Prediction of degradation pathways of phenolic compounds in the human gut microbiota through enzyme promiscuity methods

Abstract

The relevance of phenolic compounds in the human diet has increased in recent years, particularly due to their role as natural antioxidants and chemopreventive agents in different diseases. In the human body, phenolic compounds are mainly metabolized by the gut microbiota; however, their metabolism is not well represented in public databases and existing reconstructions. In a previous work, using different sources of knowledge, bioinformatic and modelling tools, we developed AGREDA, an extended metabolic network more amenable to analyze the interaction of the human gut microbiota with diet. Despite the substantial improvement achieved by AGREDA, it was not sufficient to represent the diverse metabolic space of phenolic compounds. In this article, we make use of an enzyme promiscuity approach to complete further the metabolism of phenolic compounds in the human gut microbiota. In particular, we apply RetroPath RL, a previously developed approach based on Monte Carlo Tree Search strategy reinforcement learning, in order to predict the degradation pathways of compounds present in Phenol-Explorer, the largest database of phenolic compounds in the literature. Reactions predicted by RetroPath RL were integrated with AGREDA, leading to a more complete version of the human gut microbiota metabolic network. We assess the impact of our improvements in the metabolic processing of various foods, finding previously undetected connections with output microbial metabolites. By means of untargeted metabolomics data, we present in vitro experimental validation for output microbial metabolites released in the fermentation of lentils with feces of children representing different clinical conditions.

Fig. 1. Summary of the enzyme promiscuity pipeline.

The extended metabolic space analysis connects sources to sinks through reactions inferred by RetroPath RL with rules derived from RetroRules. Sources are phenolic compounds obtained from Phenol-Explorer (colored red), and sinks are metabolites involved in reactions existing in species present in AGORA (colored green), which were obtained from AGREDA and the Model Seed Database. An example predicted reaction by the RetroPath algorithm is shown. This reaction transforms the source Daidzein 4’-O-glucuronide into Daidzein and D-glucuronate, using a rule derived from the annotated reaction that produces Luteolin and D-glucuronate from Luteolin 7-O-glucuronide. 2D chemical structures were drawn using RDKit.

Fig. 2. Main metabolic features included in AGREDA_1.1.

a Representation of the different sub-classes of input phenolic compounds added to AGREDA_1.1. The number of compounds captured by AGREDA_1.1 for each sub-class is detailed in the legend, e.g. ‘Isoflavanoids 24’; (b) Barplot showing the percentage coverage of AGREDA_1.0 and AGREDA_1.1 in terms of phenolic compounds included in Phenol-Explorer. The number at the top of the bars is the total number of phenolic compounds for each sub-class, e.g. 86 compounds for Isoflavanoids; (c) Contribution of different phyla to the reactions added to AGREDA_1.1. The number of reactions added to AGREDA_1.1 present in each phylum is also provided in the legend, e.g. ‘Firmicutes 175’. Source Data are provided as a Source Data file.

Fig. 3. Functional analysis of AGREDA_1.1 with foods available in Phenol-Explorer19.

a Frequency of input phenolic compounds added to AGREDA_1.1 in the 40 foods of Phenol-Explorer (F1, F2, …, F40); (b) Degradation pathway of 3-Feruloylquinic acid (3-FQA) predicted by AGREDA_1.1. 2D chemical structures were drawn using RDKit; (c) Number of output microbial metabolites derived from the input compounds available in the 40 foods of Phenol-Explorer with AGREDA_1.0 and AGREDA_1.1. Source Data are provided as a Source Data file.

Fig. 4. Comparison between the predictions of AGREDA_1.017 and AGREDA_1.1 with in vitro experiments.

Representation of the presence of 63 output microbial compounds predicted in AGREDA_1.0 and AGREDA_1.1 to derive from the fermentation of lentils with children feces and measured with an untargeted metabolomics approach. “AFF2”, “AFF3”, “AFF4”, “AFF5”, “AFF6” and “AFF7” denote samples 2, 3, 4, 5, 6 and 7 from children allergic to cow’s milk, respectively; “CFF1”, “CFF2”, “CFF3”, “CFF4”, “CFF5”, “CFF6” and “CFF7” denote samples 1, 2, 3, 4, 5, 6 and 7 from celiac children, respectively; “LFF2”, “LFF3”, “LFF4” and “LFF6” denote samples 2, 3, 4 and 6 from lean children, respectively; “OFF1”, “OFF2”, “OFF3”, “OFF4”, “OFF5”, “OFF6” and “OFF7” denote samples 1, 2, 3, 4, 5, 6 and 7 from obese children, respectively; TP true positives, TN true negatives, FP false positives, FN false negatives. Source Data are provided as a Source Data file.