More Examples

These tutorials illustrate how to combine BioNeuralNet components for a cohesive multi-omics analysis.

• Example 1: SmCCNet + DPMON for Disease Prediction
• Example 2: SmCCNet + GNN Embeddings + Subject Representation

Example 1 demonstrates:

• Constructing a network (SmCCNet).

• Leveraging DPMON for end-to-end disease prediction.

Example 2 demonstrates:

• Generating a graph using cosine similarity.

• Using GNNEmbedding to create node embeddings.

• Integrating embeddings into subject data for further analysis.

BioNeuralNet offers a variety of tools for graph-based analyses of multi-omics data, including:

• Graph Embedding: Generate GNN embeddings.

• Subject Representation: Integrate embeddings into omics data..

• Disease Prediction: DPMON for end-to-end classification.

• Graph Clustering: PageRank or Hierarchical clustering for subnetwork identification.