plasmidhub 1.0.0__py3-none-any.whl

plasmidhub/plot.py

@@ -0,0 +1,169 @@
+import json
+import networkx as nx
+import matplotlib.pyplot as plt
+import matplotlib.patches as mpatches
+import os
+import logging
+
+logger = logging.getLogger(__name__)
+
+def load_network_from_json(json_file):
+    """Load a network graph from a JSON file."""
+    with open(json_file, 'r') as f:
+        data = json.load(f)
+    return nx.cytoscape_graph(data)
+
+def visualize_network_basic(G, k, output_path_no_ext):
+    """Visualize the network with basic grey nodes and edges"""
+
+    min_weight = 5
+    max_weight = 100
+    min_width = 0.2  # reduced thickness
+    max_width = 2.0  # reduced thickness
+
+    edge_weights = nx.get_edge_attributes(G, 'weight')
+    for edge in G.edges():
+        if edge not in edge_weights:
+            edge_weights[edge] = min_weight
+
+    edge_widths = []
+    for edge in G.edges():
+        weight = edge_weights.get(edge, min_weight)
+        weight_clipped = max(min_weight, min(weight, max_weight))
+        scaled_width = min_width + (weight_clipped - min_weight) / (max_weight - min_weight) * (max_width - min_width)
+        edge_widths.append(scaled_width)
+
+    pos = nx.spring_layout(G, k=k, seed=69420, iterations=100)
+
+    # With labels
+    fig, ax = plt.subplots(figsize=(25, 25))
+    nx.draw_networkx_nodes(G, pos, node_color='grey', node_size=900, node_shape='o',
+                           linewidths=1, edgecolors='black', alpha=0.65, ax=ax)
+    nx.draw_networkx_edges(G, pos, width=edge_widths, edge_color='grey', alpha=0.7, ax=ax)
+    nx.draw_networkx_labels(G, pos, font_size=10, font_weight='bold', ax=ax)
+    plt.axis('off')
+    plt.tight_layout()
+    plt.savefig(output_path_no_ext + ".pdf", format="pdf")
+    plt.savefig(output_path_no_ext + ".svg", format="svg")
+    plt.close()
+
+    # Without labels
+    fig, ax = plt.subplots(figsize=(25, 25))
+    nx.draw_networkx_nodes(G, pos, node_color='grey', node_size=900, node_shape='o',
+                           linewidths=1, edgecolors='black', alpha=0.65, ax=ax)
+    nx.draw_networkx_edges(G, pos, width=edge_widths, edge_color='grey', alpha=0.7, ax=ax)
+    plt.axis('off')
+    plt.tight_layout()
+    plt.savefig(output_path_no_ext + "_nolabels.pdf", format="pdf")
+    plt.savefig(output_path_no_ext + "_nolabels.svg", format="svg")
+    plt.close()
+
+def visualize_network_colored_by_cluster(G, k, output_path_no_ext, cluster_mapping_file, cluster_color_file):
+    """Visualize the network with node colors based on cluster assignment"""
+
+    # Check if cluster_list.txt contains only the header
+    cluster_list_file = os.path.join(os.path.dirname(cluster_mapping_file), "cluster_list.txt")
+    if os.path.exists(cluster_list_file):
+        with open(cluster_list_file) as f:
+            lines = f.readlines()
+            if len(lines) <= 1:
+                logger.warning("No clusters detected with the given parameters!")
+
+    # Load plasmid-cluster mappings
+    cluster_map = {}
+    with open(cluster_mapping_file) as f:
+        for line in f:
+            parts = line.strip().split('\t')
+            if len(parts) == 2:
+                plasmid, cluster = parts
+                cluster_map[plasmid] = cluster
+
+    # Load cluster-color mappings
+    color_map = {}
+    with open(cluster_color_file) as f:
+        for line in f:
+            parts = line.strip().split('\t')
+            if len(parts) == 2:
+                cluster, color = parts
+                color_map[cluster] = color
+
+    # Assign colors to nodes
+    node_colors = []
+    for node in G.nodes():
+        cluster = cluster_map.get(node)
+        color = color_map.get(cluster, "#cccccc")  # default light grey for unclustered
+        node_colors.append(color)
+
+    # Edge weight scaling
+    min_weight = 5
+    max_weight = 100
+    min_width = 0.2
+    max_width = 2.0
+    edge_weights = nx.get_edge_attributes(G, 'weight')
+    edge_widths = []
+    for edge in G.edges():
+        weight = edge_weights.get(edge, min_weight)
+        weight_clipped = max(min_weight, min(weight, max_weight))
+        scaled_width = min_width + (weight_clipped - min_weight) / (max_weight - min_weight) * (max_width - min_width)
+        edge_widths.append(scaled_width)
+
+    pos = nx.spring_layout(G, k=k, seed=69420, iterations=100)
+
+    # --- Create legend handles ---
+    legend_handles = [
+        mpatches.Patch(color=color, label=cluster)
+        for cluster, color in sorted(color_map.items())
+    ]
+
+    # With labels
+    fig, ax = plt.subplots(figsize=(25, 25))
+    nx.draw_networkx_nodes(G, pos, node_color=node_colors, node_size=900, node_shape='o',
+                           linewidths=1, edgecolors='black', alpha=0.9, ax=ax)
+    nx.draw_networkx_edges(G, pos, width=edge_widths, edge_color='grey', alpha=0.7, ax=ax)
+    nx.draw_networkx_labels(G, pos, font_size=10, font_weight='bold', ax=ax)
+    plt.axis('off')
+
+    # Add legend
+    legend = ax.legend(handles=legend_handles, loc='upper right', fontsize=16, title="Clusters", title_fontsize=18,
+                       bbox_to_anchor=(1.02, 1.0))
+    plt.tight_layout()
+    plt.savefig(output_path_no_ext + "_cluster_colored.pdf", format="pdf")
+    plt.savefig(output_path_no_ext + "_cluster_colored.svg", format="svg")
+    plt.close()
+
+    # Without labels
+    fig, ax = plt.subplots(figsize=(25, 25))
+    nx.draw_networkx_nodes(G, pos, node_color=node_colors, node_size=900, node_shape='o',
+                           linewidths=1, edgecolors='black', alpha=0.9, ax=ax)
+    nx.draw_networkx_edges(G, pos, width=edge_widths, edge_color='grey', alpha=0.7, ax=ax)
+    plt.axis('off')
+
+    # Add legend
+    legend = ax.legend(handles=legend_handles, loc='upper right', fontsize=16, title="Clusters", title_fontsize=18,
+                       bbox_to_anchor=(1.02, 1.0))
+    plt.tight_layout()
+    plt.savefig(output_path_no_ext + "_cluster_colored_nolabels.pdf", format="pdf")
+    plt.savefig(output_path_no_ext + "_cluster_colored_nolabels.svg", format="svg")
+    plt.close()
+
+
+def run_visualizations(results_dir, k_min, k_max):
+    """Main function to load graph and generate visualizations over k range."""
+    json_file = os.path.join(results_dir, "network.json")
+    G = load_network_from_json(json_file)
+
+    # Add cluster-colored visualizations if cluster color file exists
+    cluster_mapping_file = os.path.join(results_dir, "plasmid_cluster_mapping.txt")
+    cluster_color_file = os.path.join(results_dir, "cluster_colours.txt")
+    if os.path.exists(cluster_mapping_file) and os.path.exists(cluster_color_file):
+        logger.info("Generating cluster-colored visualizations...")
+        for k in range(k_min, k_max):
+            filename_base = os.path.join(results_dir, f"network_k_{k}")
+            visualize_network_colored_by_cluster(G, k, filename_base, cluster_mapping_file, cluster_color_file)
+    else:
+        logger.info("Cluster mapping or color file not found. Skipping cluster-colored plots.")
+
+
+    for k in range(k_min, k_max):
+        filename_base = os.path.join(results_dir, f"network_k_{k}")
+        visualize_network_basic(G, k, filename_base)

plasmidhub/plot_only.py

@@ -0,0 +1,153 @@
+import argparse
+import os
+import json
+import numpy as np
+import networkx as nx
+import matplotlib.pyplot as plt
+import matplotlib.patches as mpatches
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Plot-only mode in plasmidnet for custom plots")
+    parser.add_argument("--results_dir", required=True, help="Path to directory")
+    parser.add_argument("--plot_k", nargs=2, type=float, metavar=('MIN_K', 'MAX_K'),
+                        required=True, help="Specify minimum and maximum k values for plotting")
+    parser.add_argument("--min_edge_width", type=float, default=0.2)
+    parser.add_argument("--max_edge_width", type=float, default=2.0)
+    parser.add_argument("--node_size", type=int, default=900)
+    parser.add_argument("--node_color", type=str, default="#cccccc")
+    parser.add_argument("--node_shape", type=str, default="o")
+    parser.add_argument("--figsize", nargs=2, type=float, default=[25, 25])
+    parser.add_argument("--iterations", type=int, default=100)
+    return parser.parse_args()
+
+def load_network_from_json(json_file):
+    with open(json_file, 'r') as f:
+        data = json.load(f)
+    return nx.cytoscape_graph(data)
+
+def scale_edge_weights(G, min_width, max_width):
+    edge_weights = nx.get_edge_attributes(G, 'weight')
+    min_weight = 5
+    max_weight = 100
+    scaled = []
+    for edge in G.edges():
+        weight = edge_weights.get(edge, min_weight)
+        clipped = max(min_weight, min(weight, max_weight))
+        scaled_width = min_width + ((clipped - min_weight) / (max_weight - min_weight)) * (max_width - min_width)
+        scaled.append(scaled_width)
+    return scaled
+
+def visualize_network(G, k, output_path, args):
+    pos = nx.spring_layout(G, k=k, seed=69420, iterations=args.iterations)
+    edge_widths = scale_edge_weights(G, args.min_edge_width, args.max_edge_width)
+
+    # With labels
+    fig, ax = plt.subplots(figsize=tuple(args.figsize))
+    nx.draw_networkx_nodes(G, pos, node_color=args.node_color, node_size=args.node_size,
+                           node_shape=args.node_shape, linewidths=1, edgecolors='black', alpha=0.85, ax=ax)
+    nx.draw_networkx_edges(G, pos, width=edge_widths, edge_color='grey', alpha=0.7, ax=ax)
+    nx.draw_networkx_labels(G, pos, font_size=10, font_weight='bold', ax=ax)
+    plt.axis('off')
+    plt.tight_layout()
+    plt.savefig(output_path + ".pdf")
+    plt.close()
+
+    # Without labels
+    fig, ax = plt.subplots(figsize=tuple(args.figsize))
+    nx.draw_networkx_nodes(G, pos, node_color=args.node_color, node_size=args.node_size,
+                           node_shape=args.node_shape, linewidths=1, edgecolors='black', alpha=0.85, ax=ax)
+    nx.draw_networkx_edges(G, pos, width=edge_widths, edge_color='grey', alpha=0.7, ax=ax)
+    plt.axis('off')
+    plt.tight_layout()
+    plt.savefig(output_path + "_nolabels.pdf")
+    plt.close()
+
+def visualize_network_colored_by_cluster(G, k, output_path_no_ext, cluster_mapping_file, cluster_color_file, args):
+    cluster_map = {}
+    with open(cluster_mapping_file) as f:
+        for line in f:
+            parts = line.strip().split('\t')
+            if len(parts) == 2:
+                plasmid, cluster = parts
+                cluster_map[plasmid] = cluster
+
+    color_map = {}
+    with open(cluster_color_file) as f:
+        for line in f:
+            parts = line.strip().split('\t')
+            if len(parts) == 2:
+                cluster, color = parts
+                color_map[cluster] = color
+
+    node_colors = []
+    for node in G.nodes():
+        cluster = cluster_map.get(node)
+        color = color_map.get(cluster, args.node_color)
+        node_colors.append(color)
+
+    edge_widths = scale_edge_weights(G, args.min_edge_width, args.max_edge_width)
+    pos = nx.spring_layout(G, k=k, seed=69420, iterations=args.iterations)
+
+    legend_handles = [
+        mpatches.Patch(color=color, label=cluster)
+        for cluster, color in sorted(color_map.items())
+    ]
+
+    # With labels
+    fig, ax = plt.subplots(figsize=tuple(args.figsize))
+    nx.draw_networkx_nodes(G, pos, node_color=node_colors, node_size=args.node_size, node_shape=args.node_shape,
+                           linewidths=1, edgecolors='black', alpha=0.9, ax=ax)
+    nx.draw_networkx_edges(G, pos, width=edge_widths, edge_color='grey', alpha=0.7, ax=ax)
+    nx.draw_networkx_labels(G, pos, font_size=10, font_weight='bold', ax=ax)
+    ax.legend(handles=legend_handles, loc='upper right', fontsize=16, title="Clusters", title_fontsize=18,
+              bbox_to_anchor=(1.02, 1.0))
+    plt.axis('off')
+    plt.tight_layout()
+    plt.savefig(output_path_no_ext + "_cluster_colored.pdf")
+    plt.savefig(output_path_no_ext + "_cluster_colored.svg")
+    plt.close()
+
+    # Without labels
+    fig, ax = plt.subplots(figsize=tuple(args.figsize))
+    nx.draw_networkx_nodes(G, pos, node_color=node_colors, node_size=args.node_size, node_shape=args.node_shape,
+                           linewidths=1, edgecolors='black', alpha=0.9, ax=ax)
+    nx.draw_networkx_edges(G, pos, width=edge_widths, edge_color='grey', alpha=0.7, ax=ax)
+    ax.legend(handles=legend_handles, loc='upper right', fontsize=16, title="Clusters", title_fontsize=18,
+              bbox_to_anchor=(1.02, 1.0))
+    plt.axis('off')
+    plt.tight_layout()
+    plt.savefig(output_path_no_ext + "_cluster_colored_nolabels.pdf")
+    plt.savefig(output_path_no_ext + "_cluster_colored_nolabels.svg")
+    plt.close()
+
+def run():
+    args = parse_args()
+
+    print("Generating network visualizations...")
+
+    json_path = os.path.join(args.results_dir, "network.json")
+    if not os.path.exists(json_path):
+        raise FileNotFoundError(f"network.json not found in {args.results_dir}")
+
+    G = load_network_from_json(json_path)
+
+    plots_dir = os.path.join(args.results_dir, "plots")
+    os.makedirs(plots_dir, exist_ok=True)
+
+    cluster_mapping = os.path.join(args.results_dir, "plasmid_cluster_mapping.txt")
+    cluster_colors = os.path.join(args.results_dir, "cluster_colours.txt")
+    colored = os.path.exists(cluster_mapping) and os.path.exists(cluster_colors)
+
+    k_min, k_max = args.plot_k
+
+    for k in np.arange(k_min, k_max + 0.1, 1.0):
+        output_base = os.path.join(plots_dir, f"custom_plot_k_{k}")
+        visualize_network(G, k, output_base, args)
+
+        if colored:
+            visualize_network_colored_by_cluster(G, k, output_base, cluster_mapping, cluster_colors, args)
+
+    print(f"Plots saved to: {plots_dir}")
+
+if __name__ == "__main__":
+    run()

plasmidhub/preprocessing.py

@@ -0,0 +1,48 @@
+import os
+from Bio import SeqIO
+import logging
+logger = logging.getLogger(__name__)
+
+def validate_and_list_plasmids(input_dir):
+    valid_extensions = ['.fna', '.fa', '.fasta']
+    plasmid_files = []
+    invalid_files = []
+
+    for fname in os.listdir(input_dir):
+        if not any(fname.lower().endswith(ext) for ext in valid_extensions):
+            continue
+        fpath = os.path.join(input_dir, fname)
+        try:
+            with open(fpath, 'r') as handle:
+                records = list(SeqIO.parse(handle, 'fasta'))
+                if len(records) == 0:
+                    invalid_files.append(fname)
+                else:
+                    plasmid_files.append(os.path.abspath(fpath))
+        except Exception:
+            invalid_files.append(fname)
+
+    if invalid_files:
+        logger.warning("Warning: The following files are not valid FASTA files or unreadable:")
+        for f in invalid_files:
+            logger.warning(f" - {f}")
+
+    # Sort by filename - if you sort by name, it affect the layout of the plot (just the visualization, not the network itrself)!
+    # plasmid_files.sort(key=lambda x: os.path.basename(x).lower())
+
+    return plasmid_files
+
+def write_plasmid_list(plasmid_files, output_file="Plasmid_list.txt"):
+    with open(output_file, 'w') as f:
+        for path in plasmid_files:
+            f.write(path + '\n')
+
+def write_plasmid_sizes(plasmid_files, output_file="Plasmid_sizes.txt"):
+    with open(output_file, 'w') as f:
+        f.write("PlasmidID\tSize\n")
+        for path in plasmid_files:
+            total_len = 0
+            with open(path, 'r') as handle:
+                for rec in SeqIO.parse(handle, 'fasta'):
+                    total_len += len(rec.seq)
+            f.write(f"{os.path.basename(path)}\t{total_len}\n")

plasmidhub-1.0.0.dist-info/LICENSE

@@ -0,0 +1,24 @@
+MIT License
+
+Copyright (c) 2025 Dr. Balint Timmer
+
+Institute of Metagenomics, University of Debrecen, Debrecen, Hungary
+Institute of Medical Microbiology, Faculty of Medicine, University of Pecs, Pecs, Hungary
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense,
+and to permit persons to whom the Software is         
+furnished to do so, subject to the following conditions:                      
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.                               
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR    
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,      
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE   
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER        
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 
+SOFTWARE.

plasmidhub-1.0.0.dist-info/METADATA

@@ -0,0 +1,193 @@
+Metadata-Version: 2.1
+Name: plasmidhub
+Version: 1.0.0
+Summary: A command-line tool for plasmid clustering, analysis, and visualization.
+Home-page: https://github.com/YOUR_USERNAME/Plasmidhub
+Author: Dr. Balint Timmer
+Author-email: "Dr. Balint Timmer" <timmer.balint@med.unideb.hu>
+License: MIT License
+        
+        Copyright (c) 2025 Dr. Balint Timmer
+        
+        Institute of Metagenomics, University of Debrecen, Debrecen, Hungary
+        Institute of Medical Microbiology, Faculty of Medicine, University of Pecs, Pecs, Hungary
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense,
+        and to permit persons to whom the Software is         
+        furnished to do so, subject to the following conditions:                      
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.                               
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR    
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,      
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE   
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER        
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 
+        SOFTWARE.
+Keywords: plasmid,bioinformatics,network,clustering,AMR,virulence,plasmid network
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython>=1.83
+Requires-Dist: pandas>=2.0
+Requires-Dist: networkx>=3.1
+Requires-Dist: matplotlib>=3.7
+Requires-Dist: python-louvain>=0.16
+Requires-Dist: numpy>=1.24
+Requires-Dist: scipy>=1.8
+
+ <img src="https://img.shields.io/github/license/BALINTESBL/plasmidhub" alt="License"> <img src="https://img.shields.io/pypi/v/plasmidhub" alt="PyPI">  ![Build Status](https://github.com/BALINTESBL/plasmidhub/actions/workflows/tests.yml/badge.svg)
+ 
+# Plasmidhub
+Plasmidhub is a free and open-source command-line tool for comprehensive plasmid network analysis based on nucleotide sequence similarity. It enables researchers to cluster plasmids and identify genetically related groups using a dynamic, database-independent approach. Plasmidhub's approach: 
+* Is applicable to any plasmid
+* Provides an unambiguous classification
+* Considers the whole sequence of the plasmids
+
+Network visualizations, stats and data are provided for further analysis.
+
+## Download and Installation
+PlasmidHub can be installed easily via PyPI, Bioconda, or directly from GitHub.
+
+### Pip
+```
+pip install plasmidhub
+```
+**Note:** It's highly recommended to use a virtual environment or conda environment.
+Recommended environment setup:
+```
+conda create -n plasmidhub python=3.8
+conda activate plasmidhub
+```
+### Bioconda
+
+If you use Conda for environment management:
+```
+conda install -c bioconda plasmidhub
+```
+Make sure you have the bioconda channel configured. If not, configure them with:
+```
+conda config --add channels defaults
+conda config --add channels bioconda
+conda config --add channels conda-forge
+```
+### GitHub
+To get the latest version:
+```
+git clone https://github.com/BALINTESBL/plasmidhub.git
+cd plasmidhub
+pip install .
+```
+### Dependencies
+This tool requires the following external software to be installed:
+- [FastANI](https://github.com/ParBLiSS/FastANI)
+- [ABRicate](https://github.com/tseemann/abricate)
+
+## Inputs
+Plasmidhub requires plasmid FASTA files (.fna or .fa or .fasta). Your FASTA files need to be placed in one directory. Ideally, there are no other files in the directory.
+
+## Usage
+Perform plasmid network analysis with default settings by defining only the directory path of your plasmid FASTA files! Or, you can also adjust parameters.
+Example usage:
+```
+% plasmidhub path/to/my/plasmid/FASTA/files --fragLen 1000 --kmer 14 --coverage_threshold 0.5 --ani_threshold 95 --min_cluster_size 4 --plot_k 2.0 3.0 -t 32
+
+```
+This command will:
+* Compute pairwise ANI using FastANI
+* Build a plasmid similarity network
+* Save network metrics and statistics (results/statistics)
+* Cluster plasmids
+* Annotate resistance and virulence genes with ABRicate (results/abricate_results)
+* Generate network visualizations (results/plots)
+### Key Options
+
+| Category       | Flag                   | Description                             | Default                   |
+| -------------- | ---------------------- | --------------------------------------- | ------------------------- |
+| **Input**      | `                      | Path to folder with plasmid FASTA files | –                         |
+| **FastANI**    | `--fragLen`            | Fragment length                         | `1000`                    |
+|                | `--kmer`               | K-mer size                              | `14`                      |
+|                | `--coverage_threshold` | Minimum proportion of the plasmid lenghts| `0.5`                     |
+|                |                        |  covered by the matching fragments      |                           |
+|                | `--ani_threshold`      | Minimum ANI score (after applying       | `95.0`                    |
+|                |                        |  coverage threshold)                    |                           | 
+| **Clustering** | `--cluster_off`        | Disable clustering                      | –                         |
+|                | `--min_cluster_size`   | Minimum cluster size (plasmids)         | `3`                       |
+| **ABRicate**   | `--skip_abricate`      | Skip annotation step                    | –                         |
+|                | `--abricate_dbs`       | Databases to use e.g.:                  | `plasmidfinder card vfdb` |
+|                |                        |  --abricate_dbs ncbi ecoli_vf           |                           |
+| **Plotting**   | `--plot_k`             | Range of k values                       |`3` `3`                    |
+|                | `--plot_skip`          | Skips plotting                          |                           |
+| **Threads**    | `-t` or `--threads`    | Number of threads                       | `4`                       |
+### Plot-only mode 
+In plot-only mode, network visualizations can be generated from existing networks directly, by using --plot_only flag and defining the directory path. In this mode, several parameters can be adjusted.
+Example usage:
+```
+% plasmidhub --plot_only path/to/my/results  --plot_k 3 5 --plot_node_color blue --plot_node_size 500 --plot_node_shape s --plot_figsize 20 20 -t 32
+
+```
+| **Plotting**   | Flag                   | Description                             | Default                   |
+| -------------- | ---------------------- | --------------------------------------- | ------------------------- | 
+|                | `--plot_node_size`     | Size of nodes                           | `900`                     |
+|                | `--plot_node_shape`    | Shape of nodes (`o`, `s`, `^`, etc.)    | `o` (circle)              |
+|                | `--plot_edge_width`    | Min/max edge width                      | `0.2 2.0`                 |
+|                | `--plot_figsize`       | Figure size in inches                   | `25 25`                   |
+|                | `--plot_iterations`    | Spring layout iterations                | `100`                     |
+
+Node shapes: 
+| Marker | Description                |
+| ------ | -------------------------- |
+| `'o'`  | Circle                     |
+| `'s'`  | Square                     |
+| `'^'`  | Upward-pointing triangle   |   
+| `'v'`  | Downward-pointing triangle |       
+| `'>'`  | Right-pointing triangle    |       
+| `'<'`  | Left-pointing triangle     |          
+| `'D'`  | Diamond                    |        
+| `'d'`  | Thin diamond               |    
+| `'p'`  | Pentagon                   |    
+| `'h'`  | Hexagon 1                  |               
+| `'H'`  | Hexagon 2                  |
+|  `'*'` | Star                       |
+| `'+'`  | Plus                       |
+| `'x'`  | Cross                      |
+| `'X'`  | Filled X                   |
+
+Plots generated with Plasmidhub:
+<img width="1668" height="1668" alt="image" src="https://github.com/user-attachments/assets/afed18b8-6dbe-44b8-b539-23aa47b4bfb0" />
+
+## Overview
+
+Plasmidhub performs an all-vs-all comparison of input plasmid sequences using FastANI. FastANI results ("raw results") are filtered  by the coverage (what proportion of the full plasmid sequences are covered by the matching fragments). The remaining pairs are filtered by the minimum ANI score. ANI scores are further weighted by the proportion of matching fragments, and data are sorted into a similarity matrix. The network is build from the similarity matrix, where:
+- **Nodes** represent plasmids
+- **Edges** represent genetic relatedness (weighted ANI)
+
+Within the network, communities are detected via Louvain method (subclusters). Plasmid clusters are complete subgraphs (cliques) detected within the whole network. Clusters comprising highly similar or identical plasmids. If relevant and scientifically appropriate, plasmids of the same cluster may be considered as equivalent. This approach is alignment-free, reference-free, database-independent, and uses relative similarity-based system to overcome the limitations of database dependency (untypeable plasmids, multireplicon/multi-MOB plasmids, mosaic, hybrid plasmids ect.)
+Network and node statistics are saved to a distinct directory for downstream analyses (connectance, modularity, nestedness, community partition, degree centrality, node degrees, betweenness, closeness ect.)
+
+Resistance and virulence genes can be annotated via [ABRicate](https://github.com/tseemann/abricate). The abricate files are saved to a distinct subdirectory. By default, plasmidfinder, vfdb and card databases are used, but optionally other databases can be specified from the databases available with ABRicate. 
+
+To generate custom visualizations, feel free to use and modify the *plot.py*.
+
+## Troubleshooting
+Users are welcome to report any issue or feedback related to Plasmidhub by posting a [Github issue](https://github.com/BALINTESBL/plasmidhub/issues).
+
+---
+
+Developed by **Dr. Bálint Timmer**  
+*Institute of Metagenomics, University of Debrecen, Debrecen, Hungary* 
+*Department of Medical Microbiology, University of Pécs Medical School, Pécs, Hungary* 
+
+ <img width="33" height="33" alt="image" src="https://github.com/user-attachments/assets/bd9f17e9-e9ce-4edb-8319-ef0091c45f00" /> <img width="99" height="32.054" alt="image" src="https://github.com/user-attachments/assets/5f3d5b6b-cef6-478a-af66-614b2e2860b2" />
+ 
+Contact: [timmer.balint@med.unideb.hu](mailto:timmer.balint@med.unideb.hu) , [timmer.balint@pte.hu](mailto:timmer.balint@pte.hu)

plasmidhub-1.0.0.dist-info/RECORD

@@ -0,0 +1,18 @@
+plasmidhub/__init__.py,sha256=jGpatuTP-5KcGG6mvMculsbklnol_RIr2tTuDj2IHh8,21
+plasmidhub/abricate.py,sha256=T295S6vXbOAomgcEtWmq9wnj5ZxhlFcJJKJ7AmpJD00,1428
+plasmidhub/ani.py,sha256=59Idb0M0MWwkBw-R-9AzZpONr4YAFza2l47IiT2phGI,904
+plasmidhub/cluster_color.py,sha256=Sp7hV0sRbhGOx2dVMAeeaiEtEf5FX9oyHQNOeAKapBc,1579
+plasmidhub/clustering.py,sha256=9sdMbyBgDokId1xnzFKX4XI5V4COJ5x1XATYfSKD4UE,5804
+plasmidhub/filtering.py,sha256=e-bpJf9Ge6Vbmyy1K4cDp2yPMqnJpJ1wAE046mf4ga4,2539
+plasmidhub/main.py,sha256=w7SHWUwj2Z_OCHw-wTmIJCEnMt46KIyipFLahyuDvTQ,15417
+plasmidhub/network_builder.py,sha256=0hlJP_mYluQ20PR-A0YjOBQErGr-O7NCtIeMQRNHpVo,8480
+plasmidhub/node_stats.py,sha256=85Uy-NlT8MfErZQ65jtRdFIQHD32Z1BefJDk5OXfoAU,2318
+plasmidhub/plot.py,sha256=hGWyRGPM-q77qBILHLsaFaNZoeekQ39ZDcsSD3abqMI,6983
+plasmidhub/plot_only.py,sha256=UDEmH3FBFTIMPfymScvbuKo8lzB8VniCRlpEVtnSubI,6475
+plasmidhub/preprocessing.py,sha256=xj1BDT9gsiLVj2gLuLaiGvJmb_6tFMH_5HTJNWW3jxs,1780
+plasmidhub-1.0.0.dist-info/LICENSE,sha256=TLYeEpymgVrs1pFYz30Tj_911HUZbakCHp0HNfpHiMA,1282
+plasmidhub-1.0.0.dist-info/METADATA,sha256=DIo8OLbFLY-kpwzq16gLHyCweOSyy5gAiCWfCSGGbdM,11531
+plasmidhub-1.0.0.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
+plasmidhub-1.0.0.dist-info/entry_points.txt,sha256=RypObT2-nI493vnZSRZf-E47n8mzvzsHDCYLlQHX1FU,52
+plasmidhub-1.0.0.dist-info/top_level.txt,sha256=yTI35SryspznaWY3hgD7mJmaYI-w5fBHqS03OKytKsM,11
+plasmidhub-1.0.0.dist-info/RECORD,,

plasmidhub-1.0.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.3.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

plasmidhub-1.0.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+plasmidhub = plasmidhub.main:main

plasmidhub-1.0.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+plasmidhub