risk-network 0.0.16b0__tar.gz → 0.0.16b2__tar.gz

{risk_network-0.0.16b0 → risk_network-0.0.16b2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: risk-network
-Version: 0.0.16b0
+Version: 0.0.16b2
 Summary: A Python package for scalable network analysis and high-quality visualization.
 Author-email: Ira Horecka <ira89@icloud.com>
 License: GPL-3.0-or-later
@@ -44,7 +44,7 @@ Dynamic: license-file
 ![Python](https://img.shields.io/badge/python-3.8%2B-yellow)
 [![pypiv](https://img.shields.io/pypi/v/risk-network.svg)](https://pypi.python.org/pypi/risk-network)
 ![License](https://img.shields.io/badge/license-GPLv3-purple)
-[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17257418.svg)](https://doi.org/10.5281/zenodo.17257418)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17257417.svg)](https://doi.org/10.5281/zenodo.17257417)
 ![Tests](https://github.com/riskportal/risk/actions/workflows/ci.yml/badge.svg)
 
 **RISK** (Regional Inference of Significant Kinships) is a next-generation tool for biological network annotation and visualization. It integrates community detection algorithms, rigorous overrepresentation analysis, and a modular framework for diverse network types. RISK identifies biologically coherent relationships within networks and generates publication-ready visualizations, making it a useful tool for biological and interdisciplinary network analysis.

{risk_network-0.0.16b0 → risk_network-0.0.16b2}/README.md

@@ -3,7 +3,7 @@
 ![Python](https://img.shields.io/badge/python-3.8%2B-yellow)
 [![pypiv](https://img.shields.io/pypi/v/risk-network.svg)](https://pypi.python.org/pypi/risk-network)
 ![License](https://img.shields.io/badge/license-GPLv3-purple)
-[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17257418.svg)](https://doi.org/10.5281/zenodo.17257418)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17257417.svg)](https://doi.org/10.5281/zenodo.17257417)
 ![Tests](https://github.com/riskportal/risk/actions/workflows/ci.yml/badge.svg)
 
 **RISK** (Regional Inference of Significant Kinships) is a next-generation tool for biological network annotation and visualization. It integrates community detection algorithms, rigorous overrepresentation analysis, and a modular framework for diverse network types. RISK identifies biologically coherent relationships within networks and generates publication-ready visualizations, making it a useful tool for biological and interdisciplinary network analysis.

{risk_network-0.0.16b0 → risk_network-0.0.16b2}/src/risk/__init__.py

@@ -5,7 +5,7 @@ risk
 RISK: Regional Inference of Significant Kinships
 """
 
-from ._risk import RISK
+from .risk import RISK
 
 __all__ = ["RISK"]
-__version__ = "0.0.16-beta.0"
+__version__ = "0.0.16-beta.2"

{risk_network-0.0.16b0/src/risk/_annotation → risk_network-0.0.16b2/src/risk/annotation}/__init__.py

@@ -3,8 +3,8 @@ risk/_annotation
 ~~~~~~~~~~~~~~~~
 """
 
-from ._annotation import (
+from .annotation import (
     define_top_annotation,
     get_weighted_description,
 )
-from ._io import AnnotationHandler
+from .io import AnnotationHandler

{risk_network-0.0.16b0/src/risk/_annotation → risk_network-0.0.16b2/src/risk/annotation}/_nltk_setup.py

@@ -1,6 +1,6 @@
 """
-risk/_annotation/_nltk_setup
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+risk/annotation/_nltk_setup
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import os
@@ -11,7 +11,7 @@ import nltk
 from nltk.data import find
 from nltk.data import path as nltk_data_path
 
-from .._log import logger
+from ..log import logger
 
 
 def setup_nltk_resources(required_resources: Optional[List[Tuple[str, str]]] = None) -> None:

risk_network-0.0.16b0/src/risk/_annotation/_annotation.py → risk_network-0.0.16b2/src/risk/annotation/annotation.py

@@ -1,6 +1,6 @@
 """
-risk/_annotation/_annotation
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+risk/annotation/annotation
+~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import re
@@ -14,7 +14,7 @@ import pandas as pd
 from nltk.tokenize import word_tokenize
 from scipy.sparse import coo_matrix
 
-from .._log import logger
+from ..log import logger
 from ._nltk_setup import setup_nltk_resources
 
 
@@ -123,19 +123,19 @@ def load_annotation(
 def define_top_annotation(
     network: nx.Graph,
     ordered_annotation_labels: List[str],
-    neighborhood_significance_sums: List[int],
+    cluster_significance_sums: List[int],
     significant_significance_matrix: np.ndarray,
     significant_binary_significance_matrix: np.ndarray,
     min_cluster_size: int = 5,
     max_cluster_size: int = 1000,
 ) -> pd.DataFrame:
     """
-    Define top annotations based on neighborhood significance sums and binary significance matrix.
+    Define top annotations based on cluster significance sums and binary significance matrix.
 
     Args:
         network (NetworkX graph): The network graph.
         ordered_annotation_labels (list of str): List of ordered annotation labels.
-        neighborhood_significance_sums (list of int): List of neighborhood significance sums.
+        cluster_significance_sums (list of int): List of cluster significance sums.
         significant_significance_matrix (np.ndarray): Enrichment matrix below alpha threshold.
         significant_binary_significance_matrix (np.ndarray): Binary significance matrix below alpha threshold.
         min_cluster_size (int, optional): Minimum cluster size. Defaults to 5.
@@ -146,12 +146,12 @@ def define_top_annotation(
     """
     # Sum the columns of the significant significance matrix (positive floating point values)
     significant_significance_scores = significant_significance_matrix.sum(axis=0)
-    # Create DataFrame to store annotations, their neighborhood significance sums, and significance scores
+    # Create DataFrame to store annotations, their cluster significance sums, and significance scores
     annotation_significance_matrix = pd.DataFrame(
         {
             "id": range(len(ordered_annotation_labels)),
             "full_terms": ordered_annotation_labels,
-            "significant_neighborhood_significance_sums": neighborhood_significance_sums,
+            "significant_cluster_significance_sums": cluster_significance_sums,
             "significant_significance_score": significant_significance_scores,
         }
     )
@@ -159,11 +159,11 @@ def define_top_annotation(
     # Apply size constraints to identify potential significant annotations
     annotation_significance_matrix.loc[
         (
-            annotation_significance_matrix["significant_neighborhood_significance_sums"]
+            annotation_significance_matrix["significant_cluster_significance_sums"]
             >= min_cluster_size
         )
         & (
-            annotation_significance_matrix["significant_neighborhood_significance_sums"]
+            annotation_significance_matrix["significant_cluster_significance_sums"]
             <= max_cluster_size
         ),
         "significant_annotation",
@@ -179,11 +179,11 @@ def define_top_annotation(
     for attribute in annotation_significance_matrix.index.values[
         annotation_significance_matrix["significant_annotation"]
     ]:
-        # Identify significant neighborhoods based on the binary significance matrix
-        significant_neighborhoods = list(
+        # Identify significant clusters based on the binary significance matrix
+        significant_clusters = list(
             compress(list(network), significant_binary_significance_matrix[:, attribute])
         )
-        significant_network = nx.subgraph(network, significant_neighborhoods)
+        significant_network = nx.subgraph(network, significant_clusters)
         # Analyze connected components within the significant subnetwork
         connected_components = sorted(
             nx.connected_components(significant_network), key=len, reverse=True
@@ -257,26 +257,23 @@ def get_weighted_description(words_column: pd.Series, scores_column: pd.Series)
                 continue
             # Lemmatize the token to merge similar forms
             token_norm = LEMMATIZER.lemmatize(token_clean)
-            weighted_counts[token_norm] = weighted_counts.get(token_norm, 0) + weight
+            # Apply weighting boost for biologically structured number-word hybrids
+            if re.match(r"^\d+[\-\w]+", token_norm):
+                actual_weight = int(weight * 1.5)
+            else:
+                actual_weight = weight
+            weighted_counts[token_norm] = weighted_counts.get(token_norm, 0) + actual_weight
 
     # Reconstruct a weighted token list by repeating each token by its aggregated count.
     weighted_words = []
     for token, count in weighted_counts.items():
         weighted_words.extend([token] * count)
 
-    # Combine tokens that match number-word patterns (e.g. "4-alpha") and remove pure numeric tokens.
+    # Combine tokens that match number-word patterns (e.g. "4-alpha"), but do not remove numeric tokens.
+    # All tokens are included in the final list.
     combined_tokens = []
     for token in weighted_words:
-        if re.match(r"^\d+-\w+", token):
-            combined_tokens.append(token)
-        elif token.replace(".", "", 1).isdigit():
-            continue
-        else:
-            combined_tokens.append(token)
-
-    # If the only token is numeric, return a default value.
-    if len(combined_tokens) == 1 and combined_tokens[0].isdigit():
-        return "N/A"
+        combined_tokens.append(token)
 
     # Simplify the token list to remove near-duplicates based on the Jaccard index.
     simplified_words = _simplify_word_list(combined_tokens)

risk_network-0.0.16b0/src/risk/_annotation/_io.py → risk_network-0.0.16b2/src/risk/annotation/io.py

@@ -1,6 +1,6 @@
 """
-risk/_annotation/_io
-~~~~~~~~~~~~~~~~~~~~
+risk/annotation/io
+~~~~~~~~~~~~~~~~~~
 """
 
 import json
@@ -9,8 +9,8 @@ from typing import Any, Dict
 import networkx as nx
 import pandas as pd
 
-from .._log import log_header, logger, params
-from ._annotation import load_annotation
+from ..log import log_header, logger, params
+from .annotation import load_annotation
 
 
 class AnnotationHandler:

risk_network-0.0.16b2/src/risk/cluster/__init__.py

@@ -0,0 +1,8 @@
+"""
+risk/cluster
+~~~~~~~~~~~~
+"""
+
+from .api import ClusterAPI
+from .label import define_domains, trim_domains
+from .cluster import process_significant_clusters

{risk_network-0.0.16b0/src/risk/_neighborhoods → risk_network-0.0.16b2/src/risk/cluster}/_community.py

@@ -1,6 +1,6 @@
 """
-risk/_neighborhoods/_community
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+risk/cluster/_community
+~~~~~~~~~~~~~~~~~~~~~~~
 """
 
 import community as community_louvain
@@ -12,14 +12,14 @@ from leidenalg import RBConfigurationVertexPartition, find_partition
 from networkx.algorithms.community import greedy_modularity_communities
 from scipy.sparse import csr_matrix
 
-from .._log import logger
+from ..log import logger
 
 
-def calculate_greedy_modularity_neighborhoods(
+def calculate_greedy_modularity_clusters(
     network: nx.Graph, fraction_shortest_edges: float = 1.0
 ) -> csr_matrix:
     """
-    Calculate neighborhoods using the Greedy Modularity method with CSR matrix output.
+    Calculate clusters using the Greedy Modularity method with CSR matrix output.
 
     Args:
         network (nx.Graph): The network graph.
@@ -27,7 +27,7 @@ def calculate_greedy_modularity_neighborhoods(
             subgraphs before clustering. Defaults to 1.0.
 
     Returns:
-        csr_matrix: A binary neighborhood matrix (CSR) where nodes in the same community have 1, and others have 0.
+        csr_matrix: A binary cluster matrix (CSR) where nodes in the same community have 1, and others have 0.
 
     Raises:
         ValueError: If the subgraph has no edges after filtering.
@@ -55,12 +55,12 @@ def calculate_greedy_modularity_neighborhoods(
     # Create a CSR matrix
     num_nodes = len(nodes)
     data = np.ones(len(row_indices), dtype=int)
-    neighborhoods = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
+    clusters = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
 
-    return neighborhoods
+    return clusters
 
 
-def calculate_label_propagation_neighborhoods(
+def calculate_label_propagation_clusters(
     network: nx.Graph, fraction_shortest_edges: float = 1.0
 ) -> csr_matrix:
     """
@@ -72,7 +72,7 @@ def calculate_label_propagation_neighborhoods(
             subgraphs before clustering. Defaults to 1.0.
 
     Returns:
-        csr_matrix: A binary neighborhood matrix (CSR) on Label Propagation.
+        csr_matrix: A binary cluster matrix (CSR) on Label Propagation.
 
     Raises:
         ValueError: If the subgraph has no edges after filtering.
@@ -92,7 +92,7 @@ def calculate_label_propagation_neighborhoods(
     # Prepare data for CSR matrix
     row_indices = []
     col_indices = []
-    # Assign neighborhoods based on community labels using the mapped indices
+    # Assign clusters based on community labels using the mapped indices
     for community in communities:
         mapped_indices = [node_index_map[node] for node in community]
         for i in mapped_indices:
@@ -103,19 +103,19 @@ def calculate_label_propagation_neighborhoods(
     # Create a CSR matrix
     num_nodes = len(nodes)
     data = np.ones(len(row_indices), dtype=int)
-    neighborhoods = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
+    clusters = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
 
-    return neighborhoods
+    return clusters
 
 
-def calculate_leiden_neighborhoods(
+def calculate_leiden_clusters(
     network: nx.Graph,
     resolution: float = 1.0,
     fraction_shortest_edges: float = 1.0,
     random_seed: int = 888,
 ) -> csr_matrix:
     """
-    Calculate neighborhoods using the Leiden method with CSR matrix output.
+    Calculate clusters using the Leiden method with CSR matrix output.
 
     Args:
         network (nx.Graph): The network graph.
@@ -125,7 +125,7 @@ def calculate_leiden_neighborhoods(
         random_seed (int, optional): Random seed for reproducibility. Defaults to 888.
 
     Returns:
-        csr_matrix: A binary neighborhood matrix (CSR) where nodes in the same community have 1, and others have 0.
+        csr_matrix: A binary cluster matrix (CSR) where nodes in the same community have 1, and others have 0.
 
     Raises:
         ValueError: If the subgraph has no edges after filtering.
@@ -160,19 +160,19 @@ def calculate_leiden_neighborhoods(
     # Create a CSR matrix
     num_nodes = len(nodes)
     data = np.ones(len(row_indices), dtype=int)
-    neighborhoods = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
+    clusters = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
 
-    return neighborhoods
+    return clusters
 
 
-def calculate_louvain_neighborhoods(
+def calculate_louvain_clusters(
     network: nx.Graph,
     resolution: float = 0.1,
     fraction_shortest_edges: float = 1.0,
     random_seed: int = 888,
 ) -> csr_matrix:
     """
-    Calculate neighborhoods using the Louvain method.
+    Calculate clusters using the Louvain method.
 
     Args:
         network (nx.Graph): The network graph.
@@ -182,7 +182,7 @@ def calculate_louvain_neighborhoods(
         random_seed (int, optional): Random seed for reproducibility. Defaults to 888.
 
     Returns:
-        csr_matrix: A binary neighborhood matrix in CSR format.
+        csr_matrix: A binary cluster matrix in CSR format.
 
     Raises:
         ValueError: If the subgraph has no edges after filtering.
@@ -217,16 +217,16 @@ def calculate_louvain_neighborhoods(
     # Create a CSR matrix
     num_nodes = len(nodes)
     data = np.ones(len(row_indices), dtype=int)
-    neighborhoods = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
+    clusters = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
 
-    return neighborhoods
+    return clusters
 
 
-def calculate_markov_clustering_neighborhoods(
+def calculate_markov_clustering_clusters(
     network: nx.Graph, fraction_shortest_edges: float = 1.0
 ) -> csr_matrix:
     """
-    Apply Markov Clustering (MCL) to the network and return a binary neighborhood matrix (CSR).
+    Apply Markov Clustering (MCL) to the network and return a binary cluster matrix (CSR).
 
     Args:
         network (nx.Graph): The network graph.
@@ -234,7 +234,7 @@ def calculate_markov_clustering_neighborhoods(
             subgraphs before clustering. Defaults to 1.0.
 
     Returns:
-        csr_matrix: A binary neighborhood matrix (CSR) on Markov Clustering.
+        csr_matrix: A binary cluster matrix (CSR) on Markov Clustering.
 
     Raises:
         ValueError: If the subgraph has no edges after filtering.
@@ -288,12 +288,12 @@ def calculate_markov_clustering_neighborhoods(
 
     # Step 5: Create a CSR matrix
     data = np.ones(len(row_indices), dtype=int)
-    neighborhoods = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
+    clusters = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
 
-    return neighborhoods
+    return clusters
 
 
-def calculate_spinglass_neighborhoods(
+def calculate_spinglass_clusters(
     network: nx.Graph, fraction_shortest_edges: float = 1.0
 ) -> csr_matrix:
     """
@@ -305,7 +305,7 @@ def calculate_spinglass_neighborhoods(
             subgraphs before clustering. Defaults to 1.0.
 
     Returns:
-        csr_matrix: A binary neighborhood matrix (CSR) based on Spinglass communities.
+        csr_matrix: A binary cluster matrix (CSR) based on Spinglass communities.
 
     Raises:
         ValueError: If the subgraph has no edges after filtering.
@@ -340,7 +340,7 @@ def calculate_spinglass_neighborhoods(
             logger.error(f"Error running Spinglass on component: {e}")
             continue
 
-        # Step 3: Assign neighborhoods based on community labels
+        # Step 3: Assign clusters based on community labels
         for community in communities:
             mapped_indices = [
                 node_index_map[igraph_subgraph.vs[node]["_nx_name"]] for node in community
@@ -353,12 +353,12 @@ def calculate_spinglass_neighborhoods(
     # Step 4: Create a CSR matrix
     num_nodes = len(nodes)
     data = np.ones(len(row_indices), dtype=int)
-    neighborhoods = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
+    clusters = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
 
-    return neighborhoods
+    return clusters
 
 
-def calculate_walktrap_neighborhoods(
+def calculate_walktrap_clusters(
     network: nx.Graph, fraction_shortest_edges: float = 1.0
 ) -> csr_matrix:
     """
@@ -370,7 +370,7 @@ def calculate_walktrap_neighborhoods(
             subgraphs before clustering. Defaults to 1.0.
 
     Returns:
-        csr_matrix: A binary neighborhood matrix (CSR) on Walktrap communities.
+        csr_matrix: A binary cluster matrix (CSR) on Walktrap communities.
 
     Raises:
         ValueError: If the subgraph has no edges after filtering.
@@ -400,9 +400,9 @@ def calculate_walktrap_neighborhoods(
     # Create a CSR matrix
     num_nodes = len(nodes)
     data = np.ones(len(row_indices), dtype=int)
-    neighborhoods = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
+    clusters = csr_matrix((data, (row_indices, col_indices)), shape=(num_nodes, num_nodes))
 
-    return neighborhoods
+    return clusters
 
 
 def _create_percentile_limited_subgraph(G: nx.Graph, fraction_shortest_edges: float) -> nx.Graph: