Microbes produce an array of secondary metabolites that perform diverse functions from communication to defense. These metabolites have been used to benefit human health and sustainability. In their analysis of the Genomes from Earth's Microbiomes (GEM) catalog, Nayfach and co-authors observed that, whereas genes coding for certain classes of secondary metabolites are limited or enriched in certain microbial taxa, "specific chemistry is not limited or amplified by the environment, and that most classes of secondary metabolites can be found nearly anywhere". Although metagenome mining is a powerful way to annotate biosynthetic gene clusters (BCGs), chemical evidence is required to confirm the presence of metabolites and comprehensively address this fundamental hypothesis, as metagenomic data only identify metabolic potential. To describe the Earth's metabolome, we use an integrated omics approach: the direct survey of metabolites associated with microbial communities spanning diverse environments using untargeted metabolomics coupled with metagenome analysis. We show, in contrast to Nayfach and co-authors, that the presence of certain classes of secondary metabolites can be limited or amplified by the environment. Importantly, our data indicate that considering the relative abundances of secondary metabolites (i.e., rather than only presence/absence) strengthens differences in metabolite profiles across environments, and that their richness and composition in any given sample do not directly reflect those of co-occurring microbial communities, but rather vary with the environment.

Inflammatory bowel diseases (IBDs), including ulcerative colitis and Crohn's disease, affect several million individuals worldwide. These diseases are heterogeneous at the clinical, immunological and genetic levels and result from a complex interaction between the host and environmental factors. Investigating drug efficacy in cultured human fresh IBD tissues can improve our understanding of the reasons why certain medications are more or less effective for different patients. We propose an explainable machine learning (ML) approach that combines bioinformatics and domain insight, to informatively integrate multi-modal data to predict inter-patient specific variation in drug response. Using explanation of our models, we interpret the models' predictions inferring unique combinations of important features associated with human tissue pharmacological responses. The inferred multi-modal features originate from multi-omic data (genomic and transcriptomic), demographic, medicinal and pharmacological data and all are associated with drug efficacy generated by a preclinical human fresh IBD tissue assay. To pharmacologically assess patient variation in response to IBD treatment, we used the reduction in the release of the inflammatory cytokine TNFa; from the fresh IBD tissues in the presence or absence of test drugs, as a measure of drug efficacy. The TNF pathway is a common target in current therapies for IBD; we initially explored the effects of a mitogen-activated protein kinase (MAPK) inhibitor on the production of TNFa; however, we later show the approach can be applied to other targets, test drugs or mechanisms of interest. Our best model was able to predict TNFa; levels from a combination of integrated demographic, medicinal and genomic features with an error as low as 4.98% on unseen patients. We incorporated transcriptomic data to validate and expand insights from genomic features. Our results showed variations in drug effectiveness between patients that differed in gender, age or condition and linked new genetic polymorphisms in our cohort of IBD patients to variation in response to the anti-inflammatory treatment BIRB796 (Doramapimod). Our approach models drug response in a relevant human tissue model of IBD while also identifying its most predictive features as part of a transparent ML-based precision medicine strategy.