Predicting drug-microbiome interactions with machine learning

Exploring the interactions of JAK inhibitor and S1P receptor modulator drugs with the human gut microbiome: Implications for colonic drug delivery and inflammatory bowel disease

The gut microbiota is a complex ecosystem, home to hundreds of bacterial species and a vast repository of enzymes capable of metabolising a wide range of pharmaceuticals. Several drugs have been shown to affect negatively the composition and function of the gut microbial ecosystem. Janus Kinase (JAK) inhibitors and Sphingosine-1-phosphate (S1P) receptor modulators are drugs recently approved for inflammatory bowel disease through an immediate release formulation and would potentially benefit from colonic targeted delivery to enhance the local drug concentration at the diseased site. However, their impact on the human gut microbiota and susceptibility to bacterial metabolism remain unexplored. With the use of calorimetric, optical density measurements, and metagenomics next-generation sequencing, we show that JAK inhibitors (tofacitinib citrate, baricitinib, filgotinib) have a minor impact on the composition of the human gut microbiota, while ozanimod exerts a significant antimicrobial effect, leading to a prevalence of the Enterococcus genus and a markedly different metabolic landscape when compared to the untreated microbiota. Moreover, ozanimod, unlike the JAK inhibitors, is the only drug subject to enzymatic degradation by the human gut microbiota sourced from six healthy donors. Overall, given the crucial role of the gut microbiome in health, screening assays to investigate the interaction of drugs with the microbiota should be encouraged for the pharmaceutical industry as a standard in the drug discovery and development process.

A graph neural network approach for predicting drug susceptibility in the human microbiome

Recent studies have illuminated the critical role of the human microbiome in maintaining health and influencing the pharmacological responses of drugs. Clinical trials, encompassing approximately 150 drugs, have unveiled interactions with the gastrointestinal microbiome, resulting in the conversion of these drugs into inactive metabolites. It is imperative to explore the field of pharmacomicrobiomics during the early stages of drug discovery, prior to clinical trials. To achieve this, the utilization of machine learning and deep learning models is highly desirable. In this study, we have proposed graph-based neural network models, namely GCN, GAT, and GINCOV models, utilizing the SMILES dataset of drug microbiome. Our primary objective was to classify the susceptibility of drugs to depletion by gut microbiota. Our results indicate that the GINCOV surpassed the other models, achieving impressive performance metrics, with an accuracy of 93% on the test dataset. This proposed Graph Neural Network (GNN) model offers a rapid and efficient method for screening drugs susceptible to gut microbiota depletion and also encourages the improvement of patient-specific dosage responses and formulations.

Identification of microbe-disease signed associations via multi-scale variational graph autoencoder based on signed message propagation

BACKGROUND

Plenty of clinical and biomedical research has unequivocally highlighted the tremendous significance of the human microbiome in relation to human health. Identifying microbes associated with diseases is crucial for early disease diagnosis and advancing precision medicine.

RESULTS

Considering that the information about changes in microbial quantities under fine-grained disease states helps to enhance a comprehensive understanding of the overall data distribution, this study introduces MSignVGAE, a framework for predicting microbe-disease sign associations using signed message propagation. MSignVGAE employs a graph variational autoencoder to model noisy signed association data and extends the multi-scale concept to enhance representation capabilities. A novel strategy for propagating signed message in signed networks addresses heterogeneity and consistency among nodes connected by signed edges. Additionally, we utilize the idea of denoising autoencoder to handle the noise in similarity feature information, which helps overcome biases in the fused similarity data. MSignVGAE represents microbe-disease associations as a heterogeneous graph using similarity information as node features. The multi-class classifier XGBoost is utilized to predict sign associations between diseases and microbes.

CONCLUSIONS

MSignVGAE achieves AUROC and AUPR values of 0.9742 and 0.9601, respectively. Case studies on three diseases demonstrate that MSignVGAE can effectively capture a comprehensive distribution of associations by leveraging signed information.

AI-powered microscopy image analysis for parasitology: integrating human expertise

Microscopy image analysis plays a pivotal role in parasitology research. Deep learning (DL), a subset of artificial intelligence (AI), has garnered significant attention. However, traditional DL-based methods for general purposes are data-driven, often lacking explainability due to their black-box nature and sparse instructional resources. To address these challenges, this article presents a comprehensive review of recent advancements in knowledge-integrated DL models tailored for microscopy image analysis in parasitology. The massive amounts of human expert knowledge from parasitologists can enhance the accuracy and explainability of AI-driven decisions. It is expected that the adoption of knowledge-integrated DL models will open up a wide range of applications in the field of parasitology.

Polysaccharides extracted from larvae of Lucilia sericata ameliorated ulcerative colitis by regulating the intestinal barrier and gut microbiota

Pest management technology has been a promising bioconversion method for waste resource utilization. Unlike many pests that consume waste, the larvae of Lucilia sericata, also known as maggots, have many outstanding advantages as following: with their strong adaption to environment and not easily infected and exhibiting a medicinal nutritional value. Herein, the potential efficacies of maggot polysaccharides (MP), as well as their underlying mechanisms, were explored in Dextran sulfate sodium (DSS)-induced colitis mice and TNF-α-elicited Caco-2 cells. We extracted two bioactive polysaccharides from maggots, MP-80 and MP-L, whose molecular weights were 4.25 × 103 and 2.28 × 103 g/mol, respectively. MP-80 and MP-L contained nine sugar residues: 1,4-α-Arap, 1,3-β-Galp, 1,4,6-β-Galp, 1,6-α-Glcp, 1-α-Glcp, 1,4-β-Glcp, 1-β-Xylp, 1,2-α-Manp, and 1-β-Manp. We demonstrated that MP-80 and MP-L significantly ameliorated DSS-induced symptoms and histopathological damage. Immuno-analysis revealed that compared with MP-L, MP-80 could better restore intestinal barrier and reduced inflammation by suppressing NLRP3/NF-κB pathways, which might be attributed to its enriched galactose fraction. Moreover, 16S rRNA sequencing revealed that MP-80 and MP-L both improved the dysbiosis and diversity of gut microbiota and acted on multiple microbial functions. Our study sheds new light on the possibility of using maggot polysaccharides as an alternative therapy for colitis.

LCASPMDA: a computational model for predicting potential microbe-drug associations based on learnable graph convolutional attention networks and self-paced iterative sampling ensemble

Introduction

Numerous studies show that microbes in the human body are very closely linked to the human host and can affect the human host by modulating the efficacy and toxicity of drugs. However, discovering potential microbe-drug associations through traditional wet labs is expensive and time-consuming, hence, it is important and necessary to develop effective computational models to detect possible microbe-drug associations.

Methods

In this manuscript, we proposed a new prediction model named LCASPMDA by combining the learnable graph convolutional attention network and the self-paced iterative sampling ensemble strategy to infer latent microbe-drug associations. In LCASPMDA, we first constructed a heterogeneous network based on newly downloaded known microbe-drug associations. Then, we adopted the learnable graph convolutional attention network to learn the hidden features of nodes in the heterogeneous network. After that, we utilized the self-paced iterative sampling ensemble strategy to select the most informative negative samples to train the Multi-Layer Perceptron classifier and put the newly-extracted hidden features into the trained MLP classifier to infer possible microbe-drug associations.

Results and discussion

Intensive experimental results on two different public databases including the MDAD and the aBiofilm showed that LCASPMDA could achieve better performance than state-of-the-art baseline methods in microbe-drug association prediction.

Exploring the influence of the microbiome on the pharmacology of anti-asthmatic drugs

The microbiome is increasingly implicated in playing a role in physiology and pharmacology; in this review, we investigate the literature on the possibility of bacterial influence on the pharmacology of anti-asthmatic drugs, and the potential impact this has on asthmatic patients. Current knowledge in this area of research reveals an interaction between the gut and lung microbiome and the development of asthma. The influence of microbiome on the pharmacokinetics and pharmacodynamics of anti-asthmatic drugs is limited; however, understanding this interaction will assist in creating a more efficient treatment approach. This literature review highlighted that bioaccumulation and biotransformation in the presence of certain gut bacterial strains could affect drug metabolism in anti-asthmatic drugs. Furthermore, the bacterial richness in the lungs and the gut can influence drug efficacy and could also play a role in drug response. The implications of the above findings suggest that the microbiome is a contributing factor to an individuals' pharmacological response to anti-asthmatic drugs. Hence, future directions for research should follow investigating how these processes affect asthmatic patients and consider the role of the microbiome on drug efficacy and modify treatment guidelines accordingly.

NMGMDA: a computational model for predicting potential microbe-drug associations based on minimize matrix nuclear norm and graph attention network

The prediction of potential microbe-drug associations is of great value for drug research and development, especially, methods, based on deep learning, have been achieved significant improvement in bio-medicine. In this manuscript, we proposed a novel computational model named NMGMDA based on the nuclear norm minimization and graph attention network to infer latent microbe-drug associations. Firstly, we created a heterogeneous microbe-drug network in NMGMDA by fusing the drug and microbe similarities with the established drug-microbe associations. After this, by using GAT and NNM to calculate the predict scores. Lastly, we created a fivefold cross validation framework to assess the new model NMGMDA's progressiveness. According to the simulation results, NMGMDA outperforms some of the most advanced methods, with a reliable AUC of 0.9946 on both MDAD and aBioflm databases. Furthermore, case studies on Ciprofloxacin, Moxifoxacin, HIV-1 and Mycobacterium tuberculosis were carried out in order to assess the effectiveness of NMGMDA even more. The experimental results demonstrated that, following the removal of known correlations from the database, 16 and 14 medications as well as 19 and 17 microbes in the top 20 predictions were validated by pertinent literature. This demonstrates the potential of our new model, NMGMDA, to reach acceptable prediction performance.

The triple interactions between gut microbiota, mycobiota and host immunity

The gut microbiome is mainly composed of microbiota and mycobiota, both of which play important roles in the development of the host immune system, metabolic regulation, and maintenance of intestinal homeostasis. With the increasing awareness of the pathogenic essence of infectious, immunodeficiency, and tumor-related diseases, the interactions between gut bacteria, fungi, and host immunity have been shown to directly influence the disease process or final therapeutic outcome, and collaborative and antagonistic relationships are commonly found between bacteria and fungi. Interventions represented by probiotics, prebiotics, engineered probiotics, fecal microbiota transplantation (FMT), and drugs can effectively modulate the triple interactions. In particular, traditional probiotics represented by Bifidobacterium and Lactobacillus and next-generation probiotics represented by Akkermansia muciniphila and Faecalibacterium prausnitzii showed a high enrichment trend in the gut of patients with a high response to inflammation remission and tumor immunotherapy, which predicts the potential medicinal value of these beneficial microbial formulations. However, there are bottlenecks in all these interventions that need to be broken. Meanwhile, further unraveling the underlying mechanisms of the "triple interactions" model can guide precise interventions and ultimately improve the efficiency of interventions on the host gut microbiome and immune modulation, thus directly or indirectly improving anti-inflammatory and tumor immunotherapy effects.

Drug-microbiota interactions: an emerging priority for precision medicine

Individual variability in drug response (IVDR) can be a major cause of adverse drug reactions (ADRs) and prolonged therapy, resulting in a substantial health and economic burden. Despite extensive research in pharmacogenomics regarding the impact of individual genetic background on pharmacokinetics (PK) and pharmacodynamics (PD), genetic diversity explains only a limited proportion of IVDR. The role of gut microbiota, also known as the second genome, and its metabolites in modulating therapeutic outcomes in human diseases have been highlighted by recent studies. Consequently, the burgeoning field of pharmacomicrobiomics aims to explore the correlation between microbiota variation and IVDR or ADRs. This review presents an up-to-date overview of the intricate interactions between gut microbiota and classical therapeutic agents for human systemic diseases, including cancer, cardiovascular diseases (CVDs), endocrine diseases, and others. We summarise how microbiota, directly and indirectly, modify the absorption, distribution, metabolism, and excretion (ADME) of drugs. Conversely, drugs can also modulate the composition and function of gut microbiota, leading to changes in microbial metabolism and immune response. We also discuss the practical challenges, strategies, and opportunities in this field, emphasizing the critical need to develop an innovative approach to multi-omics, integrate various data types, including human and microbiota genomic data, as well as translate lab data into clinical practice. To sum up, pharmacomicrobiomics represents a promising avenue to address IVDR and improve patient outcomes, and further research in this field is imperative to unlock its full potential for precision medicine.

New era of artificial intelligence and machine learning-based detection, diagnosis, and therapeutics in Parkinson's disease

Parkinson's disease (PD) is characterized by the loss of neuronal cells, which leads to synaptic dysfunction and cognitive defects. Despite the advancements in treatment strategies, the management of PD is still a challenging event. Early prediction and diagnosis of PD are of utmost importance for effective management of PD. In addition, the classification of patients with PD as compared to normal healthy individuals also imposes drawbacks in the early diagnosis of PD. To address these challenges, artificial intelligence (AI) and machine learning (ML) models have been implicated in the diagnosis, prediction, and treatment of PD. Recent times have also demonstrated the implication of AI and ML models in the classification of PD based on neuroimaging methods, speech recording, gait abnormalities, and others. Herein, we have briefly discussed the role of AI and ML in the diagnosis, treatment, and identification of novel biomarkers in the progression of PD. We have also highlighted the role of AI and ML in PD management through altered lipidomics and gut-brain axis. We briefly explain the role of early PD detection through AI and ML algorithms based on speech recordings, handwriting patterns, gait abnormalities, and neuroimaging techniques. Further, the review discuss the potential role of the metaverse, the Internet of Things, and electronic health records in the effective management of PD to improve the quality of life. Lastly, we also focused on the implementation of AI and ML-algorithms in neurosurgical process and drug discovery.

Crohn's Disease Prediction Using Sequence Based Machine Learning Analysis of Human Microbiome

Human microbiota refers to the trillions of microorganisms that inhabit our bodies and have been discovered to have a substantial impact on human health and disease. By sampling the microbiota, it is possible to generate massive quantities of data for analysis using Machine Learning algorithms. In this study, we employed several modern Machine Learning techniques to predict Inflammatory Bowel Disease using raw sequence data. The dataset was obtained from NCBI preprocessed graph representations and converted into a structured form. Seven well-known Machine Learning frameworks, including Random Forest, Support Vector Machines, Extreme Gradient Boosting, Light Gradient Boosting Machine, Gaussian Naïve Bayes, Logistic Regression, and k-Nearest Neighbor, were used. Grid Search was employed for hyperparameter optimization. The performance of the Machine Learning models was evaluated using various metrics such as accuracy, precision, fscore, kappa, and area under the receiver operating characteristic curve. Additionally, Mc Nemar's test was conducted to assess the statistical significance of the experiment. The data was constructed using k-mer lengths of 3, 4 and 5. The Light Gradient Boosting Machine model overperformed over other models with 67.24%, 74.63% and 76.47% accuracy for k-mer lengths of 3, 4 and 5, respectively. The LightGBM model also demonstrated the best performance in each metric. The study showed promising results predicting disease from raw sequence data. Finally, Mc Nemar's test results found statistically significant differences between different Machine Learning approaches.

In Vivo Metabolite Profiling of DMU-212 in ApcMin/+ Mice Using UHPLC-Q/Orbitrap/LTQ MS

3,4,5,4'-Trans-tetramethoxystilbene (Synonyms: DMU-212) is a resveratrol analogue with stronger antiproliferative activity and more bioavailability. However, the metabolite characterization of this component remains insufficient. An efficient strategy was proposed for the comprehensive in vivo metabolite profiling of DMU-212 after oral administration in Apc^Min/+ mice based on the effectiveness of the medicine. Ultra-high performance liquid chromatography-quadrupole/orbitrap/linear ion trap mass spectrometry (UHPLC-Q/Orbitrap/LTQ MS) in the AcquireX^TM intelligent data acquisition mode, combining the exact mass and structural information, was established for the profiling and identification of the metabolites of DMU-212 in vivo, and the possible metabolic pathways were subsequently proposed after the oral dose of 240mg/kg for 3 weeks in the colorectal adenoma (CRA) spontaneous model Apc^Min/+ mice. A total of 63 metabolites of DMU-212 were tentatively identified, including 48, 48, 34 and 28 metabolites in the Apc^Min/+ mice's intestinal contents, liver, serum, and colorectal tissues, respectively. The metabolic pathways, including demethylation, oxidation, desaturation, methylation, acetylation, glucuronide and cysteine conjugation were involved in the metabolism. Additionally, further verification of the representative active metabolites was employed using molecular docking analysis. This study provides important information for the further investigation of the active constituents of DMU-212 and its action mechanisms for CRA prevention.

Clinical Diagnostics of Bacterial Infections and Their Resistance to Antibiotics-Current State and Whole Genome Sequencing Implementation Perspectives

Antimicrobial resistance (AMR), defined as the ability of microorganisms to withstand antimicrobial treatment, is responsible for millions of deaths annually. The rapid spread of AMR across continents warrants systematic changes in healthcare routines and protocols. One of the fundamental issues with AMR spread is the lack of rapid diagnostic tools for pathogen identification and AMR detection. Resistance profile identification often depends on pathogen culturing and thus may last up to several days. This contributes to the misuse of antibiotics for viral infection, the use of inappropriate antibiotics, the overuse of broad-spectrum antibiotics, or delayed infection treatment. Current DNA sequencing technologies offer the potential to develop rapid infection and AMR diagnostic tools that can provide information in a few hours rather than days. However, these techniques commonly require advanced bioinformatics knowledge and, at present, are not suited for routine lab use. In this review, we give an overview of the AMR burden on healthcare, describe current pathogen identification and AMR screening methods, and provide perspectives on how DNA sequencing may be used for rapid diagnostics. Additionally, we discuss the common steps used for DNA data analysis, currently available pipelines, and tools for analysis. Direct, culture-independent sequencing has the potential to complement current culture-based methods in routine clinical settings. However, there is a need for a minimum set of standards in terms of evaluating the results generated. Additionally, we discuss the use of machine learning algorithms regarding pathogen phenotype detection (resistance/susceptibility to an antibiotic).

Longevity of centenarians is reflected by the gut microbiome with youth-associated signatures

Centenarians are an excellent model to study the relationship between the gut microbiome and longevity. To characterize the gut microbiome signatures of aging, we conducted a cross-sectional investigation of 1,575 individuals (20-117 years) from Guangxi province of China, including 297 centenarians (n = 45 with longitudinal sampling). Compared to their old adult counterparts, centenarians displayed youth-associated features in the gut microbiome characterized by an over-representation of a Bacteroides-dominated enterotype, increase in species evenness, enrichment of potentially beneficial Bacteroidetes and depletion of potential pathobionts. Health status stratification in older individuals did not alter the directional trends for these signature comparisons but revealed more apparent associations in less healthy individuals. Importantly, longitudinal analysis of centenarians across a 1.5-year period indicated that the youth-associated gut microbial signatures were enhanced with regard to increased evenness, reduction in interindividual variation and stability of Bacteroides, and that centenarians with low microbial evenness were prone to large microbiome instability during aging. These results together highlight a youth-related aging pattern of the gut microbiome for long-lived individuals.

Decipher enzymes from human microbiota for drug discovery and development

The human microbiota plays an important role in human health and contributes to the metabolism of therapeutic drugs affecting their potency. However, the current knowledge on human gut bacterial metabolism is limited and lacks an understanding of the underlying mechanisms of observed drug biotransformations. Despite the complexity of the gut microbial community, genomic and metagenomic sequencing provides insights into the diversity of chemical reactions that can be carried out by the microbiota and poses new challenges to functionally annotate thousands of bacterial enzymes. Here, we outline methods to systematically address the structural and functional space of the human microbiome, highlighting a combination of in silico and in vitro approaches. Systematic knowledge about microbial enzymes could eventually be applied for personalized therapy, the development of prodrugs and modulators of unwanted bacterial activity, and the further discovery of new antibiotics.

GACNNMDA: a computational model for predicting potential human microbe-drug associations based on graph attention network and CNN-based classifier

As new drug targets, human microbes are proven to be closely related to human health. Effective computational methods for inferring potential microbe-drug associations can provide a useful complement to conventional experimental methods and will facilitate drug research and development. However, it is still a challenging work to predict potential interactions for new microbes or new drugs, since the number of known microbe-drug associations is very limited at present. In this manuscript, we first constructed two heterogeneous microbe-drug networks based on multiple measures of similarity of microbes and drugs, and known microbe-drug associations or known microbe-disease-drug associations, respectively. And then, we established two feature matrices for microbes and drugs through concatenating various attributes of microbes and drugs. Thereafter, after taking these two feature matrices and two heterogeneous microbe-drug networks as inputs of a two-layer graph attention network, we obtained low dimensional feature representations for microbes and drugs separately. Finally, through integrating low dimensional feature representations with two feature matrices to form the inputs of a convolutional neural network respectively, a novel computational model named GACNNMDA was designed to predict possible scores of microbe-drug pairs. Experimental results show that the predictive performance of GACNNMDA is superior to existing advanced methods. Furthermore, case studies on well-known microbes and drugs demonstrate the effectiveness of GACNNMDA as well. Source codes and supplementary materials are available at: https://github.com/tyqGitHub/TYQ/tree/master/GACNNMDA.

Dietary interventions, the gut microbiome, and aggressive behavior: Review of research evidence and potential next steps

Research in biosocial criminology and other related disciplines has established links between nutrition and aggressive behavior. In addition to observational studies, randomized trials of nutritional supplements like vitamins, omega-3 fatty acids, and folic acid provide evidence of the dietary impact on aggression. However, the exact mechanism of the diet-aggression link is not well understood. The current article proposes that the gut microbiome plays an important role in the process, with the microbiota-gut-brain axis serving as such a mediating mechanism between diet and behavior. Based on animal and human studies, this review synthesizes a wide array of research across several academic fields: from the effects of dietary interventions on aggression, to the results of microbiota transplantation on socioemotional and behavioral outcomes, to the connections between early adversity, stress, microbiome, and aggression. Possibilities for integrating the microbiotic perspective with the more traditional, sociologically oriented theories in criminology are discussed, using social disorganization and self-control theories as examples. To extend the existing lines of research further, the article considers harnessing the experimental potential of noninvasive and low-cost dietary interventions to help establish the causal impact of the gut microbiome on aggressive behavior, while adhering to the high ethical standards and modern research requirements. Implications of this research for criminal justice policy and practice are essential: not only can it help determine whether the improved gut microbiome functioning moderates aggressive and violent behavior but also provide ways to prevent and reduce such behavior, alone or in combination with other crime prevention programs.

Oxymatrine ameliorates white matter injury by modulating gut microbiota after intracerebral hemorrhage in mice

INTRODUCTION

White matter injury (WMI) significantly affects neurobehavioral recovery in intracerebral hemorrhage (ICH) patients. Gut dysbiosis plays an important role in the pathogenesis of neurological disorders. Oxymatrine (OMT) has therapeutic effects on inflammation-mediated diseases. Whether OMT exerts therapeutic effects on WMI after ICH and the role of gut microbiota involved in this process is largely unknown.

METHODS

Neurological deficits, WMI, gut microbial composition, intestinal barrier function, and systemic inflammation were investigated after ICH. Fecal microbiota transplantation (FMT) was performed to elucidate the role of gut microbiota in the pathogenesis of ICH.

RESULTS

OMT promoted long-term neurological function recovery and ameliorated WMI in the peri-hematoma region and distal corticospinal tract (CST) region after ICH. ICH induced significant and persistent gut dysbiosis, which was obviously regulated by OMT. In addition, OMT alleviated intestinal barrier dysfunction and systemic inflammation. Correlation analysis revealed that gut microbiota alteration was significantly correlated with inflammation, intestinal barrier permeability, and neurological deficits after ICH. Moreover, OMT-induced gut microbiota alteration could confer protection against neurological deficits and intestinal barrier disruption.

CONCLUSIONS

Our study demonstrates that OMT ameliorates ICH-induced WMI and neurological deficits by modulating gut microbiota.

GSAMDA: a computational model for predicting potential microbe–drug associations based on graph attention network and sparse autoencoder

Background

Clinical studies show that microorganisms are closely related to human health, and the discovery of potential associations between microbes and drugs will facilitate drug research and development. However, at present, few computational methods for predicting microbe–drug associations have been proposed.

Results

In this work, we proposed a novel computational model named GSAMDA based on the graph attention network and sparse autoencoder to infer latent microbe–drug associations. In GSAMDA, we first built a heterogeneous network through integrating known microbe–drug associations, microbe similarities and drug similarities. And then, we adopted a GAT-based autoencoder and a sparse autoencoder module respectively to learn topological representations and attribute representations for nodes in the newly constructed heterogeneous network. Finally, based on these two kinds of node representations, we constructed two kinds of feature matrices for microbes and drugs separately, and then, utilized them to calculate possible association scores for microbe–drug pairs.

Conclusion

A novel computational model is proposed for predicting potential microbe–drug associations based on graph attention network and sparse autoencoder. Compared with other five state-of-the-art competitive methods, the experimental results illustrated that our model can achieve better performance. Moreover, case studies on two categories of representative drugs and microbes further demonstrated the effectiveness of our model as well.

Enterorenal crosstalks in diabetic nephropathy and novel therapeutics targeting the gut microbiota

The role of gut-kidney crosstalk in the progression of diabetic nephropathy (DN) is receiving increasing concern. On one hand, the decline in renal function increases circulating uremic toxins and affects the composition and function of gut microbiota. On the other hand, intestinal dysbiosis destroys the epithelial barrier, leading to increased exposure to endotoxins, thereby exacerbating kidney damage by inducing systemic inflammation. Dietary inventions, such as higher fiber intake, prebiotics, probiotics, postbiotics, fecal microbial transplantation (FMT), and engineering bacteria and phages, are potential microbiota-based therapies for DN. Furthermore, novel diabetic agents, such as glucagon-like peptide-1 (GLP-1) receptor agonists, dipeptidyl peptidase-4 (DPP-4) inhibitors, and sodium-dependent glucose transporter-2 (SGLT-2) inhibitors, may affect the progression of DN partly through gut microbiota. In the current review, we mainly summarize the evidence concerning the gut-kidney axis in the advancement of DN and discuss therapies targeting the gut microbiota, expecting to provide new insight into the clinical treatment of DN.

Perspective: Leveraging the Gut Microbiota to Predict Personalized Responses to Dietary, Prebiotic, and Probiotic Interventions

Humans often show variable responses to dietary, prebiotic, and probiotic interventions. Emerging evidence indicates that the gut microbiota is a key determinant for this population heterogeneity. Here, we provide an overview of some of the major computational and experimental tools being applied to critical questions of microbiota-mediated personalized nutrition and health. First, we discuss the latest advances in in silico modeling of the microbiota-nutrition-health axis, including the application of statistical, mechanistic, and hybrid artificial intelligence models. Second, we address high-throughput in vitro techniques for assessing interindividual heterogeneity, from ex vivo batch culturing of stool and continuous culturing in anaerobic bioreactors, to more sophisticated organ-on-a-chip models that integrate both host and microbial compartments. Third, we explore in vivo approaches for better understanding of personalized, microbiota-mediated responses to diet, prebiotics, and probiotics, from nonhuman animal models and human observational studies, to human feeding trials and crossover interventions. We highlight examples of existing, consumer-facing precision nutrition platforms that are currently leveraging the gut microbiota. Furthermore, we discuss how the integration of a broader set of the tools and techniques described in this piece can generate the data necessary to support a greater diversity of precision nutrition strategies. Finally, we present a vision of a precision nutrition and healthcare future, which leverages the gut microbiota to design effective, individual-specific interventions.

Review on predicting pairwise relationships between human microbes, drugs and diseases: from biological data to computational models

In recent years, with the rapid development of techniques in bioinformatics and life science, a considerable quantity of biomedical data has been accumulated, based on which researchers have developed various computational approaches to discover potential associations between human microbes, drugs and diseases. This paper provides a comprehensive overview of recent advances in prediction of potential correlations between microbes, drugs and diseases from biological data to computational models. Firstly, we introduced the widely used datasets relevant to the identification of potential relationships between microbes, drugs and diseases in detail. And then, we divided a series of a lot of representative computing models into five major categories including network, matrix factorization, matrix completion, regularization and artificial neural network for in-depth discussion and comparison. Finally, we analysed possible challenges and opportunities in this research area, and at the same time we outlined some suggestions for further improvement of predictive performances as well.

Advancing pharmacy and healthcare with virtual digital technologies

Digitalisation of the healthcare sector promises to revolutionise patient healthcare globally. From the different technologies, virtual tools including artificial intelligence, blockchain, virtual, and augmented reality, to name but a few, are providing significant benefits to patients and the pharmaceutical sector alike, ranging from improving access to clinicians and medicines, as well as improving real-time diagnoses and treatments. Indeed, it is envisioned that such technologies will communicate together in real-time, as well as with their physical counterparts, to create a large-scale, cyber healthcare system. Despite the significant benefits that virtual-based digital health technologies can bring to patient care, a number of challenges still remain, ranging from data security to acceptance within the healthcare sector. This review provides a timely account of the benefits and challenges of virtual health interventions, as well an outlook on how such technologies can be transitioned from research-focused towards real-world healthcare and pharmaceutical applications to transform treatment pathways for patients worldwide.

Active Machine learning for formulation of precision probiotics

It is becoming clear that the human gut microbiome is critical to health and well-being, with increasing evidence demonstrating that dysbiosis can promote disease. Increasingly, precision probiotics are being investigated as investigational drug products for restoration of healthy microbiome balance. To reach the distal gut alive where the density of microbiota is highest, oral probiotics should be protected from harsh conditions during transit through the stomach and small intestines. At present, few probiotic formulations are designed with this delivery strategy in mind. This study employs an emerging machine learning (ML) technique, known as active ML, to predict how excipients at pharmaceutically relevant concentrations affect the intestinal proliferation of a common probiotic, Lactobacillus paracasei. Starting with a labelled dataset of just 6 bacteria-excipient interactions, active ML was able to predict the effects of a further 111 excipients using uncertainty sampling. The average certainty of the final model was 67.70% and experimental validation demonstrated that 3/4 excipient-probiotic interactions could be correctly predicted. The model can be used to enable superior probiotic delivery to maximise proliferation in vivo and marks the first use of active ML in microbiome science.

Clinical translation of advanced colonic drug delivery technologies

Targeted drug delivery to the colon offers a myriad of benefits, including treatment of local diseases, direct access to unique therapeutic targets and the potential for increasing systemic drug bioavailability and efficacy. Although a range of traditional colonic delivery technologies are available, these systems exhibit inconsistent drug release due to physiological variability between and within individuals, which may be further exacerbated by underlying disease states. In recent years, significant translational and commercial advances have been made with the introduction of new technologies that incorporate independent multi-stimuli release mechanisms (pH and/or microbiota-dependent release). Harnessing these advanced technologies offers new possibilities for drug delivery via the colon, including the delivery of biopharmaceuticals, vaccines, nutrients, and microbiome therapeutics for the treatment of both local and systemic diseases. This review details the latest advances in colonic drug delivery, with an emphasis on emerging therapeutic opportunities and clinical technology translation.

Machine learning predicts the effect of food on orally administered medicines

Food-mediated changes to drug absorption, termed the food effect, are hard to predict and can have significant implications for the safety and efficacy of oral drug products in patients. Mimicking the prandial states of the human gastrointestinal tract in preclinical studies is challenging, poorly predictive and can produce difficult to interpret datasets. Machine learning (ML) has emerged from the computer science field and shows promise in interpreting complex datasets present in the pharmaceutical field. A ML-based approach aimed to predict the food effect based on an extensive dataset of over 311 drugs with more than 20 drug physicochemical properties, referred to as features. Machine learning techniques were tested; including logistic regression, support vector machine, k-Nearest neighbours and random forest. First a standard ML pipeline using a 80:20 split for training and testing was tried to predict no food effect, negative food effect and positive food effect, however this lead to specificities of less than 40%. To overcome this, a strategic ML pipeline was devised and three tasks were developed. Random forest achieved the strongest performance overall. High accuracies and sensitivities of 70%, 80% and 70% and specificities of 71%, 76% and 71% were achieved for classifying; (i) no food effect vs food effect, (ii) negative food vs positive food effect and (iii) no food effect vs negative food effect vs positive food effect, respectively. Feature importance using random forest ranked the features by importance for building the predictive tasks. The calculated dose number was the most important feature. Here, ML has provided an effective screening tool for predicting the food effect, with the potential to select lead compounds with no food effect, reduce the number of animal studies, and accelerate oral drug development studies.

Nanoencapsulation for Probiotic Delivery

Gut microbiota dynamically participate in diverse physiological activities with direct impact on the host's health. A range of factors associated with the highly complex intestinal flora ecosystem poses challenges in regulating the homeostasis of microbiota. The consumption of live probiotic bacteria, in principle, can address these challenges and confer health benefits. In this context, one of the major problems is ensuring the survival of probiotic cells when faced with physical and chemical assaults during their intake and subsequent gastrointestinal passage to the gut. Advances in the field have focused on improving conventional encapsulation techniques in the microscale to achieve high cell viability, gastric and temperature resistance, and longer shelf lives. However, these microencapsulation approaches are known to have limitations with possible difficulties in clinical translation. In this Perspective, we present a brief overview of the current progress of different probiotic encapsulation methods and highlight the contemporary and emerging single-cell encapsulation strategies using nanocoatings for individual probiotic cells. Finally, we discuss the relative advantages of various nanoencapsulation approaches and the future trend toward developing coated probiotics with advanced features and health benefits.

Machine Learning and Machine Vision Accelerate 3D Printed Orodispersible Film Development

Orodispersible films (ODFs) are an attractive delivery system for a myriad of clinical applications and possess both large economical and clinical rewards. However, the manufacturing of ODFs does not adhere to contemporary paradigms of personalised, on-demand medicine, nor sustainable manufacturing. To address these shortcomings, both three-dimensional (3D) printing and machine learning (ML) were employed to provide on-demand manufacturing and quality control checks of ODFs. Direct ink writing (DIW) was able to fabricate complex ODF shapes, with thicknesses of less than 100 µm. ML algorithms were explored to classify the ODFs according to their active ingredient, by using their near-infrared (NIR) spectrums. A supervised model of linear discriminant analysis was found to provide 100% accuracy in classifying ODFs. A subsequent partial least square algorithm was applied to verify the dose, where a coefficient of determination of 0.96, 0.99 and 0.98 was obtained for ODFs of paracetamol, caffeine, and theophylline, respectively. Therefore, it was concluded that the combination of 3D printing, NIR and ML can result in a rapid production and verification of ODFs. Additionally, a machine vision tool was used to automate the in vitro testing. These collective digital technologies demonstrate the potential to automate the ODF workflow.

Machine Learning Predicts Drug Metabolism and Bioaccumulation by Intestinal Microbiota

Over 150 drugs are currently recognised as being susceptible to metabolism or bioaccumulation (together described as depletion) by gastrointestinal microorganisms; however, the true number is likely higher. Microbial drug depletion is often variable between and within individuals, depending on their unique composition of gut microbiota. Such variability can lead to significant differences in pharmacokinetics, which may be associated with dosing difficulties and lack of medication response. In this study, literature mining and unsupervised learning were used to curate a dataset of 455 drug-microbiota interactions. From this, 11 supervised learning models were developed that could predict drugs' susceptibility to depletion by gut microbiota. The best model, a tuned extremely randomised trees classifier, achieved performance metrics of AUROC: 75.1% ± 6.8; weighted recall: 79.2% ± 3.9; balanced accuracy: 69.0% ± 4.6; and weighted precision: 80.2% ± 3.7 when validated on 91 drugs. This machine learning model is the first of its kind and provides a rapid, reliable, and resource-friendly tool for researchers and industry professionals to screen drugs for susceptibility to depletion by gut microbiota. The recognition of drug-microbiome interactions can support successful drug development and promote better formulations and dosage regimens for patients.

Connected healthcare: Improving patient care using digital health technologies

Now more than ever, traditional healthcare models are being overhauled with digital technologies of Healthcare 4.0 increasingly adopted. Worldwide, digital devices are improving every stage of the patient care pathway. For one, sensors are being used to monitor patient metrics 24/7, permitting swift diagnosis and interventions. At the treatment stage, 3D printers are under investigation for the concept of personalised medicine by allowing patients access to on-demand, customisable therapeutics. Robots are also being explored for treatment, by empowering precision surgery, rehabilitation, or targeted drug delivery. Within medical logistics, drones are being leveraged to deliver critical treatments to remote areas, collect samples, and even provide emergency aid. To enable seamless integration within healthcare, the Internet of Things technology is being exploited to form closed-loop systems that remotely communicate with one another. This review outlines the most promising healthcare technologies and devices, their strengths, drawbacks, and opportunities for clinical adoption.

Progesterone Metabolism by Human and Rat Hepatic and Intestinal Tissue

Following oral administration, the bioavailability of progesterone is low and highly variable. As a result, no clinically relevant, natural progesterone oral formulation is available. After oral delivery, first-pass metabolism initially occurs in the intestines; however, very little information on progesterone metabolism in this organ currently exists. The aim of this study is to investigate the contributions of liver and intestine to progesterone clearance. In the presence of NADPH, a rapid clearance of progesterone was observed in human and rat liver samples (t_1/2 2.7 and 2.72 min, respectively). The rate of progesterone depletion in intestine was statistically similar between rat and human (t_1/2 197.6 min in rat and 157.2 min in human). However, in the absence of NADPH, progesterone was depleted at a significantly lower rate in rat intestine compared to human. The roles of aldo keto reductases (AKR), xanthine oxidase (XAO) and aldehyde oxidase (AOX) in progesterone metabolism were also investigated. The rate of progesterone depletion was found to be significantly reduced by AKR1C, 1D1 and 1B1 in human liver and by AKR1B1 in human intestine. The inhibition of AOX also caused a significant reduction in progesterone degradation in human liver, whereas no change was observed in the presence of an XAO inhibitor. Understanding the kinetics of intestinal as well as liver metabolism is important for the future development of progesterone oral formulations. This novel information can inform decisions on the development of targeted formulations and help predict dosage regimens.

The Novel Interplay between Commensal Gut Bacteria and Metabolites in Diet-Induced Hyperlipidemic Rats Treated with Simvastatin

Hyperlipidemia is one kind of metabolic syndrome for which the treatment commonly includes simvastatin (SV). Individuals vary widely in statin responses, and growing evidence implicates gut microbiome involvement in this variability. However, the associated molecular mechanisms between metabolic improvement and microbiota composition following SV treatment are still not fully understood. In this study, combinatory approaches using ultrahigh-performance liquid chromatography coupled with hybrid triple quadrupole time-of-flight mass spectrometry (UHPLC-Q-TOF MS/MS)-based metabolomic profiling, PCR-denaturing gradient gel electrophoresis (PCR-DGGE), quantitative PCR (qPCR), and 16S rRNA gene sequencing-based gut microbiota profiling were performed to investigate the interplay of endogenous metabolites and the gut microbiota related to SV treatment. A total of 6 key differential endogenous metabolites were identified that affect the metabolism of amino acids (phenylalanine and tyrosine), unsaturated fatty acids (linoleic acid and 9-hydroxyoctadecadienoic acid (9-HODE)), and the functions of gut microbial metabolism. Moreover, a total of 22 differentially abundant taxa were obtained following SV treatment. Three bacterial taxa were identified to be involved in SV treatment, namely, Bacteroidaceae, Prevotellaceae, and Porphyromonadaceae. These findings suggested that the phenylalanine and tyrosine-associated amino acid metabolism pathways, as well as the linoleic acid and 9-HODE-associated unsaturated fatty acid metabolism pathways, which are involved in gut flora interactions, might be potential therapeutic targets for improvement in SV hypolipidemic efficacy. The mass spectrometric data have been deposited to MassIVE (https://massive.ucsd.edu/ProteoSAFe/static/massive.jsp). Username: MSV000087842_reviewer. Password: hardworkingzsr.

Machine learning predicts 3D printing performance of over 900 drug delivery systems

Three-dimensional printing (3DP) is a transformative technology that is advancing pharmaceutical research by producing personalized drug products. However, advances made via 3DP have been slow due to the lengthy trial-and-error approach in optimization. Artificial intelligence (AI) is a technology that could revolutionize pharmaceutical 3DP through analyzing large datasets. Herein, literature-mined data for developing AI machine learning (ML) models was used to predict key aspects of the 3DP formulation pipeline and in vitro dissolution properties. A total of 968 formulations were mined and assessed from 114 articles. The ML techniques explored were able to learn and provide accuracies as high as 93% for values in the filament hot melt extrusion process. In addition, ML algorithms were able to use data from the composition of the formulations with additional input features to predict the drug release of 3D printed medicines. The best prediction was obtained by an artificial neural network that was able to predict drug release times of a formulation with a mean error of ±24.29 min. In addition, the most important variables were revealed, which could be leveraged in formulation development. Thus, it was concluded that ML proved to be a suitable approach to modelling the 3D printing workflow.