risk-network 0.0.9b9__tar.gz → 0.0.9b13__tar.gz

{risk_network-0.0.9b9 → risk_network-0.0.9b13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: risk-network
-Version: 0.0.9b9
+Version: 0.0.9b13
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>
@@ -695,6 +695,7 @@ Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: ipywidgets
+Requires-Dist: leidenalg
 Requires-Dist: markov_clustering
 Requires-Dist: matplotlib
 Requires-Dist: networkx
@@ -702,6 +703,7 @@ Requires-Dist: nltk==3.8.1
 Requires-Dist: numpy
 Requires-Dist: openpyxl
 Requires-Dist: pandas
+Requires-Dist: python-igraph
 Requires-Dist: python-louvain
 Requires-Dist: scikit-learn
 Requires-Dist: scipy

{risk_network-0.0.9b9 → risk_network-0.0.9b13}/pyproject.toml

@@ -27,6 +27,7 @@ classifiers = [
 ]
 dependencies = [
     "ipywidgets",
+    "leidenalg",
     "markov_clustering",
     "matplotlib",
     "networkx",
@@ -34,6 +35,7 @@ dependencies = [
     "numpy",
     "openpyxl",
     "pandas",
+    "python-igraph",
     "python-louvain",
     "scikit-learn",
     "scipy",

{risk_network-0.0.9b9 → risk_network-0.0.9b13}/risk/__init__.py

@@ -7,4 +7,4 @@ RISK: RISK Infers Spatial Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.9-beta.9"
+__version__ = "0.0.9-beta.13"

risk_network-0.0.9b13/risk/neighborhoods/community.py

@@ -0,0 +1,367 @@
+"""
+risk/neighborhoods/community
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+"""
+
+import community as community_louvain
+import igraph as ig
+import markov_clustering as mc
+import networkx as nx
+import numpy as np
+from leidenalg import find_partition, RBConfigurationVertexPartition
+from networkx.algorithms.community import greedy_modularity_communities
+
+
+def calculate_greedy_modularity_neighborhoods(
+    network: nx.Graph, edge_rank_percentile: float = 1.0
+) -> np.ndarray:
+    """Calculate neighborhoods using the Greedy Modularity method.
+
+    Args:
+        network (nx.Graph): The network graph.
+        edge_rank_percentile (float, optional): Shortest edge rank percentile threshold for creating
+            subgraphs before clustering.
+
+    Returns:
+        np.ndarray: A binary neighborhood matrix where nodes in the same community have 1, and others have 0.
+    """
+    # Create a subgraph with the shortest edges based on the rank percentile
+    subnetwork = _create_percentile_limited_subgraph(
+        network, edge_rank_percentile=edge_rank_percentile
+    )
+    # Detect communities using the Greedy Modularity method
+    communities = greedy_modularity_communities(subnetwork)
+    # Get the list of nodes in the original NetworkX graph
+    nodes = list(network.nodes())
+    node_index_map = {node: idx for idx, node in enumerate(nodes)}
+    # Create a binary neighborhood matrix
+    num_nodes = len(nodes)
+    # Initialize neighborhoods with zeros and set self-self entries to 1
+    neighborhoods = np.eye(num_nodes, dtype=int)
+    # Fill in the neighborhood matrix for nodes in the same community
+    for community in communities:
+        # Iterate through all pairs of nodes in the same community
+        for node_i in community:
+            for node_j in community:
+                idx_i = node_index_map[node_i]
+                idx_j = node_index_map[node_j]
+                # Set them as neighbors (1) in the binary matrix
+                neighborhoods[idx_i, idx_j] = 1
+
+    return neighborhoods
+
+
+def calculate_label_propagation_neighborhoods(
+    network: nx.Graph, edge_rank_percentile: float = 1.0
+) -> np.ndarray:
+    """Apply Label Propagation to the network to detect communities.
+
+    Args:
+        network (nx.Graph): The network graph.
+        edge_rank_percentile (float, optional): Shortest edge rank percentile threshold for creating
+            subgraphs before clustering.
+
+    Returns:
+        np.ndarray: A binary neighborhood matrix on Label Propagation.
+    """
+    # Create a subgraph with the shortest edges based on the rank percentile
+    subnetwork = _create_percentile_limited_subgraph(
+        network, edge_rank_percentile=edge_rank_percentile
+    )
+    # Apply Label Propagation for community detection
+    communities = nx.algorithms.community.label_propagation.label_propagation_communities(
+        subnetwork
+    )
+    # Get the list of nodes in the network
+    nodes = list(network.nodes())
+    node_index_map = {node: idx for idx, node in enumerate(nodes)}
+    # Create a binary neighborhood matrix
+    num_nodes = len(nodes)
+    # Initialize neighborhoods with zeros and set self-self entries to 1
+    neighborhoods = np.eye(num_nodes, dtype=int)
+    # Assign neighborhoods based on community labels using the mapped indices
+    for community in communities:
+        for node_i in community:
+            for node_j in community:
+                idx_i = node_index_map[node_i]
+                idx_j = node_index_map[node_j]
+                neighborhoods[idx_i, idx_j] = 1
+
+    return neighborhoods
+
+
+def calculate_leiden_neighborhoods(
+    network: nx.Graph,
+    resolution: float = 1.0,
+    edge_rank_percentile: float = 1.0,
+    random_seed: int = 888,
+) -> np.ndarray:
+    """Calculate neighborhoods using the Leiden method.
+
+    Args:
+        network (nx.Graph): The network graph.
+        resolution (float, optional): Resolution parameter for the Leiden method. Defaults to 1.0.
+        edge_rank_percentile (float, optional): Shortest edge rank percentile threshold for creating
+            subgraphs before clustering.
+        random_seed (int, optional): Random seed for reproducibility. Defaults to 888.
+
+    Returns:
+        np.ndarray: A binary neighborhood matrix where nodes in the same community have 1, and others have 0.
+    """
+    # Create a subgraph with the shortest edges based on the rank percentile
+    subnetwork = _create_percentile_limited_subgraph(
+        network, edge_rank_percentile=edge_rank_percentile
+    )
+    # Convert NetworkX graph to iGraph
+    igraph_network = ig.Graph.from_networkx(subnetwork)
+    # Apply Leiden algorithm using RBConfigurationVertexPartition, which supports resolution
+    partition = find_partition(
+        igraph_network,
+        partition_type=RBConfigurationVertexPartition,
+        resolution_parameter=resolution,
+        seed=random_seed,
+    )
+    # Get the list of nodes in the original NetworkX graph
+    nodes = list(network.nodes())
+    node_index_map = {node: idx for idx, node in enumerate(nodes)}
+    # Create a binary neighborhood matrix
+    num_nodes = len(nodes)
+    # Initialize neighborhoods with zeros and set self-self entries to 1
+    neighborhoods = np.eye(num_nodes, dtype=int)
+    # Assign neighborhoods based on community partitions using the mapped indices
+    for community in partition:
+        for node_i in community:
+            for node_j in community:
+                idx_i = node_index_map[igraph_network.vs[node_i]["_nx_name"]]
+                idx_j = node_index_map[igraph_network.vs[node_j]["_nx_name"]]
+                neighborhoods[idx_i, idx_j] = 1
+
+    return neighborhoods
+
+
+def calculate_louvain_neighborhoods(
+    network: nx.Graph,
+    resolution: float = 0.1,
+    edge_rank_percentile: float = 1.0,
+    random_seed: int = 888,
+) -> np.ndarray:
+    """Calculate neighborhoods using the Louvain method.
+
+    Args:
+        network (nx.Graph): The network graph.
+        resolution (float, optional): Resolution parameter for the Louvain method. Defaults to 0.1.
+        edge_rank_percentile (float, optional): Shortest edge rank percentile threshold for creating
+            subgraphs before clustering.
+        random_seed (int, optional): Random seed for reproducibility. Defaults to 888.
+
+    Returns:
+        np.ndarray: A binary neighborhood matrix on the Louvain method.
+    """
+    # Create a subgraph with the shortest edges based on the rank percentile
+    subnetwork = _create_percentile_limited_subgraph(
+        network, edge_rank_percentile=edge_rank_percentile
+    )
+    # Apply Louvain method to partition the network
+    partition = community_louvain.best_partition(
+        subnetwork, resolution=resolution, random_state=random_seed
+    )
+    # Get the list of nodes in the network and create a mapping to indices
+    nodes = list(network.nodes())
+    node_index_map = {node: idx for idx, node in enumerate(nodes)}
+    # Create a binary neighborhood matrix
+    num_nodes = len(nodes)
+    # Initialize neighborhoods with zeros and set self-self entries to 1
+    neighborhoods = np.eye(num_nodes, dtype=int)
+    # Group nodes by community
+    community_groups = {}
+    for node, community in partition.items():
+        community_groups.setdefault(community, []).append(node)
+
+    # Assign neighborhoods based on community partitions using the mapped indices
+    for community, nodes in community_groups.items():
+        for node_i in nodes:
+            for node_j in nodes:
+                idx_i = node_index_map[node_i]
+                idx_j = node_index_map[node_j]
+                neighborhoods[idx_i, idx_j] = 1
+
+    return neighborhoods
+
+
+def calculate_markov_clustering_neighborhoods(
+    network: nx.Graph, edge_rank_percentile: float = 1.0
+) -> np.ndarray:
+    """Apply Markov Clustering (MCL) to the network and return a binary neighborhood matrix.
+
+    Args:
+        network (nx.Graph): The network graph.
+        edge_rank_percentile (float, optional): Shortest edge rank percentile threshold for creating
+            subgraphs before clustering.
+
+    Returns:
+        np.ndarray: A binary neighborhood matrix on Markov Clustering.
+    """
+    # Create a subgraph with the shortest edges based on the rank percentile
+    subnetwork = _create_percentile_limited_subgraph(
+        network, edge_rank_percentile=edge_rank_percentile
+    )
+    # Step 1: Convert the subnetwork to an adjacency matrix
+    subnetwork_nodes = list(subnetwork.nodes())
+    adjacency_matrix = nx.to_numpy_array(subnetwork, nodelist=subnetwork_nodes)
+    # Step 2: Run Markov Clustering (MCL) on the subnetwork's adjacency matrix
+    result = mc.run_mcl(adjacency_matrix)
+    clusters = mc.get_clusters(result)
+    # Step 3: Prepare the original network nodes and indices
+    nodes = list(network.nodes())
+    node_index_map = {node: idx for idx, node in enumerate(nodes)}
+    num_nodes = len(nodes)
+    # Step 4: Initialize the neighborhood matrix for the original network
+    neighborhoods = np.eye(num_nodes, dtype=int)
+    # Step 5: Fill the neighborhoods matrix using the clusters from the subnetwork
+    for cluster in clusters:
+        for node_i in cluster:
+            for node_j in cluster:
+                # Map the indices back to the original network's node indices
+                original_node_i = subnetwork_nodes[node_i]
+                original_node_j = subnetwork_nodes[node_j]
+
+                if original_node_i in node_index_map and original_node_j in node_index_map:
+                    idx_i = node_index_map[original_node_i]
+                    idx_j = node_index_map[original_node_j]
+                    neighborhoods[idx_i, idx_j] = 1
+
+    return neighborhoods
+
+
+def calculate_spinglass_neighborhoods(
+    network: nx.Graph, edge_rank_percentile: float = 1.0
+) -> np.ndarray:
+    """Apply Spinglass Community Detection to the network, handling disconnected components.
+
+    Args:
+        network (nx.Graph): The network graph.
+        edge_rank_percentile (float, optional): Shortest edge rank percentile threshold for creating
+            subgraphs before clustering.
+
+    Returns:
+        np.ndarray: A binary neighborhood matrix based on Spinglass communities.
+    """
+    # Create a subgraph with the shortest edges based on the rank percentile
+    subnetwork = _create_percentile_limited_subgraph(
+        network, edge_rank_percentile=edge_rank_percentile
+    )
+    # Step 1: Find connected components in the graph
+    components = list(nx.connected_components(subnetwork))
+    # Prepare to store community results
+    nodes = list(network.nodes())
+    node_index_map = {node: idx for idx, node in enumerate(nodes)}
+    num_nodes = len(nodes)
+    # Initialize neighborhoods with zeros and set self-self entries to 1
+    neighborhoods = np.eye(num_nodes, dtype=int)
+    # Step 2: Run Spinglass on each connected component
+    for component in components:
+        # Extract the subgraph corresponding to the current component
+        subgraph = network.subgraph(component)
+        # Convert the subgraph to an iGraph object
+        igraph_subgraph = ig.Graph.from_networkx(subgraph)
+        # Ensure the subgraph is connected before running Spinglass
+        if not igraph_subgraph.is_connected():
+            print("Warning: Subgraph is not connected. Skipping...")
+            continue
+
+        # Apply Spinglass community detection
+        try:
+            communities = igraph_subgraph.community_spinglass()
+        except Exception as e:
+            print(f"Error running Spinglass on component: {e}")
+            continue
+
+        # Step 3: Assign neighborhoods based on community labels
+        for community in communities:
+            for node_i in community:
+                for node_j in community:
+                    idx_i = node_index_map[igraph_subgraph.vs[node_i]["_nx_name"]]
+                    idx_j = node_index_map[igraph_subgraph.vs[node_j]["_nx_name"]]
+                    neighborhoods[idx_i, idx_j] = 1
+
+    return neighborhoods
+
+
+def calculate_walktrap_neighborhoods(
+    network: nx.Graph, edge_rank_percentile: float = 1.0
+) -> np.ndarray:
+    """Apply Walktrap Community Detection to the network.
+
+    Args:
+        network (nx.Graph): The network graph.
+        edge_rank_percentile (float, optional): Shortest edge rank percentile threshold for creating
+            subgraphs before clustering.
+
+    Returns:
+        np.ndarray: A binary neighborhood matrix on Walktrap communities.
+    """
+    # Create a subgraph with the shortest edges based on the rank percentile
+    subnetwork = _create_percentile_limited_subgraph(
+        network, edge_rank_percentile=edge_rank_percentile
+    )
+    # Convert NetworkX graph to iGraph
+    igraph_network = ig.Graph.from_networkx(subnetwork)
+    # Apply Walktrap community detection
+    communities = igraph_network.community_walktrap().as_clustering()
+    # Get the list of nodes in the original NetworkX graph
+    nodes = list(network.nodes())
+    node_index_map = {node: idx for idx, node in enumerate(nodes)}
+    # Create a binary neighborhood matrix
+    num_nodes = len(nodes)
+    # Initialize neighborhoods with zeros and set self-self entries to 1
+    neighborhoods = np.eye(num_nodes, dtype=int)
+    # Assign neighborhoods based on community labels
+    for community in communities:
+        for node_i in community:
+            for node_j in community:
+                idx_i = node_index_map[igraph_network.vs[node_i]["_nx_name"]]
+                idx_j = node_index_map[igraph_network.vs[node_j]["_nx_name"]]
+                neighborhoods[idx_i, idx_j] = 1
+
+    return neighborhoods
+
+
+def _create_percentile_limited_subgraph(G: nx.Graph, edge_rank_percentile: float) -> nx.Graph:
+    """Create a subgraph containing the shortest edges based on the specified rank percentile
+    of all edge lengths in the input graph.
+
+    Args:
+        G (nx.Graph): The input graph with 'length' attributes on edges.
+        edge_rank_percentile (float): The rank percentile (between 0 and 1) to filter edges.
+
+    Returns:
+        nx.Graph: A subgraph with nodes and edges where the edges are within the shortest
+        specified rank percentile.
+    """
+    # Step 1: Extract edges with their lengths
+    edges_with_length = [(u, v, d) for u, v, d in G.edges(data=True) if "length" in d]
+    if not edges_with_length:
+        raise ValueError(
+            "No edge lengths found in the graph. Ensure edges have 'length' attributes."
+        )
+
+    # Step 2: Sort edges by length in ascending order
+    edges_with_length.sort(key=lambda x: x[2]["length"])
+    # Step 3: Calculate the cutoff index for the given rank percentile
+    cutoff_index = int(edge_rank_percentile * len(edges_with_length))
+    if cutoff_index == 0:
+        raise ValueError("The rank percentile is too low, resulting in no edges being included.")
+
+    # Step 4: Create the subgraph by selecting only the shortest edges within the rank percentile
+    subgraph = nx.Graph()
+    subgraph.add_nodes_from(G.nodes(data=True))  # Retain all nodes from the original graph
+    subgraph.add_edges_from(edges_with_length[:cutoff_index])
+    # Step 5: Remove nodes with no edges
+    subgraph.remove_nodes_from(list(nx.isolates(subgraph)))
+    # Step 6: Check if the resulting subgraph has no edges and issue a warning
+    if subgraph.number_of_edges() == 0:
+        raise Warning(
+            "The resulting subgraph has no edges. Consider adjusting the rank percentile."
+        )
+
+    return subgraph

{risk_network-0.0.9b9 → risk_network-0.0.9b13}/risk/neighborhoods/neighborhoods.py

@@ -15,6 +15,7 @@ from sklearn.metrics.pairwise import cosine_similarity
 from risk.neighborhoods.community import (
     calculate_greedy_modularity_neighborhoods,
     calculate_label_propagation_neighborhoods,
+    calculate_leiden_neighborhoods,
     calculate_louvain_neighborhoods,
     calculate_markov_clustering_neighborhoods,
     calculate_spinglass_neighborhoods,
@@ -29,22 +30,20 @@ warnings.filterwarnings(action="ignore", category=DataConversionWarning)
 def get_network_neighborhoods(
     network: nx.Graph,
     distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
-    edge_length_threshold: Union[float, List, Tuple, np.ndarray] = 1.0,
-    louvain_resolution: float = 1.0,
+    edge_rank_percentile: Union[float, List, Tuple, np.ndarray] = 1.0,
+    louvain_resolution: float = 0.1,
+    leiden_resolution: float = 1.0,
     random_seed: int = 888,
 ) -> np.ndarray:
     """Calculate the combined neighborhoods for each node based on the specified community detection algorithm(s).
 
     Args:
         network (nx.Graph): The network graph.
-        distance_metric (str, List, Tuple, or np.ndarray, optional): The distance metric(s) to use. Can be a string for one
-            metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'label_propagation',
-            'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
-        edge_length_threshold (float, List, Tuple, or np.ndarray, optional): Edge length threshold(s) for creating subgraphs.
-            Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
-            Defaults to 1.0.
-        louvain_resolution (float, optional): Resolution parameter for the Louvain method. Defaults to 1.0.
-        random_seed (int, optional): Random seed for methods requiring random initialization. Defaults to 888.
+        distance_metric (str, List, Tuple, or np.ndarray, optional): The distance metric(s) to use.
+        edge_rank_percentile (float, List, Tuple, or np.ndarray, optional): Shortest edge rank percentile threshold(s) for creating subgraphs.
+        louvain_resolution (float, optional): Resolution parameter for the Louvain method.
+        leiden_resolution (float, optional): Resolution parameter for the Leiden method.
+        random_seed (int, optional): Random seed for methods requiring random initialization.
 
     Returns:
         np.ndarray: Summed neighborhood matrix from all selected algorithms.
@@ -56,11 +55,11 @@ def get_network_neighborhoods(
     # Ensure distance_metric is a list/tuple for multi-algorithm handling
     if isinstance(distance_metric, (str, np.ndarray)):
         distance_metric = [distance_metric]
-    # Ensure edge_length_threshold is a list/tuple for multi-threshold handling
-    if isinstance(edge_length_threshold, (float, int)):
-        edge_length_threshold = [edge_length_threshold] * len(distance_metric)
+    # Ensure edge_rank_percentile is a list/tuple for multi-threshold handling
+    if isinstance(edge_rank_percentile, (float, int)):
+        edge_rank_percentile = [edge_rank_percentile] * len(distance_metric)
     # Check that the number of distance metrics matches the number of edge length thresholds
-    if len(distance_metric) != len(edge_length_threshold):
+    if len(distance_metric) != len(edge_rank_percentile):
         raise ValueError(
             "The number of distance metrics must match the number of edge length thresholds."
         )
@@ -69,29 +68,47 @@ def get_network_neighborhoods(
     num_nodes = network.number_of_nodes()
     combined_neighborhoods = np.zeros((num_nodes, num_nodes), dtype=int)
 
-    # Loop through each distance metric and corresponding edge length threshold
-    for metric, threshold in zip(distance_metric, edge_length_threshold):
-        # Create a subgraph based on the specific edge length threshold for this algorithm
-        subgraph = _create_percentile_limited_subgraph(network, edge_length_percentile=threshold)
+    # Loop through each distance metric and corresponding edge rank percentile
+    for metric, percentile in zip(distance_metric, edge_rank_percentile):
         # Call the appropriate neighborhood function based on the metric
-        if metric == "louvain":
-            neighborhoods = calculate_louvain_neighborhoods(
-                subgraph, louvain_resolution, random_seed=random_seed
+        if metric == "greedy_modularity":
+            neighborhoods = calculate_greedy_modularity_neighborhoods(
+                network, edge_rank_percentile=percentile
             )
-        elif metric == "greedy_modularity":
-            neighborhoods = calculate_greedy_modularity_neighborhoods(subgraph)
         elif metric == "label_propagation":
-            neighborhoods = calculate_label_propagation_neighborhoods(subgraph)
+            neighborhoods = calculate_label_propagation_neighborhoods(
+                network, edge_rank_percentile=percentile
+            )
+        elif metric == "leiden":
+            neighborhoods = calculate_leiden_neighborhoods(
+                network,
+                resolution=leiden_resolution,
+                edge_rank_percentile=percentile,
+                random_seed=random_seed,
+            )
+        elif metric == "louvain":
+            neighborhoods = calculate_louvain_neighborhoods(
+                network,
+                resolution=louvain_resolution,
+                edge_rank_percentile=percentile,
+                random_seed=random_seed,
+            )
         elif metric == "markov_clustering":
-            neighborhoods = calculate_markov_clustering_neighborhoods(subgraph)
-        elif metric == "walktrap":
-            neighborhoods = calculate_walktrap_neighborhoods(subgraph)
+            neighborhoods = calculate_markov_clustering_neighborhoods(
+                network, edge_rank_percentile=percentile
+            )
         elif metric == "spinglass":
-            neighborhoods = calculate_spinglass_neighborhoods(subgraph)
+            neighborhoods = calculate_spinglass_neighborhoods(
+                network, edge_rank_percentile=percentile
+            )
+        elif metric == "walktrap":
+            neighborhoods = calculate_walktrap_neighborhoods(
+                network, edge_rank_percentile=percentile
+            )
         else:
             raise ValueError(
-                "Incorrect distance metric specified. Please choose from 'greedy_modularity', 'louvain',"
-                "'label_propagation', 'markov_clustering', 'walktrap', 'spinglass'."
+                "Incorrect distance metric specified. Please choose from 'greedy_modularity', 'label_propagation',"
+                "'leiden', 'louvain', 'markov_clustering', 'spinglass', 'walktrap'."
             )
 
         # Sum the neighborhood matrices
@@ -100,50 +117,16 @@ def get_network_neighborhoods(
     # Ensure that the maximum value in each row is set to 1
     # This ensures that for each row, only the strongest relationship (the maximum value) is retained,
     # while all other values are reset to 0. This transformation simplifies the neighborhood matrix by
-    # focusing on the most significant connection per row.
-    combined_neighborhoods = _set_max_to_one(combined_neighborhoods)
+    # focusing on the most significant connection per row (or nodes).
+    combined_neighborhoods = _set_max_row_value_to_one(combined_neighborhoods)
 
     return combined_neighborhoods
 
 
-def _create_percentile_limited_subgraph(G: nx.Graph, edge_length_percentile: float) -> nx.Graph:
-    """Create a subgraph containing all nodes and edges where the edge length is below the
-    specified percentile of all edge lengths in the input graph.
-
-    Args:
-        G (nx.Graph): The input graph with 'length' attributes on edges.
-        edge_length_percentile (float): The percentile (between 0 and 1) to filter edges by length.
-
-    Returns:
-        nx.Graph: A subgraph with all nodes and edges where the edge length is below the
-        calculated threshold length.
-    """
-    # Extract edge lengths and handle missing lengths
-    edge_lengths = [d["length"] for _, _, d in G.edges(data=True) if "length" in d]
-    if not edge_lengths:
-        raise ValueError(
-            "No edge lengths found in the graph. Ensure edges have 'length' attributes."
-        )
-
-    # Calculate the specific edge length for the given percentile
-    percentile_length = np.percentile(edge_lengths, edge_length_percentile * 100)
-    # Create the subgraph by directly filtering edges during iteration
-    subgraph = nx.Graph()
-    subgraph.add_nodes_from(G.nodes(data=True))  # Retain all nodes from the original graph
-    # Add edges below the specified percentile length in a single pass
-    for u, v, d in G.edges(data=True):
-        if d.get("length", 1) <= percentile_length:
-            subgraph.add_edge(u, v, **d)
-
-    # Return the subgraph; optionally check if it's too sparse
-    if subgraph.number_of_edges() == 0:
-        raise Warning("The resulting subgraph has no edges. Consider adjusting the percentile.")
-
-    return subgraph
-
-
-def _set_max_to_one(matrix: np.ndarray) -> np.ndarray:
-    """For each row in the input matrix, set the maximum value(s) to 1 and all other values to 0.
+def _set_max_row_value_to_one(matrix: np.ndarray) -> np.ndarray:
+    """For each row in the input matrix, set the maximum value(s) to 1 and all other values to 0. This is particularly
+    useful for neighborhood matrices that have undergone multiple neighborhood detection algorithms, where the
+    maximum value in each row represents the most significant relationship per node in the combined neighborhoods.
 
     Args:
         matrix (np.ndarray): A 2D numpy array representing the neighborhood matrix.

{risk_network-0.0.9b9 → risk_network-0.0.9b13}/risk/network/plot/labels.py

@@ -617,8 +617,7 @@ class Labels:
         """
         # Return custom labels if domain is in ids_to_labels
         if ids_to_labels and domain in ids_to_labels:
-            terms = ids_to_labels[domain].replace(" ", TERM_DELIMITER)
-            return terms
+            return ids_to_labels[domain]
 
         else:
             terms = self.graph.domain_id_to_domain_terms_map[domain].split(" ")

{risk_network-0.0.9b9 → risk_network-0.0.9b13}/risk/risk.py

@@ -52,7 +52,8 @@ class RISK(NetworkIO, AnnotationsIO):
         annotations: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
-        edge_length_threshold: Union[float, List, Tuple, np.ndarray] = 0.5,
+        leiden_resolution: float = 1.0,
+        edge_rank_percentile: Union[float, List, Tuple, np.ndarray] = 0.5,
         null_distribution: str = "network",
         random_seed: int = 888,
     ) -> Dict[str, Any]:
@@ -65,7 +66,8 @@ class RISK(NetworkIO, AnnotationsIO):
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
             louvain_resolution (float, optional): Resolution parameter for Louvain clustering. Defaults to 0.1.
-            edge_length_threshold (float, List, Tuple, or np.ndarray, optional): Edge length threshold(s) for creating subgraphs.
+            leiden_resolution (float, optional): Resolution parameter for Leiden clustering. Defaults to 1.0.
+            edge_rank_percentile (float, List, Tuple, or np.ndarray, optional): Shortest edge rank percentile threshold(s) for creating subgraphs.
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
             null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
@@ -79,7 +81,8 @@ class RISK(NetworkIO, AnnotationsIO):
         params.log_neighborhoods(
             distance_metric=distance_metric,
             louvain_resolution=louvain_resolution,
-            edge_length_threshold=edge_length_threshold,
+            leiden_resolution=leiden_resolution,
+            edge_rank_percentile=edge_rank_percentile,
             statistical_test_function="hypergeom",
             null_distribution=null_distribution,
             random_seed=random_seed,
@@ -93,7 +96,8 @@ class RISK(NetworkIO, AnnotationsIO):
             network,
             distance_metric,
             louvain_resolution=louvain_resolution,
-            edge_length_threshold=edge_length_threshold,
+            leiden_resolution=leiden_resolution,
+            edge_rank_percentile=edge_rank_percentile,
             random_seed=random_seed,
         )
         # Run hypergeometric test to compute neighborhood significance
@@ -112,7 +116,8 @@ class RISK(NetworkIO, AnnotationsIO):
         annotations: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
-        edge_length_threshold: Union[float, List, Tuple, np.ndarray] = 0.5,
+        leiden_resolution: float = 1.0,
+        edge_rank_percentile: Union[float, List, Tuple, np.ndarray] = 0.5,
         null_distribution: str = "network",
         random_seed: int = 888,
     ) -> Dict[str, Any]:
@@ -125,7 +130,8 @@ class RISK(NetworkIO, AnnotationsIO):
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
             louvain_resolution (float, optional): Resolution parameter for Louvain clustering. Defaults to 0.1.
-            edge_length_threshold (float, List, Tuple, or np.ndarray, optional): Edge length threshold(s) for creating subgraphs.
+            leiden_resolution (float, optional): Resolution parameter for Leiden clustering. Defaults to 1.0.
+            edge_rank_percentile (float, List, Tuple, or np.ndarray, optional): Shortest edge rank percentile threshold(s) for creating subgraphs.
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
             null_distribution (str, optional): Type of null distribution ('network' or 'annotations'). Defaults to "network".
@@ -139,7 +145,8 @@ class RISK(NetworkIO, AnnotationsIO):
         params.log_neighborhoods(
             distance_metric=distance_metric,
             louvain_resolution=louvain_resolution,
-            edge_length_threshold=edge_length_threshold,
+            leiden_resolution=leiden_resolution,
+            edge_rank_percentile=edge_rank_percentile,
             statistical_test_function="poisson",
             null_distribution=null_distribution,
             random_seed=random_seed,
@@ -153,7 +160,8 @@ class RISK(NetworkIO, AnnotationsIO):
             network,
             distance_metric,
             louvain_resolution=louvain_resolution,
-            edge_length_threshold=edge_length_threshold,
+            leiden_resolution=leiden_resolution,
+            edge_rank_percentile=edge_rank_percentile,
             random_seed=random_seed,
         )
         # Run Poisson test to compute neighborhood significance
@@ -172,7 +180,8 @@ class RISK(NetworkIO, AnnotationsIO):
         annotations: Dict[str, Any],
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
-        edge_length_threshold: Union[float, List, Tuple, np.ndarray] = 0.5,
+        leiden_resolution: float = 1.0,
+        edge_rank_percentile: Union[float, List, Tuple, np.ndarray] = 0.5,
         score_metric: str = "sum",
         null_distribution: str = "network",
         num_permutations: int = 1000,
@@ -188,7 +197,8 @@ class RISK(NetworkIO, AnnotationsIO):
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
             louvain_resolution (float, optional): Resolution parameter for Louvain clustering. Defaults to 0.1.
-            edge_length_threshold (float, List, Tuple, or np.ndarray, optional): Edge length threshold(s) for creating subgraphs.
+            leiden_resolution (float, optional): Resolution parameter for Leiden clustering. Defaults to 1.0.
+            edge_rank_percentile (float, List, Tuple, or np.ndarray, optional): Shortest edge rank percentile threshold(s) for creating subgraphs.
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
             score_metric (str, optional): Scoring metric for neighborhood significance. Defaults to "sum".
@@ -205,7 +215,8 @@ class RISK(NetworkIO, AnnotationsIO):
         params.log_neighborhoods(
             distance_metric=distance_metric,
             louvain_resolution=louvain_resolution,
-            edge_length_threshold=edge_length_threshold,
+            leiden_resolution=leiden_resolution,
+            edge_rank_percentile=edge_rank_percentile,
             statistical_test_function="permutation",
             score_metric=score_metric,
             null_distribution=null_distribution,
@@ -222,7 +233,8 @@ class RISK(NetworkIO, AnnotationsIO):
             network,
             distance_metric,
             louvain_resolution=louvain_resolution,
-            edge_length_threshold=edge_length_threshold,
+            leiden_resolution=leiden_resolution,
+            edge_rank_percentile=edge_rank_percentile,
             random_seed=random_seed,
         )
 
@@ -408,7 +420,8 @@ class RISK(NetworkIO, AnnotationsIO):
         network: nx.Graph,
         distance_metric: Union[str, List, Tuple, np.ndarray] = "louvain",
         louvain_resolution: float = 0.1,
-        edge_length_threshold: Union[float, List, Tuple, np.ndarray] = 0.5,
+        leiden_resolution: float = 1.0,
+        edge_rank_percentile: Union[float, List, Tuple, np.ndarray] = 0.5,
         random_seed: int = 888,
     ) -> np.ndarray:
         """Load significant neighborhoods for the network.
@@ -420,7 +433,8 @@ class RISK(NetworkIO, AnnotationsIO):
                 metric or a list/tuple/ndarray of metrics ('greedy_modularity', 'louvain', 'label_propagation',
                 'markov_clustering', 'walktrap', 'spinglass'). Defaults to 'louvain'.
             louvain_resolution (float, optional): Resolution parameter for Louvain clustering. Defaults to 0.1.
-            edge_length_threshold (float, List, Tuple, or np.ndarray, optional): Edge length threshold(s) for creating subgraphs.
+            leiden_resolution (float, optional): Resolution parameter for Leiden clustering. Defaults to 1.0.
+            edge_rank_percentile (float, List, Tuple, or np.ndarray, optional): Shortest edge rank percentile threshold(s) for creating subgraphs.
                 Can be a single float for one threshold or a list/tuple of floats corresponding to multiple thresholds.
                 Defaults to 0.5.
             random_seed (int, optional): Seed for random number generation. Defaults to 888.
@@ -431,19 +445,22 @@ class RISK(NetworkIO, AnnotationsIO):
         # Display the chosen distance metric
         if distance_metric == "louvain":
             for_print_distance_metric = f"louvain (resolution={louvain_resolution})"
+        elif distance_metric == "leiden":
+            for_print_distance_metric = f"leiden (resolution={leiden_resolution})"
         else:
             for_print_distance_metric = distance_metric
         # Log and display neighborhood settings
         logger.debug(f"Distance metric: '{for_print_distance_metric}'")
-        logger.debug(f"Edge length threshold: {edge_length_threshold}")
+        logger.debug(f"Edge length threshold: {edge_rank_percentile}")
         logger.debug(f"Random seed: {random_seed}")
 
         # Compute neighborhoods based on the network and distance metric
         neighborhoods = get_network_neighborhoods(
             network,
             distance_metric,
-            edge_length_threshold,
+            edge_rank_percentile,
             louvain_resolution=louvain_resolution,
+            leiden_resolution=leiden_resolution,
             random_seed=random_seed,
         )
 

{risk_network-0.0.9b9 → risk_network-0.0.9b13}/risk_network.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: risk-network
-Version: 0.0.9b9
+Version: 0.0.9b13
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>
@@ -695,6 +695,7 @@ Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: ipywidgets
+Requires-Dist: leidenalg
 Requires-Dist: markov_clustering
 Requires-Dist: matplotlib
 Requires-Dist: networkx
@@ -702,6 +703,7 @@ Requires-Dist: nltk==3.8.1
 Requires-Dist: numpy
 Requires-Dist: openpyxl
 Requires-Dist: pandas
+Requires-Dist: python-igraph
 Requires-Dist: python-louvain
 Requires-Dist: scikit-learn
 Requires-Dist: scipy

{risk_network-0.0.9b9 → risk_network-0.0.9b13}/risk_network.egg-info/requires.txt

@@ -1,4 +1,5 @@
 ipywidgets
+leidenalg
 markov_clustering
 matplotlib
 networkx
@@ -6,6 +7,7 @@ nltk==3.8.1
 numpy
 openpyxl
 pandas
+python-igraph
 python-louvain
 scikit-learn
 scipy

{risk_network-0.0.9b9 → risk_network-0.0.9b13}/setup.py

@@ -31,13 +31,14 @@ setup(
     include_package_data=True,
     install_requires=[
         "ipywidgets",
+        "leidenalg",
         "markov_clustering",
         "matplotlib",
         "networkx",
         "nltk==3.8.1",
         "numpy",
         "openpyxl",
-        "pandas",
+        "pandas" "python-igraph",
         "python-louvain",
         "scikit-learn",
         "scipy",

risk_network-0.0.9b9/risk/neighborhoods/community.py

@@ -1,189 +0,0 @@
-"""
-risk/neighborhoods/community
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-"""
-
-import community as community_louvain
-import networkx as nx
-import numpy as np
-import markov_clustering as mc
-from networkx.algorithms.community import asyn_lpa_communities, greedy_modularity_communities
-
-
-def calculate_greedy_modularity_neighborhoods(network: nx.Graph) -> np.ndarray:
-    """Calculate neighborhoods using the Greedy Modularity method.
-
-    Args:
-        network (nx.Graph): The network graph to analyze for community structure.
-
-    Returns:
-        np.ndarray: A binary neighborhood matrix where nodes in the same community have 1, and others have 0.
-    """
-    # Detect communities using the Greedy Modularity method
-    communities = greedy_modularity_communities(network)
-    # Create a binary neighborhood matrix
-    n_nodes = network.number_of_nodes()
-    neighborhoods = np.zeros((n_nodes, n_nodes), dtype=int)
-    # Create a mapping from node to index in the matrix
-    node_index = {node: i for i, node in enumerate(network.nodes())}
-    # Fill in the neighborhood matrix for nodes in the same community
-    for community in communities:
-        # Iterate through all pairs of nodes in the same community
-        for node_i in community:
-            idx_i = node_index[node_i]
-            for node_j in community:
-                idx_j = node_index[node_j]
-                # Set them as neighbors (1) in the binary matrix
-                neighborhoods[idx_i, idx_j] = 1
-
-    return neighborhoods
-
-
-def calculate_label_propagation_neighborhoods(network: nx.Graph) -> np.ndarray:
-    """Apply Label Propagation to the network to detect communities.
-
-    Args:
-        network (nx.Graph): The network graph.
-
-    Returns:
-        np.ndarray: Binary neighborhood matrix on Label Propagation.
-    """
-    # Apply Label Propagation for community detection
-    communities = nx.algorithms.community.label_propagation.label_propagation_communities(network)
-    # Create a binary neighborhood matrix
-    num_nodes = network.number_of_nodes()
-    neighborhoods = np.zeros((num_nodes, num_nodes), dtype=int)
-    # Create a mapping from node to index in the matrix
-    node_index = {node: i for i, node in enumerate(network.nodes())}
-    # Assign neighborhoods based on community labels
-    for community in communities:
-        for node_i in community:
-            idx_i = node_index[node_i]
-            for node_j in community:
-                idx_j = node_index[node_j]
-                neighborhoods[idx_i, idx_j] = 1
-
-    return neighborhoods
-
-
-def calculate_louvain_neighborhoods(
-    network: nx.Graph, resolution: float, random_seed: int = 888
-) -> np.ndarray:
-    """Calculate neighborhoods using the Louvain method.
-
-    Args:
-        network (nx.Graph): The network graph.
-        resolution (float): Resolution parameter for the Louvain method.
-        random_seed (int, optional): Random seed for reproducibility. Defaults to 888.
-
-    Returns:
-        np.ndarray: Binary neighborhood matrix on the Louvain method.
-    """
-    # Apply Louvain method to partition the network
-    partition = community_louvain.best_partition(
-        network, resolution=resolution, random_state=random_seed
-    )
-    # Create a binary neighborhood matrix
-    num_nodes = network.number_of_nodes()
-    neighborhoods = np.zeros((num_nodes, num_nodes), dtype=int)
-    # Create a mapping from node to index in the matrix
-    node_index = {node: i for i, node in enumerate(network.nodes())}
-    # Group nodes by community
-    community_groups = {}
-    for node, community in partition.items():
-        community_groups.setdefault(community, []).append(node)
-
-    # Assign neighborhoods based on community partitions
-    for community, nodes in community_groups.items():
-        for node_i in nodes:
-            idx_i = node_index[node_i]
-            for node_j in nodes:
-                idx_j = node_index[node_j]
-                neighborhoods[idx_i, idx_j] = 1
-
-    return neighborhoods
-
-
-def calculate_markov_clustering_neighborhoods(network: nx.Graph) -> np.ndarray:
-    """Apply Markov Clustering (MCL) to the network.
-
-    Args:
-        network (nx.Graph): The network graph.
-
-    Returns:
-        np.ndarray: Binary neighborhood matrix on Markov Clustering.
-    """
-    # Convert the graph to an adjacency matrix
-    adjacency_matrix = nx.to_numpy_array(network)
-    # Run Markov Clustering (MCL)
-    result = mc.run_mcl(adjacency_matrix)  # MCL with default parameters
-    # Get clusters (communities) from MCL result
-    clusters = mc.get_clusters(result)
-    # Create a binary neighborhood matrix
-    num_nodes = network.number_of_nodes()
-    neighborhoods = np.zeros((num_nodes, num_nodes), dtype=int)
-    # Create a mapping from node to index in the matrix
-    node_index = {node: i for i, node in enumerate(network.nodes())}
-    # Assign neighborhoods based on MCL clusters
-    for cluster in clusters:
-        for node_i in cluster:
-            idx_i = node_index[node_i]
-            for node_j in cluster:
-                idx_j = node_index[node_j]
-                neighborhoods[idx_i, idx_j] = 1
-
-    return neighborhoods
-
-
-def calculate_spinglass_neighborhoods(network: nx.Graph) -> np.ndarray:
-    """Apply Spin Glass Community Detection to the network.
-
-    Args:
-        network (nx.Graph): The network graph.
-
-    Returns:
-        np.ndarray: Binary neighborhood matrix on Spin Glass communities.
-    """
-    # Apply Asynchronous Label Propagation (LPA)
-    communities = asyn_lpa_communities(network)
-    # Create a binary neighborhood matrix
-    num_nodes = network.number_of_nodes()
-    neighborhoods = np.zeros((num_nodes, num_nodes), dtype=int)
-    # Create a mapping from node to index in the matrix
-    node_index = {node: i for i, node in enumerate(network.nodes())}
-    # Assign neighborhoods based on community labels from LPA
-    for community in communities:
-        for node_i in community:
-            idx_i = node_index[node_i]
-            for node_j in community:
-                idx_j = node_index[node_j]
-                neighborhoods[idx_i, idx_j] = 1
-
-    return neighborhoods
-
-
-def calculate_walktrap_neighborhoods(network: nx.Graph) -> np.ndarray:
-    """Apply Walktrap Community Detection to the network.
-
-    Args:
-        network (nx.Graph): The network graph.
-
-    Returns:
-        np.ndarray: Binary neighborhood matrix on Walktrap communities.
-    """
-    # Apply Asynchronous Label Propagation (LPA)
-    communities = asyn_lpa_communities(network)
-    # Create a binary neighborhood matrix
-    num_nodes = network.number_of_nodes()
-    neighborhoods = np.zeros((num_nodes, num_nodes), dtype=int)
-    # Create a mapping from node to index in the matrix
-    node_index = {node: i for i, node in enumerate(network.nodes())}
-    # Assign neighborhoods based on community labels from LPA
-    for community in communities:
-        for node_i in community:
-            idx_i = node_index[node_i]
-            for node_j in community:
-                idx_j = node_index[node_j]
-                neighborhoods[idx_i, idx_j] = 1
-
-    return neighborhoods