A data-driven approach for predicting the impact of drugs on the human microbiome

KNDM: A Knowledge Graph Transformer and Node Category Sensitive Contrastive Learning Model for Drug and Microbe Association Prediction

It has been proven that the microbiome in human bodies can promote or inhibit the treatment effects of the drugs by affecting their toxicities and activities. Therefore, identifying drug-related microbes helps in understanding how drugs exert their functions under the influence of these microbes. Most recent methods for drug-related microbe prediction are developed based on graph learning. However, those methods fail to fully utilize the diverse characteristics of drug and microbe entities from the perspective of a knowledge graph, as well as the contextual relationships among multiple meta-paths from the meta-path perspective. Moreover, previous methods overlook the consistency between the entity features derived from the knowledge graph and the node semantic features extracted from the meta-paths. To address these limitations, we propose a knowledge-graph transformer and node category-sensitive contrastive learning-based drug and microbe association prediction model (KNDM). This model learns the diverse features of drug and microbe entities, encodes the contextual relationships across multiple meta-paths, and integrates the feature consistency. First, we construct a knowledge graph consisting of drug and microbe entities, which aids in revealing similarities and associations between any two entities. Second, considering the heterogeneity of entities in the knowledge graph, we propose an entity category-sensitive transformer to integrate the diversity of multiple entity types and the various relationships among them. Third, multiple meta-paths are constructed to capture and embed the semantic relationships based on similarities and associations among drug and microbe nodes. A meta-path semantic feature learning strategy with recursive gating is proposed to capture specific semantic features of individual meta-paths while fusing contextual relationships among multiple meta-paths. Finally, we develop a node-category-sensitive contrastive learning strategy to enhance the consistency between entity features and node semantic features. Extensive experiments demonstrate that KNDM outperforms eight state-of-the-art drug-microbe association prediction models, while ablation studies validate the effectiveness of its key innovations. Additionally, case studies on candidate microbes associated with three drugs-curcumin, epigallocatechin gallate, and ciprofloxacin-further showcase KNDM's capability to identify potential drug-microbe associations.

Similarity of drug targets to human microbiome metaproteome promotes pharmacological promiscuity

Similarity between candidate drug targets and human proteins is commonly assessed to minimize the occurrence of side effects. Although numerous drugs have been found to disrupt the health of the human microbiome, no comprehensive comparison between established drug targets and the human microbiome metaproteome has yet been conducted. Therefore, herein, sequence and structure alignments between human and pathogen drug targets and representative human gut, oral, and vaginal microbiome metaproteomes were performed. Both human and pathogen drug targets were found to be similar in sequence, function, structure, and drug binding capacity to proteins in diverse pathogenic and non-pathogenic bacteria from all three microbiomes. The gut metaproteome was identified as particularly susceptible overall to off-target effects. Certain symptoms, such as infections and immune disorders, may be more common among drugs that non-selectively target host microbiota. These findings suggest that similarities between human microbiome metaproteomes and drug target candidates should be routinely checked.

Pre-trained molecular representations enable antimicrobial discovery

The rise in antimicrobial resistance poses a worldwide threat, reducing the efficacy of common antibiotics. Determining the antimicrobial activity of new chemical compounds through experimental methods remains time-consuming and costly. While compound-centric deep learning models promise to accelerate this search and prioritization process, current strategies require large amounts of custom training data. Here, we introduce a lightweight computational strategy for antimicrobial discovery that builds on MolE (Molecular representation through redundancy reduced Embedding), a self-supervised deep learning framework that leverages unlabeled chemical structures to learn task-independent molecular representations. By combining MolE representation learning with available, experimentally validated compound-bacteria activity data, we design a general predictive model that enables assessing compounds with respect to their antimicrobial potential. Our model correctly identifies recent growth-inhibitory compounds that are structurally distinct from current antibiotics. Using this approach, we discover de novo, and experimentally confirm, three human-targeted drugs as growth inhibitors of Staphylococcus aureus. This framework offers a viable, cost-effective strategy to accelerate antibiotic discovery.

MPEMDA: A multi-similarity integration approach with pre-completion and error correction for predicting microbe-drug associations

Exploring the associations between microbes and drugs offers valuable insights into their underlying mechanisms. Traditional wet lab experiments, while reliable, are often time-consuming and labor-intensive, making computational approaches an attractive alternative. Existing similarity-based machine learning models for predicting microbe-drug associations typically rely on integrated similarities as input, neglecting the unique contributions of individual similarities, which can compromise predictive accuracy. To overcome these limitations, we develop MPEMDA, a novel method that pre-completes the microbe-drug association matrix using various similarity combinations and employs a label propagation algorithm with error correction to predict microbe-drug associations. Compared with existing methods, MPEMDA simultaneously utilizes the integrated and individual similarities obtained through the Similarity Network Fusion (SNF) method to pre-complete the known drug-microbe association matrix, followed by error correction to optimize the predictive scores generated by the label propagation algorithm. Experimental results on three benchmark datasets show that MPEMDA outperforms state-of-the-art methods in both the 5-fold cross-validation and de novo test. Additionally, case studies on drugs and microbes highlight the method's strong potential to identify novel microbe-drug associations. The MPEMDA code is available at https://github.com/lyx8527/MPEMDA.

IUPHAR themed review: The gut microbiome in schizophrenia

Gut microbial dysbiosis or altered gut microbial consortium, in schizophrenia suggests a pathogenic role through the gut-brain axis, influencing neuroinflammatory and neurotransmitter pathways critical to psychotic, affective, and cognitive symptoms. Paradoxically, conventional psychotropic interventions may exacerbate this dysbiosis, with antipsychotics, particularly olanzapine, demonstrating profound effects on microbial architecture through disruption of bacterial phyla ratios, diminished taxonomic diversity, and attenuated short-chain fatty acid synthesis. To address these challenges, novel therapeutic strategies targeting the gut microbiome, encompassing probiotic supplementation, prebiotic compounds, faecal microbiota transplantation, and rationalised co-pharmacotherapy, show promise in attenuating antipsychotic-induced metabolic disruptions while enhancing therapeutic efficacy. Harnessing such insights, precision medicine approaches promise to transform antipsychotic prescribing practices by identifying patients at risk of metabolic side effects based on their microbial profiles. This IUPHAR review collates the current literature landscape of the gut-brain axis and its intricate relationship with schizophrenia while advocating for integrating microbiome assessments and therapeutic management. Such a fundamental shift in proposing microbiome-informed psychotropic prescriptions to optimise therapeutic efficacy and reduce adverse metabolic impacts would align antipsychotic treatments with microbiome safety, prioritising 'gut-neutral' or gut-favourable drugs to safeguard long-term patient outcomes in schizophrenia therapy.

Molecular Mimicry Between Gut Microbiome and Rheumatoid Arthritis: Current Concepts

Rheumatoid arthritis (RA) represents an autoimmune condition impacted by a combination of genetic and environmental factors, with the gut microbiome (GMB) being one of the influential environmental factors. Patients with RA display notable modifications in the composition of their GMB, characterised by decreased diversity and distinct bacterial alterations. The GMB, comprising an extensive array of approximately 35,000 bacterial species residing within the gastrointestinal tract, has garnered considerable attention as a pivotal contributor to both human health and the pathogenesis of diseases. This article provides an in-depth exploration of the intricate involvement of the GMB in the context of RA. The oral-GMB axis highlights the complex role of bacteria in RA pathogenesis by producing antibodies to citrullinated proteins (ACPAs) through molecular mimicry. Dysbiosis affects Tregs, cytokine levels, and RA disease activity, suggesting that regulating cytokines could be a strategy for managing inflammation in RA. The GMB also has significant implications for drug responses and toxicity, giving rise to the field of pharmacomicrobiomics. The composition of the microbiota can impact the efficacy and toxicity of drugs, while the microbiota's metabolites can influence drug response. Recent research has identified specific bacteria, metabolites, and immune responses associated with RA, offering potential targets for personalised management. However, several challenges, including the variation in microbial composition, establishing causality, accounting for confounding factors, and translating findings into clinical practice, need to be addressed. Microbiome-targeted therapy is still in its early stages and requires further research and standardisation for effective implementation.

Microplastic diversity increases the abundance of antibiotic resistance genes in soil

The impact of microplastics on antibiotic resistance has attracted widespread attention. However, previous studies primarily focused on the effects of individual microplastics. In reality, diverse microplastic types accumulate in soil, and it remains less well studied whether microplastic diversity (i.e., variations in color, shape or polymer type) can be an important driver of increased antibiotic resistance gene (ARG) abundance. Here, we employed microcosm studies to investigate the effects of microplastic diversity on soil ARG dynamics through metagenomic analysis. Additionally, we evaluated the associated potential health risks by profiling virulence factor genes (VFGs) and mobile genetic elements (MGEs). Our findings reveal that as microplastic diversity increases, there is a corresponding rise in the abundance of soil ARGs, VFGs and MGEs. We further identified microbial adaptive strategies involving genes (changed genetic diversity), community (increased specific microbes), and functions (enriched metabolic pathways) that correlate with increased ARG abundance and may thus contribute to ARG dissemination. Additional global change factors, including fungicide application and plant diversity reduction, also contributed to elevated ARG abundance. Our findings suggest that, in addition to considering contamination levels, it is crucial to monitor microplastic diversity in ecosystems due to their potential role in driving the dissemination of antibiotic resistance through multiple pathways.

Natural Compounds for Bone Remodeling: A Computational and Experimental Approach Targeting Bone Metabolism-Related Proteins

Osteoporosis, characterized by reduced bone density and increased fracture risk, affects over 200 million people worldwide, predominantly older adults and postmenopausal women. The disruption of the balance between bone-forming osteoblasts and bone-resorbing osteoclasts underlies osteoporosis pathophysiology. Standard treatment includes lifestyle modifications, calcium and vitamin D supplementation and specific drugs that either inhibit osteoclasts or stimulate osteoblasts. However, these treatments have limitations, including side effects and compliance issues. Natural products have emerged as potential osteoporosis therapeutics, but their mechanisms of action remain poorly understood. In this study, we investigate the efficacy of natural compounds in modulating molecular targets relevant to osteoporosis, focusing on the Mitogen-Activated Protein Kinase (MAPK) pathway and the gut microbiome's influence on bone homeostasis. Using an in silico and in vitro methodology, we have identified quercetin as a promising candidate in modulating MAPK activity, offering a potential therapeutic perspective for osteoporosis treatment.

Multi-scale topology and position feature learning and relationship-aware graph reasoning for prediction of drug-related microbes

MOTIVATION

The human microbiome may impact the effectiveness of drugs by modulating their activities and toxicities. Predicting candidate microbes for drugs can facilitate the exploration of the therapeutic effects of drugs. Most recent methods concentrate on constructing of the prediction models based on graph reasoning. They fail to sufficiently exploit the topology and position information, the heterogeneity of multiple types of nodes and connections, and the long-distance correlations among nodes in microbe-drug heterogeneous graph.

RESULTS

We propose a new microbe-drug association prediction model, NGMDA, to encode the position and topological features of microbe (drug) nodes, and fuse the different types of features from neighbors and the whole heterogeneous graph. First, we formulate the position and topology features of microbe (drug) nodes by t-step random walks, and the features reveal the topological neighborhoods at multiple scales and the position of each node. Second, as the features of nodes are high-dimensional and sparse, we designed an embedding enhancement strategy based on supervised fully connected autoencoders to form the embeddings with representative features and the more discriminative node distributions. Third, we propose an adaptive neighbor feature fusion module, which fuses features of neighbors by the constructed position- and topology-sensitive heterogeneous graph neural networks. A novel self-attention mechanism is developed to estimate the importance of the position and topology of each neighbor to a target node. Finally, a heterogeneous graph feature fusion module is constructed to learn the long-distance correlations among the nodes in the whole heterogeneous graph by a relationship-aware graph transformer. Relationship-aware graph transformer contains the strategy for encoding the connection relationship types among the nodes, which is helpful for integrating the diverse semantics of these connections. The extensive comparison experimental results demonstrate NGMDA's superior performance over five state-of-the-art prediction methods. The ablation experiment shows the contributions of the multi-scale topology and position feature learning, the embedding enhancement strategy, the neighbor feature fusion, and the heterogeneous graph feature fusion. Case studies over three drugs further indicate that NGMDA has ability in discovering the potential drug-related microbes.

AVAILABILITY AND IMPLEMENTATION

Source codes and Supplementary Material are available at https://github.com/pingxuan-hlju/NGMDA.

Orally Administered Drugs and Their Complicated Relationship with Our Gastrointestinal Tract

Orally administered compounds represent the great majority of all pharmaceutical compounds produced for human use and are the most popular among patients since they are practical and easy to self-administer. Following ingestion, orally administered drugs begin a "perilous" journey down the gastrointestinal tract and their bioavailability is modulated by numerous factors. The gastrointestinal (GI) tract anatomy can modulate drug bioavailability and accounts for interpatient drug response heterogeneity. Furthermore, host genetics is a contributor to drug bioavailability modulation. Importantly, a component of the GI tract that has been gaining notoriety with regard to drug treatment interactions is the gut microbiota, which shares a two-way interaction with pharmaceutical compounds in that they can be influenced by and are able to influence administered drugs. Overall, orally administered drugs are a patient-friendly treatment option. However, during their journey down the GI tract, there are numerous host factors that can modulate drug bioavailability in a patient-specific manner.