Chemical reaction vector embeddings: towards predicting drug metabolism in the human gut microbiome

Abstract

Bacteria in the human gut have the ability to activate, inactivate, and reactivate drugs with both intended and unintended effects. For example, the drug digoxin is reduced to the inactive metabolite dihydrodigoxin by the gut Actinobacterium E. lenta, and patients colonized with high levels of drug metabolizing strains may have limited response to the drug. Understanding the complete space of drugs that are metabolized by the human gut microbiome is critical for predicting bacteria-drug relationships and their effects on individual patient response. Discovery and validation of drug metabolism via bacterial enzymes has yielded >50 drugs after nearly a century of experimental research. However, there are limited computational tools for screening drugs for potential metabolism by the gut microbiome. We developed a pipeline for comparing and characterizing chemical transformations using continuous vector representations of molecular structure learned using unsupervised representation learning. We applied this pipeline to chemical reaction data from MetaCyc to characterize the utility of vector representations for chemical reaction transformations. After clustering molecular and reaction vectors, we performed enrichment analyses and queries to characterize the space. We detected enriched enzyme names, Gene Ontology terms, and Enzyme Consortium (EC) classes within reaction clusters. In addition, we queried reactions against drug-metabolite transformations known to be metabolized by the human gut microbiome. The top results for these known drug transformations contained similar substructure modifications to the original drug pair. This work enables high throughput screening of drugs and their resulting metabolites against chemical reactions common to gut bacteria.

Role of Gut Microbiota in the Pharmacological Effects of Natural Products

“…Digoxin is an example of a drug that decreases drug efficacy when it metabolized by microbiota. It has been reported that gut microbiota can degrade digoxin to its inactive form, such as dihydrodigoxin and dihydrodigoxigenin [45], which hardly bind Na + -K + -ATPase of cardiac cells [46]. Conversely, some new effects can be functioned during the interaction between drugs and gut microbiota.…”

Applications of Genetics, Genomics and Bioinformatics in Drug Discovery

“…Understanding the complete space of drug metabolism by the human gut microbiome is critical for predicting bacteria-drug relationships and their effects on drug response. To address the challenge that there are limited computational tools for predicting drug metabolism by the gut microbiome, Mallory et al 15 developed a pipeline for comparing and characterizing chemical transformations using continuous vector representations of molecular structure based on unsupervised learning, and characterized the utility of vector representations for chemical reaction transformations. After clustering molecular and reaction vectors, enriched enzyme names, Gene Ontology terms, and Enzyme…”

Towards a mechanistic understanding of reciprocal drug–microbiome interactions

“…Drug‐specific chemical probes have also been employed to probe enzyme activity and to pull down enzymes conveying a drug conversion of interest, as elegantly applied for the identification of beta‐glucuronidases (Jariwala et al , 2020). Finally, computational approaches based on metabolic reaction networks, comparative genomics of bacterial isolates, or microbiome composition have been employed to identify possible genetic factors responsible for drug metabolism (Klünemann et al , 2014; Mallory et al , 2018; Guthrie et al , 2019). Once identified, microbial genes involved in drug metabolism can serve as potential biomarkers to quantitatively predict the drug metabolic capacity of a given microbial community (Zimmermann et al , 2019b) (Fig 3), opening new paths for understanding the impact of microbial drug metabolism on the host and eventually its role in the interpersonal variability in drug response.…”