Understanding gut microbiome‐based machine learning platforms: A review on therapeutic approaches using deep learning

Malakar, Shilpa; Sutaoney, Priya; Madhyastha, Harishkumar; Shah, Kamal; Chauhan, Nagendra Singh; Banerjee, Paromita

doi:10.1111/cbdd.14505

Cited by 2 publications

(1 citation statement)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next-generation sequencing (NGS) generates large numbers of sequences at an unprecedented rate. Amplicon analysis is commonly used to study the microbiome and has been used in large-scale projects, including the Human Microbiome Project [11,12]. The 16S rRNA gene, which is used to analyze these microbial communities, is highly conserved among bacteria and is commonly used to distinguish bacteria at the taxonomic level, while internal transcribed spacers (ITSs) in nuclear ribosomal DNA are commonly used in fungal studies [13,14].…”

Section: Introductionmentioning

confidence: 99%

Human Health Benefits and Microbial Consortium of Stevia Fermented with Barley Nuruk

Han,

Ko,

Shin

et al. 2024

Fermentation

View full text Add to dashboard Cite

In this study, the microbial community present during the barley yeast fermentation of stevia leaves and its correlation with antioxidant, anti-obesity, and anti-inflammatory properties, as well as metabolites, were investigated using UPLC-Q-TOF-MS. Stevia was fermented using commercial TSB media (TSB 1, TSB 3, and TSB 5) and sucrose (Sucrose 1, Sucrose 3, and Sucrose 5) for 1, 3, and 5 days, respectively. Stevia ferments showed higher DPPH and ABTS radical scavenging capacity compared to samples incubated with sucrose for 5 days, and all six ferments inhibited nitric oxide production in a concentration-dependent manner in LPS-induced mouse macrophages. Furthermore, UPLC-QTOF-MS analysis identified 23 related substances, including 10 terpenoids (including rubusoside, steviolbioside, and rebadioside derivatives), dulcoside A, and phlomisoside II, which are indicators of stevia, as well as five flavonoids, four phenolic acids, and four fatty acids. We also identified the microbial community during fermentation via the next-generation sequencing of the 16S rRNA gene for bacteria and the internal transcribed spacer (ITS) gene for fungi. The results showed that TSB 1 and Sucrose 1 ferments were dominated by the pathogens Enterococcus hirae (58.93%) and Cronobacter sakazakii (80.92%), while samples fermented for more than 3 days were pathogen-free and dominated by lactic acid bacteria such as Pediococcus stilesii (73.37%). Microbial community analysis using the ITS region showed that Saccharomycopsis fibuligera, classified as a yeast rather than a mold, dominated the stevia fermentation regardless of the fermentation duration. In particular, the microbial community of the fermentation with a sucrose solution was dominated by S. fibuligera by more than 99% throughout the fermentation periods of 1, 3, and 5 days. Finally, to apply the stevia ferments topically to human skin, skin irritation tests were performed on 30 volunteers. The results showed that the highly concentrated extracts (1 mg/mL) of all six stevia ferments were hypoallergenic. Taken together, these findings suggest that barley nuruk fermented from stevia leaves with a sucrose solution offers promise as a natural ingredient for use in functional foods and cosmetics.

show abstract

Section: Introductionmentioning

confidence: 99%

Human Health Benefits and Microbial Consortium of Stevia Fermented with Barley Nuruk

Han,

Ko,

Shin

et al. 2024

Fermentation

View full text Add to dashboard Cite

show abstract

Exploring Pathogen Presence Prediction in Pastured Poultry Farms through Transformer-Based Models and Attention Mechanism Explainability

Ram Das,

Pillai,

Nanduri

et al. 2024

Microorganisms

View full text Add to dashboard Cite

In this study, we explore how transformer models, which are known for their attention mechanisms, can improve pathogen prediction in pastured poultry farming. By combining farm management practices with microbiome data, our model outperforms traditional prediction methods in terms of the F1 score—an evaluation metric for model performance—thus fulfilling an essential need in predictive microbiology. Additionally, the emphasis is on making our model’s predictions explainable. We introduce a novel approach for identifying feature importance using the model’s attention matrix and the PageRank algorithm, offering insights that enhance our comprehension of established techniques such as DeepLIFT. Our results showcase the efficacy of transformer models in pathogen prediction for food safety and mark a noteworthy contribution to the progress of explainable AI within the biomedical sciences. This study sheds light on the impact of effective farm management practices and highlights the importance of technological advancements in ensuring food safety.

show abstract

Understanding gut microbiome‐based machine learning platforms: A review on therapeutic approaches using deep learning

Cited by 2 publications

References 98 publications

Human Health Benefits and Microbial Consortium of Stevia Fermented with Barley Nuruk

Human Health Benefits and Microbial Consortium of Stevia Fermented with Barley Nuruk

Exploring Pathogen Presence Prediction in Pastured Poultry Farms through Transformer-Based Models and Attention Mechanism Explainability

Contact Info

Product

Resources

About