updating to reflect new STRING formats and SGD id,

adding robokop baseline to yeast graph, moving strict norm flag to yeast sources to keep baseline normalized strictly
RobokopU24 · May 30, 2023 · 754249e · 754249e
1 parent b3f326f
commit 754249e
Show file tree

Hide file tree

Showing 3 changed files with 65 additions and 17 deletions.
diff --git a/Common/data_sources.py b/Common/data_sources.py
@@ -23,20 +23,21 @@
 PHAROS = 'PHAROS'
 PLANT_GOA = 'PlantGOA'
 SCENT = 'Scent'
-STRING_DB = 'STRING-DB'
+SGD = 'SGD'
+HUMAN_STRING = 'STRING-DB-Human'
 TEXT_MINING_KP = 'textminingkp'
 UBERGRAPH = 'Ubergraph'
 UBERGRAPH_REDUNDANT = 'UbergraphRedundant'
 UNIREF = 'UniRef'
 VP = 'ViralProteome'
-YEASTSGD = 'YeastSGDInfo'
 YEAST_HISTONES = "YeastHistoneMapping"
-YEAST_COSTANZA = "Costanza2016Data"
+YEAST_COSTANZA = 'Costanza2016Data'
 YEAST_GSE61888 = 'YeastGSE61888'
 YEAST_GASCHDIAMIDE = 'YeastGaschDiamideGeneExpression'
-YEAST_STRING_DB = 'Yeast-STRING-DB'
+YEAST_STRING = 'STRING-DB-Yeast'
 
-RESOURCE_HOGS = [GTEX, GWAS_CATALOG, UNIREF, ONTOLOGICAL_HIERARCHY, UBERGRAPH, UBERGRAPH_REDUNDANT, YEASTSGD, STRING_DB, CAM_KP]
+RESOURCE_HOGS = [GTEX, GWAS_CATALOG, UNIREF, ONTOLOGICAL_HIERARCHY, UBERGRAPH_REDUNDANT,
+                 SGD, HUMAN_STRING, CAM_KP]
 
 SOURCE_DATA_LOADER_CLASS_IMPORTS = {
     BIOLINK: ("parsers.biolink.src.loadBL", "BLLoader"),
@@ -53,24 +54,24 @@
     HGNC: ("parsers.hgnc.src.loadHGNC", "HGNCLoader"),
     HMDB: ("parsers.hmdb.src.loadHMDB", "HMDBLoader"),
     HUMAN_GOA: ("parsers.GOA.src.loadGOA", "HumanGOALoader"),
+    HUMAN_STRING: ("parsers.STRING.src.loadSTRINGDB", "HumanSTRINGDBLoader"),
     INTACT: ("parsers.IntAct.src.loadIA", "IALoader"),
     MONDO_PROPS: ("parsers.MONDOProperties.src.loadMP", "MPLoader"),
     ONTOLOGICAL_HIERARCHY: ("parsers.UberGraph.src.loadUG", "OHLoader"),
     PANTHER: ("parsers.panther.src.loadPanther", "PLoader"),
     PHAROS: ("parsers.PHAROS.src.loadPHAROS", "PHAROSLoader"),
     PLANT_GOA: ("parsers.GOA.src.loadGOA", "PlantGOALoader"),
     SCENT: ("parsers.scent.src.loadScent", "ScentLoader"),
-    STRING_DB: ("parsers.STRING.src.loadSTRINGDB", "STRINGDBLoader"),
+    SGD: ("parsers.SGD.src.loadSGD", "SGDLoader"),
     TEXT_MINING_KP: ("parsers.textminingkp.src.loadTMKP", "TMKPLoader"),
     UBERGRAPH: ("parsers.UberGraph.src.loadUG", "UGLoader"),
     UBERGRAPH_REDUNDANT: ("parsers.UberGraph.src.loadUG", "UGRedundantLoader"),
     UNIREF: ("parsers.ViralProteome.src.loadUniRef", "UniRefSimLoader"),
     VP: ("parsers.ViralProteome.src.loadVP", "VPLoader"),
-    YEASTSGD: ("parsers.yeast.src.loadYeastSGDInfo", "YeastSGDLoader"),
     YEAST_HISTONES: ("parsers.yeast.src.loadHistoneMap", "YeastHistoneMapLoader"),
     YEAST_COSTANZA: ("parsers.yeast.src.loadCostanza2016", "Costanza2016Loader"),
     YEAST_GASCHDIAMIDE: ("parsers.yeast.src.loadYeastGeneExpressionGasch.py", "YeastGaschDiamideLoader"),
-    YEAST_STRING_DB: ("parsers.yeast.src.loadYeastGSTRINGDB.py", "STRINGDBLoader")
+    YEAST_STRING: ("parsers.STRING.src.loadSTRINGDB", "YeastSTRINGDBLoader")
 }
 
 

diff --git a/graph_specs/default-graph-spec.yml b/graph_specs/default-graph-spec.yml
@@ -12,7 +12,7 @@ graphs:
     graph_description: 'ROBOKOP (KG) is an open-source biomedical KG that supports the ROBOKOP application. This is the baseline version of that graph, which does not include knowledge sources with specific genetic variants.'
     graph_url: http://robokopkg.renci.org/browser/
     conflation: True
-    output_format: jsonl
+    output_format: neo4j
     sources:
       - source_id: Biolink
         # optional parameters for each data source - see README for more info
@@ -39,7 +39,7 @@ graphs:
       - source_id: PANTHER
       - source_id: PHAROS
       - source_id: textminingkp
-      - source_id: STRING-DB
+      - source_id: STRING-DB-Human
       - source_id: Ubergraph
 
   - graph_id: RobokopKG

diff --git a/graph_specs/yeast-graph-spec.yml b/graph_specs/yeast-graph-spec.yml
@@ -1,15 +1,62 @@
 # yeast graph spec
 graphs:
-  - graph_id: Yeast_Test_Graph
-    conflation: False
-    strict_normalization: False
+
+  - graph_id: Baseline
+    # optional parameters to be applied to the entire graph - see README for more info
+    # node_normalization_version: latest
+    # edge_normalization_version: latest
+    # graph_name: Robokop Baseline
+    # graph_description: 'The baseline graph from which RobokopKG and other graphs are built.'
+    # conflation: True # (whether to conflate node types like Genes and Proteins)
+    graph_name: ROBOKOP Baseline
+    graph_description: 'ROBOKOP (KG) is an open-source biomedical KG that supports the ROBOKOP application. This is the baseline version of that graph, which does not include knowledge sources with specific genetic variants.'
+    graph_url: http://robokopkg.renci.org/browser/
+    conflation: True
+    output_format: neo4j
     sources:
-      - source_id: YeastSGDInfo
+      - source_id: Biolink
+        # optional parameters for each data source - see README for more info
+        # source_version: latest (the version of the source data)
+        # parsing_version: latest (the version of the parser used to parse the data)
+        # node_normalization_version: latest
+        # edge_normalization_version: latest
+        # conflation: False
+        # strict_normalization: True (whether or not data should be discarded when it can not be normalized)
+        # merge_strategy: default (used to specify alternative merge strategies)
+      - source_id: CHEBIProps
+      - source_id: CTD
+      - source_id: DrugCentral
+      - source_id: GtoPdb
+      - source_id: Hetio
+      - source_id: HGNC
+      - source_id: HMDB
+      - source_id: HumanGOA
+      - source_id: IntAct
+      - source_id: MONDOProps
+        source_version: '3_23_2023'
+      - source_id: PANTHER
+      - source_id: PHAROS
+      - source_id: textminingkp
+      - source_id: STRING-DB-Human
+      - source_id: Ubergraph
+
+  - graph_id: YobokopKG
+    conflation: True
+    output_format: neo4j
+    subgraphs:
+      - graph_id: Baseline
+    sources:
+      - source_id: SGD
+        strict_normalization: False
       - source_id: YeastHistoneMapping
+        strict_normalization: False
       - source_id: Costanza2016Data
+        strict_normalization: False
       - source_id: YeastGSE61888
+        strict_normalization: False
       - source_id: YeastGaschDiamideGeneExpression
-      - source_id: Yeast-STRING-DB
-#      - source_id: GenomeAllianceOrthologs
+        strict_normalization: False
+      - source_id: STRING-DB-Yeast
+      - source_id: GenomeAllianceOrthologs
       - source_id: OntologicalHierarchy
-        merge_strategy: connected_edge_subset
+        merge_strategy: connected_edge_subset