calculate depth and information content for CLASS node type

alliance-genome · Sep 12, 2019 · c4e3482 · c4e3482
1 parent 487e492
commit c4e3482
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 10 deletions.
diff --git a/genedescriptions/data_manager.py b/genedescriptions/data_manager.py
@@ -17,7 +17,7 @@
 from ontobio.io.gafparser import GafParser
 from genedescriptions.commons import Gene, DataType, Module
 from genedescriptions.config_parser import GenedescConfigParser, ConfigModuleProperty
-from genedescriptions.ontology_tools import set_all_depths_in_subgraph
+from genedescriptions.ontology_tools import set_all_depths
 
 
 class ExpressionClusterType(Enum):
@@ -156,8 +156,7 @@ def set_ontology(self, ontology_type: DataType, ontology: Ontology, config: Gene
         terms_replacement_regex = config.get_module_property(module=module, prop=ConfigModuleProperty.RENAME_TERMS)
         if terms_replacement_regex:
             self.rename_ontology_terms(ontology=new_ontology, terms_replacement_regex=terms_replacement_regex)
-        for root_id in new_ontology.get_roots():
-            set_all_depths_in_subgraph(ontology=new_ontology, root_id=root_id, relations=None)
+        set_all_depths(ontology=new_ontology, relations=None)
         if slim_cache_path:
             slim_url = config.get_module_property(module=module, prop=ConfigModuleProperty.SLIM_URL)
             self.load_slim(module=module, slim_url=slim_url, slim_cache_path=slim_cache_path)
@@ -209,8 +208,7 @@ def load_ontology_from_file(self, ontology_type: DataType, ontology_url: str, on
         terms_replacement_regex = config.get_module_property(module=module, prop=ConfigModuleProperty.RENAME_TERMS)
         if terms_replacement_regex:
             self.rename_ontology_terms(ontology=new_ontology, terms_replacement_regex=terms_replacement_regex)
-        for root_id in new_ontology.get_roots():
-            set_all_depths_in_subgraph(ontology=new_ontology, root_id=root_id, relations=None)
+        set_all_depths(ontology=new_ontology, relations=None)
         slim_url = config.get_module_property(module=module, prop=ConfigModuleProperty.SLIM_URL)
         self.load_slim(module=module, slim_url=slim_url, slim_cache_path=slim_cache_path)
 

diff --git a/genedescriptions/ontology_tools.py b/genedescriptions/ontology_tools.py
@@ -9,6 +9,13 @@
 logger = logging.getLogger(__name__)
 
 
+def set_all_depths(ontology: Ontology, relations: List[str] = None, comparison_func=max):
+    for root_id in ontology.get_roots():
+        if ontology.node_type(root_id) == "CLASS":
+            set_all_depths_in_subgraph(ontology=ontology, root_id=root_id, relations=relations,
+                                       comparison_func=comparison_func)
+
+
 def set_all_depths_in_subgraph(ontology: Ontology, root_id: str, relations: List[str] = None, comparison_func=max,
                                current_depth: int = 0):
     """calculate and set max_depth and min_depth (maximum and minimum distances from root terms in the ontology)
@@ -34,17 +41,18 @@ def set_all_depths_in_subgraph(ontology: Ontology, root_id: str, relations: List
 def set_all_information_content_values(ontology: Ontology, relations: List[str] = None):
     roots = ontology.get_roots(relations=relations)
     for root_id in roots:
-        if "num_subsumers" not in ontology.node(root_id):
+        if "num_subsumers" not in ontology.node(root_id) and ontology.node_type(root_id) == "CLASS":
             _set_num_subsumers_in_subgraph(ontology=ontology, root_id=root_id, relations=relations)
     for root_id in roots:
-        if "num_leaves" not in ontology.node(root_id):
+        if "num_leaves" not in ontology.node(root_id) and ontology.node_type(root_id) == "CLASS":
             _set_num_leaves_in_subgraph(ontology=ontology, root_id=root_id, relations=relations)
     for root_id in roots:
-        if "depth" not in ontology.node(root_id):
+        if "depth" not in ontology.node(root_id) and ontology.node_type(root_id) == "CLASS":
             set_all_depths_in_subgraph(ontology=ontology, root_id=root_id, relations=relations)
     for root_id in roots:
-        _set_information_content_in_subgraph(ontology=ontology, root_id=root_id,
-                                             maxleaves=ontology.node(root_id)["num_leaves"], relations=relations)
+        if ontology.node_type(root_id) == "CLASS":
+            _set_information_content_in_subgraph(ontology=ontology, root_id=root_id,
+                                                 maxleaves=ontology.node(root_id)["num_leaves"], relations=relations)
 
 
 def get_all_paths_to_root(node_id: str, ontology: Ontology, min_distance_from_root: int = 0,