Node degree distribution

assets/multiqc_config.yml

@@ -25,6 +25,7 @@ custom_content:
     - input
     - input_seeds
     - input_network
+    - network_node_degree_distribution
     - drugstone_link
     - overlap
     - jaccard_similarity

assets/network_node_degree_distribution_header.yaml

@@ -0,0 +1,16 @@
+parent_id: input
+id: network_node_degree_distribution
+parent_name: Input
+section_name: Network node degree distribution
+description: Node degree distributions of the input network(s).
+plot_type: linegraph
+pconfig:
+  id: network_node_degree_distribution_line_graph
+  title: Node Degree Distribution
+  xlab: Node Degree
+  data_labels:
+    - name: Counts
+      ylab: Counts
+    - name: Percentages
+      ylab: Percentage
+data:

bin/graph_tool_parser.py

@@ -5,11 +5,14 @@
 
 import argparse
 import csv
+import json
 import logging
 import sys
 import os
 import graph_tool.all as gt
 from pathlib import Path
+from collections import Counter
+import yaml
 
 logger = logging.getLogger()
 
@@ -60,6 +63,42 @@ def save_multiqc(g, stem):
         )
 
 
+def save_node_degree_distribution(g, stem):
+    # Calculate degree for each vertex
+    degrees = [v.out_degree() for v in g.vertices()]
+
+    # Count frequency of each degree
+    degree_counts = Counter(degrees)
+
+    # Get total number of vertices for normalization
+    total_vertices = len(degrees)
+
+    # Create absolute counts dictionary: {degree: count}
+    absolute_counts = [
+        [degree, count] for degree, count in sorted(degree_counts.items())
+    ]
+
+    # Create relative frequencies dictionary: {degree: percentage}
+    relative_frequencies = [
+        [degree, count / total_vertices * 100]
+        for degree, count in sorted(degree_counts.items())
+    ]
+    # save node degree distribution as yaml
+    node_degree_distribution = {
+        "name": stem,
+        "absolute": absolute_counts,
+        "relative": relative_frequencies,
+    }
+
+    with open(f"{stem}.node_degree_distribution.yaml", "w") as file:
+        yaml.safe_dump(
+            node_degree_distribution,
+            file,
+            sort_keys=False,
+            default_flow_style=None,  # keeps list pairs as [x, y]
+        )
+
+
 def save_diamond(g, stem):
     with open(f"{stem}.diamond.csv", "w") as file:
         writer = csv.writer(file, lineterminator="\n")
@@ -108,6 +147,7 @@ def save(g, stem, format):
     if format == "gt":
         save_gt(g=g, stem=stem)
         save_multiqc(g=g, stem=stem)
+        save_node_degree_distribution(g=g, stem=stem)
     elif format == "diamond":
         save_diamond(g=g, stem=stem)
     elif format == "domino":
@@ -170,7 +210,13 @@ def parse_args(argv=None):
         "-f",
         "--format",
         help="Output format (default gt). If format it gt, a summary file for multiqc will be generated as well.",
-        choices=("gt", "diamond", "domino", "robust", "rwr"),
+        choices=(
+            "gt",
+            "diamond",
+            "domino",
+            "robust",
+            "rwr",
+        ),
         default="gt",
     )
     parser.add_argument(

bin/multiqc_formatter.py

@@ -0,0 +1,64 @@
+#!/usr/bin/env python
+import argparse
+from pathlib import Path
+import yaml
+import sys
+
+
+def parse_args(argv=None):
+    parser = argparse.ArgumentParser(
+        description="formats file for multiqc custom contents",
+        epilog="Example: python multiqc_formatter.py -i network.gt -f network_degree",
+    )
+    parser.add_argument(
+        "-i", "--input", type=Path, nargs="*", required=True, help="Input files"
+    )
+    parser.add_argument("-H", "--header", type=Path, required=True, help="Header file")
+    return parser.parse_args(argv)
+
+
+def parse_input(input_files, header_file):
+    with open(header_file, "r") as header:
+        header_data = yaml.safe_load(header)
+        header_id = header_data.get("id", "")
+
+    if header_id == "network_node_degree_distribution":
+        save_node_degree_distribution(input_files, header_file)
+
+
+def save_node_degree_distribution(input_files, header_file):
+    with open(header_file, "r", encoding="utf-8") as header:
+        mqc_payload = yaml.safe_load(header) or {}
+
+    absolute_data = {}
+    relative_data = {}
+
+    for file in input_files:
+        with open(file, "r", encoding="utf-8") as distribution_file:
+            distribution = yaml.safe_load(distribution_file) or {}
+
+        network_name = distribution.get("name") or file.stem
+        absolute = distribution.get("absolute")
+        relative = distribution.get("relative")
+
+        if absolute is None or relative is None:
+            raise ValueError(
+                f"Invalid distribution YAML in {file}: expected keys 'absolute' and 'relative'"
+            )
+
+        absolute_data[network_name] = absolute
+        relative_data[network_name] = relative
+
+    mqc_payload["data"] = [absolute_data, relative_data]
+
+    with open("./node_degree_distribution_mqc.yaml", "w", encoding="utf-8") as file:
+        yaml.safe_dump(mqc_payload, file, sort_keys=False, default_flow_style=None)
+
+
+def main():
+    args = parse_args()
+    parse_input(args.input, args.header)
+
+
+if __name__ == "__main__":
+    sys.exit(main())

bin/network_annotation.py

@@ -91,6 +91,9 @@ def run(args):
     # Assign component ID to each component of the subnetwork
     component_id = assign_component_ids(subnetwork)
 
+    # Add node degrees as vertex properties
+    add_node_degrees(subnetwork, name_to_degree_full, name_to_degree_sub)
+
     # Save the network containing the annotations in graph-tool format
     subnetwork.save(args.output_file)
 
@@ -140,5 +143,24 @@ def assign_component_ids(graph):
     return graph.vp["component_id"]
 
 
+def add_node_degrees(subnetwork, name_to_degree_full, name_to_degree_sub):
+    """
+    Adds the node degree from both the full network and the subnetwork as vertex properties.
+    """
+    # Add degree in the full network
+    subnetwork.vp["degree_in_full_network"] = subnetwork.new_vertex_property("int")
+    # Add degree in the subnetwork
+    subnetwork.vp["degree_in_module"] = subnetwork.new_vertex_property("int")
+
+    for v in subnetwork.vertices():
+        name = subnetwork.vp["name"][v]
+        full_degree = name_to_degree_full.get(name, 0)
+        sub_degree = name_to_degree_sub.get(name, 0)
+        subnetwork.vp["degree_in_full_network"][v] = full_degree
+        subnetwork.vp["degree_in_module"][v] = sub_degree
+
+    return subnetwork.vp["degree_in_full_network"], subnetwork.vp["degree_in_module"]
+
+
 if __name__ == "__main__":
     main()

bin/visualize_modules.py

@@ -104,6 +104,7 @@ def parse_args(argv=None):
 def main(argv=None):
     """Coordinate argument parsing and program execution."""
     args = parse_args(argv)
+
     logging.basicConfig(level=args.log_level, format="[%(levelname)s] %(message)s")
     if not args.module.is_file():
         logger.error(f"The given input file {args.file_in} was not found!")

conf/base.config

@@ -11,7 +11,7 @@
 process {
 
     // Set default container for python dependencies
-    container = 'ghcr.io/repo4eu/modulediscovery_python_dependencies:v0.1.0'
+    container = 'ghcr.io/repo4eu/modulediscovery_python_dependencies:v0.2.0'
 
     cpus   = { 1      * task.attempt }
     memory = { 6.GB   * task.attempt }

conf/modules.config

@@ -21,6 +21,13 @@ process {
         ]
     }
 
+    withName: 'MULTIQCFORMATTER' {
+        publishDir = [
+            path: { "${params.outdir}/mqc_summaries"},
+            mode: params.publish_dir_mode,
+            saveAs: {filename -> filename.equals('versions.yml') ? null : filename}
+        ]
+    }
     // Input parsing
 
     withName: GRAPHTOOLPARSER {

docs/output.md

@@ -51,7 +51,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 ### Prepare network
 
-The [graph-tool](https://graph-tool.skewed.de/) library is used to parse the input network(s) into the [`.gt`](https://graph-tool.skewed.de/static/docs/stable/gt_format.html) format, the internal representation used for networks within the pipeline. Additionally, it is used to generate networks in the specific formats required by the various disease module inference methods. This step also gathers summary statistics for the MultiQC report, including the number of nodes and edges, the network [diameter](https://graph-tool.skewed.de/static/docs/stable/autosummary/graph_tool.topology.pseudo_diameter.html#graph_tool.topology.pseudo_diameter), the number of connected components, the size of the largest connected component, the count of self-loops (nodes with edges to themselves), and the number of duplicate edges (multiple edges connecting the same two nodes).
+The [graph-tool](https://graph-tool.skewed.de/) library is used to parse the input network(s) into the [`.gt`](https://graph-tool.skewed.de/static/docs/stable/gt_format.html) format, the internal representation used for networks within the pipeline. Additionally, it is used to generate networks in the specific formats required by the various disease module inference methods. This step also gathers summary statistics for the MultiQC report, including the number of nodes and edges, the network [diameter](https://graph-tool.skewed.de/static/docs/stable/autosummary/graph_tool.topology.pseudo_diameter.html#graph_tool.topology.pseudo_diameter), the number of connected components, the size of the largest connected component, the distribution of node degrees, the count of self-loops (nodes with edges to themselves), and the number of duplicate edges (multiple edges connecting the same two nodes).
 
 <details markdown="1">
 <summary>Output files</summary>
@@ -63,6 +63,7 @@ The [graph-tool](https://graph-tool.skewed.de/) library is used to parse the inp
   - `<network>.robust.tsv`: Input network in the format required for ROBUST or ROBUST (bias-aware). Only created if the methods are used.
   - `<network>.rwr.csv`: Input network in the format required for RWR. Only created if the method is used.
 - `mqc_summaries/`
+  - ` node_degree_distribution_mqc.yaml`: Network node degree distribution for the MultiQC report.
   - ` input_network_mqc.tsv`: Network summary statistics for the MultiQC report.
 
 </details>
@@ -84,7 +85,7 @@ The format of the input seed file(s) is validated, and any seed nodes not presen
 
 ## Disease module inference
 
-The inferred disease modules are exported in multiple formats, including [`.gt`](https://graph-tool.skewed.de/static/docs/stable/gt_format.html), [`.graphml`](https://de.wikipedia.org/wiki/GraphML), and node and edge lists in `.tsv`. If a method returns only a node list rather than a full network, the connecting edges are extracted from the input network. Module nodes are annotated with their seed status (`is_seed`), their subnetwork participation degree ([`spd`](https://nedrex.net/tutorial/availableFunctions.html)), and a component identifier (`component_id`) to indicate which connected component they belong to. Additionally, tool-specific node properties are added, which are explained in the sections below.
+The inferred disease modules are exported in multiple formats, including [`.gt`](https://graph-tool.skewed.de/static/docs/stable/gt_format.html), [`.graphml`](https://de.wikipedia.org/wiki/GraphML), and node and edge lists in `.tsv`. If a method returns only a node list rather than a full network, the connecting edges are extracted from the input network. Module nodes are annotated with their seed status (`is_seed`), their degree within both the whole network (`degree_in_full_network`) and the disease module(`degree_in_module`), their subnetwork participation degree ([`spd`](https://nedrex.net/tutorial/availableFunctions.html)), and a component identifier (`component_id`) to indicate which connected component they belong to. Additionally, tool-specific node properties are added, which are explained in the sections below.
 
 ### Only seeds
 

modules/local/graphtoolparser/main.nf

@@ -7,9 +7,10 @@ process GRAPHTOOLPARSER {
     val format
 
     output:
-    tuple val(meta), path("*${format}*")               , emit: network
-    tuple val(meta), path("input_network_multiqc.tsv") , emit: multiqc, optional: true
-    path "versions.yml"                                , emit: versions
+    tuple val(meta), path("*${format}*")                    , emit: network
+    tuple val(meta), path("input_network_multiqc.tsv")      , emit: multiqc     , optional: true
+    tuple val(meta), path("*node_degree_distribution.yaml") , emit: node_degree , optional: true
+    path "versions.yml"                                     , emit: versions
 
     when:
     task.ext.when == null || task.ext.when

modules/local/multiqcformatter/main.nf

@@ -0,0 +1,21 @@
+process MULTIQCFORMATTER {
+    label 'process_single'
+
+    input:
+    tuple path(header), path(inputFiles, stageAs: 'input/*')
+    output:
+    path("*mqc*")       , emit : multiqc
+    path "versions.yml" , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+    script:
+    """
+    multiqc_formatter.py -i $inputFiles -H $header
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$(python --version | sed 's/Python //g')
+    END_VERSIONS
+    """
+
+}