risk-network 0.0.9b45__py3-none-any.whl → 0.0.10__py3-none-any.whl

risk/__init__.py

@@ -7,4 +7,4 @@ RISK: Regional Inference of Significant Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.9-beta.45"
+__version__ = "0.0.10"

risk/annotations/annotations.py

@@ -53,7 +53,7 @@ def ensure_nltk_resource(resource: str) -> None:
             print(f"Unzipped '{resource}' successfully.")
             break  # Stop after unzipping the first found ZIP.
 
-    # Final check: Try to load the resource one last time.
+    # Final check: Try to check resource one last time. If it fails, rai
     try:
         nltk.data.find(resource_path)
         print(f"Resource '{resource}' is now available.")
@@ -62,6 +62,11 @@ def ensure_nltk_resource(resource: str) -> None:
 
 
 # Ensure the NLTK stopwords and WordNet resources are available
+# punkt is known to have issues with the default download method, so we use a custom function if it fails
+try:
+    ensure_nltk_resource("punkt")
+except LookupError:
+    nltk.download("punkt")
 ensure_nltk_resource("stopwords")
 ensure_nltk_resource("wordnet")
 # Use NLTK's stopwords - load all languages

risk/neighborhoods/domains.py

@@ -3,12 +3,12 @@ risk/neighborhoods/domains
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
 """
 
-from contextlib import suppress
 from itertools import product
 from typing import Tuple, Union
 
 import numpy as np
 import pandas as pd
+from numpy.linalg import LinAlgError
 from scipy.cluster.hierarchy import linkage, fcluster
 from sklearn.metrics import silhouette_score
 from tqdm import tqdm
@@ -42,7 +42,7 @@ def define_domains(
     Args:
         top_annotations (pd.DataFrame): DataFrame of top annotations data for the network nodes.
         significant_neighborhoods_significance (np.ndarray): The binary significance matrix below alpha.
-        linkage_criterion (str): The clustering criterion for defining groups.
+        linkage_criterion (str): The clustering criterion for defining groups. Choose "off" to disable clustering.
         linkage_method (str): The linkage method for clustering. Choose "auto" to optimize.
         linkage_metric (str): The linkage metric for clustering. Choose "auto" to optimize.
         linkage_threshold (float, str): The threshold for clustering. Choose "auto" to optimize.
@@ -73,7 +73,7 @@ def define_domains(
         domains = fcluster(Z, max_d_optimal, criterion=linkage_criterion)
         top_annotations["domain"] = 0
         top_annotations.loc[top_annotations["significant_annotations"], "domain"] = domains
-    except ValueError:
+    except (ValueError, LinAlgError):
         # If a ValueError is encountered, handle it by assigning unique domains
         n_rows = len(top_annotations)
         if linkage_criterion == "off":
@@ -247,28 +247,36 @@ def _optimize_silhouette_across_linkage_and_metrics(
         bar_format="{l_bar}{bar}| {n_fmt}/{total_fmt} [{elapsed}<{remaining}]",
     ):
         # Some linkage methods and metrics may not work with certain data
-        with suppress(ValueError):
+        try:
             Z = linkage(m, method=method, metric=metric)
-            # Only optimize silhouette score if the threshold is "auto"
             if linkage_threshold == "auto":
-                threshold, score = _find_best_silhouette_score(Z, m, metric, linkage_criterion)
-                if score > best_overall_score:
-                    best_overall_score = score
-                    best_overall_threshold = threshold
-                    best_overall_method = method
-                    best_overall_metric = metric
+                try:
+                    threshold, score = _find_best_silhouette_score(Z, m, metric, linkage_criterion)
+                except (ValueError, LinAlgError):
+                    continue  # Skip to the next combination
+                current_threshold = threshold
             else:
-                # Use the provided threshold without optimization
                 score = silhouette_score(
                     m,
                     fcluster(Z, linkage_threshold * np.max(Z[:, 2]), criterion=linkage_criterion),
                     metric=metric,
                 )
-                if score > best_overall_score:
-                    best_overall_score = score
-                    best_overall_threshold = linkage_threshold
-                    best_overall_method = method
-                    best_overall_metric = metric
+                current_threshold = linkage_threshold
+        except (ValueError, LinAlgError):
+            continue  # Skip to the next combination
+
+        if score > best_overall_score:
+            best_overall_score = score
+            best_overall_threshold = float(current_threshold)  # Ensure it's a float
+            best_overall_method = method
+            best_overall_metric = metric
+
+    # Ensure that we always return a valid tuple:
+    if best_overall_score == -np.inf:
+        # No valid linkage was found; return default values.
+        best_overall_threshold = float(linkage_threshold) if linkage_threshold != "auto" else 0.0
+        best_overall_method = linkage_method
+        best_overall_metric = linkage_metric
 
     return best_overall_method, best_overall_metric, best_overall_threshold
 
@@ -280,7 +288,6 @@ def _find_best_silhouette_score(
     linkage_criterion: str,
     lower_bound: float = 0.001,
     upper_bound: float = 1.0,
-    resolution: float = 0.001,
 ) -> Tuple[float, float]:
     """Find the best silhouette score using binary search.
 
@@ -291,7 +298,6 @@ def _find_best_silhouette_score(
         linkage_criterion (str): Clustering criterion.
         lower_bound (float, optional): Lower bound for search. Defaults to 0.001.
         upper_bound (float, optional): Upper bound for search. Defaults to 1.0.
-        resolution (float, optional): Desired resolution for the best threshold. Defaults to 0.001.
 
     Returns:
         Tuple[float, float]:
@@ -300,6 +306,7 @@ def _find_best_silhouette_score(
     """
     best_score = -np.inf
     best_threshold = None
+    minimum_linkage_threshold = 1e-6
 
     # Test lower bound
     max_d_lower = np.max(Z[:, 2]) * lower_bound
@@ -328,7 +335,7 @@ def _find_best_silhouette_score(
         lower_bound = (lower_bound + upper_bound) / 2
 
     # Binary search loop
-    while upper_bound - lower_bound > resolution:
+    while upper_bound - lower_bound > minimum_linkage_threshold:
         mid_threshold = (upper_bound + lower_bound) / 2
         max_d_mid = np.max(Z[:, 2]) * mid_threshold
         clusters_mid = fcluster(Z, max_d_mid, criterion=linkage_criterion)

risk/network/geometry.py

@@ -12,7 +12,7 @@ def assign_edge_lengths(
     compute_sphere: bool = True,
     surface_depth: float = 0.0,
 ) -> nx.Graph:
-    """Assign edge lengths in the graph, optionally mapping nodes to a sphere and including edge weights.
+    """Assign edge lengths in the graph, optionally mapping nodes to a sphere.
 
     Args:
         G (nx.Graph): The input graph.
@@ -33,9 +33,8 @@ def assign_edge_lengths(
             return np.arccos(np.clip(dot_products, -1.0, 1.0))
         return np.linalg.norm(u_coords - v_coords, axis=1)
 
-    # Normalize graph coordinates and weights
+    # Normalize graph coordinates
     _normalize_graph_coordinates(G)
-    _normalize_weights(G)
 
     # Map nodes to sphere and adjust depth if required
     if compute_sphere:
@@ -110,22 +109,6 @@ def _normalize_graph_coordinates(G: nx.Graph) -> None:
         G.nodes[node]["x"], G.nodes[node]["y"] = normalized_xy[i]
 
 
-def _normalize_weights(G: nx.Graph) -> None:
-    """Normalize the weights of the edges in the graph.
-
-    Args:
-        G (nx.Graph): The input graph with weighted edges.
-    """
-    # "weight" is present for all edges - weights are 1.0 if weight was not specified by the user
-    weights = [data["weight"] for _, _, data in G.edges(data=True)]
-    if weights:  # Ensure there are weighted edges
-        min_weight = min(weights)
-        max_weight = max(weights)
-        range_weight = max_weight - min_weight if max_weight > min_weight else 1
-        for _, _, data in G.edges(data=True):
-            data["normalized_weight"] = (data["weight"] - min_weight) / range_weight
-
-
 def _create_depth(G: nx.Graph, surface_depth: float = 0.0) -> nx.Graph:
     """Adjust the 'z' attribute of each node based on the subcluster strengths and normalized surface depth.
 

{risk_network-0.0.9b45.dist-info → risk_network-0.0.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: risk-network
-Version: 0.0.9b45
+Version: 0.0.10
 Summary: A Python package for biological network analysis
 Author: Ira Horecka
 Author-email: Ira Horecka <ira89@icloud.com>
@@ -726,92 +726,73 @@ Dynamic: requires-python
 ![License](https://img.shields.io/badge/license-GPLv3-purple)
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.xxxxxxx.svg)](https://doi.org/10.5281/zenodo.xxxxxxx)
 ![Downloads](https://img.shields.io/pypi/dm/risk-network)
-![Platforms](https://img.shields.io/badge/platform-linux%20%7C%20macos%20%7C%20windows-lightgrey)
+![Tests](https://github.com/riskportal/network/actions/workflows/ci.yml/badge.svg)
 
-**RISK** (Regional Inference of Significant Kinships) is a next-generation tool designed to streamline the analysis of biological and non-biological networks. RISK enhances network analysis with its modular architecture, extensive file format support, and advanced clustering algorithms. It simplifies the creation of publication-quality figures, making it an important tool for researchers across disciplines.
+**RISK** (Regional Inference of Significant Kinships) is a next-generation tool for biological network annotation and visualization. RISK integrates community detection-based clustering, rigorous statistical enrichment analysis, and a modular framework to uncover biologically meaningful relationships and generate high-resolution visualizations. RISK supports diverse data formats and is optimized for large-scale network analysis, making it a valuable resource for researchers in systems biology and beyond.
 
 ## Documentation and Tutorial
 
-- **Documentation**: Comprehensive documentation is available [here](Documentation link).
-- **Tutorial**: An interactive Jupyter notebook tutorial can be found [here](https://github.com/riskportal/network-tutorial).
-We highly recommend new users to consult the documentation and tutorial early on to fully leverage RISK's capabilities.
+An interactive Jupyter notebook tutorial can be found [here](https://github.com/riskportal/network-tutorial). We highly recommend new users to consult the documentation and tutorial early on to fully utilize RISK's capabilities.
 
 ## Installation
 
-RISK is compatible with Python 3.8 and later versions and operates on all major operating systems. Install RISK via pip:
+RISK is compatible with Python 3.8 or later and runs on all major operating systems. To install the latest version of RISK, run:
 
 ```bash
-pip install risk-network
+pip install risk-network --upgrade
 ```
 
 ## Features
 
-- **Comprehensive Network Analysis**: Analyze biological networks such as protein–protein interaction (PPI) and gene regulatory networks, as well as non-biological networks.
-- **Advanced Clustering Algorithms**: Utilize algorithms like Louvain, Markov Clustering, Spinglass, and more to identify key functional modules.
-- **Flexible Visualization**: Generate clear, publication-quality figures with customizable node and edge attributes, including colors, shapes, sizes, and labels.
-- **Efficient Data Handling**: Optimized for large datasets, supporting multiple file formats such as JSON, CSV, TSV, Excel, Cytoscape, and GPickle.
-- **Statistical Analysis**: Integrated statistical tests, including hypergeometric, permutation, and Poisson tests, to assess the significance of enriched regions.
+- **Comprehensive Network Analysis**: Analyze biological networks (e.g., protein–protein interaction and genetic interaction networks) as well as non-biological networks.
+- **Advanced Clustering Algorithms**: Supports Louvain, Leiden, Markov Clustering, Greedy Modularity, Label Propagation, Spinglass, and Walktrap for identifying structured network regions.
+- **Flexible Visualization**: Produce customizable, high-resolution network visualizations with kernel density estimate overlays, adjustable node and edge attributes, and export options in SVG, PNG, and PDF formats.
+- **Efficient Data Handling**: Supports multiple input/output formats, including JSON, CSV, TSV, Excel, Cytoscape, and GPickle.
+- **Statistical Analysis**: Assess functional enrichment using hypergeometric, permutation, binomial, chi-squared, Poisson, and z-score tests, ensuring statistical adaptability across datasets.
 - **Cross-Domain Applicability**: Suitable for network analysis across biological and non-biological domains, including social and communication networks.
 
 ## Example Usage
 
-We applied RISK to a *Saccharomyces cerevisiae* protein–protein interaction network, revealing both established and novel functional relationships. The visualization below highlights key biological processes such as ribosomal assembly and mitochondrial organization.
+We applied RISK to a *Saccharomyces cerevisiae* protein–protein interaction network from Michaelis et al. (2023), filtering for proteins with six or more interactions to emphasize core functional relationships. RISK identified compact, statistically enriched clusters corresponding to biological processes such as ribosomal assembly and mitochondrial organization.
 
-![RISK Main Figure](https://i.imgur.com/5OP3Hqe.jpeg)
+[![Figure 1](https://i.imgur.com/lJHJrJr.jpeg)](https://i.imgur.com/lJHJrJr.jpeg)
 
-RISK successfully detected both known and novel functional clusters within the yeast interactome. Clusters related to Golgi transport and actin nucleation were clearly defined and closely located, showcasing RISK's ability to map well-characterized interactions. Additionally, RISK identified links between mRNA processing pathways and vesicle trafficking proteins, consistent with recent studies demonstrating the role of vesicles in mRNA localization and stability.
+This figure highlights RISK’s capability to detect both established and novel functional modules within the yeast interactome.
 
 ## Citation
 
-If you use RISK in your research, please cite the following:
+If you use RISK in your research, please cite:
 
-**Horecka**, *et al.*, "RISK: a next-generation tool for biological network annotation and visualization", **[Journal Name]**, 2024. DOI: [10.1234/zenodo.xxxxxxx](https://doi.org/10.1234/zenodo.xxxxxxx)
+**Horecka et al.**, "RISK: a next-generation tool for biological network annotation and visualization", **Bioinformatics**, 2025. DOI: [10.1234/zenodo.xxxxxxx](https://doi.org/10.1234/zenodo.xxxxxxx)
 
 ## Software Architecture and Implementation
 
-RISK features a streamlined, modular architecture designed to meet diverse research needs. Each module focuses on a specific task—such as network input/output, statistical analysis, or visualization—ensuring ease of adaptation and extension. This design enhances flexibility and reduces development overhead for users integrating RISK into their workflows.
+RISK features a streamlined, modular architecture designed to meet diverse research needs. It includes dedicated modules for:
 
-### Supported Data Formats
-
-- **Input/Output**: JSON, CSV, TSV, Excel, Cytoscape, GPickle.
-- **Visualization Outputs**: SVG, PNG, PDF.
-
-### Clustering Algorithms
-
-- **Available Algorithms**:
-  - Greedy Modularity
-  - Label Propagation
-  - Louvain
-  - Markov Clustering
-  - Spinglass
-  - Walktrap
-- **Distance Metrics**: Supports both spherical and Euclidean distance metrics.
-
-### Statistical Tests
-
-- **Hypergeometric Test**
-- **Permutation Test** (single- or multi-process modes)
-- **Poisson Test**
+- **Data I/O**: Supports JSON, CSV, TSV, Excel, Cytoscape, and GPickle formats.
+- **Clustering**: Supports multiple clustering methods, including Louvain, Leiden, Markov Clustering, Greedy Modularity, Label Propagation, Spinglass, and Walktrap. Provides flexible distance metrics tailored to network structure.
+- **Statistical Analysis**: Provides a suite of tests for overrepresentation analysis of annotations.
+- **Visualization**: Offers customizable, high-resolution output in multiple formats, including SVG, PNG, and PDF.
 
 ## Performance and Efficiency
 
-In benchmarking tests using the yeast interactome network, RISK demonstrated substantial improvements over previous tools in both computational performance and memory efficiency. RISK processed the dataset approximately **3.25 times faster**, reducing CPU time by **69%**, and required **25% less peak memory usage**, underscoring its efficient utilization of computational resources.
+Benchmarking results demonstrate that RISK efficiently scales to networks exceeding hundreds of thousands of edges, maintaining low execution times and optimal memory usage across statistical tests.
 
 ## Contributing
 
-We welcome contributions from the community. Please use the following resources:
+We welcome contributions from the community:
 
-- [Issues Tracker](https://github.com/irahorecka/risk/issues)
-- [Source Code](https://github.com/irahorecka/risk/tree/main/risk)
+- [Issues Tracker](https://github.com/riskportal/network/issues)
+- [Source Code](https://github.com/riskportal/network/tree/main/risk)
 
 ## Support
 
-If you encounter issues or have suggestions for new features, please use the [Issues Tracker](https://github.com/irahorecka/risk/issues) on GitHub.
+If you encounter issues or have suggestions for new features, please use the [Issues Tracker](https://github.com/riskportal/network/issues) on GitHub.
 
 ## License
 
-RISK is freely available as open-source software under the [GNU General Public License v3.0](https://www.gnu.org/licenses/gpl-3.0.en.html).
+RISK is open source under the [GNU General Public License v3.0](https://www.gnu.org/licenses/gpl-3.0.en.html).
 
 ---
 
-**Note**: For detailed documentation and to access the interactive tutorial, please visit the links provided in the [Documentation and Tutorial](#documentation-and-tutorial) section.
+**Note**: For detailed documentation and to access the interactive tutorial, please visit the links above.

{risk_network-0.0.9b45.dist-info → risk_network-0.0.10.dist-info}/RECORD

@@ -1,7 +1,7 @@
-risk/__init__.py,sha256=jIlf9Do3EstfEM4dHHrgF3VRwVSyPYhBW38kms1VToc,127
+risk/__init__.py,sha256=256SpbomSJ88a12A8DmDUsPOxlkwJ7cqbu7E4FHrcw4,120
 risk/risk.py,sha256=s827_lRknFseOP9O4zW8sP-IcCd2EzrpV_tnVY_tz5s,1104
 risk/annotations/__init__.py,sha256=parsbcux1U4urpUqh9AdzbDWuLj9HlMidycMPkpSQFo,179
-risk/annotations/annotations.py,sha256=5X2R8RFxgK6kgSoj05UdCPcpkRRPOaHjGwnIrjeD5Ww,16299
+risk/annotations/annotations.py,sha256=mDgW5X4wck7oQqcMOw1T0XNkFZnSm1vx3MKIUX-FABI,16505
 risk/annotations/io.py,sha256=z1AJySsU-KL_IYuHa7j3nvuczmOHgK3WfaQ4TRunvrA,10499
 risk/log/__init__.py,sha256=7LxDysQu7doi0LAvlY2YbjN6iJH0fNknqy8lSLgeljo,217
 risk/log/console.py,sha256=PgjyEvyhYLUSHXPUKEqOmxsDsfrjPICIgqo_cAHq0N8,4575
@@ -9,10 +9,10 @@ risk/log/parameters.py,sha256=VtwfMzLU1xI4yji3-Ch5vHjH-KdwTfwaEMmi7hFQTs0,5716
 risk/neighborhoods/__init__.py,sha256=Q74HwTH7okI-vaskJPy2bYwb5sNjGASTzJ6m8V8arCU,234
 risk/neighborhoods/api.py,sha256=ywngw2TQVV27gYlWDXcs8-qnmeepnvb-W9ov6J6VEPM,23341
 risk/neighborhoods/community.py,sha256=5Q_-VAJC-5SY5EUsB8gIlemeDoAL85uLjyl16pItHiQ,16699
-risk/neighborhoods/domains.py,sha256=4K1tbiia3_TQKUrGdfmKVdYlRD2EEzPnMCKRv6IGxu4,14448
+risk/neighborhoods/domains.py,sha256=INWgpAy4cLsfBb5exkh3MEAIgRreNH6d7UlKjVijHX4,14678
 risk/neighborhoods/neighborhoods.py,sha256=l9FhADB1C-OxM8E9QXOcA4osUDgA1vs4ud-OCGKKybc,21457
 risk/network/__init__.py,sha256=oVi3FA1XXKD84014Cykq-9bpX4_s0F3aAUfNOU-07Qw,73
-risk/network/geometry.py,sha256=eVtGHMgBf9fEqQZUFdHWjw-zFYYpfUONoHFSAxoRkug,6219
+risk/network/geometry.py,sha256=c9XweJ0-DImZPU2YAJTJAwVYnW_0OGlWClyvJpeIZE4,5476
 risk/network/io.py,sha256=RCH4nQdgYDXcNwMfpSz7qEmPO0pJ1p9fL0rNQptsQrc,21673
 risk/network/graph/__init__.py,sha256=ziGJew3yhtqvrb9LUuneDu_LwW2Wa9vd4UuhoL5l1CA,91
 risk/network/graph/api.py,sha256=xS_rNDvZPdwIar2E9x9BKMeR0DcYuwcHiUpc_EcJ4-o,8536
@@ -33,8 +33,8 @@ risk/stats/stat_tests.py,sha256=tj0ri9w89_1fsjGLuafTWpfBEwZXpSLn7Ej2aAQ5lxk,1177
 risk/stats/permutation/__init__.py,sha256=OLmYLm2uj96hPsSaUs0vUqFYw6Thwch_aHtpL7L0ZFw,127
 risk/stats/permutation/permutation.py,sha256=BWjgdBpLVcHvmwHy0bmD4aJFccxifNBSrrCBPppyKf4,10569
 risk/stats/permutation/test_functions.py,sha256=KlECWTz1EZ6EPF_OAgHb0uznaIhopiVYb_AKUKuC4no,3120
-risk_network-0.0.9b45.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
-risk_network-0.0.9b45.dist-info/METADATA,sha256=2KudsInDITKJe7RnMfguwO6x2uMVJufM1TBvB92nxzA,47627
-risk_network-0.0.9b45.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-risk_network-0.0.9b45.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
-risk_network-0.0.9b45.dist-info/RECORD,,
+risk_network-0.0.10.dist-info/LICENSE,sha256=jOtLnuWt7d5Hsx6XXB2QxzrSe2sWWh3NgMfFRetluQM,35147
+risk_network-0.0.10.dist-info/METADATA,sha256=MbLHMXmOv8iTUZLm8S4EKj2uDB419weRpRvWIyBKSCM,46966
+risk_network-0.0.10.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+risk_network-0.0.10.dist-info/top_level.txt,sha256=NX7C2PFKTvC1JhVKv14DFlFAIFnKc6Lpsu1ZfxvQwVw,5
+risk_network-0.0.10.dist-info/RECORD,,

{risk_network-0.0.9b45.dist-info → risk_network-0.0.10.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.0)
+Generator: setuptools (76.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any