napistu 0.3.6__py3-none-any.whl → 0.4.0__py3-none-any.whl

napistu/ingestion/string.py

@@ -8,15 +8,11 @@ from napistu import sbml_dfs_core
 from napistu import sbml_dfs_utils
 from napistu import source
 from napistu import utils
+from napistu.ingestion import napistu_edgelist
 from napistu.constants import BQB
 from napistu.constants import MINI_SBO_FROM_NAME
-from napistu.ingestion import napistu_edgelist
-from napistu.ingestion.constants import SBML_SPECIES_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SBML_SPECIES_DICT_NAME
-from napistu.ingestion.constants import SMBL_REACTION_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SMBL_REACTION_DICT_IS_REVERSIBLE
-from napistu.ingestion.constants import SMBL_REACTION_DICT_NAME
-from napistu.ingestion.constants import SMBL_REACTION_SPEC_SBO_TERM
+from napistu.constants import ONTOLOGIES
+from napistu.constants import SBML_DFS
 from napistu.ingestion.constants import STRING_DOWNSTREAM_COMPARTMENT
 from napistu.ingestion.constants import STRING_DOWNSTREAM_NAME
 from napistu.ingestion.constants import STRING_PROTEIN_ID
@@ -137,10 +133,10 @@ def convert_string_to_sbml_dfs(
 
     # define identifier mapping from aliases to use:
     alias_to_identifier = {
-        "Ensembl_gene": ("ensembl_gene", BQB.IS_ENCODED_BY),
-        "Ensembl_transcript": ("ensembl_transcript", BQB.IS_ENCODED_BY),
-        "Ensembl_translation": ("ensembl_protein", BQB.IS),
-        "Ensembl_UniProt_AC": ("uniprot", BQB.IS),
+        "Ensembl_gene": (ONTOLOGIES.ENSEMBL_GENE, BQB.IS_ENCODED_BY),
+        "Ensembl_transcript": (ONTOLOGIES.ENSEMBL_TRANSCRIPT, BQB.IS_ENCODED_BY),
+        "Ensembl_translation": (ONTOLOGIES.ENSEMBL_PROTEIN, BQB.IS),
+        "Ensembl_UniProt_AC": (ONTOLOGIES.UNIPROT, BQB.IS),
     }
 
     # filter aliases to only keep required ones
@@ -276,17 +272,17 @@ def _build_species_df(
     species_df = (
         pd.Series(
             list(set(edgelist[source_col]).union(edgelist[target_col])),
-            name=SBML_SPECIES_DICT_NAME,
+            name=SBML_DFS.S_NAME,
         )
         .to_frame()
-        .set_index(SBML_SPECIES_DICT_NAME, drop=False)
+        .set_index(SBML_DFS.S_NAME, drop=False)
         .apply(
             _get_identifiers,
             alias_to_identifier=alias_to_identifier,
             dat_alias=aliases,
             axis=1,
         )
-        .rename(SBML_SPECIES_DICT_IDENTIFIERS)
+        .rename(SBML_DFS.S_IDENTIFIERS)
         .reset_index()
     )
     return species_df
@@ -312,8 +308,8 @@ def _build_interactor_edgelist(
         **{
             STRING_UPSTREAM_COMPARTMENT: compartment,
             STRING_DOWNSTREAM_COMPARTMENT: compartment,
-            SMBL_REACTION_SPEC_SBO_TERM: sbo_interactor,
-            SMBL_REACTION_DICT_IDENTIFIERS: lambda x: identifiers.Identifiers([]),
+            SBML_DFS.SBO_TERM: sbo_interactor,
+            SBML_DFS.R_IDENTIFIERS: lambda x: identifiers.Identifiers([]),
         }
     )
     if add_reverse_interactions:
@@ -336,10 +332,10 @@ def _build_interactor_edgelist(
         )
 
     interaction_edgelist = dat
-    interaction_edgelist[SMBL_REACTION_DICT_NAME] = _build_string_reaction_name(
+    interaction_edgelist[SBML_DFS.R_NAME] = _build_string_reaction_name(
         dat[STRING_UPSTREAM_NAME], dat[STRING_DOWNSTREAM_NAME]
     )
-    interaction_edgelist[SMBL_REACTION_DICT_IS_REVERSIBLE] = True
+    interaction_edgelist[SBML_DFS.R_ISREVERSIBLE] = True
 
     return interaction_edgelist
 

napistu/ingestion/trrust.py

@@ -8,16 +8,11 @@ from napistu import identifiers
 from napistu import sbml_dfs_core
 from napistu import source
 from napistu import utils
+from napistu.constants import BQB
+from napistu.constants import IDENTIFIERS
 from napistu.constants import MINI_SBO_FROM_NAME
 from napistu.constants import SBOTERM_NAMES
-from napistu.ingestion.constants import SBML_COMPARTMENT_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SBML_COMPARTMENT_DICT_NAME
-from napistu.ingestion.constants import SBML_SPECIES_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SBML_SPECIES_DICT_NAME
-from napistu.ingestion.constants import SMBL_REACTION_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SMBL_REACTION_DICT_IS_REVERSIBLE
-from napistu.ingestion.constants import SMBL_REACTION_DICT_NAME
-from napistu.ingestion.constants import SMBL_REACTION_SPEC_SBO_TERM
+from napistu.constants import SBML_DFS
 from napistu.ingestion.constants import SPECIES_FULL_NAME_HUMAN
 from napistu.ingestion.constants import STRING_DOWNSTREAM_COMPARTMENT
 from napistu.ingestion.constants import STRING_DOWNSTREAM_NAME
@@ -81,16 +76,16 @@ def convert_trrust_to_sbml_dfs(
     species_df = (
         pd.DataFrame(
             {
-                SBML_SPECIES_DICT_NAME: list(
+                SBML_DFS.S_NAME: list(
                     {*edge_summaries_df["from"], *edge_summaries_df["to"]}
                 )
             }
         )
         .merge(
-            uniprot_2_symbol.rename({TRRUST_SYMBOL: SBML_SPECIES_DICT_NAME}, axis=1),
+            uniprot_2_symbol.rename({TRRUST_SYMBOL: SBML_DFS.S_NAME}, axis=1),
             how="left",
         )
-        .set_index(SBML_SPECIES_DICT_NAME)
+        .set_index(SBML_DFS.S_NAME)
     )
 
     # create Identifiers objects for all species with uniprot IDs
@@ -106,14 +101,14 @@ def convert_trrust_to_sbml_dfs(
         [
             identifiers.Identifiers(
                 [
-                    identifiers.format_uri(uri=x, biological_qualifier_type="BQB_IS")
-                    for x in species_w_ids.loc[[ind]]["url"].tolist()
+                    identifiers.format_uri(uri=x, biological_qualifier_type=BQB.IS)
+                    for x in species_w_ids.loc[[ind]][IDENTIFIERS.URL].tolist()
                 ]
             )
             for ind in species_w_ids.index.unique()
         ],
         index=species_w_ids.index.unique(),
-    ).rename(SBML_SPECIES_DICT_IDENTIFIERS)
+    ).rename(SBML_DFS.S_IDENTIFIERS)
 
     # just retain s_name and s_Identifiers
     # this just needs a source object which will be added later
@@ -124,21 +119,21 @@ def convert_trrust_to_sbml_dfs(
         .merge(
             species_w_ids_series,
             how="left",
-            left_on=SBML_SPECIES_DICT_NAME,
+            left_on=SBML_DFS.S_NAME,
             right_index=True,
         )
         .reset_index(drop=True)
     )
     # stub genes with missing IDs
-    species_df[SBML_SPECIES_DICT_IDENTIFIERS] = species_df[SBML_SPECIES_DICT_IDENTIFIERS].fillna(  # type: ignore
+    species_df[SBML_DFS.S_IDENTIFIERS] = species_df[SBML_DFS.S_IDENTIFIERS].fillna(  # type: ignore
         value=identifiers.Identifiers([])
     )
 
     # define distinct compartments
     compartments_df = pd.DataFrame(
         {
-            SBML_COMPARTMENT_DICT_NAME: TRRUST_COMPARTMENT_NUCLEOPLASM,
-            SBML_COMPARTMENT_DICT_IDENTIFIERS: identifiers.Identifiers(
+            SBML_DFS.C_NAME: TRRUST_COMPARTMENT_NUCLEOPLASM,
+            SBML_DFS.C_IDENTIFIERS: identifiers.Identifiers(
                 [
                     identifiers.format_uri(
                         uri=identifiers.create_uri_url(
@@ -159,7 +154,7 @@ def convert_trrust_to_sbml_dfs(
         upstream_compartment=TRRUST_COMPARTMENT_NUCLEOPLASM,
         downstream_compartment=TRRUST_COMPARTMENT_NUCLEOPLASM,
     )
-    gene_gene_identifier_edgelist[SMBL_REACTION_DICT_NAME] = [
+    gene_gene_identifier_edgelist[SBML_DFS.R_NAME] = [
         f"{x} {y} of {z}"
         for x, y, z in zip(
             gene_gene_identifier_edgelist[STRING_UPSTREAM_NAME],
@@ -171,15 +166,15 @@ def convert_trrust_to_sbml_dfs(
     # convert relationships to SBO terms
     interaction_edgelist = gene_gene_identifier_edgelist.replace(
         {"sign": MINI_SBO_FROM_NAME}
-    ).rename({"sign": SMBL_REACTION_SPEC_SBO_TERM}, axis=1)
+    ).rename({"sign": SBML_DFS.SBO_TERM}, axis=1)
 
     # format pubmed identifiers of interactions
-    interaction_edgelist[SMBL_REACTION_DICT_IDENTIFIERS] = [
+    interaction_edgelist[SBML_DFS.R_IDENTIFIERS] = [
         _format_pubmed_for_interactions(x) for x in interaction_edgelist["reference"]
     ]
 
     # directionality: by default, set r_isreversible to False for TRRUST data
-    interaction_edgelist[SMBL_REACTION_DICT_IS_REVERSIBLE] = False
+    interaction_edgelist[SBML_DFS.R_ISREVERSIBLE] = False
 
     # reduce to essential variables
     interaction_edgelist = interaction_edgelist[
@@ -188,10 +183,10 @@ def convert_trrust_to_sbml_dfs(
             STRING_DOWNSTREAM_NAME,
             STRING_UPSTREAM_COMPARTMENT,
             STRING_DOWNSTREAM_COMPARTMENT,
-            SMBL_REACTION_DICT_NAME,
-            SMBL_REACTION_SPEC_SBO_TERM,
-            SMBL_REACTION_DICT_IDENTIFIERS,
-            SMBL_REACTION_DICT_IS_REVERSIBLE,
+            SBML_DFS.R_NAME,
+            SBML_DFS.SBO_TERM,
+            SBML_DFS.R_IDENTIFIERS,
+            SBML_DFS.R_ISREVERSIBLE,
         ]
     ]
 
@@ -277,7 +272,7 @@ def _format_pubmed_for_interactions(pubmed_set):
         url = identifiers.create_uri_url(ontology="pubmed", identifier=p, strict=False)
         if url is not None:
             valid_url = identifiers.format_uri(
-                uri=url, biological_qualifier_type="BQB_IS_DESCRIBED_BY"
+                uri=url, biological_qualifier_type=BQB.IS_DESCRIBED_BY
             )
 
             ids.append(valid_url)

napistu/matching/interactions.py

@@ -10,9 +10,9 @@ from napistu import utils
 from napistu import sbml_dfs_core
 from napistu.matching.species import features_to_pathway_species
 from napistu.constants import (
-    CPR_EDGELIST_REQ_VARS,
+    NAPISTU_EDGELIST_REQ_VARS,
     IDENTIFIER_EDGELIST_REQ_VARS,
-    CPR_EDGELIST,
+    NAPISTU_EDGELIST,
     SBML_DFS,
     IDENTIFIERS,
 )
@@ -56,8 +56,8 @@ def edgelist_to_pathway_species(
     """
 
     required_vars_distinct_features = {
-        CPR_EDGELIST.IDENTIFIER_UPSTREAM,
-        CPR_EDGELIST.IDENTIFIER_DOWNSTREAM,
+        NAPISTU_EDGELIST.IDENTIFIER_UPSTREAM,
+        NAPISTU_EDGELIST.IDENTIFIER_DOWNSTREAM,
     }
     missing_required_vars_distinct_features = (
         required_vars_distinct_features.difference(
@@ -76,8 +76,8 @@ def edgelist_to_pathway_species(
     distinct_identifiers = (
         pd.concat(
             [
-                formatted_edgelist[CPR_EDGELIST.IDENTIFIER_UPSTREAM],
-                formatted_edgelist[CPR_EDGELIST.IDENTIFIER_DOWNSTREAM],
+                formatted_edgelist[NAPISTU_EDGELIST.IDENTIFIER_UPSTREAM],
+                formatted_edgelist[NAPISTU_EDGELIST.IDENTIFIER_DOWNSTREAM],
             ]
         )
         .drop_duplicates()
@@ -99,16 +99,16 @@ def edgelist_to_pathway_species(
     edges_on_pathway = formatted_edgelist.merge(
         features_on_pathway[[SBML_DFS.S_ID, IDENTIFIERS.IDENTIFIER]].rename(
             {
-                SBML_DFS.S_ID: CPR_EDGELIST.S_ID_UPSTREAM,
-                IDENTIFIERS.IDENTIFIER: CPR_EDGELIST.IDENTIFIER_UPSTREAM,
+                SBML_DFS.S_ID: NAPISTU_EDGELIST.S_ID_UPSTREAM,
+                IDENTIFIERS.IDENTIFIER: NAPISTU_EDGELIST.IDENTIFIER_UPSTREAM,
             },
             axis=1,
         )
     ).merge(
         features_on_pathway[[SBML_DFS.S_ID, IDENTIFIERS.IDENTIFIER]].rename(
             {
-                SBML_DFS.S_ID: CPR_EDGELIST.S_ID_DOWNSTREAM,
-                IDENTIFIERS.IDENTIFIER: CPR_EDGELIST.IDENTIFIER_DOWNSTREAM,
+                SBML_DFS.S_ID: NAPISTU_EDGELIST.S_ID_DOWNSTREAM,
+                IDENTIFIERS.IDENTIFIER: NAPISTU_EDGELIST.IDENTIFIER_DOWNSTREAM,
             },
             axis=1,
         )
@@ -159,15 +159,15 @@ def edgelist_to_scids(
 
     # expand from s_ids to sc_ids
     s_id_pairs = edges_on_pathway[
-        [CPR_EDGELIST.S_ID_UPSTREAM, CPR_EDGELIST.S_ID_DOWNSTREAM]
+        [NAPISTU_EDGELIST.S_ID_UPSTREAM, NAPISTU_EDGELIST.S_ID_DOWNSTREAM]
     ].drop_duplicates()
     sc_id_pairs = s_id_pairs.merge(
         sbml_dfs.compartmentalized_species[[SBML_DFS.S_ID]]
         .reset_index()
         .rename(
             {
-                SBML_DFS.S_ID: CPR_EDGELIST.S_ID_UPSTREAM,
-                SBML_DFS.SC_ID: CPR_EDGELIST.SC_ID_UPSTREAM,
+                SBML_DFS.S_ID: NAPISTU_EDGELIST.S_ID_UPSTREAM,
+                SBML_DFS.SC_ID: NAPISTU_EDGELIST.SC_ID_UPSTREAM,
             },
             axis=1,
         )
@@ -176,8 +176,8 @@ def edgelist_to_scids(
         .reset_index()
         .rename(
             {
-                SBML_DFS.S_ID: CPR_EDGELIST.S_ID_DOWNSTREAM,
-                SBML_DFS.SC_ID: CPR_EDGELIST.SC_ID_DOWNSTREAM,
+                SBML_DFS.S_ID: NAPISTU_EDGELIST.S_ID_DOWNSTREAM,
+                SBML_DFS.SC_ID: NAPISTU_EDGELIST.SC_ID_DOWNSTREAM,
             },
             axis=1,
         )
@@ -232,7 +232,7 @@ def filter_to_direct_mechanistic_interactions(
     )
 
     # reduce to distinct sc_id pairs
-    sc_id_pairs = edgelist_w_scids[list(CPR_EDGELIST_REQ_VARS)].drop_duplicates()
+    sc_id_pairs = edgelist_w_scids[list(NAPISTU_EDGELIST_REQ_VARS)].drop_duplicates()
 
     # define all existing direct regulatory interactions
     pathway_interactions = pd.concat(
@@ -241,36 +241,36 @@ def filter_to_direct_mechanistic_interactions(
             sbml_dfs.reaction_species[
                 sbml_dfs.reaction_species[SBML_DFS.STOICHIOMETRY] == 0
             ][[SBML_DFS.R_ID, SBML_DFS.SC_ID]]
-            .rename({SBML_DFS.SC_ID: CPR_EDGELIST.SC_ID_UPSTREAM}, axis=1)
+            .rename({SBML_DFS.SC_ID: NAPISTU_EDGELIST.SC_ID_UPSTREAM}, axis=1)
             .merge(
                 sbml_dfs.reaction_species[
                     sbml_dfs.reaction_species[SBML_DFS.STOICHIOMETRY] < 0
                 ][[SBML_DFS.R_ID, SBML_DFS.SC_ID]].rename(
-                    {SBML_DFS.SC_ID: CPR_EDGELIST.SC_ID_DOWNSTREAM}, axis=1
+                    {SBML_DFS.SC_ID: NAPISTU_EDGELIST.SC_ID_DOWNSTREAM}, axis=1
                 )
             ),
             # pair <0 -> >0 # substrates affect products
             sbml_dfs.reaction_species[
                 sbml_dfs.reaction_species[SBML_DFS.STOICHIOMETRY] < 0
             ][[SBML_DFS.R_ID, SBML_DFS.SC_ID]]
-            .rename({SBML_DFS.SC_ID: CPR_EDGELIST.SC_ID_UPSTREAM}, axis=1)
+            .rename({SBML_DFS.SC_ID: NAPISTU_EDGELIST.SC_ID_UPSTREAM}, axis=1)
             .merge(
                 sbml_dfs.reaction_species[
                     sbml_dfs.reaction_species[SBML_DFS.STOICHIOMETRY] > 0
                 ][[SBML_DFS.R_ID, SBML_DFS.SC_ID]].rename(
-                    {SBML_DFS.SC_ID: CPR_EDGELIST.SC_ID_DOWNSTREAM}, axis=1
+                    {SBML_DFS.SC_ID: NAPISTU_EDGELIST.SC_ID_DOWNSTREAM}, axis=1
                 )
             ),
             # pair 0 -> >0 # modifiers affect products
             sbml_dfs.reaction_species[
                 sbml_dfs.reaction_species[SBML_DFS.STOICHIOMETRY] == 0
             ][[SBML_DFS.R_ID, SBML_DFS.SC_ID]]
-            .rename({SBML_DFS.SC_ID: CPR_EDGELIST.SC_ID_UPSTREAM}, axis=1)
+            .rename({SBML_DFS.SC_ID: NAPISTU_EDGELIST.SC_ID_UPSTREAM}, axis=1)
             .merge(
                 sbml_dfs.reaction_species[
                     sbml_dfs.reaction_species[SBML_DFS.STOICHIOMETRY] > 0
                 ][[SBML_DFS.R_ID, SBML_DFS.SC_ID]].rename(
-                    {SBML_DFS.SC_ID: CPR_EDGELIST.SC_ID_DOWNSTREAM}, axis=1
+                    {SBML_DFS.SC_ID: NAPISTU_EDGELIST.SC_ID_DOWNSTREAM}, axis=1
                 )
             ),
         ]
@@ -282,16 +282,16 @@ def filter_to_direct_mechanistic_interactions(
         .merge(
             sbml_dfs.species[SBML_DFS.S_NAME]
             .to_frame()
-            .rename({SBML_DFS.S_NAME: CPR_EDGELIST.S_NAME_UPSTREAM}, axis=1),
-            left_on=CPR_EDGELIST.S_ID_UPSTREAM,
+            .rename({SBML_DFS.S_NAME: NAPISTU_EDGELIST.S_NAME_UPSTREAM}, axis=1),
+            left_on=NAPISTU_EDGELIST.S_ID_UPSTREAM,
             right_index=True,
             # add species metadata for matches
         )
         .merge(
             sbml_dfs.species[SBML_DFS.S_NAME]
             .to_frame()
-            .rename({SBML_DFS.S_NAME: CPR_EDGELIST.S_NAME_DOWNSTREAM}, axis=1),
-            left_on=CPR_EDGELIST.S_ID_DOWNSTREAM,
+            .rename({SBML_DFS.S_NAME: NAPISTU_EDGELIST.S_NAME_DOWNSTREAM}, axis=1),
+            left_on=NAPISTU_EDGELIST.S_ID_DOWNSTREAM,
             right_index=True,
             # add metadata for reactions where interaction occurs
         )
@@ -305,11 +305,11 @@ def filter_to_direct_mechanistic_interactions(
     edgelist_w_direct_mechanistic_interactions = edgelist_w_scids.merge(
         direct_edge_interactions[
             [
-                CPR_EDGELIST.SC_ID_UPSTREAM,
-                CPR_EDGELIST.SC_ID_DOWNSTREAM,
+                NAPISTU_EDGELIST.SC_ID_UPSTREAM,
+                NAPISTU_EDGELIST.SC_ID_DOWNSTREAM,
                 SBML_DFS.R_ID,
-                CPR_EDGELIST.S_NAME_UPSTREAM,
-                CPR_EDGELIST.S_NAME_DOWNSTREAM,
+                NAPISTU_EDGELIST.S_NAME_UPSTREAM,
+                NAPISTU_EDGELIST.S_NAME_DOWNSTREAM,
                 SBML_DFS.R_NAME,
             ]
         ]
@@ -369,23 +369,25 @@ def filter_to_indirect_mechanistic_interactions(
         edgelist_w_scids = paths._filter_paths_by_precomputed_distances(
             edgelist_w_scids.rename(
                 {
-                    CPR_EDGELIST.SC_ID_UPSTREAM: CPR_EDGELIST.SC_ID_ORIGIN,
-                    CPR_EDGELIST.SC_ID_DOWNSTREAM: CPR_EDGELIST.SC_ID_DEST,
+                    NAPISTU_EDGELIST.SC_ID_UPSTREAM: NAPISTU_EDGELIST.SC_ID_ORIGIN,
+                    NAPISTU_EDGELIST.SC_ID_DOWNSTREAM: NAPISTU_EDGELIST.SC_ID_DEST,
                 },
                 axis=1,
             ),
             precomputed_distances,
         ).rename(
             {
-                CPR_EDGELIST.SC_ID_ORIGIN: CPR_EDGELIST.SC_ID_UPSTREAM,
-                CPR_EDGELIST.SC_ID_DEST: CPR_EDGELIST.SC_ID_DOWNSTREAM,
+                NAPISTU_EDGELIST.SC_ID_ORIGIN: NAPISTU_EDGELIST.SC_ID_UPSTREAM,
+                NAPISTU_EDGELIST.SC_ID_DEST: NAPISTU_EDGELIST.SC_ID_DOWNSTREAM,
             },
             axis=1,
         )
 
     # find paths from 1 upstream to all desired downstream sc_ids
     # (this is the convention with igraph)
-    indexed_origin_vertices = edgelist_w_scids.set_index(CPR_EDGELIST.SC_ID_UPSTREAM)
+    indexed_origin_vertices = edgelist_w_scids.set_index(
+        NAPISTU_EDGELIST.SC_ID_UPSTREAM
+    )
 
     # loop through upstream cspecies and find paths to all downstream species
     global_dict = dict()
@@ -410,7 +412,7 @@ def filter_to_indirect_mechanistic_interactions(
             sbml_dfs,
             origin=an_origin_index,
             # find all unique destinations (as a list for compatibility with igraph dest)
-            dest=origin_targets[CPR_EDGELIST.SC_ID_DOWNSTREAM].unique().tolist(),
+            dest=origin_targets[NAPISTU_EDGELIST.SC_ID_DOWNSTREAM].unique().tolist(),
             weight_var=NAPISTU_GRAPH_EDGES.WEIGHTS,
         )
 
@@ -483,7 +485,7 @@ def filter_to_indirect_mechanistic_interactions(
 
     indirect_shortest_paths = edgelist_w_scids.merge(
         all_shortest_paths,
-        left_on=[CPR_EDGELIST.SC_ID_UPSTREAM, CPR_EDGELIST.SC_ID_DOWNSTREAM],
+        left_on=[NAPISTU_EDGELIST.SC_ID_UPSTREAM, NAPISTU_EDGELIST.SC_ID_DOWNSTREAM],
         right_on=[NAPISTU_GRAPH_EDGES.FROM, NAPISTU_GRAPH_EDGES.TO],
     )
 
@@ -498,9 +500,9 @@ def _edgelist_to_scids_if_needed(
 ) -> pd.DataFrame:
     """Map a set of edgelist species to cspecies or skip if cspecies were provided."""
 
-    if utils.match_pd_vars(edgelist, CPR_EDGELIST_REQ_VARS).are_present:
+    if utils.match_pd_vars(edgelist, NAPISTU_EDGELIST_REQ_VARS).are_present:
         logger.info(
-            f"An edgelist with {', '.join(CPR_EDGELIST_REQ_VARS)} was provided; identifier matching will be skipped"
+            f"An edgelist with {', '.join(NAPISTU_EDGELIST_REQ_VARS)} was provided; identifier matching will be skipped"
         )
         return edgelist
     else:

napistu/matching/species.py

@@ -33,7 +33,7 @@ def features_to_pathway_species(
         pd.Dataframe containing a "feature_identifiers_var" variable used to match entries
     species_identifiers: pd.DataFrame
         A table of molecular species identifiers produced from sbml_dfs.get_identifiers("species")
-        generally using sbml_dfs_core.export_sbml_dfs()
+        generally using sbml_dfs.export_sbml_dfs()
     ontologies: set
         A set of ontologies used to match features to pathway species
     feature_identifiers_var: str

napistu/modify/gaps.py

@@ -20,6 +20,7 @@ from napistu.constants import MINI_SBO_FROM_NAME
 from napistu.constants import SBOTERM_NAMES
 from napistu.constants import SOURCE_SPEC
 from napistu.ingestion.constants import EXCHANGE_COMPARTMENT
+from napistu.network.constants import GRAPH_WIRING_APPROACHES
 
 logger = logging.getLogger(__name__)
 
@@ -463,7 +464,7 @@ def _identify_species_needing_transport_reactions(
 
     # create a directed graph
     directed_graph = net_create.create_napistu_graph(
-        sbml_dfs, directed=True, graph_type="bipartite"
+        sbml_dfs, directed=True, wiring_approach=GRAPH_WIRING_APPROACHES.BIPARTITE
     )
 
     # consider each s_id and protein separately

napistu/network/constants.py

@@ -7,17 +7,6 @@ from types import SimpleNamespace
 from napistu.constants import SBML_DFS
 from napistu.constants import SBOTERM_NAMES
 
-# Graph types
-NAPISTU_GRAPH_TYPES = SimpleNamespace(
-    BIPARTITE="bipartite", REGULATORY="regulatory", SURROGATE="surrogate"
-)
-
-VALID_NAPISTU_GRAPH_TYPES = [
-    NAPISTU_GRAPH_TYPES.BIPARTITE,
-    NAPISTU_GRAPH_TYPES.REGULATORY,
-    NAPISTU_GRAPH_TYPES.SURROGATE,
-]
-
 NAPISTU_GRAPH = SimpleNamespace(VERTICES="vertices", EDGES="edges", METADATA="metadata")
 
 NAPISTU_GRAPH_DIRECTEDNESS = SimpleNamespace(
@@ -57,6 +46,67 @@ VALID_NAPISTU_GRAPH_NODE_TYPES = [
     NAPISTU_GRAPH_NODE_TYPES.SPECIES,
 ]
 
+# translating an SBML_dfs -> NapistuGraph
+
+GRAPH_WIRING_APPROACHES = SimpleNamespace(
+    BIPARTITE="bipartite", REGULATORY="regulatory", SURROGATE="surrogate"
+)
+
+VALID_GRAPH_WIRING_APPROACHES = list(GRAPH_WIRING_APPROACHES.__dict__.values())
+
+GRAPH_WIRING_HIERARCHIES = {
+    # three tiers with reactions in the middle
+    # in a bipartite networks molecules are connected to reactions but not other molecules
+    GRAPH_WIRING_APPROACHES.BIPARTITE: [
+        [
+            SBOTERM_NAMES.CATALYST,
+            SBOTERM_NAMES.INHIBITOR,
+            SBOTERM_NAMES.INTERACTOR,
+            SBOTERM_NAMES.MODIFIER,
+            SBOTERM_NAMES.REACTANT,
+            SBOTERM_NAMES.STIMULATOR,
+        ],
+        [NAPISTU_GRAPH_NODE_TYPES.REACTION],
+        [SBOTERM_NAMES.MODIFIED, SBOTERM_NAMES.PRODUCT],
+    ],
+    # the regulatory graph defines a hierarchy of upstream and downstream
+    # entities in a reaction
+    # modifier/stimulator/inhibitor -> catalyst -> reactant -> reaction -> product
+    GRAPH_WIRING_APPROACHES.REGULATORY: [
+        [SBOTERM_NAMES.INHIBITOR, SBOTERM_NAMES.MODIFIER, SBOTERM_NAMES.STIMULATOR],
+        [SBOTERM_NAMES.CATALYST],
+        [SBOTERM_NAMES.INTERACTOR, SBOTERM_NAMES.REACTANT],
+        [NAPISTU_GRAPH_NODE_TYPES.REACTION],
+        [SBOTERM_NAMES.MODIFIED, SBOTERM_NAMES.PRODUCT],
+    ],
+    # an alternative layout to regulatory where enyzmes are downstream of substrates.
+    # this doesn't make much sense from a regulatory perspective because
+    # enzymes modify substrates not the other way around. but, its what one might
+    # expect if catalysts are a surrogate for reactions as is the case for metabolic
+    # network layouts
+    GRAPH_WIRING_APPROACHES.SURROGATE: [
+        [SBOTERM_NAMES.INHIBITOR, SBOTERM_NAMES.MODIFIER, SBOTERM_NAMES.STIMULATOR],
+        [SBOTERM_NAMES.INTERACTOR, SBOTERM_NAMES.REACTANT],
+        [SBOTERM_NAMES.CATALYST],
+        [NAPISTU_GRAPH_NODE_TYPES.REACTION],
+        [SBOTERM_NAMES.MODIFIED, SBOTERM_NAMES.PRODUCT],
+    ],
+}
+
+# when should reaction vertices be excluded from the graph?
+
+DROP_REACTIONS_WHEN = SimpleNamespace(
+    ALWAYS="always",
+    # if there are 2 participants
+    EDGELIST="edgelist",
+    # if there are 2 participants which are both "interactor"
+    SAME_TIER="same_tier",
+)
+
+VALID_DROP_REACTIONS_WHEN = list(DROP_REACTIONS_WHEN.__dict__.values())
+
+# adding weights to NapistuGraph
+
 NAPISTU_WEIGHTING_STRATEGIES = SimpleNamespace(
     CALIBRATED="calibrated", MIXED="mixed", TOPOLOGY="topology", UNWEIGHTED="unweighted"
 )
@@ -116,40 +166,6 @@ VALID_NET_POLARITIES = [
     NET_POLARITY.AMBIGUOUS_INHIBITION,
 ]
 
-# the regulatory graph defines a hierarchy of upstream and downstream
-# entities in a reaction
-# modifier/stimulator/inhibitor -> catalyst -> reactant -> reaction -> product
-
-REGULATORY_GRAPH_HIERARCHY = [
-    [SBOTERM_NAMES.MODIFIER, SBOTERM_NAMES.STIMULATOR, SBOTERM_NAMES.INHIBITOR],
-    [SBOTERM_NAMES.CATALYST],
-    [SBOTERM_NAMES.REACTANT],
-    [NAPISTU_GRAPH_NODE_TYPES.REACTION],
-    # normally we don't expect interactors to be defined because they are handled by
-    # net_create._format_interactors_for_regulatory_graph() but include them here
-    # until Issue #102 is solved
-    [SBOTERM_NAMES.INTERACTOR],
-    [SBOTERM_NAMES.PRODUCT],
-]
-
-# an alternative layout to regulatory where enyzmes are downstream of substrates.
-# this doesn't make much sense from a regulatory perspective because
-# enzymes modify substrates not the other way around. but, its what one might
-# expect if catalysts are a surrogate for reactions as is the case for metabolic
-# network layouts
-
-SURROGATE_GRAPH_HIERARCHY = [
-    [SBOTERM_NAMES.MODIFIER, SBOTERM_NAMES.STIMULATOR, SBOTERM_NAMES.INHIBITOR],
-    [SBOTERM_NAMES.REACTANT],
-    [SBOTERM_NAMES.CATALYST],
-    [NAPISTU_GRAPH_NODE_TYPES.REACTION],
-    # normally we don't expect interactors to be defined because they are handled by
-    # net_create._format_interactors_for_regulatory_graph() but include them here
-    # until Issue #102 is solved
-    [SBOTERM_NAMES.INTERACTOR],
-    [SBOTERM_NAMES.PRODUCT],
-]
-
 NEIGHBORHOOD_NETWORK_TYPES = SimpleNamespace(
     DOWNSTREAM="downstream", HOURGLASS="hourglass", UPSTREAM="upstream"
 )

napistu/network/data_handling.py

@@ -6,7 +6,7 @@ import pandas as pd
 
 from napistu import sbml_dfs_core
 from napistu.network import net_create
-from napistu.network.napistu_graph_core import NapistuGraph
+from napistu.network.ng_core import NapistuGraph
 
 from napistu.constants import SBML_DFS, ENTITIES_W_DATA
 from napistu.network.constants import NAPISTU_GRAPH, DEFAULT_WT_TRANS, WEIGHTING_SPEC

napistu/network/neighborhoods.py

@@ -22,7 +22,7 @@ from napistu.constants import SBML_DFS
 from napistu.constants import MINI_SBO_NAME_TO_POLARITY
 from napistu.constants import MINI_SBO_TO_NAME
 
-from napistu.network.constants import NAPISTU_GRAPH_TYPES
+from napistu.network.constants import GRAPH_WIRING_APPROACHES
 from napistu.network.constants import NEIGHBORHOOD_NETWORK_TYPES
 from napistu.network.constants import VALID_NEIGHBORHOOD_NETWORK_TYPES
 
@@ -316,7 +316,7 @@ def create_neighborhood_prefix(network_type: str, order: int, top_n: int) -> str
 def load_neighborhoods_by_partition(
     selected_partition: int,
     neighborhood_outdir: str,
-    graph_type: str = NAPISTU_GRAPH_TYPES.REGULATORY,
+    wiring_approach: str = GRAPH_WIRING_APPROACHES.REGULATORY,
 ) -> None:
     """
     Load Neighborhoods By Partition
@@ -380,7 +380,7 @@ def load_neighborhoods_by_partition(
         model_prefix="curated",
         network_dir=consensus_outdir,
         directed=True,
-        graph_type=graph_type,
+        wiring_approach=wiring_approach,
     )
 
     all_neighborhoods_df, neighborhoods_dict = load_neighborhoods(