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.

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.

BACKGROUND: Tryptophan metabolism is important in blood pressure regulation. The tryptophan-indole pathway is exclusively mediated by the gut microbiota. ACE2 (angiotensin-converting enzyme 2) participates in tryptophan absorption, and a lack of ACE2 leads to changes in the gut microbiota. The gut microbiota has been recognized as a regulator of blood pressure. Furthermore, there is ample evidence for sex differences in the gut microbiota. However, it is unclear whether such sex differences impact blood pressure differentially through the tryptophan-indole pathway. METHODS: To study the sex-specific mechanisms of gut microbiota-mediated tryptophan-indole pathway in hypertension, we generated a novel rat model with Clustered Regularly Interspaced Short Palindromic Repeats/Cas9 (Clustered Regularly Interspaced Short Palindromic Repeats–associated protein 9)–targeted deletion of Ace2 in the Dahl salt-sensitive rat. Cecal microbiota transfers from donors of both sexes to female S recipients were performed. Also, Dahl salt-sensitive rats of both sexes were orally gavaged with indole to investigate blood pressure response. RESULTS: The female gut microbiota and its tryptophan-indole pathway exhibited greater buffering capacity when exposed to tryptophan, due to Ace2 deficiency, and salt. In contrast, the male gut microbiota and its tryptophan-indole pathway were more vulnerable. Female rats with male cecal microbiota responded to salt with a higher blood pressure increase compared with those with female cecal microbiota. Indole, a tryptophan-derived metabolite produced by gut bacteria, increased blood pressure in male but not in female rats. Moreover, salt altered host-mediated tryptophan metabolism, characterized by reduced serum serotonin of both sexes and higher levels of kynurenine derivatives in the females. CONCLUSIONS: We uncovered a novel sex-specific mechanism in the gut microbiota-mediated tryptophan-indole pathway in blood pressure regulation. Salt tipped the tryptophan metabolism between the host and gut microbiota in a sex-dependent manner. Our study provides evidence for a novel concept that gut microbiota and its metabolism play sex-specific roles in the development of salt-sensitive hypertension.

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.