Leveraging explainable AI for gut microbiome-based colorectal cancer classification.

Studies have shown a link between colorectal cancer (CRC) and gut microbiome compositions. In these studies, machine learning is used to infer CRC biomarkers using global explanation methods. While these methods allow the identification of bacteria generally correlated with CRC, they fail to recognize species that are only influential for some individuals. In this study, we investigate the potential of Shapley Additive Explanations (SHAP) for a more personalized CRC biomarker identification. Analyses of five independent datasets show that this method can even separate CRC subjects into subgroups with distinct CRC probabilities and bacterial biomarkers.

Effect of urolithin A on the improvement of vascular endothelial function depends on the gut microbiota.

Background: Urolithin A (UA) is a metabolite produced by gut microbiota from ingested ellagic acid. Although the effect of ellagic acid intake on vascular endothelial function (VEF) improvement has been reported, the effect of UA intake on VEF improvement remains obscure. In addition, UA has been reported to improve the intestinal barrier function, and UA may have improved VEF by gut microbiome alteration. Objective: In this study, we conducted a clinical trial to explore and analyze the effects of UA intake on vascular endothelial function (VEF) and characteristics of the intestinal environment, such as gut microbiome profiling and organic acid composition. Methods: A placebo-controlled, randomized, double-blinded, parallel group trial was conducted on participants who could metabolize small amounts of UA from ellagic acid (non-UA producers) and had relatively poor VEF. VEF was assessed using the flow-mediated vasodilatation (FMD) score. Participants were administered placebo, UA 10 mg/day, or UA 50 mg/day for 12 weeks. FMD was measured and fecal samples were collected at 0, 4, 8, and 12 weeks of treatment. Gut microbiome analysis and organic acid level measurements were performed to evaluate the effects of UA intake on the intestinal environment. This clinical trial is publicly registered at the UMIN-CTR, trial number: UMIN000042014. Results: The gut microbiota of the UA 50 mg/day group showed a significant increase in alpha diversity (Faith's phylogenetic diversity). Four and nine microbial genera were significantly altered in the UA 10 mg/day and UA 50 mg/day groups, respectively (p < 0.05, not corrected). Participants whose FMD scores improved with UA intake had poor baseline FMD values as well as a low Bacillota/Bacteroidota ratio. Conclusion: Urolithin A intake alters the gut microbiota and improves their alpha diversity. In addition, the effect of UA on VEF correlated with the individual gut microbiota. Our results have practical implications for a new approach to providing healthcare that focuses on intestinal environment-based diet therapy.

PCA-based unsupervised feature extraction for gene expression analysis of COVID-19 patients.

Coronavirus disease 2019 (COVID-19) is raging worldwide. This potentially fatal infectious disease is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). However, the complete mechanism of COVID-19 is not well understood. Therefore, we analyzed gene expression profiles of COVID-19 patients to identify disease-related genes through an innovative machine learning method that enables a data-driven strategy for gene selection from a data set with a small number of samples and many candidates. Principal-component-analysis-based unsupervised feature extraction (PCAUFE) was applied to the RNA expression profiles of 16 COVID-19 patients and 18 healthy control subjects. The results identified 123 genes as critical for COVID-19 progression from 60,683 candidate probes, including immune-related genes. The 123 genes were enriched in binding sites for transcription factors NFKB1 and RELA, which are involved in various biological phenomena such as immune response and cell survival: the primary mediator of canonical nuclear factor-kappa B (NF-κB) activity is the heterodimer RelA-p50. The genes were also enriched in histone modification H3K36me3, and they largely overlapped the target genes of NFKB1 and RELA. We found that the overlapping genes were downregulated in COVID-19 patients. These results suggest that canonical NF-κB activity was suppressed by H3K36me3 in COVID-19 patient blood.