Genetically engineered Lactobacillus paracasei rescues colonic angiotensin converting enzyme 2 (ACE2) and attenuates hypertension in female Ace2 knock out rats.

Engineered gut microbiota represents a new frontier in medicine, in part serving as a vehicle for the delivery of therapeutic biologics to treat a range of host conditions. The gut microbiota plays a significant role in blood pressure regulation; thus, manipulation of gut microbiota is a promising avenue for hypertension treatment. In this study, we tested the potential of Lactobacillus paracasei, genetically engineered to produce and deliver human angiotensin converting enzyme 2 (Lacto-hACE2), to regulate blood pressure in a rat model of hypertension with genetic ablation of endogenous Ace2 (Ace2-/- and Ace2-/y). Our findings reveal a sex-specific reduction in blood pressure in female (Ace2-/-) but not male (Ace2-/y) rats following colonization with the Lacto-hACE2. This beneficial effect of lowering blood pressure was aligned with a specific reduction in colonic angiotensin II, but not renal angiotensin II, suggesting the importance of colonic Ace2 in the regulation of blood pressure. We conclude that this approach of targeting the colon with engineered bacteria for delivery of ACE2 represents a promising new paradigm in the development of antihypertensive therapeutics.

Survey and Evaluation of Hypertension Machine Learning Research.

Background Machine learning (ML) is pervasive in all fields of research, from automating tasks to complex decision-making. However, applications in different specialities are variable and generally limited. Like other conditions, the number of studies employing ML in hypertension research is growing rapidly. In this study, we aimed to survey hypertension research using ML, evaluate the reporting quality, and identify barriers to ML's potential to transform hypertension care. Methods and Results The Harmonious Understanding of Machine Learning Analytics Network survey questionnaire was applied to 63 hypertension-related ML research articles published between January 2019 and September 2021. The most common research topics were blood pressure prediction (38%), hypertension (22%), cardiovascular outcomes (6%), blood pressure variability (5%), treatment response (5%), and real-time blood pressure estimation (5%). The reporting quality of the articles was variable. Only 46% of articles described the study population or derivation cohort. Most articles (81%) reported at least 1 performance measure, but only 40% presented any measures of calibration. Compliance with ethics, patient privacy, and data security regulations were mentioned in 30 (48%) of the articles. Only 14% used geographically or temporally distinct validation data sets. Algorithmic bias was not addressed in any of the articles, with only 6 of them acknowledging risk of bias. Conclusions Recent ML research on hypertension is limited to exploratory research and has significant shortcomings in reporting quality, model validation, and algorithmic bias. Our analysis identifies areas for improvement that will help pave the way for the realization of the potential of ML in hypertension and facilitate its adoption.

Combating hypertension beyond genome-wide association studies: Microbiome and artificial intelligence as opportunities for precision medicine.

The single largest contributor to human mortality is cardiovascular disease, the top risk factor for which is hypertension (HTN). The last two decades have placed much emphasis on the identification of genetic factors contributing to HTN. As a result, over 1,500 genetic alleles have been associated with human HTN. Mapping studies using genetic models of HTN have yielded hundreds of blood pressure (BP) loci but their individual effects on BP are minor, which limits opportunities to target them in the clinic. The value of collecting genome-wide association data is evident in ongoing research, which is beginning to utilize these data at individual-level genetic disparities combined with artificial intelligence (AI) strategies to develop a polygenic risk score (PRS) for the prediction of HTN. However, PRS alone may or may not be sufficient to account for the incidence and progression of HTN because genetics is responsible for <30% of the risk factors influencing the etiology of HTN pathogenesis. Therefore, integrating data from other nongenetic factors influencing BP regulation will be important to enhance the power of PRS. One such factor is the composition of gut microbiota, which constitute a more recently discovered important contributor to HTN. Studies to-date have clearly demonstrated that the transition from normal BP homeostasis to a state of elevated BP is linked to compositional changes in gut microbiota and its interaction with the host. Here, we first document evidence from studies on gut dysbiosis in animal models and patients with HTN followed by a discussion on the prospects of using microbiota data to develop a metagenomic risk score (MRS) for HTN to be combined with PRS and a clinical risk score (CRS). Finally, we propose that integrating AI to learn from the combined PRS, MRS and CRS may further enhance predictive power for the susceptibility and progression of HTN.

Repurposing a Drug Targeting Inflammatory Bowel Disease for Lowering Hypertension.

Background The gut and gut microbiota, which were previously neglected in blood pressure regulation, are becoming increasingly recognized as factors contributing to hypertension. Diseases affecting the gut such as inflammatory bowel disease (IBD) present with aberrant energy metabolism of colonic epithelium and gut dysbiosis, both of which are also mechanisms contributing to hypertension. We reasoned that current measures to remedy deficits in colonic energy metabolism and dysbiosis in IBD could also ameliorate hypertension. Among them, 5-aminosalicylic acid (5-ASA; mesalamine) is a PPARγ (peroxisome proliferator-activated receptor gamma) agonist. It attenuates IBD by a dual mechanism of selectively enhancing colonic epithelial cell energy metabolism and ameliorating gut dysbiosis. Methods and Results A total of 2 groups of 11- to 12-week-old male, hypertensive, Dahl salt-sensitive (S) rats were gavaged with (n=10) or without (n=10) 5-aminosalicylic acid (150 mg/kg) for 4 weeks. Rats receiving 5-aminosalicylic acid treatment had a lower mean blood pressure than controls (145±3 mm Hg versus 153±4 mm Hg; P<0.0001). This reduction in blood pressure was accompanied by increased activity of PPARγ, increased expression of energy metabolism-related genes, and lowering of the Firmicutes/Bacteroidetes ratio in the colon, the reduction of which is a marker for the correction of gut dysbiosis. Furthermore, these data were consistent with the American Gut Project wherein the Firmicutes/Bacteroidetes ratio of non-IBD (n=611) patients was significantly lower than patients with IBD (n=631). Conclusions 5-Aminosalicylic acid could be repurposed for hypertension by specifically enhancing the gut energy metabolism and correction of microbiota dysbiosis.

Faecalibacterium prausnitzii Attenuates CKD via Butyrate-Renal GPR43 Axis.

BACKGROUND: Despite available clinical management strategies, chronic kidney disease (CKD) is associated with severe morbidity and mortality worldwide, which beckons new solutions. Host-microbial interactions with a depletion of Faecalibacterium prausnitzii in CKD are reported. However, the mechanisms about if and how F prausnitzii can be used as a probiotic to treat CKD remains unknown. METHODS: We evaluated the microbial compositions in 2 independent CKD populations for any potential probiotic. Next, we investigated if supplementation of such probiotic in a mouse CKD model can restore gut-renal homeostasis as monitored by its effects on suppression on renal inflammation, improvement in gut permeability and renal function. Last, we investigated the molecular mechanisms underlying the probiotic-induced beneficial outcomes. RESULTS: We observed significant depletion of Faecalibacterium in the patients with CKD in both Western (n=283) and Eastern populations (n=75). Supplementation of F prausnitzii to CKD mice reduced renal dysfunction, renal inflammation, and lowered the serum levels of various uremic toxins. These are coupled with improved gut microbial ecology and intestinal integrity. Moreover, we demonstrated that the beneficial effects in kidney induced by F prausnitzii-derived butyrate were through the GPR (G protein-coupled receptor)-43. CONCLUSIONS: Using a mouse CKD model, we uncovered a novel beneficial role of F prausnitzii in the restoration of renal function in CKD, which is, at least in part, attributed to the butyrate-mediated GPR-43 signaling in the kidney. Our study provides the necessary foundation to harness the therapeutic potential of F prausnitzii for ameliorating CKD.

Application of Artificial Intelligence in Cardiovascular Medicine.

The advent of advances in machine learning (ML)-based techniques has popularized wide applications of artificial intelligence (AI) in various fields ranging from robotics to medicine. In recent years, there has been a surge in the application of AI to research in cardiovascular medicine, which is largely driven by the availability of large-scale clinical and multi-omics datasets. Such applications are providing a new perspective for a better understanding of cardiovascular disease (CVD), which could be used to develop novel diagnostic and therapeutic strategies. For example, studies have shown that ML has a substantial potential for early diagnosis of different types of CVD, prediction of adverse disease outcomes such as heart failure, and development of newer and personalized treatments. In this article, we provide an overview and discuss the current status of a wide range of AI applications, including machine learning, reinforcement learning, and deep learning, in cardiovascular medicine. © 2021 American Physiological Society. Compr Physiol 11:1-12, 2021.

Gut microbiome-based supervised machine learning for clinical diagnosis of inflammatory bowel diseases.

Despite the availability of various diagnostic tests for inflammatory bowel diseases (IBD), misdiagnosis of IBD occurs frequently, and thus, there is a clinical need to further improve the diagnosis of IBD. As gut dysbiosis is reported in patients with IBD, we hypothesized that supervised machine learning (ML) could be used to analyze gut microbiome data for predictive diagnostics of IBD. To test our hypothesis, fecal 16S metagenomic data of 729 subjects with IBD and 700 subjects without IBD from the American Gut Project were analyzed using five different ML algorithms. Fifty differential bacterial taxa were identified [linear discriminant analysis effect size (LEfSe): linear discriminant analysis (LDA) score > 3] between the IBD and non-IBD groups, and ML classifications trained with these taxonomic features using random forest (RF) achieved a testing area under the receiver operating characteristic curves (AUC) of ∼0.80. Next, we tested if operational taxonomic units (OTUs), instead of bacterial taxa, could be used as ML features for diagnostic classification of IBD. Top 500 high-variance OTUs were used for ML training, and an improved testing AUC of ∼0.82 (RF) was achieved. Lastly, we tested if supervised ML could be used for differentiating Crohn's disease (CD) and ulcerative colitis (UC). Using 331 CD and 141 UC samples, 117 differential bacterial taxa (LEfSe: LDA score > 3) were identified, and the RF model trained with differential taxonomic features or high-variance OTU features achieved a testing AUC > 0.90. In summary, our study demonstrates the promising potential of artificial intelligence via supervised ML modeling for predictive diagnostics of IBD using gut microbiome data.NEW & NOTEWORTHY Our study demonstrates the promising potential of artificial intelligence via supervised machine learning modeling for predictive diagnostics of different types of inflammatory bowel diseases using fecal gut microbiome data.

Machine Learning Strategy for Gut Microbiome-Based Diagnostic Screening of Cardiovascular Disease.

Cardiovascular disease (CVD) is the number one leading cause for human mortality. Besides genetics and environmental factors, in recent years, gut microbiota has emerged as a new factor influencing CVD. Although cause-effect relationships are not clearly established, the reported associations between alterations in gut microbiota and CVD are prominent. Therefore, we hypothesized that machine learning (ML) could be used for gut microbiome-based diagnostic screening of CVD. To test our hypothesis, fecal 16S ribosomal RNA sequencing data of 478 CVD and 473 non-CVD human subjects collected through the American Gut Project were analyzed using 5 supervised ML algorithms including random forest, support vector machine, decision tree, elastic net, and neural networks. Thirty-nine differential bacterial taxa were identified between the CVD and non-CVD groups. ML modeling using these taxonomic features achieved a testing area under the receiver operating characteristic curve (0.0, perfect antidiscrimination; 0.5, random guessing; 1.0, perfect discrimination) of ≈0.58 (random forest and neural networks). Next, the ML models were trained with the top 500 high-variance features of operational taxonomic units, instead of bacterial taxa, and an improved testing area under the receiver operating characteristic curves of ≈0.65 (random forest) was achieved. Further, by limiting the selection to only the top 25 highly contributing operational taxonomic unit features, the area under the receiver operating characteristic curves was further significantly enhanced to ≈0.70. Overall, our study is the first to identify dysbiosis of gut microbiota in CVD patients as a group and apply this knowledge to develop a gut microbiome-based ML approach for diagnostic screening of CVD.

Machine learning-based classification and diagnosis of clinical cardiomyopathies.

Dilated cardiomyopathy (DCM) and ischemic cardiomyopathy (ICM) are two common types of cardiomyopathies leading to heart failure. Accurate diagnostic classification of different types of cardiomyopathies is critical for precision medicine in clinical practice. In this study, we hypothesized that machine learning (ML) can be used as a novel diagnostic approach to analyze cardiac transcriptomic data for classifying clinical cardiomyopathies. RNA-Seq data of human left ventricle tissues were collected from 41 DCM patients, 47 ICM patients, and 49 nonfailure controls (NF) and tested using five ML algorithms: support vector machine with radial kernel (svmRadial), neural networks with principal component analysis (pcaNNet), decision tree (DT), elastic net (ENet), and random forest (RF). Initial ML classifications achieved ~93% accuracy (svmRadial) for NF vs. DCM, ~82% accuracy (RF) for NF vs. ICM, and ~80% accuracy (ENet and svmRadial) for DCM vs. ICM. Next, 50 highly contributing genes (HCGs) for classifying NF and DCM, 68 HCGs for classifying NF and ICM, and 59 HCGs for classifying DCM and ICM were selected for retraining ML models. Impressively, the retrained models achieved ~90% accuracy (RF) for NF vs. DCM, ~90% accuracy (pcaNNet) for NF vs. ICM, and ~85% accuracy (pcaNNet and RF) for DCM vs. ICM. Pathway analyses further confirmed the involvement of those selected HCGs in cardiac dysfunctions such as cardiomyopathies, cardiac hypertrophies, and fibrosis. Overall, our study demonstrates the promising potential of using artificial intelligence via ML modeling as a novel approach to achieve a greater level of precision in diagnosing different types of cardiomyopathies.

Identification of Upstream Transcriptional Regulators of Ischemic Cardiomyopathy Using Cardiac RNA-Seq Meta-Analysis.

Ischemic cardiomyopathy (ICM), characterized by pre-existing myocardial infarction or severe coronary artery disease, is the major cause of heart failure (HF). Identification of novel transcriptional regulators in ischemic HF can provide important biomarkers for developing new diagnostic and therapeutic strategies. In this study, we used four RNA-seq datasets from four different studies, including 41 ICM and 42 non-failing control (NF) samples of human left ventricle tissues, to perform the first RNA-seq meta-analysis in the field of clinical ICM, in order to identify important transcriptional regulators and their targeted genes involved in ICM. Our meta-analysis identified 911 differentially expressed genes (DEGs) with 582 downregulated and 329 upregulated. Interestingly, 54 new DEGs were detected only by meta-analysis but not in individual datasets. Upstream regulator analysis through Ingenuity Pathway Analysis (IPA) identified three key transcriptional regulators. TBX5 was identified as the only inhibited regulator (z-score = -2.89). F2R and SFRP4 were identified as the activated regulators (z-scores = 2.56 and 2.00, respectively). Multiple downstream genes regulated by TBX5, F2R, and SFRP4 were involved in ICM-related diseases such as HF and arrhythmia. Overall, our study is the first to perform an RNA-seq meta-analysis for clinical ICM and provides robust candidate genes, including three key transcriptional regulators, for future diagnostic and therapeutic applications in ischemic heart failure.