Tutorials

These tutorials demonstrate integrated workflows that combine multiple BioNeuralNet components.

Example 1: Sparse Multiple Canonical Correlation Network (SmCCNet) Workflow with Graph Neural Network (GNN) Embeddings This tutorial demonstrates how to:

  • Construct a network using SmCCNet.

  • Generate node embeddings with a Graph Neural Network (GNN).

  • Integrate embeddings into subject-level omics data for enhanced analysis.

Example 2: Weighted Gene Co-expression Network Analysis (WGCNA) Workflow with Graph Neural Network (GNN) Embeddings This tutorial illustrates:

  • Building a weighted gene co-expression network using WGCNA.

  • Generating embeddings via a GNN and integrating them into omics data.

  • Enhancing subject-level representations for downstream analyses.

Example 3: Disease Prediction Using Graph Information (SmCCNet + DPMON) This tutorial demonstrates how to:

  • Generate an adjacency matrix using SmCCNet from multi-omics data.

  • Use DPMON for disease prediction by integrating the generated network and omics data.

  • Predict disease phenotypes leveraging graph-based models.

Example 4: Sparse Multiple Canonical Correlation Network (SmCCNet) + PageRank Clustering + Visualization This tutorial showcases:

  • Constructing a network using SmCCNet.

  • Identifying meaningful clusters in the network using PageRank-based clustering.

  • Visualizing the resulting sub-networks for biological insights.

By following these tutorials, you will learn how BioNeuralNe’ modules can interoperate to:

  • Perform advanced multi-omics analyses.

  • Generate networks and embeddings.

  • Predict disease phenotypes.

  • Visualize and interpret biological graphs.