Recon8D: A metabolic regulome network from oct-omics and machine learning.

The complexity and incompleteness of metabolic-regulatory networks make it challenging to predict metabolomes from other omics. Using machine learning, we predicted metabolomic variation across ~1000 different cancer cell lines from matched oct-omics data: genomics, epigenomics (histone post-translational modifications (PTMs) and DNA-methylation), transcriptomics, RNA splicing, miRNA-omics, proteomics, and phosphoproteomics. Overall, the metabolome is tightly associated with the transcriptome, while miRNAs, phosphoproteins and histone PTMs have the highest metabolic information per feature.