risk-network 0.0.12b0__tar.gz → 0.0.12b2__tar.gz

risk_network-0.0.12b2/PKG-INFO

@@ -0,0 +1,122 @@
+Metadata-Version: 2.4
+Name: risk-network
+Version: 0.0.12b2
+Summary: A Python package for biological network analysis
+Author-email: Ira Horecka <ira89@icloud.com>
+License: GPL-3.0-or-later
+Project-URL: Homepage, https://github.com/riskportal/network
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Scientific/Engineering :: Visualization
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Development Status :: 4 - Beta
+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
+Requires-Dist: nltk
+Requires-Dist: numpy
+Requires-Dist: openpyxl
+Requires-Dist: pandas
+Requires-Dist: python-igraph
+Requires-Dist: python-louvain
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: statsmodels
+Requires-Dist: threadpoolctl
+Requires-Dist: tqdm
+Dynamic: license-file
+
+# RISK Network
+
+<p align="center">
+  <img src="https://i.imgur.com/8TleEJs.png" width="50%" />
+</p>
+
+<br>
+
+![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.xxxxxxx.svg)](https://doi.org/10.5281/zenodo.xxxxxxx)
+![Downloads](https://img.shields.io/pypi/dm/risk-network)
+![Tests](https://github.com/riskportal/network/actions/workflows/ci.yml/badge.svg)
+
+**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
+
+Full documentation is available at:
+
+- **Docs:** [https://riskportal.github.io/network-tutorial](https://riskportal.github.io/network-tutorial)  
+- **Tutorial Jupyter Notebook Repository:** [https://github.com/riskportal/network-tutorial](https://github.com/riskportal/network-tutorial)
+
+## Installation
+
+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 --upgrade
+```
+
+## Features
+
+- **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 (network-aware), 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 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.
+
+[![Figure 1](https://i.imgur.com/lJHJrJr.jpeg)](https://i.imgur.com/lJHJrJr.jpeg)
+
+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:
+
+**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. RISK’s modular design enables users to run individual components—such as clustering, statistical testing, or visualization—independently or in combination, depending on the analysis workflow. It includes dedicated modules for:
+
+- **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.
+- **Configuration Management**: Centralized parameters in risk.params ensure reproducibility and easy tuning for large-scale analyses.
+
+## Performance and Efficiency
+
+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:
+
+- [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/riskportal/network/issues) on GitHub.
+
+## License
+
+RISK is open source under the [GNU General Public License v3.0](https://www.gnu.org/licenses/gpl-3.0.en.html).

{risk_network-0.0.12b0 → risk_network-0.0.12b2}/pyproject.toml

@@ -1,20 +1,19 @@
 [build-system]
-requires = ["setuptools >= 77.0.3", "numpy"]
+requires = ["setuptools", "numpy"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "risk-network"
-dynamic = ["version"]  # Indicates that version is determined dynamically
+dynamic = ["version"]
 description = "A Python package for biological network analysis"
 authors = [
     { name = "Ira Horecka", email = "ira89@icloud.com" },
 ]
 readme = "README.md"
-license = { file = "LICENSE" }
+requires-python = ">=3.8"
 classifiers = [
     "Intended Audience :: Developers",
     "Intended Audience :: Science/Research",
-    "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)",
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3.8",
@@ -43,11 +42,18 @@ dependencies = [
     "threadpoolctl",
     "tqdm",
 ]
-requires-python = ">=3.8"
+
+[project.license]
+text = "GPL-3.0-or-later"
+
+[project.urls]
+"Homepage" = "https://github.com/riskportal/network"
 
 [tool.setuptools]
 package-dir = {"" = "src"}
-packages = ["risk"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
 
 [tool.setuptools.dynamic]
 version = { attr = "risk.__version__" }

{risk_network-0.0.12b0 → risk_network-0.0.12b2}/src/risk/__init__.py

@@ -7,4 +7,4 @@ RISK: Regional Inference of Significant Kinships
 
 from risk.risk import RISK
 
-__version__ = "0.0.12-beta.0"
+__version__ = "0.0.12-beta.2"

risk_network-0.0.12b2/src/risk/annotations/__init__.py

@@ -0,0 +1,10 @@
+"""
+risk/annotations
+~~~~~~~~~~~~~~~~
+"""
+
+from risk.annotations.annotations import (
+    define_top_annotations,
+    get_weighted_description,
+)
+from risk.annotations.io import AnnotationsIO

risk_network-0.0.12b2/src/risk/annotations/annotations.py

@@ -0,0 +1,354 @@
+"""
+risk/annotations/annotations
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+"""
+
+import re
+from collections import Counter
+from itertools import compress
+from typing import Any, Dict, List, Set
+
+import networkx as nx
+import numpy as np
+import pandas as pd
+from nltk.tokenize import word_tokenize
+from scipy.sparse import coo_matrix
+
+from risk.annotations.nltk_setup import setup_nltk_resources
+from risk.log import logger
+
+
+def initialize_nltk():
+    """Initialize all required NLTK components."""
+    setup_nltk_resources()
+
+    # After resources are available, initialize the components
+    from nltk.corpus import stopwords
+    from nltk.stem import WordNetLemmatizer
+
+    global STOP_WORDS, LEMMATIZER
+    STOP_WORDS = set(stopwords.words("english"))
+    LEMMATIZER = WordNetLemmatizer()
+
+
+# Initialize NLTK components
+initialize_nltk()
+
+
+def load_annotations(
+    network: nx.Graph, annotations_input: Dict[str, Any], min_nodes_per_term: int = 2
+) -> Dict[str, Any]:
+    """Convert annotations input to a sparse matrix and reindex based on the network's node labels.
+
+    Args:
+        network (nx.Graph): The network graph.
+        annotations_input (Dict[str, Any]): A dictionary with annotations.
+        min_nodes_per_term (int, optional): The minimum number of network nodes required for each annotation
+            term to be included. Defaults to 2.
+
+    Returns:
+        Dict[str, Any]: A dictionary containing ordered nodes, ordered annotations, and the sparse binary annotations
+            matrix.
+
+    Raises:
+        ValueError: If no annotations are found for the nodes in the network.
+        ValueError: If no annotations have at least min_nodes_per_term nodes in the network.
+    """
+    # Step 1: Map nodes and annotations to indices
+    node_label_order = [attr["label"] for _, attr in network.nodes(data=True) if "label" in attr]
+    node_to_idx = {node: i for i, node in enumerate(node_label_order)}
+    annotation_to_idx = {annotation: i for i, annotation in enumerate(annotations_input)}
+    # Step 2: Construct a sparse binary matrix directly
+    row = []
+    col = []
+    data = []
+    for annotation, nodes in annotations_input.items():
+        for node in nodes:
+            if node in node_to_idx and annotation in annotation_to_idx:
+                row.append(node_to_idx[node])
+                col.append(annotation_to_idx[annotation])
+                data.append(1)
+
+    # Create a sparse binary matrix
+    num_nodes = len(node_to_idx)
+    num_annotations = len(annotation_to_idx)
+    annotations_pivot = coo_matrix((data, (row, col)), shape=(num_nodes, num_annotations)).tocsr()
+    # Step 3: Filter out annotations with fewer than min_nodes_per_term occurrences
+    valid_annotations = annotations_pivot.sum(axis=0).A1 >= min_nodes_per_term
+    annotations_pivot = annotations_pivot[:, valid_annotations]
+    # Step 4: Raise errors for empty matrices
+    if annotations_pivot.nnz == 0:
+        raise ValueError("No terms found in the annotation file for the nodes in the network.")
+
+    num_remaining_annotations = annotations_pivot.shape[1]
+    if num_remaining_annotations == 0:
+        raise ValueError(
+            f"No annotation terms found with at least {min_nodes_per_term} nodes in the network."
+        )
+
+    # Step 5: Extract ordered nodes and annotations
+    ordered_nodes = tuple(node_label_order)
+    ordered_annotations = tuple(
+        annotation for annotation, is_valid in zip(annotation_to_idx, valid_annotations) if is_valid
+    )
+
+    # Log the filtering details
+    logger.info(f"Minimum number of nodes per annotation term: {min_nodes_per_term}")
+    logger.info(f"Number of input annotation terms: {num_annotations}")
+    logger.info(f"Number of remaining annotation terms: {num_remaining_annotations}")
+
+    return {
+        "ordered_nodes": ordered_nodes,
+        "ordered_annotations": ordered_annotations,
+        "matrix": annotations_pivot,
+    }
+
+
+def define_top_annotations(
+    network: nx.Graph,
+    ordered_annotation_labels: List[str],
+    neighborhood_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.
+
+    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.
+        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.
+        max_cluster_size (int, optional): Maximum cluster size. Defaults to 1000.
+
+    Returns:
+        pd.DataFrame: DataFrame with top annotations and their properties.
+    """
+    # 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
+    annotations_significance_matrix = pd.DataFrame(
+        {
+            "id": range(len(ordered_annotation_labels)),
+            "full_terms": ordered_annotation_labels,
+            "significant_neighborhood_significance_sums": neighborhood_significance_sums,
+            "significant_significance_score": significant_significance_scores,
+        }
+    )
+    annotations_significance_matrix["significant_annotations"] = False
+    # Apply size constraints to identify potential significant annotations
+    annotations_significance_matrix.loc[
+        (
+            annotations_significance_matrix["significant_neighborhood_significance_sums"]
+            >= min_cluster_size
+        )
+        & (
+            annotations_significance_matrix["significant_neighborhood_significance_sums"]
+            <= max_cluster_size
+        ),
+        "significant_annotations",
+    ] = True
+    # Initialize columns for connected components analysis
+    annotations_significance_matrix["num_connected_components"] = 0
+    annotations_significance_matrix["size_connected_components"] = None
+    annotations_significance_matrix["size_connected_components"] = annotations_significance_matrix[
+        "size_connected_components"
+    ].astype(object)
+    annotations_significance_matrix["num_large_connected_components"] = 0
+
+    for attribute in annotations_significance_matrix.index.values[
+        annotations_significance_matrix["significant_annotations"]
+    ]:
+        # Identify significant neighborhoods based on the binary significance matrix
+        significant_neighborhoods = list(
+            compress(list(network), significant_binary_significance_matrix[:, attribute])
+        )
+        significant_network = nx.subgraph(network, significant_neighborhoods)
+        # Analyze connected components within the significant subnetwork
+        connected_components = sorted(
+            nx.connected_components(significant_network), key=len, reverse=True
+        )
+        size_connected_components = np.array([len(c) for c in connected_components])
+
+        # Filter the size of connected components by min_cluster_size and max_cluster_size
+        filtered_size_connected_components = size_connected_components[
+            (size_connected_components >= min_cluster_size)
+            & (size_connected_components <= max_cluster_size)
+        ]
+        # Calculate the number of connected components and large connected components
+        num_connected_components = len(connected_components)
+        num_large_connected_components = len(filtered_size_connected_components)
+
+        # Assign the number of connected components
+        annotations_significance_matrix.loc[attribute, "num_connected_components"] = (
+            num_connected_components
+        )
+        # Filter out attributes with more than one connected component
+        annotations_significance_matrix.loc[
+            annotations_significance_matrix["num_connected_components"] > 1,
+            "significant_annotations",
+        ] = False
+        # Assign the number of large connected components
+        annotations_significance_matrix.loc[attribute, "num_large_connected_components"] = (
+            num_large_connected_components
+        )
+        # Assign the size of connected components, ensuring it is always a list
+        annotations_significance_matrix.at[attribute, "size_connected_components"] = (
+            filtered_size_connected_components.tolist()
+        )
+
+    return annotations_significance_matrix
+
+
+def get_weighted_description(words_column: pd.Series, scores_column: pd.Series) -> str:
+    """Generate a weighted description from words and their corresponding scores,
+    using improved weighting logic with normalization, lemmatization, and aggregation.
+
+    Args:
+        words_column (pd.Series): A pandas Series containing strings (phrases) to process.
+        scores_column (pd.Series): A pandas Series containing significance scores to weigh the terms.
+
+    Returns:
+        str: A coherent description formed from the most frequent and significant words.
+    """
+    # Normalize significance scores to [0,1]. If all scores are identical, use 1.
+    if scores_column.max() == scores_column.min():
+        normalized_scores = pd.Series([1] * len(scores_column), index=scores_column.index)
+    else:
+        normalized_scores = (scores_column - scores_column.min()) / (
+            scores_column.max() - scores_column.min()
+        )
+
+    # Accumulate weighted counts for each token (after cleaning and lemmatization)
+    weighted_counts = {}
+    for phrase, score in zip(words_column, normalized_scores):
+        # Tokenize the phrase
+        tokens = word_tokenize(str(phrase))
+        # Determine the weight (scale factor; here multiplying normalized score by 10)
+        weight = max(1, int((0 if pd.isna(score) else score) * 10))
+        for token in tokens:
+            # Clean token: lowercase and remove extraneous punctuation (but preserve intra-word hyphens)
+            token_clean = re.sub(r"[^\w\-]", "", token).strip()
+            if not token_clean:
+                continue
+            # Skip tokens that are pure numbers
+            if token_clean.isdigit():
+                continue
+            # Skip stopwords
+            if token_clean in STOP_WORDS:
+                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
+
+    # 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.
+    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"
+
+    # Simplify the token list to remove near-duplicates based on the Jaccard index.
+    simplified_words = _simplify_word_list(combined_tokens)
+    # Generate a coherent description from the simplified words.
+    description = _generate_coherent_description(simplified_words)
+
+    return description
+
+
+def _simplify_word_list(words: List[str], threshold: float = 0.80) -> List[str]:
+    """Filter out words that are too similar based on the Jaccard index,
+    keeping the word with the higher aggregated count.
+
+    Args:
+        words (List[str]): The list of tokens to be filtered.
+        threshold (float, optional): The similarity threshold for the Jaccard index. Defaults to 0.80.
+
+    Returns:
+        List[str]: A list of filtered words, where similar words are reduced to the most frequent one.
+    """
+    # Count the occurrences (which reflect the weighted importance)
+    word_counts = Counter(words)
+    filtered_words = []
+    used_words = set()
+
+    # Iterate through words sorted by descending weighted frequency
+    for word in sorted(word_counts, key=lambda w: word_counts[w], reverse=True):
+        if word in used_words:
+            continue
+
+        word_set = set(word)
+        # Find similar words (including the current word) based on the Jaccard index
+        similar_words = [
+            other_word
+            for other_word in word_counts
+            if _calculate_jaccard_index(word_set, set(other_word)) >= threshold
+        ]
+        # Choose the word with the highest weighted count among the similar group
+        similar_words.sort(key=lambda w: word_counts[w], reverse=True)
+        best_word = similar_words[0]
+        filtered_words.append(best_word)
+        used_words.update(similar_words)
+
+    # Preserve the original order (by frequency) from the filtered set
+    final_words = [word for word in words if word in filtered_words]
+
+    return final_words
+
+
+def _calculate_jaccard_index(set1: Set[Any], set2: Set[Any]) -> float:
+    """Calculate the Jaccard index between two sets.
+
+    Args:
+        set1 (Set[Any]): The first set.
+        set2 (Set[Any]): The second set.
+
+    Returns:
+        float: The Jaccard index (intersection over union). Returns 0 if the union is empty.
+    """
+    intersection = len(set1.intersection(set2))
+    union = len(set1.union(set2))
+    return intersection / union if union else 0
+
+
+def _generate_coherent_description(words: List[str]) -> str:
+    """Generate a coherent description from a list of words.
+
+    If there is only one unique entry, return it directly.
+    Otherwise, order the words by frequency and join them into a single string.
+
+    Args:
+        words (List[str]): A list of tokens.
+
+    Returns:
+        str: A coherent, space-separated description.
+    """
+    if not words:
+        return "N/A"
+
+    # If there is only one unique word, return it directly
+    unique_words = set(words)
+    if len(unique_words) == 1:
+        return list(unique_words)[0]
+
+    # Count weighted occurrences and sort in descending order.
+    word_counts = Counter(words)
+    most_common_words = [word for word, _ in word_counts.most_common()]
+    description = " ".join(most_common_words)
+
+    return description