
 title: analysis
 description: >-
-  The `analysis` object represents a information about the data generation (e.g.
-  experimental platform) and data analysis steps leading to (a set of) genomic variation
-  call(s). This is in contrast to the Beacon v2 default model which has a separate
-  `run` schema.
+  The `analysis` object represents a information about the data analysis steps
+  leading to (a set of) genomic variation call(s).
 type: object
+note: >-
+  On 2024-07-08 aligned with current Beacon v2 main
+
 properties:
   id:
     type: string
@@ -20,38 +21,45 @@ properties:
     type: string
     examples:
       - pgxbs-kftva59y
-  description:
+  runId:
+    description: >-
+      Run identifier (external accession or internal ID).
+      NOTE: Not used in bycon
+    type: string
+    examples:
+      - SRR10903401
+  analysisDate:
+    description: Date at which analysis was performed.
     type: string
+    format: date
     examples:
-      - CNV analysis from SNP6 array
-  platformModel:
+      - '2021-10-17'
+  pipelineName:
     description: >-
-      Ontology value for experimental platform or methodology used. For
-      sequencing platforms the use of "OBI:0400103 - DNA sequencer" is suggested.
-    $ref: ../common/ontologyTerm.yaml
+      Analysis pipeline and version if a standardized pipeline was used
+    type: string
     examples:
-      - id: geo:GPL3381
-        label: "Stanford Microarray Facility cDNA array [SHDV]"
-      - id: OBI:0002750
-        label: Oxford Nanopore MinION
-      - id: EFO:0010938
-        label: large-insert clone DNA microarray
-  experimentAccession:
+      - progenetix-labelseg-v1.2
+  pipelineRef:
     description: >-
-      Identifier for primary experimental data.
-      Provenance: progenetix.org
-    $ref: ../common/ontologyTerm.yaml
+      Link to Analysis pipeline resource
+    type: string
     examples:
-      - id: geo:GSM93480
-  seriesAccession:
+      - https://github.com/baudisgroup/LabelSeg
+  aligner:
     description: >-
-      Identifier for primary experimental series.
-      Provenance: progenetix.org
-    $ref: ../common/ontologyTerm.yaml
+      Reference to mapping/alignment software
+      NOTE: Not used in bycon
+    type: string
+    examples:
+      - bwa-0.7.8
+  variantCaller:
+    description: >-
+      Reference to variant calling software / pipeline
+      NOTE: Not used in bycon
+    type: string
     examples:
-      - id: geo:GSE4079
-  provenance:
-    "$ref": ../common/provenance.yaml
+      - GATK4.0
   info:
     type: object
   updated:
@@ -62,4 +70,5 @@ properties:
 required:
   - id
   - biosampleId
+  - analysisDate
 additionalProperties: true