napistu 0.4.0__tar.gz → 0.4.2__tar.gz

{napistu-0.4.0/src/napistu.egg-info → napistu-0.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: napistu
-Version: 0.4.0
+Version: 0.4.2
 Summary: Connecting high-dimensional data to curated pathways
 Home-page: https://github.com/napistu/napistu-py
 Author: Sean Hackett
@@ -61,7 +61,12 @@ Dynamic: license-file
 
 # Napistu Python Library
 
+[![PyPI version](https://badge.fury.io/py/napistu.svg)](https://badge.fury.io/py/napistu)
 [![Documentation Status](https://readthedocs.org/projects/napistu/badge/?version=latest)](https://napistu.readthedocs.io/en/latest/?badge=latest)
+[![CI](https://github.com/napistu/napistu-py/actions/workflows/ci.yml/badge.svg)](https://github.com/napistu/napistu-py/actions/workflows/ci.yml)
+[![Release](https://github.com/napistu/napistu-py/actions/workflows/release.yml/badge.svg)](https://github.com/napistu/napistu-py/actions/workflows/release.yml)
+[![Deploy to Cloud Run](https://github.com/napistu/napistu-py/actions/workflows/deploy.yml/badge.svg)](https://github.com/napistu/napistu-py/actions/workflows/deploy.yml)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
 This Python package hosts the majority of the algorithmic code for the [Napistu project](https://github.com/napistu/napistu).
 

{napistu-0.4.0 → napistu-0.4.2}/README.md

@@ -1,6 +1,11 @@
 # Napistu Python Library
 
+[![PyPI version](https://badge.fury.io/py/napistu.svg)](https://badge.fury.io/py/napistu)
 [![Documentation Status](https://readthedocs.org/projects/napistu/badge/?version=latest)](https://napistu.readthedocs.io/en/latest/?badge=latest)
+[![CI](https://github.com/napistu/napistu-py/actions/workflows/ci.yml/badge.svg)](https://github.com/napistu/napistu-py/actions/workflows/ci.yml)
+[![Release](https://github.com/napistu/napistu-py/actions/workflows/release.yml/badge.svg)](https://github.com/napistu/napistu-py/actions/workflows/release.yml)
+[![Deploy to Cloud Run](https://github.com/napistu/napistu-py/actions/workflows/deploy.yml/badge.svg)](https://github.com/napistu/napistu-py/actions/workflows/deploy.yml)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
 This Python package hosts the majority of the algorithmic code for the [Napistu project](https://github.com/napistu/napistu).
 

{napistu-0.4.0 → napistu-0.4.2}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = napistu
-version = 0.4.0
+version = 0.4.2
 description = Connecting high-dimensional data to curated pathways
 long_description = file: README.md
 long_description_content_type = text/markdown

{napistu-0.4.0 → napistu-0.4.2}/src/napistu/constants.py

@@ -402,12 +402,14 @@ ONTOLOGIES = SimpleNamespace(
     ENSEMBL_PROTEIN_VERSION="ensembl_protein_version",
     GENE_NAME="gene_name",
     GO="go",
+    KEGG="kegg",
     MIRBASE="mirbase",
     NCBI_ENTREZ_GENE="ncbi_entrez_gene",
     PHAROS="pharos",
     REACTOME="reactome",
     SYMBOL="symbol",
     UNIPROT="uniprot",
+    WIKIPATHWAYS="wikipathways",
 )
 
 ONTOLOGIES_LIST = list(ONTOLOGIES.__dict__.values())

{napistu-0.4.0 → napistu-0.4.2}/src/napistu/gcs/constants.py

@@ -5,17 +5,17 @@ from types import SimpleNamespace
 
 GCS_SUBASSET_NAMES = SimpleNamespace(
     SBML_DFS="sbml_dfs",
-    IDENTIFIERS="identifiers",
-    REGULATORY_GRAPH="regulatory_graph",
-    REGULATORY_DISTANCES="regulatory_distances",
+    NAPISTU_GRAPH="napistu_graph",
+    SPECIES_IDENTIFIERS="species_identifiers",
+    PRECOMPUTED_DISTANCES="precomputed_distances",
 )
 
 
 GCS_FILETYPES = SimpleNamespace(
     SBML_DFS="sbml_dfs.pkl",
-    IDENTIFIERS="identifiers.tsv",
-    REGULATORY_GRAPH="regulatory_graph.pkl",
-    REGULATORY_DISTANCES="regulatory_distances.json",
+    NAPISTU_GRAPH="napistu_graph.pkl",
+    SPECIES_IDENTIFIERS="species_identifiers.tsv",
+    PRECOMPUTED_DISTANCES="precomputed_distances.parquet",
 )
 
 
@@ -27,9 +27,9 @@ GCS_ASSETS = SimpleNamespace(
             "file": "test_pathway.tar.gz",
             "subassets": {
                 GCS_SUBASSET_NAMES.SBML_DFS: GCS_FILETYPES.SBML_DFS,
-                GCS_SUBASSET_NAMES.IDENTIFIERS: GCS_FILETYPES.IDENTIFIERS,
-                GCS_SUBASSET_NAMES.REGULATORY_GRAPH: GCS_FILETYPES.REGULATORY_GRAPH,
-                GCS_SUBASSET_NAMES.REGULATORY_DISTANCES: GCS_FILETYPES.REGULATORY_DISTANCES,
+                GCS_SUBASSET_NAMES.NAPISTU_GRAPH: GCS_FILETYPES.NAPISTU_GRAPH,
+                GCS_SUBASSET_NAMES.SPECIES_IDENTIFIERS: GCS_FILETYPES.SPECIES_IDENTIFIERS,
+                GCS_SUBASSET_NAMES.PRECOMPUTED_DISTANCES: GCS_FILETYPES.PRECOMPUTED_DISTANCES,
             },
             "public_url": "https://storage.googleapis.com/shackett-napistu-public/test_pathway.tar.gz",
         },
@@ -37,8 +37,8 @@ GCS_ASSETS = SimpleNamespace(
             "file": "human_consensus.tar.gz",
             "subassets": {
                 GCS_SUBASSET_NAMES.SBML_DFS: GCS_FILETYPES.SBML_DFS,
-                GCS_SUBASSET_NAMES.IDENTIFIERS: GCS_FILETYPES.IDENTIFIERS,
-                GCS_SUBASSET_NAMES.REGULATORY_GRAPH: GCS_FILETYPES.REGULATORY_GRAPH,
+                GCS_SUBASSET_NAMES.NAPISTU_GRAPH: GCS_FILETYPES.NAPISTU_GRAPH,
+                GCS_SUBASSET_NAMES.SPECIES_IDENTIFIERS: GCS_FILETYPES.SPECIES_IDENTIFIERS,
             },
             "public_url": "https://storage.googleapis.com/shackett-napistu-public/human_consensus.tar.gz",
         },
@@ -46,11 +46,11 @@ GCS_ASSETS = SimpleNamespace(
             "file": "human_consensus_w_distances.tar.gz",
             "subassets": {
                 GCS_SUBASSET_NAMES.SBML_DFS: GCS_FILETYPES.SBML_DFS,
-                GCS_SUBASSET_NAMES.IDENTIFIERS: GCS_FILETYPES.IDENTIFIERS,
-                GCS_SUBASSET_NAMES.REGULATORY_GRAPH: GCS_FILETYPES.REGULATORY_GRAPH,
-                GCS_SUBASSET_NAMES.REGULATORY_DISTANCES: GCS_FILETYPES.REGULATORY_DISTANCES,
+                GCS_SUBASSET_NAMES.NAPISTU_GRAPH: GCS_FILETYPES.NAPISTU_GRAPH,
+                GCS_SUBASSET_NAMES.SPECIES_IDENTIFIERS: GCS_FILETYPES.SPECIES_IDENTIFIERS,
+                GCS_SUBASSET_NAMES.PRECOMPUTED_DISTANCES: GCS_FILETYPES.PRECOMPUTED_DISTANCES,
             },
-            "public_url": "https://storage.googleapis.com/calico-cpr-public/human_consensus_w_distances.tar.gz",
+            "public_url": "https://storage.googleapis.com/shackett-napistu-public/human_consensus_w_distances.tar.gz",
         },
         "reactome_members": {
             "file": "external_pathways/external_pathways_reactome_neo4j_members.csv",

{napistu-0.4.0 → napistu-0.4.2}/src/napistu/network/constants.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 from types import SimpleNamespace
 
+
 from napistu.constants import SBML_DFS
 from napistu.constants import SBOTERM_NAMES
 
@@ -13,7 +14,7 @@ NAPISTU_GRAPH_DIRECTEDNESS = SimpleNamespace(
     DIRECTED="directed", UNDIRECTED="undirected"
 )
 
-NAPISTU_GRAPH_NODES = SimpleNamespace(NAME="name")
+NAPISTU_GRAPH_VERTICES = SimpleNamespace(NAME="name")
 
 NAPISTU_GRAPH_EDGES = SimpleNamespace(
     DIRECTED="directed",
@@ -198,3 +199,24 @@ SCORE_CALIBRATION_POINTS_DICT = {
 }
 
 SOURCE_VARS_DICT = {"string_wt": 10}
+
+# network propagation
+NET_PROPAGATION_DEFS = SimpleNamespace(PERSONALIZED_PAGERANK="personalized_pagerank")
+
+# null distributions
+NULL_STRATEGIES = SimpleNamespace(
+    UNIFORM="uniform",
+    PARAMETRIC="parametric",
+    NODE_PERMUTATION="node_permutation",
+    EDGE_PERMUTATION="edge_permutation",
+)
+
+VALID_NULL_STRATEGIES = NULL_STRATEGIES.__dict__.values()
+
+PARAMETRIC_NULL_DEFAULT_DISTRIBUTION = "norm"
+
+# masks
+
+MASK_KEYWORDS = SimpleNamespace(
+    ATTR="attr",
+)

{napistu-0.4.0 → napistu-0.4.2}/src/napistu/network/ig_utils.py

@@ -9,7 +9,7 @@ from __future__ import annotations
 
 import logging
 import random
-from typing import Any, Optional, Sequence
+from typing import Any, Optional, Sequence, List, Dict, Union
 
 import igraph as ig
 import numpy as np
@@ -384,3 +384,163 @@ def _get_top_n_nodes(
     top_node_attrs = [graph.vs[idx].attributes() for idx in top_idxs]
     top_vals = [vals[idx] for idx in top_idxs]
     return [{val_name: val, **node} for val, node in zip(top_vals, top_node_attrs)]
+
+
+def _parse_mask_input(
+    mask_input: Optional[Union[str, np.ndarray, List, Dict]], attributes: List[str]
+) -> Dict[str, Union[str, np.ndarray, List, None]]:
+    """
+    Parse mask input and convert to attribute-specific mask specifications.
+
+    Parameters
+    ----------
+    mask_input : str, np.ndarray, List, Dict, or None
+        Mask specification that can be:
+        - None: use all nodes for all attributes
+        - "attr": use each attribute as its own mask
+        - np.ndarray/List: use same mask for all attributes
+        - Dict: attribute-specific mask specifications
+    attributes : List[str]
+        List of attribute names.
+
+    Returns
+    -------
+    Dict[str, Union[str, np.ndarray, List, None]]
+        Dictionary mapping each attribute to its mask specification.
+    """
+    if mask_input is None:
+        return {attr: None for attr in attributes}
+    elif isinstance(mask_input, str):
+        if mask_input == "attr":
+            return {attr: attr for attr in attributes}
+        else:
+            # Single attribute name used for all
+            return {attr: mask_input for attr in attributes}
+    elif isinstance(mask_input, (np.ndarray, list)):
+        # Same mask for all attributes
+        return {attr: mask_input for attr in attributes}
+    elif isinstance(mask_input, dict):
+        # Validate all attributes are present
+        for attr in attributes:
+            if attr not in mask_input:
+                raise ValueError(f"Attribute '{attr}' not found in mask dictionary")
+        return mask_input
+    else:
+        raise ValueError(f"Invalid mask input type: {type(mask_input)}")
+
+
+def _get_attribute_masks(
+    graph: ig.Graph,
+    mask_specs: Dict[str, Union[str, np.ndarray, List, None]],
+) -> Dict[str, np.ndarray]:
+    """
+    Generate boolean masks for each attribute based on specifications.
+
+    Parameters
+    ----------
+    graph : ig.Graph
+        Input graph.
+    attributes : List[str]
+        List of attribute names.
+    mask_specs : Dict[str, Union[str, np.ndarray, List, None]]
+        Dictionary mapping each attribute to its mask specification.
+
+    Returns
+    -------
+    Dict[str, np.ndarray]
+        Dictionary mapping each attribute to its boolean mask array.
+    """
+    n_nodes = graph.vcount()
+    masks = {}
+
+    invalid_attrs = set(mask_specs.keys()).difference(graph.vs.attributes())
+    if invalid_attrs:
+        raise ValueError(f"Attributes {invalid_attrs} not found in graph")
+
+    for attr in mask_specs.keys():
+
+        mask_spec = mask_specs[attr]
+
+        if mask_spec is None:
+            masks[attr] = np.ones(n_nodes, dtype=bool)
+        elif isinstance(mask_spec, str):
+            attr_values = np.array(graph.vs[mask_spec])
+            masks[attr] = attr_values > 0
+        elif isinstance(mask_spec, np.ndarray):
+            masks[attr] = mask_spec.astype(bool)
+        elif isinstance(mask_spec, list):
+            mask_array = np.zeros(n_nodes, dtype=bool)
+            if isinstance(mask_spec[0], str):
+                # Node names
+                node_names = (
+                    graph.vs["name"] if "name" in graph.vs.attributes() else None
+                )
+                if node_names is None:
+                    raise ValueError("Graph has no 'name' attribute for string mask")
+                for name in mask_spec:
+                    idx = node_names.index(name)
+                    mask_array[idx] = True
+            else:
+                # Node indices
+                mask_array[mask_spec] = True
+            masks[attr] = mask_array
+        else:
+            raise ValueError(
+                f"Invalid mask specification for attribute '{attr}': {type(mask_spec)}"
+            )
+
+    return masks
+
+
+def _ensure_valid_attribute(graph: ig.Graph, attribute: str, non_negative: bool = True):
+    """
+    Ensure a vertex attribute is present, numeric, and optionally non-negative for all vertices.
+
+    This utility checks that the specified vertex attribute exists, is numeric, and (optionally) non-negative
+    for all vertices in the graph. Missing or None values are treated as 0. Raises ValueError
+    if the attribute is missing for all vertices, if all values are zero, or if any value is negative (if non_negative=True).
+
+    Parameters
+    ----------
+    graph : NapistuGraph or ig.Graph
+        The input graph (NapistuGraph or igraph.Graph).
+    attribute : str
+        The name of the vertex attribute to check.
+    non_negative : bool, default True
+        Whether to require all values to be non-negative.
+
+    Returns
+    -------
+    np.ndarray
+        Array of attribute values (with missing/None replaced by 0).
+
+    Raises
+    ------
+    ValueError
+        If the attribute is missing for all vertices, all values are zero, or any value is negative (if non_negative=True).
+    """
+    all_missing = all(
+        (attribute not in v.attributes() or v[attribute] is None) for v in graph.vs
+    )
+    if all_missing:
+        raise ValueError(f"Vertex attribute '{attribute}' is missing for all vertices.")
+
+    values = [
+        (
+            v[attribute]
+            if (attribute in v.attributes() and v[attribute] is not None)
+            else 0.0
+        )
+        for v in graph.vs
+    ]
+
+    arr = np.array(values, dtype=float)
+
+    if np.all(arr == 0):
+        raise ValueError(
+            f"Vertex attribute '{attribute}' is zero for all vertices; cannot use as reset vector."
+        )
+    if non_negative and np.any(arr < 0):
+        raise ValueError(f"Attribute '{attribute}' contains negative values.")
+
+    return arr

{napistu-0.4.0 → napistu-0.4.2}/src/napistu/network/net_create.py

@@ -26,7 +26,7 @@ from napistu.constants import (
 )
 
 from napistu.network.constants import (
-    NAPISTU_GRAPH_NODES,
+    NAPISTU_GRAPH_VERTICES,
     NAPISTU_GRAPH_EDGES,
     NAPISTU_GRAPH_EDGE_DIRECTIONS,
     NAPISTU_GRAPH_NODE_TYPES,
@@ -152,7 +152,7 @@ def create_napistu_graph(
 
     # rename nodes to name since it is treated specially
     network_nodes_df = pd.concat(network_nodes).rename(
-        columns={"node_id": NAPISTU_GRAPH_NODES.NAME}
+        columns={"node_id": NAPISTU_GRAPH_VERTICES.NAME}
     )
 
     logger.info(f"Formatting edges as a {wiring_approach} graph")
@@ -234,7 +234,7 @@ def create_napistu_graph(
         vertices=network_nodes_df.to_dict("records"),
         edges=unique_edges.to_dict("records"),
         directed=directed,
-        vertex_name_attr=NAPISTU_GRAPH_NODES.NAME,
+        vertex_name_attr=NAPISTU_GRAPH_VERTICES.NAME,
         edge_foreign_keys=(NAPISTU_GRAPH_EDGES.FROM, NAPISTU_GRAPH_EDGES.TO),
     )