Lemonite: identification of regulatory metabolites through data-driven, interpretable integration of transcriptomics and metabolomics data

Current transcriptomics-metabolomics integration approaches are either limited by poor interpretability or constrained by incomplete prior knowledge, preventing the systematic identification of regulatory metabolites. Here, we present Lemonite, a data-driven and interpretable framework for integrating bulk transcriptomics and metabolomics data to uncover regulatory metabolites acting on gene modules. Lemonite extends module network inference to jointly associate transcription factors and metabolites with gene programs, without requiring prior differential analysis or complete metabolome annotation. To contextualize predictions, we constructed a comprehensive gene/protein-metabolite knowledge graph integrating over 370 000 metabolite-gene/protein and 2.1 million protein-protein interactions. Applied to glioblastoma (n=99) and inflammatory bowel disease (n=75) cohorts, Lemonite identified over 50 functionally coherent gene modules per disease, revealing established and previously uncharacterized metabolite-gene regulatory relationships. In glioblastoma, myo-inositol and phosphatidylcholines, together with IRF6, regulate mesenchymal-like immune programs, which upon integration with single-cell transcriptomics are primarily expressed in tumor-associated macrophages and monocytes. In inflammatory bowel disease, regulatory metabolites were prioritized that change the expression of their predicted target genes in colonic epithelial cells in vitro. Overall, Lemonite provides a principled framework to explore the genome-wide regulatory potential of the metabolome and to generate biologically interpretable, experimentally testable hypotheses from multi-omics data.