napistu 0.3.5__py3-none-any.whl → 0.3.7__py3-none-any.whl

napistu/ingestion/string.py

@@ -5,17 +5,14 @@ import logging
 import pandas as pd
 from napistu import identifiers
 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
@@ -136,10 +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
@@ -158,7 +155,7 @@ def convert_string_to_sbml_dfs(
     # Define compartments
     # Currently we are mapping everything to the `CELLULAR_COMPONENT`
     # which is a catch-all go: for unknown localisation
-    compartments_df = sbml_dfs_core._stub_compartments()
+    compartments_df = sbml_dfs_utils.stub_compartments()
 
     # define interactions
     interaction_edgelist = _build_interactor_edgelist(uq_string_edgelist)
@@ -275,17 +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
@@ -311,8 +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:
@@ -335,10 +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/ingestion/yeast.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import pandas as pd
 from napistu import identifiers
 from napistu import sbml_dfs_core
+from napistu import sbml_dfs_utils
 from napistu import source
 from napistu import utils
 from napistu.constants import BQB
@@ -105,7 +106,7 @@ def convert_idea_kinetics_to_sbml_dfs(
     # Constant fields (for this data source)
 
     # setup compartments (just treat this as uncompartmentalized for now)
-    compartments_df = sbml_dfs_core._stub_compartments()
+    compartments_df = sbml_dfs_utils.stub_compartments()
 
     # Per convention unaggregated models receive an empty source
     interaction_source = source.Source(init=True)

napistu/matching/interactions.py

@@ -40,7 +40,7 @@ def edgelist_to_pathway_species(
         pd.Dataframe containing a "identifier_upstream" and "identifier_downstream" variables used to 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()
+        sbml_dfs.export_sbml_dfs()
     ontologies: set
         A set of ontologies used to match features to pathway species
     feature_id_var: str, default=FEATURE_ID_VAR_DEFAULT
@@ -138,7 +138,7 @@ def edgelist_to_scids(
         A mechanistic model
     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()
+        sbml_dfs.get_identifiers("species") generally using sbml_dfs.export_sbml_dfs()
     ontologies: set
         A set of ontologies used to match features to pathway species
 
@@ -218,7 +218,7 @@ def filter_to_direct_mechanistic_interactions(
     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()
+        using sbml_dfs.export_sbml_dfs()
     ontologies: set
         A set of ontologies used to match features to pathway species
 
@@ -342,7 +342,7 @@ def filter_to_indirect_mechanistic_interactions(
         A mechanistic model
     species_identifiers: pandas.DataFrame
         A table of molecular species identifiers produced from
-        sbml_dfs.get_identifiers("species") generally using sbml_dfs_core.export_sbml_dfs()
+        sbml_dfs.get_identifiers("species") generally using sbml_dfs.export_sbml_dfs()
     napistu_graph: igraph.Graph
         A network representation of the sbml_dfs model
     ontologies: set

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/uncompartmentalize.py

@@ -48,7 +48,7 @@ def uncompartmentalize_sbml_dfs(
         )
 
     # 1. update the compartments table to the stubbed default level: GO CELLULAR_COMPONENT
-    stubbed_compartment = sbml_dfs_core._stub_compartments().assign(
+    stubbed_compartment = sbml_dfs_utils.stub_compartments().assign(
         c_Source=_create_stubbed_source()
     )
 

napistu/network/net_create.py

@@ -1697,7 +1697,7 @@ def _create_topology_weights(
         base_score (float): offset which will be added to all weights.
         protein_multiplier (int): multiplier for non-metabolite species (lower weight paths will tend to be selected).
         metabolite_multiplier (int): multiplier for metabolites [defined a species with a ChEBI ID).
-        unknown_multiplier (int): multiplier for species without any identifier. See sbml_dfs_core.species_type_types.
+        unknown_multiplier (int): multiplier for species without any identifier. See sbml_dfs_utils.species_type_types.
         scale_multiplier_by_meandegree (bool): if True then multipliers will be rescaled by the average number of
             connections a node has (i.e., its degree) so that weights will be relatively similar regardless of network
             size and sparsity.

napistu/network/paths.py

@@ -489,7 +489,7 @@ def _label_path_reactions(sbml_dfs: sbml_dfs_core.SBML_dfs, paths_df: pd.DataFra
         reaction_info = (
             pd.concat(
                 [
-                    sbml_dfs_core.reaction_summaries(sbml_dfs, r_ids=x)
+                    sbml_dfs.reaction_formulas(r_ids=x)
                     for x in set(reaction_paths["node"])
                 ]
             )

napistu/ontologies/dogma.py

@@ -4,6 +4,7 @@ import logging
 import pandas as pd
 
 from napistu import sbml_dfs_core
+from napistu import sbml_dfs_utils
 from napistu import source
 from napistu import identifiers
 from napistu import utils
@@ -59,7 +60,7 @@ def create_dogmatic_sbml_dfs(
     )
 
     # stub required but invariant variables
-    compartments_df = sbml_dfs_core._stub_compartments()
+    compartments_df = sbml_dfs_utils.stub_compartments()
     interaction_source = source.Source(init=True)
 
     # interactions table. This is required to create the sbml_dfs but we'll drop the info later

napistu/ontologies/genodexito.py

@@ -356,7 +356,7 @@ class Genodexito:
             )
             logger.debug(
                 f"{ids.shape[0] - expanded_ids.shape[0]} "
-                "ids are not included in expanded ids"
+                "ids are not included in expanded ids. These will be filled with empty Identifiers"
             )
         else:
             matched_expanded_ids = expanded_ids
@@ -364,6 +364,10 @@ class Genodexito:
         updated_ids = ids.drop(SBML_DFS.S_IDENTIFIERS, axis=1).join(
             pd.DataFrame(matched_expanded_ids)
         )
+        # fill missing attributes with empty Identifiers
+        updated_ids[SBML_DFS.S_IDENTIFIERS] = updated_ids[
+            SBML_DFS.S_IDENTIFIERS
+        ].fillna(identifiers.Identifiers([]))
 
         setattr(sbml_dfs, "species", updated_ids)
 

napistu/ontologies/renaming.py

@@ -72,6 +72,10 @@ def rename_species_ontologies(
     updated_species = sbml_dfs.species.drop(SBML_DFS.S_IDENTIFIERS, axis=1).join(
         pd.DataFrame(species_identifiers)
     )
+    # fill missing attributes with empty Identifiers
+    updated_species[SBML_DFS.S_IDENTIFIERS] = updated_species[
+        SBML_DFS.S_IDENTIFIERS
+    ].fillna(identifiers.Identifiers([]))
 
     setattr(sbml_dfs, "species", updated_species)