WGCNA+: AI-powered WGCNA for Integration of Multi-Omics Data
Background: Weighted Gene Co-expression Network Analysis (WGCNA) is a widely adopted systems biology method to discover gene modules and module-trait associations, mostly from transcriptomics. Designed for a single layer, it cannot jointly analyze multi-omics layers, a consequential limitation in modern biomedical research. WGCNA modules are often hard to interpret, requiring vast follow-up for…
Weighted Gene Co-expression Network Analysis (WGCNA) is a popular systems biology method used to identify gene modules and module-trait associations, primarily from transcriptomics data. However, it is limited in its ability to analyze multi-omics layers simultaneously, which is a significant drawback in current biomedical research.
The modules generated by WGCNA are often difficult to interpret, necessitating extensive follow-up work for contextualization. Furthermore, there is no integrated framework for visualizing condition-specific, cross-omics relationships at both the module and feature level.
In response to these limitations, WGCNA+ has been developed as a novel R package that extends the capabilities of WGCNA to multi-omics data. WGCNA+ introduces several key innovations: (i) a unified multi-omics pipeline that handles per-layer network inference and cross-layer module enrichment; (ii) an SVD-accelerated topological overlap matrix calculation that substantially reduces computation time; (iii) a consensus framework that identifies modules reproducible across independent datasets and conditions; (iv) LASAGNA, a companion R package that enables phenotype-conditioned, multi-partite graph visualization of cross-omics relationships; (v) AI-powered annotation and infographics that provide immediate biological insight.
WGCNA+ has been tested across public transcriptomics, proteomics, and miRNA datasets. It successfully detects biologically meaningful modules, cross-omics feature and phenotype correlations, and offers AI-powered interpretation that accelerates research. The tool addresses existing gaps by providing a principled, efficient framework for co-expression network analysis across omics.
It can detect cross-omics regulatory modules and their association with phenotypes, supporting basic research, biomarker discovery, and pathway analysis. WGCNA+ offers AI-assisted interpretation and infographics, aiding in hypothesis generation. LASAGNA, the companion package, provides a phenotype-aware multi-partite visualization framework to explore cross-omics relationships.
WGCNA+ and LASAGNA are fully and freely available under an open-source license, implemented in the R language for statistical computing version 3.5 or higher. They are accessible at https://github.com/bigomics/WGCNAplus and https://github.com/bigomics/lasagna, respectively.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
