napistu 0.3.3__tar.gz → 0.3.5__tar.gz

{napistu-0.3.3 → napistu-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: napistu
-Version: 0.3.3
+Version: 0.3.5
 Summary: Connecting high-dimensional data to curated pathways
 Home-page: https://github.com/napistu/napistu-py
 Author: Sean Hackett
@@ -19,7 +19,7 @@ Requires-Dist: Jinja2
 Requires-Dist: PyYAML<7.0.0,>=6.0.0
 Requires-Dist: click<9.0.0,>=8.0.0
 Requires-Dist: click-logging
-Requires-Dist: fs<3.0.0,>=2.4.0
+Requires-Dist: fs<3.0.0,>=2.4.16
 Requires-Dist: fs-gcsfs<2.0.0,>=1.5.0
 Requires-Dist: igraph
 Requires-Dist: matplotlib<4.0.0,>=3.5.0

{napistu-0.3.3 → napistu-0.3.5}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = napistu
-version = 0.3.3
+version = 0.3.5
 description = Connecting high-dimensional data to curated pathways
 long_description = file: README.md
 long_description_content_type = text/markdown
@@ -25,7 +25,7 @@ install_requires =
 	PyYAML>=6.0.0,<7.0.0
 	click>=8.0.0,<9.0.0
 	click-logging
-	fs>=2.4.0,<3.0.0
+	fs>=2.4.16,<3.0.0
 	fs-gcsfs>=1.5.0,<2.0.0
 	igraph
 	matplotlib>=3.5.0,<4.0.0

{napistu-0.3.3 → napistu-0.3.5}/src/napistu/constants.py

@@ -149,10 +149,10 @@ INTERACTION_EDGELIST_EXPECTED_VARS = {
     "downstream_name",
     "upstream_compartment",
     "downstream_compartment",
-    "r_name",
-    "sbo_term",
-    "r_Identifiers",
-    "r_isreversible",
+    SBML_DFS.R_NAME,
+    SBML_DFS.SBO_TERM,
+    SBML_DFS.R_IDENTIFIERS,
+    SBML_DFS.R_ISREVERSIBLE,
 }
 
 BQB_PRIORITIES = pd.DataFrame(
@@ -403,12 +403,6 @@ ONTOLOGIES = SimpleNamespace(
 
 ONTOLOGIES_LIST = list(ONTOLOGIES.__dict__.values())
 
-CHARACTERISTIC_COMPLEX_ONTOLOGIES = [
-    ONTOLOGIES.ENSEMBL_GENE,
-    ONTOLOGIES.NCBI_ENTREZ_GENE,
-    ONTOLOGIES.MIRBASE,
-]
-
 ONTOLOGY_SPECIES_ALIASES = {
     ONTOLOGIES.NCBI_ENTREZ_GENE: {"ncbigene", "ncbi_gene"},
     ONTOLOGIES.ENSEMBL_GENE: {"ensembl_gene_id"},

{napistu-0.3.3 → napistu-0.3.5}/src/napistu/network/ig_utils.py

@@ -99,6 +99,41 @@ def filter_to_largest_subgraph(graph: ig.Graph) -> ig.Graph:
     return largest_subgraph
 
 
+def filter_to_largest_subgraphs(graph: ig.Graph, top_k: int) -> list[ig.Graph]:
+    """
+    Filter an igraph to its largest weakly connected components.
+
+    Parameters
+    ----------
+    graph : ig.Graph
+        The input network.
+    top_k : int
+        The number of largest components to return.
+
+    Returns
+    -------
+    list[ig.Graph]
+        A list of the top K largest components as graphs.
+    """
+    if top_k < 1:
+        raise ValueError("top_k must be 1 or greater.")
+
+    component_members = graph.components(mode="weak")
+    if not component_members:
+        return []
+
+    component_sizes = [len(x) for x in component_members]
+
+    # Sort components by size in descending order
+    sorted_components = sorted(
+        zip(component_sizes, component_members), key=lambda x: x[0], reverse=True
+    )
+
+    # Return a list of the top K subgraphs
+    top_k_components = sorted_components[:top_k]
+    return [graph.induced_subgraph(members) for _, members in top_k_components]
+
+
 def graph_to_pandas_dfs(graph: ig.Graph) -> tuple[pd.DataFrame, pd.DataFrame]:
     """
     Convert an igraph to Pandas DataFrames for vertices and edges.

{napistu-0.3.3 → napistu-0.3.5}/src/napistu/network/precompute.py

@@ -4,6 +4,7 @@ import logging
 import math
 from pathlib import Path
 from typing import Union
+import io
 
 import numpy as np
 import pandas as pd
@@ -120,7 +121,7 @@ def save_precomputed_distances(
     OSError
         If the file cannot be written to (permission issues, etc.)
     """
-    save_json(str(uri), precomputed_distances.to_dict(orient="index"))
+    save_json(str(uri), precomputed_distances.to_json())
 
 
 def load_precomputed_distances(uri: Union[str, Path]) -> pd.DataFrame:
@@ -143,12 +144,18 @@ def load_precomputed_distances(uri: Union[str, Path]) -> pd.DataFrame:
         If the specified file does not exist
     """
     try:
-        data_dict = load_json(str(uri))
+        json_string = load_json(str(uri))
+        df = pd.read_json(io.StringIO(json_string))
+
+        # Convert integer columns to float
+        for col in df.columns:
+            if df[col].dtype in ["int64", "int32", "int16", "int8"]:
+                df[col] = df[col].astype(float)
+
+        return df
     except ResourceNotFound as e:
         raise FileNotFoundError(f"File not found: {uri}") from e
 
-    return pd.DataFrame.from_dict(data_dict, orient="index").rename(index=int)
-
 
 def _calculate_distances_subset(
     napistu_graph: NapistuGraph,