From f6a06d431ae62b22b7676cefafb1061a02bb578c Mon Sep 17 00:00:00 2001
From: Bartek Foltyn <62876443+bfoltyn@users.noreply.github.com>
Date: Thu, 5 Oct 2023 23:36:49 +0200
Subject: [PATCH] Additional EFO xref context from axioms

merges https://github.com/related-sciences/nxontology-data/pull/19

Co-authored-by: Bartek Foltyn <bartosz.foltyn@getindata.com>
---
 nxontology_data/efo/efo.py                    | 45 +++++++++++++++++++
 .../efo/queries/mapping_properties.rq         | 17 +++++++
 nxontology_data/efo/queries/xref_sources.rq   | 18 ++++++++
 3 files changed, 80 insertions(+)
 create mode 100644 nxontology_data/efo/queries/mapping_properties.rq
 create mode 100644 nxontology_data/efo/queries/xref_sources.rq

diff --git a/nxontology_data/efo/efo.py b/nxontology_data/efo/efo.py
index 1b072bc..fb048c0 100644
--- a/nxontology_data/efo/efo.py
+++ b/nxontology_data/efo/efo.py
@@ -7,6 +7,7 @@
 from typing import Any
 
 import bioversions
+import curies
 import fsspec
 import networkx as nx
 import pandas as pd
@@ -142,6 +143,42 @@ def get_obsolete_df(self) -> pd.DataFrame:
     def get_alt_id_df(self) -> pd.DataFrame:
         return self.run_query("alt_id", cache=True)
 
+    def get_xref_sources_df(self) -> pd.DataFrame:
+        return self.run_query("xref_sources", cache=True)
+
+    def get_mapping_properties_df(self) -> pd.DataFrame:
+        converter = curies.get_bioregistry_converter()
+
+        converter.add_prefix(
+            "icd10cm-missing-prefix", "http://purl.bioontology.org/ontology/ICD10CM/"
+        )
+
+        df = (
+            self.run_query("mapping_properties", cache=True)
+            .assign(
+                xref_id=lambda df: df["xref_id"].apply(
+                    lambda xref: converter.compress(xref)
+                )
+            )
+            .dropna()
+            .assign(
+                xref_id=lambda df: df["xref_id"]
+                .str.replace("icd10cm-missing-prefix:", "icd10cm:")
+                .str.replace("obo:Orphanet_", "Orphanet:")
+                .str.split(":", expand=True)
+                .apply(
+                    lambda row: normalize_parsed_curie(
+                        xref_prefix=row[0],
+                        xref_accession=row[1],
+                        collapse_orphanet=True,
+                    ),
+                    axis="columns",
+                )
+            )
+        )
+
+        return df
+
     def get_synonyms(self) -> dict[str, dict[str, str]]:
         synonym_scopes = {
             "hasExactSynonym": "exact",
@@ -272,6 +309,14 @@ def write_outputs(self) -> None:
         write_dataframe(
             self.get_obsolete_df(), output_dir.joinpath(f"{self.name}_obsolete.json.gz")
         )
+        write_dataframe(
+            self.get_mapping_properties_df(),
+            output_dir.joinpath(f"{self.name}_mapping_properties.json.gz"),
+        )
+        write_dataframe(
+            self.get_xref_sources_df(),
+            output_dir.joinpath(f"{self.name}_xref_sources.json.gz"),
+        )
         if nxo.name == "efo_otar_profile":
             nxo_slim = self.create_slim_nxo(nxo)
             write_ontology(nxo_slim, output_dir, compression_threshold_mb=30.0)
diff --git a/nxontology_data/efo/queries/mapping_properties.rq b/nxontology_data/efo/queries/mapping_properties.rq
new file mode 100644
index 0000000..086f241
--- /dev/null
+++ b/nxontology_data/efo/queries/mapping_properties.rq
@@ -0,0 +1,17 @@
+PREFIX mondo: <http://purl.obolibrary.org/obo/mondo#>
+PREFIX efo: <http://www.ebi.ac.uk/efo/>
+PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
+
+SELECT ?efo_id (?xref_uri as ?xref_id)  ?mapping_property_id ?efo_uri ?xref_uri ?mapping_property_uri
+WHERE {
+  VALUES ?mapping_property_uri {mondo:closeMatch mondo:exactMatch skos:mappingRelation skos:closeMatch skos:exactMatch skos:broadMatch skos:narrowMatch skos:relatedMatch}
+
+  ?efo_uri rdf:type owl:Class .
+  ?efo_uri ?mapping_property_uri ?xref_uri
+
+
+  BIND( REPLACE( STR(?efo_uri), "^http.+/([^:]+)_(.+)$", "$1:$2" ) AS ?efo_id )
+  BIND( REPLACE( STR(?mapping_property_uri), "^http://purl\\.obolibrary\\.org/obo/mondo#(.+)$", "mondo:$1" ) AS ?mapping_property_id )
+  BIND( REPLACE( STR(?mapping_property_id), "^http://www\\.w3\\.org/2004/02/skos/core#(.+)$", "skos:$1" ) AS ?mapping_property_id )
+}
+ORDER BY ?efo_id ?xref_id ?mapping_property_id
diff --git a/nxontology_data/efo/queries/xref_sources.rq b/nxontology_data/efo/queries/xref_sources.rq
new file mode 100644
index 0000000..8aa3b9e
--- /dev/null
+++ b/nxontology_data/efo/queries/xref_sources.rq
@@ -0,0 +1,18 @@
+PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+PREFIX owl: <http://www.w3.org/2002/07/owl#>
+PREFIX oboInOwl: <http://www.geneontology.org/formats/oboInOwl#>
+
+SELECT ?efo_id ?xref  ?axiom_source
+WHERE {
+  ?axiom rdf:type owl:Axiom.
+  ?axiom owl:annotatedSource ?source.
+  ?axiom owl:annotatedProperty oboInOwl:hasDbXref.
+  ?axiom owl:annotatedTarget ?xref.
+
+  OPTIONAL { ?axiom oboInOwl:source ?axiom_source }.
+
+  BIND( REPLACE( STR(?source), "^http.+/([^:]+)_(.+)$", "$1:$2" ) AS ?efo_id )
+}
+
+GROUP BY ?efo_id ?xref ?axiom_source
+ORDER BY ?efo_id ?xref ?axiom_source