napistu 0.2.5.dev6__tar.gz → 0.3.1__tar.gz

{napistu-0.2.5.dev6/src/napistu.egg-info → napistu-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: napistu
-Version: 0.2.5.dev6
+Version: 0.3.1
 Summary: Connecting high-dimensional data to curated pathways
 Home-page: https://github.com/napistu/napistu-py
 Author: Sean Hackett
@@ -23,6 +23,7 @@ Requires-Dist: fs<3.0.0,>=2.4.0
 Requires-Dist: fs-gcsfs<2.0.0,>=1.5.0
 Requires-Dist: igraph
 Requires-Dist: matplotlib<4.0.0,>=3.5.0
+Requires-Dist: mygene<4.0.0,>=3.0.0
 Requires-Dist: numpy<3.0.0,>=1.24.0
 Requires-Dist: pandas<3.0.0,>=1.5.0
 Requires-Dist: pydantic<3.0.0,>=2.0.0
@@ -32,6 +33,7 @@ Requires-Dist: scipy<2.0.0,>=1.10.0
 Requires-Dist: tqdm
 Requires-Dist: zeep<4.0.0,>=3.0.0
 Provides-Extra: dev
+Requires-Dist: napistu[mcp,scverse]; extra == "dev"
 Requires-Dist: black>=24.0.0; extra == "dev"
 Requires-Dist: ipykernel; extra == "dev"
 Requires-Dist: pre-commit<4.0.0,>=3.0.0; extra == "dev"
@@ -52,6 +54,9 @@ Provides-Extra: rpy2
 Requires-Dist: pyarrow<19.0.0,>=15.0.0; extra == "rpy2"
 Requires-Dist: rpy2<4.0.0,>=3.5.0; extra == "rpy2"
 Requires-Dist: rpy2-arrow<1.0.0,>=0.1.0; extra == "rpy2"
+Provides-Extra: scverse
+Requires-Dist: anndata; extra == "scverse"
+Requires-Dist: mudata; extra == "scverse"
 Dynamic: license-file
 
 # Napistu Python Library
@@ -75,8 +80,8 @@ pip install .
 ```
 
 ## Documentation
-📘 **Full Documentation**: [https://napistu.readthedocs.io](https://napistu.readthedocs.io)
-** Wiki **: [napistu/wiki](https://github.com/napistu/napistu/wiki)
+- 📘 **Library Documentation**: [napistu.readthedocs.io](https://napistu.readthedocs.io)
+- 🚸 **Project Documentation**: [napistu/wiki](https://github.com/napistu/napistu/wiki)
 
 ### Quick Links
 - [Installation Guide](https://napistu.readthedocs.io/en/latest/installation.html)

{napistu-0.2.5.dev6 → napistu-0.3.1}/README.md

@@ -19,8 +19,8 @@ pip install .
 ```
 
 ## Documentation
-📘 **Full Documentation**: [https://napistu.readthedocs.io](https://napistu.readthedocs.io)
-** Wiki **: [napistu/wiki](https://github.com/napistu/napistu/wiki)
+- 📘 **Library Documentation**: [napistu.readthedocs.io](https://napistu.readthedocs.io)
+- 🚸 **Project Documentation**: [napistu/wiki](https://github.com/napistu/napistu/wiki)
 
 ### Quick Links
 - [Installation Guide](https://napistu.readthedocs.io/en/latest/installation.html)

{napistu-0.2.5.dev6 → napistu-0.3.1}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = napistu
-version = 0.2.5.dev6
+version = 0.3.1
 description = Connecting high-dimensional data to curated pathways
 long_description = file: README.md
 long_description_content_type = text/markdown
@@ -29,6 +29,7 @@ install_requires =
 	fs-gcsfs>=1.5.0,<2.0.0
 	igraph
 	matplotlib>=3.5.0,<4.0.0
+	mygene>=3.0.0,<4.0.0
 	numpy>=1.24.0,<3.0.0
 	pandas>=1.5.0,<3.0.0
 	pydantic>=2.0.0,<3.0.0
@@ -50,6 +51,7 @@ console_scripts =
 
 [options.extras_require]
 dev = 
+	napistu[mcp, scverse]
 	black>=24.0.0
 	ipykernel
 	pre-commit>=3.0.0,<4.0.0
@@ -70,6 +72,9 @@ rpy2 =
 	pyarrow>=15.0.0,<19.0.0
 	rpy2>=3.5.0,<4.0.0
 	rpy2-arrow>=0.1.0,<1.0.0
+scverse = 
+	anndata
+	mudata
 
 [tool:pytest]
 filterwarnings = 

{napistu-0.2.5.dev6 → napistu-0.3.1}/src/napistu/__main__.py

@@ -1,4 +1,4 @@
-"""The CLI for cpr"""
+"""The CLI for Napistu"""
 
 from __future__ import annotations
 
@@ -13,11 +13,14 @@ import napistu
 import igraph as ig
 import pandas as pd
 from napistu import consensus as cpr_consensus
-from napistu import constants
 from napistu import indices
 from napistu import sbml_dfs_core
 from napistu import utils
+from napistu.context import filtering
+from napistu.matching import mount
 from napistu.ingestion import bigg
+from napistu.ingestion import gtex
+from napistu.ingestion import hpa
 from napistu.ingestion import reactome
 from napistu.ingestion import sbml
 from napistu.ingestion import string
@@ -27,15 +30,17 @@ from napistu.modify import gaps
 from napistu.modify import pathwayannot
 from napistu.modify import uncompartmentalize
 from napistu.network import net_create
-from napistu.network import net_utils
+from napistu.network.ig_utils import get_graph_summary
+from napistu.network.ng_utils import read_graph_attrs_spec
 from napistu.network import precompute
-from napistu.rpy2 import has_rpy2
+from napistu.ontologies.genodexito import Genodexito
+from napistu.ontologies import dogma
+from napistu.constants import ONTOLOGIES
+from napistu.constants import RESOLVE_MATCHES_AGGREGATORS
+from napistu.ingestion.constants import PROTEINATLAS_SUBCELL_LOC_URL
+from napistu.ingestion.constants import GTEX_RNASEQ_EXPRESSION_URL
 from fs import open_fs
 
-if has_rpy2:
-    from napistu.rpy2 import rids
-    from napistu.rpy2 import netcontextr, callr
-
 logger = logging.getLogger(napistu.__name__)
 click_logging.basic_config(logger)
 
@@ -89,15 +94,12 @@ def load_ttrust(target_uri: str):
 @click.option(
     "--url",
     type=str,
-    default=constants.PROTEINATLAS_SUBCELL_LOC_URL,
+    default=PROTEINATLAS_SUBCELL_LOC_URL,
     help="URL to download the zipped protein atlas subcellular localization tsv from.",
 )
 @click_logging.simple_verbosity_option(logger)
 def load_proteinatlas_subcell(target_uri: str, url: str):
-    file_ext = constants.PROTEINATLAS_SUBCELL_LOC_URL.split(".")[-1]
-    target_filename = url.split("/")[-1].split(f".{file_ext}")[0]
-    logger.info("Start downloading proteinatlas %s to %s", url, target_uri)
-    utils.download_wget(url, target_uri, target_filename=target_filename)
+    hpa.download_hpa_data(target_uri, url)
 
 
 @load.command(name="gtex-rnaseq-expression")
@@ -105,13 +107,12 @@ def load_proteinatlas_subcell(target_uri: str, url: str):
 @click.option(
     "--url",
     type=str,
-    default=constants.GTEX_RNASEQ_EXPRESSION_URL,
+    default=GTEX_RNASEQ_EXPRESSION_URL,
     help="URL to download the gtex file from.",
 )
 @click_logging.simple_verbosity_option(logger)
 def load_gtex_rnaseq(target_uri: str, url: str):
-    logger.info("Start downloading gtex %s to %s", url, target_uri)
-    utils.download_wget(url, target_uri)
+    gtex.download_gtex_rnaseq(target_uri, url)
 
 
 @load.command(name="string-db")
@@ -411,7 +412,7 @@ def apply_manual_curations(model_uri: str, curation_dir: str, output_model_uri:
     """Apply manual curations to a consensus model
 
     The curation dir is a directory containing the manual curations
-    Check cpr.curation.curate_sbml_dfs for more information.
+    Check napistu.modify.curation.curate_sbml_dfs for more information.
     """
     model = utils.load_pickle(model_uri)
     model = curation.curate_sbml_dfs(curation_dir=curation_dir, sbml_dfs=model)
@@ -419,52 +420,80 @@ def apply_manual_curations(model_uri: str, curation_dir: str, output_model_uri:
 
 
 @refine.command(name="expand_identifiers")
-@click.argument("model_uri", type=str)
+@click.argument("sbml_dfs_uri", type=str)
 @click.argument("output_model_uri", type=str)
-@click.option(
-    "--id-type",
-    "-u",
-    type=click.Choice(["species", "compartments", "reactions"]),
-    default="species",
-)
 @click.option("--species", "-s", default="Homo sapiens", type=str)
 @click.option(
     "--ontologies", "-o", multiple=True, type=str, help="Ontologies to add or complete"
 )
+@click.option(
+    "--preferred_method",
+    "-p",
+    default="bioconductor",
+    type=str,
+    help="Preferred method to use for identifier expansion",
+)
+@click.option(
+    "--allow_fallback",
+    "-a",
+    default=True,
+    type=bool,
+    help="Allow fallback to other methods if preferred method fails",
+)
 def expand_identifiers(
-    model_uri: str,
+    sbml_dfs_uri: str,
     output_model_uri: str,
-    id_type: str,
     species: str,
-    ontologies: list[str],
+    ontologies: set[str],
+    preferred_method: str,
+    allow_fallback: bool,
 ):
     """Expand identifiers of a model
 
     Args:
-        model_uri (str): uri of model in sbml dfs format
+        sbml_dfs_uri (str): uri of model in sbml dfs format
         output_model_uri (str): output uri of model in sbml dfs format
-        id_type (str): identifier type, one of: species, compartments, reactions
         species (str): Species to use
-        ontologies (list[str]): ontologies to add or update
+        ontologies (set[str]): ontologies to add or update
 
     Example call:
     > cpr refine expand_identifiers gs://<uri> ./test.pickle -o ensembl_gene
     """
-
-    model: sbml.SBML_dfs = utils.load_pickle(model_uri)  # type: ignore
+    sbml_dfs: sbml.SBML_dfs = utils.load_pickle(sbml_dfs_uri)  # type: ignore
     if len(ontologies) == 0:
         raise ValueError("No ontologies to expand specified.")
-    expanded_ids = rids.expand_identifiers(model, id_type, species, ontologies)
-    rids.update_expanded_identifiers(model, id_type, expanded_ids)
-    utils.save_pickle(output_model_uri, model)
+
+    Genodexito(
+        species=species,
+        preferred_method=preferred_method,
+        allow_fallback=allow_fallback,
+    ).expand_sbml_dfs_ids(sbml_dfs, ontologies=ontologies)
+
+    utils.save_pickle(output_model_uri, sbml_dfs)
 
 
 @integrate.command(name="dogmatic_scaffold")
 @click.argument("output_model_uri", type=str)
 @click.option("--species", "-s", default="Homo sapiens", type=str)
+@click.option(
+    "--preferred_method",
+    "-p",
+    default="bioconductor",
+    type=str,
+    help="Preferred method to use for identifier expansion",
+)
+@click.option(
+    "--allow_fallback",
+    "-a",
+    default=True,
+    type=bool,
+    help="Allow fallback to other methods if preferred method fails",
+)
 def dogmatic_scaffold(
     output_model_uri: str,
     species: str,
+    preferred_method: str,
+    allow_fallback: bool,
 ):
     """Dogmatic Scaffold
 
@@ -476,25 +505,23 @@ def dogmatic_scaffold(
     > cpr integrate dogmatic_scaffold ./test.pickle
     """
 
-    dogmatic_sbml_dfs = rids.create_dogmatic_sbml_dfs(species)
+    dogmatic_sbml_dfs = dogma.create_dogmatic_sbml_dfs(
+        species=species,
+        preferred_method=preferred_method,
+        allow_fallback=allow_fallback,
+    )
+
     utils.save_pickle(output_model_uri, dogmatic_sbml_dfs)
 
 
 @refine.command(name="filter_gtex_tissue")
-@click.argument("model_uri", type=str)
+@click.argument("sbml_dfs_uri", type=str)
 @click.argument("gtex_file_uri", type=str)
 @click.argument("output_model_uri", type=str)
 @click.argument("tissue", type=str)
-@click.option(
-    "--filter-non-genic-reactions",
-    "-f",
-    default=False,
-    type=bool,
-    help="Filter reactions not involving genes?",
-)
 @click_logging.simple_verbosity_option(logger)
 def filter_gtex_tissue(
-    model_uri: str,
+    sbml_dfs_uri: str,
     gtex_file_uri: str,
     output_model_uri: str,
     tissue: str,
@@ -504,70 +531,73 @@ def filter_gtex_tissue(
 
     This uses zfpkm values derived from gtex to filter the model.
     """
-    logger.info("Get rcpr from R")
-    rcpr = callr.get_rcpr()
+
     logger.info("Load sbml_dfs model")
-    model: sbml.SBML_dfs = utils.load_pickle(model_uri)  # type: ignore
+    sbml_dfs: sbml.SBML_dfs = utils.load_pickle(sbml_dfs_uri)  # type: ignore
     logger.info("Load and clean gtex tissue expression")
-    dat_gtex = netcontextr.load_and_clean_gtex_data(
-        rcpr, gtex_file_uri, by_tissue_zfpkm=True
-    )
-    logger.info("Convert sbml_dfs to rcpr reaction graph")
-    model_r = netcontextr.sbml_dfs_to_rcpr_reactions(model)
+    dat_gtex = gtex.load_and_clean_gtex_data(gtex_file_uri)
     logger.info("Annotate genes with gtex tissue expression")
-    model_r_annot = netcontextr.annotate_genes(rcpr, model_r, dat_gtex, "tissue")
+    mount.bind_wide_results(
+        sbml_dfs=sbml_dfs,
+        results_df=dat_gtex.reset_index(drop=False),
+        results_name="gtex",
+        ontologies={ONTOLOGIES.ENSEMBL_GENE},
+        numeric_agg=RESOLVE_MATCHES_AGGREGATORS.MAX,
+    )
     logger.info("Trim network by gene attribute")
-    model_r_trim = netcontextr.trim_reactions_by_gene_attribute(
-        rcpr, model_r_annot, "tissue", tissue
+    filtering.filter_species_by_attribute(
+        sbml_dfs,
+        "gtex",
+        attribute_name=tissue,
+        # remove entries which are NOT in the liver
+        attribute_value=0,
+        inplace=True,
     )
-    logger.info("Apply trimmed network")
+    # remove the gtex species data from the sbml_dfs
+    sbml_dfs.remove_species_data("gtex")
 
-    if filter_non_genic_reactions:
-        logger.info("Filter non genic reactions")
-        considered_reactions = None
-    else:
-        logger.info("Keep genic reactions")
-        considered_reactions = rcpr._get_rids_from_rcpr_reactions(model_r)
-    netcontextr.apply_reactions_context_to_sbml_dfs(
-        model, model_r_trim, considered_reactions=considered_reactions
-    )
-    logger.info("Save model to %s", output_model_uri)
-    utils.save_pickle(output_model_uri, model)
+    logger.info("Save sbml_dfs to %s", output_model_uri)
+    utils.save_pickle(output_model_uri, sbml_dfs)
 
 
 @refine.command(name="filter_hpa_compartments")
-@click.argument("model_uri", type=str)
+@click.argument("sbml_dfs_uri", type=str)
 @click.argument("hpa_file_uri", type=str)
 @click.argument("output_model_uri", type=str)
 @click_logging.simple_verbosity_option(logger)
 def filter_hpa_gene_compartments(
-    model_uri: str, hpa_file_uri: str, output_model_uri: str
+    sbml_dfs_uri: str, hpa_file_uri: str, output_model_uri: str
 ):
     """Filter an interaction network using the human protein atlas
 
-    This uses R `rcpr` to filter an interaction network based on the
-    compartment information from the human protein atlas.
+    This uses loads the human proteome atlas and removes reactions (including interactions)
+    containing genes which are not colocalized.
 
     Only interactions between genes in the same compartment are kept.
     """
-    logger.info("Get rcpr from R")
-    rcpr = callr.get_rcpr()
+
     logger.info("Load sbml_dfs model")
-    model: sbml.SBML_dfs = utils.load_pickle(model_uri)  # type: ignore
+    sbml_dfs: sbml.SBML_dfs = utils.load_pickle(sbml_dfs_uri)  # type: ignore
     logger.info("Load and clean hpa data")
-    dat_hpa = netcontextr.load_and_clean_hpa_data(rcpr, hpa_file_uri)
-    logger.info("Convert sbml_dfs to rcpr string graph")
-    model_r = netcontextr.sbml_dfs_to_rcpr_string_graph(model)
+    dat_hpa = hpa.load_and_clean_hpa_data(hpa_file_uri)
     logger.info("Annotate genes with HPA compartments")
-    model_r_annot = netcontextr.annotate_genes(rcpr, model_r, dat_hpa, "compartment")
-    logger.info("Trim network by gene attribute")
-    model_r_trim = netcontextr.trim_network_by_gene_attribute(
-        rcpr, model_r_annot, "compartment"
+    mount.bind_wide_results(
+        sbml_dfs=sbml_dfs,
+        results_df=dat_hpa.reset_index(drop=False),
+        results_name="hpa",
+        ontologies={ONTOLOGIES.ENSEMBL_GENE},
+        numeric_agg=RESOLVE_MATCHES_AGGREGATORS.MAX,
     )
-    logger.info("Apply trimmed network")
-    netcontextr.apply_context_to_sbml_dfs(model, model_r_trim)
-    logger.info("Save model to %s", output_model_uri)
-    utils.save_pickle(output_model_uri, model)
+    logger.info(
+        "Trim network removing reactions with species in different compartments"
+    )
+    filtering.filter_reactions_with_disconnected_cspecies(
+        sbml_dfs, "hpa", inplace=False
+    )
+    sbml_dfs.remove_species_data("hpa")
+
+    logger.info("Save sbml_dfs to %s", output_model_uri)
+    utils.save_pickle(output_model_uri, sbml_dfs)
 
 
 @click.group()
@@ -626,9 +656,9 @@ def export_igraph(
     if graph_attrs_spec_uri is None:
         graph_attrs_spec = None
     else:
-        graph_attrs_spec = net_utils.read_graph_attrs_spec(graph_attrs_spec_uri)
+        graph_attrs_spec = read_graph_attrs_spec(graph_attrs_spec_uri)
 
-    cpr_graph = net_create.process_cpr_graph(
+    napistu_graph = net_create.process_napistu_graph(
         model,
         reaction_graph_attrs=graph_attrs_spec,
         directed=directed,
@@ -642,11 +672,11 @@ def export_igraph(
     with open_fs(base, create=True, writeable=True) as fs:
         with fs.openbin(path, "wb") as f:
             if format == "gml":
-                cpr_graph.write_gml(f)
+                napistu_graph.write_gml(f)
             elif format == "edgelist":
-                cpr_graph.write_edgelist(f)
+                napistu_graph.write_edgelist(f)
             elif format == "pickle":
-                pickle.dump(cpr_graph, f)
+                pickle.dump(napistu_graph, f)
             else:
                 raise ValueError("Unknown format: %s" % format)
 
@@ -704,11 +734,11 @@ def export_precomputed_distances(
     with open_fs(base) as fs:
         with fs.openbin(path) as f:
             if format == "gml":
-                cpr_graph = ig.Graph.Read_GML(f)
+                napistu_graph = ig.Graph.Read_GML(f)
             elif format == "edgelist":
-                cpr_graph = ig.Graph.Read_Edgelist(f)
+                napistu_graph = ig.Graph.Read_Edgelist(f)
             elif format == "pickle":
-                cpr_graph = ig.Graph.Read_Pickle(f)
+                napistu_graph = ig.Graph.Read_Pickle(f)
             else:
                 raise ValueError("Unknown format: %s" % format)
 
@@ -716,7 +746,7 @@ def export_precomputed_distances(
     weights_vars_list = utils.click_str_to_list(weights_vars)
 
     precomputed_distances = precompute.precompute_distances(
-        cpr_graph,
+        napistu_graph,
         max_steps=max_steps,
         max_score_q=max_score_q,
         partition_size=partition_size,
@@ -850,7 +880,7 @@ def calculate_sbml_dfs_stats(input_uri, output_uri):
 def calculate_igraph_stats(input_uri, output_uri):
     """Calculate statistics for an igraph object"""
     graph: ig.Graph = utils.load_pickle(input_uri)  # type: ignore
-    stats = net_utils.get_graph_summary(graph)
+    stats = get_graph_summary(graph)
     utils.save_json(output_uri, stats)
 
 

{napistu-0.2.5.dev6 → napistu-0.3.1}/src/napistu/constants.py

@@ -21,16 +21,6 @@ PACKAGE_DEFS = SimpleNamespace(
     CACHE_DIR="napistu_data",
 )
 
-PROTEINATLAS_SUBCELL_LOC_URL = (
-    "https://www.proteinatlas.org/download/tsv/subcellular_location.tsv.zip"
-)
-
-# GTEx
-GTEX_RNASEQ_EXPRESSION_URL = "https://storage.googleapis.com/adult-gtex/bulk-gex/v8/rna-seq/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_median_tpm.gct.gz"
-
-# Gencode
-GENCODE_URL = "https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_26/gencode.v26.transcripts.fa.gz"
-
 FILE_EXT_ZIP = "zip"
 FILE_EXT_GZ = "gz"
 
@@ -131,6 +121,11 @@ SBML_DFS_SCHEMA = SimpleNamespace(
 
 ENTITIES_W_DATA = {SBML_DFS.SPECIES, SBML_DFS.REACTIONS}
 
+ENTITIES_TO_ENTITY_DATA = {
+    SBML_DFS.SPECIES: SBML_DFS.SPECIES_DATA,
+    SBML_DFS.REACTIONS: SBML_DFS.REACTIONS_DATA,
+}
+
 REQUIRED_REACTION_FROMEDGELIST_COLUMNS = [
     "sc_id_up",
     "sc_id_down",
@@ -211,11 +206,14 @@ IDENTIFIERS = SimpleNamespace(
     ONTOLOGY="ontology", IDENTIFIER="identifier", BQB="bqb", URL="url"
 )
 
-SPECIES_IDENTIFIERS_REQUIRED_VARS = {
-    SBML_DFS.S_ID,
+IDENTIFIERS_REQUIRED_VARS = {
     IDENTIFIERS.ONTOLOGY,
     IDENTIFIERS.IDENTIFIER,
     IDENTIFIERS.BQB,
+}
+
+SPECIES_IDENTIFIERS_REQUIRED_VARS = IDENTIFIERS_REQUIRED_VARS | {
+    SBML_DFS.S_ID,
     SBML_DFS.S_NAME,
 }
 
@@ -296,29 +294,34 @@ MINI_SBO_NAME_TO_POLARITY = {
 # affect whether a reaction can occur
 # for example, if I remove any substrate a reaction won't occur
 # but I would have to remove all catalysts for it to not occur
+SBO_ROLES_DEFS = SimpleNamespace(
+    DEFINING="DEFINING", REQUIRED="REQUIRED", OPTIONAL="OPTIONAL", SBO_ROLE="sbo_role"
+)
+
 SBO_NAME_TO_ROLE = {
-    SBOTERM_NAMES.REACTANT: "DEFINING",
-    SBOTERM_NAMES.PRODUCT: "DEFINING",
-    SBOTERM_NAMES.INTERACTOR: "DEFINING",
-    SBOTERM_NAMES.CATALYST: "REQUIRED",
-    SBOTERM_NAMES.INHIBITOR: "OPTIONAL",
-    SBOTERM_NAMES.STIMULATOR: "OPTIONAL",
-    SBOTERM_NAMES.MODIFIER: "OPTIONAL",
+    SBOTERM_NAMES.REACTANT: SBO_ROLES_DEFS.DEFINING,
+    SBOTERM_NAMES.PRODUCT: SBO_ROLES_DEFS.DEFINING,
+    SBOTERM_NAMES.INTERACTOR: SBO_ROLES_DEFS.DEFINING,
+    SBOTERM_NAMES.CATALYST: SBO_ROLES_DEFS.REQUIRED,
+    SBOTERM_NAMES.INHIBITOR: SBO_ROLES_DEFS.OPTIONAL,
+    SBOTERM_NAMES.STIMULATOR: SBO_ROLES_DEFS.OPTIONAL,
+    SBOTERM_NAMES.MODIFIER: SBO_ROLES_DEFS.OPTIONAL,
 }
 
 # see also https://github.com/calico/netcontextr/blob/main/R/reactionTrimmingFunctions.R
 VALID_SBO_ROLES = (
     # there is a direct correspondence between the set of defining entries and the identity of a reaction
     # e.g., the stoichiometery of a metabolic reaction or the members of a protein-protein interaction
-    "DEFINING",
+    SBO_ROLES_DEFS.DEFINING,
     # 1+ entries are needed if entries were initially defined. i.e., reactions which require a catalyst
     # would no longer exist if the catalyst was removed, but many reactions do not require a catalyst.
-    "REQUIRED",
+    SBO_ROLES_DEFS.REQUIRED,
     # 0+ entries. optional species can be added or removed to a reaction without changing its identity
-    "OPTIONAL",
+    SBO_ROLES_DEFS.OPTIONAL,
 )
 
-# required variables for the edgelist formats used by mechanism_matching
+# required variables for the edgelist formats used by the matching subpackage
+# also used in some network modules
 CPR_EDGELIST = SimpleNamespace(
     S_ID_UPSTREAM="s_id_upstream",
     S_ID_DOWNSTREAM="s_id_downstream",
@@ -354,24 +357,8 @@ RESOLVE_MATCHES_AGGREGATORS = SimpleNamespace(
 
 RESOLVE_MATCHES_TMP_WEIGHT_COL = "__tmp_weight_for_aggregation__"
 
-# specifying weighting schemes schema
-
-DEFAULT_WT_TRANS = "identity"
-
-DEFINED_WEIGHT_TRANSFORMATION = {
-    DEFAULT_WT_TRANS: "_wt_transformation_identity",
-    "string": "_wt_transformation_string",
-    "string_inv": "_wt_transformation_string_inv",
-}
+# source information
 
-SCORE_CALIBRATION_POINTS_DICT = {
-    "weights": {"strong": 3, "good": 7, "okay": 20, "weak": 40},
-    "string_wt": {"strong": 950, "good": 400, "okay": 230, "weak": 150},
-}
-
-SOURCE_VARS_DICT = {"string_wt": 10}
-
-# source
 SOURCE_SPEC = SimpleNamespace(
     PATHWAY_ID="pathway_id",
     MODEL="model",
@@ -399,8 +386,11 @@ EXPECTED_PW_INDEX_COLUMNS = {
 ONTOLOGIES = SimpleNamespace(
     CHEBI="chebi",
     ENSEMBL_GENE="ensembl_gene",
+    ENSEMBL_GENE_VERSION="ensembl_gene_version",
     ENSEMBL_TRANSCRIPT="ensembl_transcript",
+    ENSEMBL_TRANSCRIPT_VERSION="ensembl_transcript_version",
     ENSEMBL_PROTEIN="ensembl_protein",
+    ENSEMBL_PROTEIN_VERSION="ensembl_protein_version",
     GENE_NAME="gene_name",
     GO="go",
     MIRBASE="mirbase",
@@ -419,7 +409,11 @@ CHARACTERISTIC_COMPLEX_ONTOLOGIES = [
     ONTOLOGIES.MIRBASE,
 ]
 
-ONTOLOGY_ALIASES = SimpleNamespace(NCBI_ENTREZ_GENE={"ncbigene", "ncbi_gene"})
+ONTOLOGY_SPECIES_ALIASES = {
+    ONTOLOGIES.NCBI_ENTREZ_GENE: {"ncbigene", "ncbi_gene"},
+    ONTOLOGIES.ENSEMBL_GENE: {"ensembl_gene_id"},
+    ONTOLOGIES.UNIPROT: {"Uniprot"},
+}
 
 ENSEMBL_MOLECULE_TYPES_TO_ONTOLOGY = {
     "G": ONTOLOGIES.ENSEMBL_GENE,

{napistu-0.2.5.dev6/src/napistu/network → napistu-0.3.1/src/napistu/context}/__init__.py

@@ -4,7 +4,7 @@ from importlib.metadata import PackageNotFoundError
 from importlib.metadata import version
 
 try:
-    __version__ = version("calicolabs-cpr")
+    __version__ = version("napistu-py")
 except PackageNotFoundError:
     # package is not installed
     pass