Harnessing human microbiomes for disease prediction

Liu, Yang; Fachrul, Muhamad; Inouye, Michael; Méric, Guillaume

doi:10.1016/j.tim.2023.12.004

Cited by 2 publications

(1 citation statement)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diet has been shown to quickly modify the gut microbiome, and the gut microbiota play an active role in human health, ranging from metabolism to immunity to disease susceptibility [ 12 , 13 , 14 ], and the microbiome has potential use in predicting the risk, progression, and severity of disease [ 15 ]. Recent human studies that have examined the associations between UPFs and the gut microbiome, separate from food that is part of a Western diet, are outlined in Table 1 , and their additional study characteristics can be viewed in Table S3 .…”

Section: Upfs and The Gut Microbiomementioning

confidence: 99%

Ultra-Processed Foods: A Narrative Review of the Impact on the Human Gut Microbiome and Variations in Classification Methods

Brichacek,

Florkowski,

Abiona

et al. 2024

Nutrients

View full text Add to dashboard Cite

Ultra-processed foods (UPFs) are foods that are industrially processed and are often pre-packaged, convenient, energy-dense, and nutrient-poor. UPFs are widespread in the current Western diet and their proposed contribution to non-communicable diseases such as obesity and cardiovascular disease is supported by numerous studies. UPFs are hypothesized to affect the body in multiple ways, including by inducing changes in the gut microbiome. This review summarizes the available research on the effect of UPFs on the gut microbiome. We also review current usage of the NOVA food classification system in randomized controlled trials and observational studies and how its implementation effects UPF research. Despite some differences in methodology between studies, results often associate UPF consumption with a number of negative health consequences. There are attempts to standardize a UPF classification system; however, reaching and implementing a consensus is difficult. Future studies focusing on the mechanisms by which UPFs effect the body, including through the microbiome and metabolome, will be essential to refine our understanding of the effects of UPFs on human health.

show abstract

Section: Upfs and The Gut Microbiomementioning

confidence: 99%

Ultra-Processed Foods: A Narrative Review of the Impact on the Human Gut Microbiome and Variations in Classification Methods

Brichacek,

Florkowski,

Abiona

et al. 2024

Nutrients

View full text Add to dashboard Cite

show abstract

Multitask Knowledge-primed Neural Network for Predicting Missing Metadata and Host Phenotype based on Human Microbiome

Monshizadeh,

Hong,

2024

Preprint

View full text Add to dashboard Cite

Microbial signatures in the human microbiome have been linked to various human diseases, and Machine Learning (ML) models have been developed for microbiome-based disease prediction, although improvements remain to be made in accuracy, reproducibility and interpretability. On the other hand, confounding factors, including host's gender, age and BMI can have a significant impact on human's microbiome, complicating microbiome-based human phenotype predictions. We recently developed MicroKPNN, an interpretable ML model that achieved promising performance for human disease prediction based on microbiome data. MicroKPNN explicitly incorporates prior knowledge of microbial species into the neural network. Here we developed MicroKPNN-MT a unified model for predicting human phenotype based on microbiome data, as well as additional metadata including age, body mass index (BMI), gender and body site. In MicroKPNN-MT, the metadata information, when available, will be used as additional input features for prediction, or otherwise will be predicted from microbiome data using additional decoders in the model. We applied MicroKPNN-MT to microbiome data collected in mBodyMap, covering healthy individuals and 25 different diseases, and demonstrated its potential as a predictive tool for multiple diseases, which at the same time provided predictions for much of the missing metadata (e.g., the BMI information was missing for 94% of the samples). Our results showed that incorporating real or predicted metadata helped improve the accuracy of disease predictions, and more importantly, helped improve the generalizability of the predictive models. Finally, our model enables the interpretation of predictive models and the identification of potential microbial markers affecting host phenotypes.

show abstract

Harnessing human microbiomes for disease prediction

Cited by 2 publications

References 121 publications

Ultra-Processed Foods: A Narrative Review of the Impact on the Human Gut Microbiome and Variations in Classification Methods

Ultra-Processed Foods: A Narrative Review of the Impact on the Human Gut Microbiome and Variations in Classification Methods

Multitask Knowledge-primed Neural Network for Predicting Missing Metadata and Host Phenotype based on Human Microbiome

Contact Info

Product

Resources

About