Merge pull request #251 from RobokopU24/signor_development_1

SIGNOR 3.0 parser. Updated to map SIGNOR phenotypes to GO terms when …

Common/data_sources.py

@@ -34,6 +34,7 @@
 REACTOME = 'Reactome'
 SCENT = 'Scent'
 SGD = 'SGD'
+SIGNOR = 'SIGNOR'
 HUMAN_STRING = 'STRING-DB-Human'
 TEXT_MINING_KP = 'textminingkp'
 UBERGRAPH_NONREDUNDANT = 'UbergraphNonredundant'
@@ -83,6 +84,7 @@
     REACTOME: ("parsers.Reactome.src.loadReactome", "ReactomeLoader"),
     SCENT: ("parsers.scent.src.loadScent", "ScentLoader"),
     SGD: ("parsers.SGD.src.loadSGD", "SGDLoader"),
+    SIGNOR: ("parsers.SIGNOR.src.loadSIGNOR", "SIGNORLoader"),
     TEXT_MINING_KP: ("parsers.textminingkp.src.loadTMKP", "TMKPLoader"),
     UBERGRAPH_NONREDUNDANT: ("parsers.UberGraph.src.loadUG", "UGLoader"),
     UBERGRAPH_REDUNDANT: ("parsers.UberGraph.src.loadUG", "UGRedundantLoader"),

Common/prefixes.py

@@ -48,6 +48,7 @@
 ORPHANET='ORPHANET'
 PUBCHEM_COMPOUND='PUBCHEM.COMPOUND'
 PUBMED='PMID'
+RNACENTRAL='RNACENTRAL'
 UBERON='UBERON'
 UNIPROTKB='UniProtKB'
 UMLS='UMLS'

graph_specs/signor-graph-spec.yml

@@ -0,0 +1,9 @@
+graphs:
+
+  - graph_id: SIGNOR
+    graph_name: 'SIGNOR 3.0: The SIGnaling Network Open Resource'
+    graph_description: 'SIGNOR is a repository of manually annotated causal relationships between human proteins, chemicals of biological relevance, stimuli and phenotypes.'
+    graph_url: https://signor.uniroma2.it
+    output_format: neo4j
+    sources:
+      - source_id: SIGNOR

parsers/SIGNOR/src/signor_mechanism_predicate_mapping.py

@@ -0,0 +1,223 @@
+from Common.biolink_constants import *
+
+ptm_dict = {
+            "acetylation": "increased",
+            "ADP-ribosylation": "increased",
+            "carboxylation": "increased",
+            "deacetylation": "decreased",
+            "degradation": "increased",  # cleavage
+            "deglycosylation": "decreased",
+            "demethylation": "decreased",
+            "dephosphorylation": "decreased",
+            "desumoylation": "decreased",
+            "deubiquitination": "decreased",
+            "glycosylation": "increased",
+            "hydroxylation": "increased",
+            "lipidation": "increased",
+            "methylation": "increased",
+            "monoubiquitination": "increased",
+            "neddylation": "increased",
+            "oxidation": "increased",
+            "palmitoylation": "increased",
+            "phosphorylation": "increased",
+            "polyubiquitination": "increased",
+            "s-nitrosylation": "increased",
+            "sumoylation": "increased",
+            "trimethylation": "increased",
+            "tyrosination": "increased",
+            "ubiquitination": "increased"
+        }
+
+mechanism_map = {
+            "binding": {
+                "predicate": f"RO:0002436",  # directly_physically_interacts_with
+            },
+
+            "catalytic activity": {
+                "predicate": f"RO:0002327",  # catalyzes
+            },
+
+            "chemical activation": {
+                "edge_properties": {
+                    CAUSAL_MECHANISM_QUALIFIER: "chemical activation"
+                }
+            },
+
+            "chemical inhibition": {
+                "edge_properties": {
+                    CAUSAL_MECHANISM_QUALIFIER: "chemical inhibition"
+                }
+            },
+
+            "chemical modification": {
+                "predicate": f"biolink:affects",
+                "edge_properties": {
+                    QUALIFIED_PREDICATE: f"RO:0003303",  # causes
+                    OBJECT_ASPECT_QUALIFIER: "chemical modification",
+                }
+            },
+            "destabilization": {
+                "predicate": f"biolink:affects",
+                "edge_properties": {
+                    QUALIFIED_PREDICATE: "RO:0003303",
+                    OBJECT_DIRECTION_QUALIFIER: "decreased",
+                    OBJECT_ASPECT_QUALIFIER: "stability"
+                }
+            },
+
+            # This probably needs to be a node property. "is_a"
+            "gtpase - activating protein": {
+            },
+
+            # This probably needs to be a node property.
+            "guanine nucleotide exchange factor": {
+            },
+
+            "post transcriptional modification": {
+                "predicate": f"biolink:affects",
+                "edge_properties": {
+                    QUALIFIED_PREDICATE: "RO:0003303",
+                    OBJECT_ASPECT_QUALIFIER: "post transcriptional modification"
+                }
+            },
+
+            "post translational modification": {
+                "predicate": f"biolink:affects",
+                "edge_properties": {
+                    QUALIFIED_PREDICATE: "RO:0003303",
+                    OBJECT_ASPECT_QUALIFIER: "post translation modification"
+                }
+            },
+
+            # new predicate?
+            "precursor of": {
+            },
+
+            "relocalization": {
+                "predicate": f"biolink:affects",
+                "edge_properties": {
+                    QUALIFIED_PREDICATE: "RO:0003303",
+                    OBJECT_ASPECT_QUALIFIER: "relocation"
+                }
+            },
+
+            "small molecule catalysis": {
+                "predicate": "RO:0002327",  # catalyses
+            },
+
+            "transcriptional regulation": {
+                "predicate": f"biolink:affects",
+                "edge_properties": {
+                    QUALIFIED_PREDICATE: "RO:0003303",
+                    CAUSAL_MECHANISM_QUALIFIER: "transcriptional_regulation"
+                }
+            },
+
+            "translation regulation": {
+                "predicate": f"biolink:affects",
+                "edge_properties": {
+                    OBJECT_ASPECT_QUALIFIER: "translation"
+                }
+            },
+
+        }
+
+# Effect to Predicate Mapping
+effect_mapping = {
+    "form complex": {
+        "biolink:in_complex_with": {},
+        "RO:0002436": {}
+    },
+
+    "down-regulates": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "downregulates"
+        }
+    },
+
+    "down-regulates activity": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "downregulates",
+            OBJECT_ASPECT_QUALIFIER: "activity"
+        }
+    },
+
+    "down-regulates quantity": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "downregulates",
+            OBJECT_ASPECT_QUALIFIER: "abundance"
+        }
+    },
+
+    "down-regulates quantity by destabilization": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "downregulates",
+            OBJECT_ASPECT_QUALIFIER: "abundance"
+        },
+
+        "biolink:affects": {
+            QUALIFIED_PREDICATE: "RO:0003303",
+            OBJECT_DIRECTION_QUALIFIER: "decreased",
+            OBJECT_ASPECT_QUALIFIER: "stability"
+        }
+    },
+
+    "down-regulates quantity by repression": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "downregulates",
+            OBJECT_ASPECT_QUALIFIER: "abundance"
+        },
+
+        "biolink:affects": {
+            QUALIFIED_PREDICATE: "RO:0003303",
+            OBJECT_DIRECTION_QUALIFIER: "decreased",
+            OBJECT_ASPECT_QUALIFIER: "expression"
+        }
+    },
+
+    "up-regulates": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "upregulates"
+        }
+    },
+
+    "up-regulates activity": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "upregulates",
+            OBJECT_ASPECT_QUALIFIER: "activity"
+        }
+    },
+
+    "up-regulates quantity": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "upregulates",
+            OBJECT_ASPECT_QUALIFIER: "abundance"
+        }
+    },
+
+    "up-regulates quantity by stabilization": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "upregulates",
+            OBJECT_ASPECT_QUALIFIER: "abundance"
+        },
+
+        "biolink:affects": {
+            QUALIFIED_PREDICATE: "RO:0003303",
+            OBJECT_DIRECTION_QUALIFIER: "increased",
+            OBJECT_ASPECT_QUALIFIER: "stability"
+        }
+    },
+
+    "up-regulates quantity by expression": {
+        "RO:0002448": {
+            OBJECT_DIRECTION_QUALIFIER: "upregulates",
+            OBJECT_ASPECT_QUALIFIER: "abundance"
+        },
+
+        "biolink:affects": {
+            QUALIFIED_PREDICATE: "RO:0003303",
+            OBJECT_DIRECTION_QUALIFIER: "increased",
+            OBJECT_ASPECT_QUALIFIER: "expression"
+        }
+    }
+}

parsers/SIGNOR/src/signor_predicate_mapping.py

@@ -0,0 +1,80 @@
+PREDICATE_MAPPING = {
+    "down-regulates":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"",
+    "object_direction_qualifier":"downregulated",
+    "object_aspect_qualifier":"",
+    },
+    "up-regulates quantity":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"biolink:causes",
+    "object_direction_qualifier":"increased",
+    "object_aspect_qualifier":"abundance",
+    },
+    "down-regulates quantity by repression":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"biolink:causes",
+    "object_direction_qualifier":"decreased",
+    "object_aspect_qualifier":"expression",
+    },
+    "up-regulates":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"",
+    "object_direction_qualifier":"upregulated",
+    "object_aspect_qualifier":"",
+    },
+    "down-regulates quantity by destabilization":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"biolink:causes",
+    "object_direction_qualifier":"decreased",
+    "object_aspect_qualifier":"stability",
+    },
+    "up-regulates quantity by expression":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"biolink:causes",
+    "object_direction_qualifier":"increased",
+    "object_aspect_qualifier":"expression",
+    },
+    "down-regulates quantity":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"biolink:causes",
+    "object_direction_qualifier":"decreased",
+    "object_aspect_qualifier":"abundance",
+    },
+    "up-regulates activity":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"biolink:causes",
+    "object_direction_qualifier":"increased",
+    "object_aspect_qualifier":"activity",
+    },
+    "down-regulates activity":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"biolink:causes",
+    "object_direction_qualifier":"decreased",
+    "object_aspect_qualifier":"activity",
+    },
+    "form complex":{
+    "predicate":"biolink:in_complex_with",
+    "qualified_predicate":"",
+    "object_direction_qualifier":"",
+    "object_aspect_qualifier":"",
+    },
+    "up-regulates quantity by stabilization":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"biolink:causes",
+    "object_direction_qualifier":"increased",
+    "object_aspect_qualifier":"stability",
+    },
+    "down-regulates quantity by repression":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"biolink:causes",
+    "object_direction_qualifier":"decreased",
+    "object_aspect_qualifier":"expression",
+    },
+    "unknown":{
+    "predicate":"biolink:regulates",
+    "qualified_predicate":"",
+    "object_direction_qualifier":"",
+    "object_aspect_qualifier":"",
+    }
+}

requirements.txt

@@ -1,5 +1,6 @@
 pandas==2.2.2
 requests==2.32.3
+requests-toolbelt>=1.0.0
 pytest==8.2.0
 robokop-genetics==0.5.0
 # intermine is on pypi but as of 6/23 it's broken for python 3.10+, this fork fixes the issue