napistu 0.3.7__py3-none-any.whl → 0.4.0__py3-none-any.whl

napistu/__main__.py

@@ -621,7 +621,11 @@ def exporter():
     "--format", "-f", default="pickle", help="Output format: gml, edgelist, pickle"
 )
 @click.option(
-    "--graph_type", "-g", type=str, default="bipartite", help="bipartite or regulatory"
+    "--wiring_approach",
+    "-g",
+    type=str,
+    default="bipartite",
+    help="bipartite or regulatory",
 )
 @click.option(
     "--weighting_strategy",
@@ -645,7 +649,7 @@ def export_igraph(
     output_uri: str,
     graph_attrs_spec_uri: str | None,
     format: str,
-    graph_type: str,
+    wiring_approach: str,
     weighting_strategy: str,
     directed: bool,
     reverse: bool,
@@ -663,7 +667,7 @@ def export_igraph(
         reaction_graph_attrs=graph_attrs_spec,
         directed=directed,
         edge_reversed=reverse,
-        graph_type=graph_type,
+        wiring_approach=wiring_approach,
         weighting_strategy=weighting_strategy,
         verbose=True,
     )
@@ -753,7 +757,7 @@ def export_precomputed_distances(
         weights_vars=weights_vars_list,
     )
 
-    precompute.save_precomputed_distances(precomputed_distances, output_uri)
+    utils.save_parquet(precomputed_distances, output_uri)
 
 
 @exporter.command(name="export_smbl_dfs_tables")

napistu/constants.py

@@ -198,22 +198,7 @@ BQB = SimpleNamespace(
     UNKNOWN="BQB_UNKNOWN",
 )
 
-VALID_BQB_TERMS = [
-    BQB.IS,
-    BQB.HAS_PART,
-    BQB.IS_PART_OF,
-    BQB.IS_VERSION_OF,
-    BQB.HAS_VERSION,
-    BQB.IS_HOMOLOG_TO,
-    BQB.IS_DESCRIBED_BY,
-    BQB.IS_ENCODED_BY,
-    BQB.ENCODES,
-    BQB.OCCURS_IN,
-    BQB.HAS_PROPERTY,
-    BQB.IS_PROPERTY_OF,
-    BQB.HAS_TAXON,
-    BQB.UNKNOWN,
-]
+VALID_BQB_TERMS = list(BQB.__dict__.values())
 
 # molecules are distinctly defined by these BQB terms
 BQB_DEFINING_ATTRS = [BQB.IS, BQB.IS_HOMOLOG_TO]
@@ -266,6 +251,7 @@ SBOTERM_NAMES = SimpleNamespace(
     CATALYST="catalyst",
     INHIBITOR="inhibitor",
     STIMULATOR="stimulator",
+    MODIFIED="modified",
     MODIFIER="modifier",
     INTERACTOR="interactor",
 )
@@ -274,22 +260,27 @@ MINI_SBO_TO_NAME = {
     "SBO:0000010": SBOTERM_NAMES.REACTANT,
     "SBO:0000011": SBOTERM_NAMES.PRODUCT,
     "SBO:0000013": SBOTERM_NAMES.CATALYST,
-    "SBO:0000020": SBOTERM_NAMES.INHIBITOR,
-    "SBO:0000459": SBOTERM_NAMES.STIMULATOR,
     "SBO:0000019": SBOTERM_NAMES.MODIFIER,
+    "SBO:0000020": SBOTERM_NAMES.INHIBITOR,
     "SBO:0000336": SBOTERM_NAMES.INTERACTOR,
+    "SBO:0000459": SBOTERM_NAMES.STIMULATOR,
+    "SBO:0000644": SBOTERM_NAMES.MODIFIED,
 }
 
 MINI_SBO_FROM_NAME = {
-    SBOTERM_NAMES.REACTANT: "SBO:0000010",
-    SBOTERM_NAMES.PRODUCT: "SBO:0000011",
     SBOTERM_NAMES.CATALYST: "SBO:0000013",
     SBOTERM_NAMES.INHIBITOR: "SBO:0000020",
-    SBOTERM_NAMES.STIMULATOR: "SBO:0000459",
-    SBOTERM_NAMES.MODIFIER: "SBO:0000019",  # parent category of inhibitor and stimulator (i.e., activator)
     SBOTERM_NAMES.INTERACTOR: "SBO:0000336",  # entity participating in a physical or functional interaction
+    SBOTERM_NAMES.MODIFIED: "SBO:0000644",
+    SBOTERM_NAMES.MODIFIER: "SBO:0000019",  # parent category of inhibitor and stimulator (i.e., activator)
+    SBOTERM_NAMES.PRODUCT: "SBO:0000011",
+    SBOTERM_NAMES.REACTANT: "SBO:0000010",  # aka substrate
+    SBOTERM_NAMES.STIMULATOR: "SBO:0000459",  # aka activator
 }
 
+VALID_SBO_TERM_NAMES = list(SBOTERM_NAMES.__dict__.values())
+VALID_SBO_TERMS = list(MINI_SBO_FROM_NAME.values())
+
 SBO_MODIFIER_NAMES = {
     SBOTERM_NAMES.INHIBITOR,
     SBOTERM_NAMES.STIMULATOR,
@@ -297,13 +288,14 @@ SBO_MODIFIER_NAMES = {
 }
 
 MINI_SBO_NAME_TO_POLARITY = {
-    SBOTERM_NAMES.REACTANT: "activation",
-    SBOTERM_NAMES.PRODUCT: "activation",
     SBOTERM_NAMES.CATALYST: "activation",
     SBOTERM_NAMES.INHIBITOR: "inhibition",
-    SBOTERM_NAMES.STIMULATOR: "activation",
-    SBOTERM_NAMES.MODIFIER: "ambiguous",
     SBOTERM_NAMES.INTERACTOR: "ambiguous",
+    SBOTERM_NAMES.MODIFIED: "ambiguous",
+    SBOTERM_NAMES.MODIFIER: "ambiguous",
+    SBOTERM_NAMES.PRODUCT: "activation",
+    SBOTERM_NAMES.REACTANT: "ambiguous",
+    SBOTERM_NAMES.STIMULATOR: "activation",
 }
 
 # how does changing a reactions' membership
@@ -321,6 +313,7 @@ SBO_NAME_TO_ROLE = {
     SBOTERM_NAMES.CATALYST: SBO_ROLES_DEFS.REQUIRED,
     SBOTERM_NAMES.INHIBITOR: SBO_ROLES_DEFS.OPTIONAL,
     SBOTERM_NAMES.STIMULATOR: SBO_ROLES_DEFS.OPTIONAL,
+    SBOTERM_NAMES.MODIFIED: SBO_ROLES_DEFS.DEFINING,
     SBOTERM_NAMES.MODIFIER: SBO_ROLES_DEFS.OPTIONAL,
 }
 
@@ -338,7 +331,7 @@ VALID_SBO_ROLES = (
 
 # required variables for the edgelist formats used by the matching subpackage
 # also used in some network modules
-CPR_EDGELIST = SimpleNamespace(
+NAPISTU_EDGELIST = SimpleNamespace(
     S_ID_UPSTREAM="s_id_upstream",
     S_ID_DOWNSTREAM="s_id_downstream",
     SC_ID_UPSTREAM="sc_id_upstream",
@@ -352,18 +345,18 @@ CPR_EDGELIST = SimpleNamespace(
 )
 
 IDENTIFIER_EDGELIST_REQ_VARS = {
-    CPR_EDGELIST.IDENTIFIER_UPSTREAM,
-    CPR_EDGELIST.IDENTIFIER_DOWNSTREAM,
+    NAPISTU_EDGELIST.IDENTIFIER_UPSTREAM,
+    NAPISTU_EDGELIST.IDENTIFIER_DOWNSTREAM,
 }
 
-CPR_EDGELIST_REQ_VARS = {
-    CPR_EDGELIST.S_ID_UPSTREAM,
-    CPR_EDGELIST.S_ID_DOWNSTREAM,
-    CPR_EDGELIST.SC_ID_UPSTREAM,
-    CPR_EDGELIST.SC_ID_DOWNSTREAM,
+NAPISTU_EDGELIST_REQ_VARS = {
+    NAPISTU_EDGELIST.S_ID_UPSTREAM,
+    NAPISTU_EDGELIST.S_ID_DOWNSTREAM,
+    NAPISTU_EDGELIST.SC_ID_UPSTREAM,
+    NAPISTU_EDGELIST.SC_ID_DOWNSTREAM,
 }
 
-CPR_PATH_REQ_VARS = {CPR_EDGELIST.SC_ID_ORIGIN, CPR_EDGELIST.SC_ID_DEST}
+NAPISTU_PATH_REQ_VARS = {NAPISTU_EDGELIST.SC_ID_ORIGIN, NAPISTU_EDGELIST.SC_ID_DEST}
 
 FEATURE_ID_VAR_DEFAULT = "feature_id"
 

napistu/ingestion/napistu_edgelist.py

@@ -20,9 +20,9 @@ def remove_reciprocal_interactions(
 
     Args:
         edgelist (pd.DataFrame): edgelist (pd.DataFrame): edgelist where the first two
-          columns are assumed to be the edge vertices
+            columns are assumed to be the edge vertices
         extra_defining_vars (list): list (which can be empty) of variables which define
-          a unique interaction beyond the vertices
+            a unique interaction beyond the vertices
 
     Returns:
         indegenerate_edgelist (pd.DataFrame): edgelist with B-A edges removed and A-B retained
@@ -58,9 +58,9 @@ def count_fraction_of_reciprocal_interactions(
 
     Args:
         edgelist (pd.DataFrame): edgelist (pd.DataFrame): edgelist where the first two
-          columns are assumed to be the edge vertices
+            columns are assumed to be the edge vertices
         extra_defining_vars (list): list (which can be empty) of variables which define
-          a unique interaction beyond the vertices
+            a unique interaction beyond the vertices
 
     Returns:
         fraction (float): fraction of A-B edges which are also included as B-A edges

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/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(