SmCCNet 2.0: A Comprehensive Tool for Multi-omics Network Inference with Shiny Visualization

Area of Science:

• Bioinformatics
• Computational Biology
• Network Analysis

Background:

• Integrating multi-omics data with disease phenotypes is crucial for understanding complex diseases.
• Existing methods may lack flexibility or user-friendliness in network reconstruction.

Approach:

• Introducing Sparse Multiple Canonical Correlation Network Analysis 2.0 (SmCCNet 2.0).
• SmCCNet 2.0 integrates single or multiple omics data types with quantitative or binary phenotypes.
• Offers a streamlined setup process, configurable manually or automatically, for user flexibility.

Key Points:

• Enables the reconstruction of multi-omics networks specific to a variable of interest, such as disease phenotype.
• Facilitates the integration of diverse omics data (e.g., genomics, transcriptomics, proteomics).
• Provides a user-friendly interface and flexible configuration options.

Conclusions:

• SmCCNet 2.0 is an advanced machine learning technique for variable-specific multi-omics network analysis.
• The package enhances the integration and network-based analysis of complex biological data.
• A network visualization tool is available to aid in the interpretation of results.