It takes guts to learn: machine learning techniques for disease detection from the gut microbiome

Curry, Kristen; Nute, Michael; Treangen, Todd J.

doi:10.1042/etls20210213

Cited by 18 publications

(14 citation statements)

References 135 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though this does not necessarily represent a suboptimal result, it might indicate low generalisability of our model given the considerable drop in the AUC when the model faces an unprecedented dataset, perhaps owing to the model having been trained with a small training set. It has also been suggested that additional data, such as metabolomic or lifestyle-related information, combined with microbial data, might improve prediction accuracy [136], especially when performing disease prediction, something strongly linked to our case, taking the evidence regarding associations between HEI and obesity into account [118], [137], [138], as well as between HPF consumption and several pathologies.…”

Section: Discussionmentioning

confidence: 98%

Uncovering the link between gut microbiome, highly processed food consumption and diet quality through bioinformatics methods

Molina

Lacruz-Pleguezuelos

Pau

et al. 2023

Preprint

View full text Add to dashboard Cite

The consumption of highly processed foods, along with other dietary and lifestyle poor habits, has an impact on health by increasing the risk of several non-communicable pathologies, such as diabetes. Gut microbiome composition, in specific, can be modulated by nutrients, deriving in different metabolic outcomes that have an influence on this high disease susceptibility and making it a possible therapeutic target for these comorbidities. In this work, gut microbiome of 60 and 46 individuals from 2 different studies focused, among other aspects, on diet-microbiome interactions, was characterised. By means of differential abundance analyses and supervised machine learning techniques based on random forest, gradient boosting and support vector machines, a set of microbial genera that could be potential biomarkers for the differentiation of individuals with poorer dietary patterns was discovered, after comparing coincidences in these taxa among classifiers and testing them for significant differences. Among these, Dialister, Phocea and Pseudoflavonifractor were suggested to have a role in the way highly processed foods affect health negatively, along with Prevotellaceae NK3B31 group and an undetermined genus from Muribaculaceae in the opposite sense. Furthermore, all the identified genera in this study had already been linked to type 2 diabetes, among which Bacteroides and Pseudoflavonifractor proved to be differentially abundant in groups of individuals with different levels of biomarkers for this disease. Nevertheless, further research via longitudinal studies and experimental validation of these genera should be carried out to confirm the association of these taxa with diet and diabetes.

show abstract

Section: Discussionmentioning

confidence: 98%

Uncovering the link between gut microbiome, highly processed food consumption and diet quality through bioinformatics methods

Molina

Lacruz-Pleguezuelos

Pau

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Methods for identifying significant changes throughout a metagenome series is an active area of research (43). Currently, a common approach is to first simplify each metagenome into a profile that can be logically aligned and compared, such as taxonomic classification relative abundance, gene function presence, and counts of short sub-sequences (k-mers) (10). Yet, each of these strategies either oversimplifies potentially important sequences of microbial communities or is biased by a reference database (20; 25).…”

Section: Discussionmentioning

confidence: 99%

Reference-free Structural Variant Detection in Microbiomes via Long-read Coassembly Graphs

Curry,

Yu,

Vance

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Bacterial genome dynamics are vital for understanding the mechanisms underlying microbial adaptation, growth, and their broader impact on host phenotype. Structural variants (SVs), genomic alterations of 10 base pairs or more, play a pivotal role in driving evolutionary processes and maintaining genomic heterogeneity within bacterial populations. While SV detection in isolate genomes is relatively straightforward, metagenomes present broader challenges due to absence of clear reference genomes and presence of mixed strains. In response, our proposed method rhea, forgoes reference genomes and metagenome-assembled genomes (MAGs) by encompassing a single metagenome coassembly graph constructed from all samples in a series. The log fold change in graph coverage between subsequent samples is then calculated to call SVs that are thriving or declining throughout the series. We show rhea to outperform existing methods for SV and horizontal gene transfer (HGT) detection in two simulated mock metagenomes, which is particularly noticeable as the simulated reads diverge from reference genomes and an increase in strain diversity is incorporated. We additionally demonstrate use cases for rhea on series metagenomic data of environmental and fermented food microbiomes to detect specific sequence alterations between subsequent time and temperature samples, suggesting host advantage. Our innovative approach leverages raw read patterns rather than references or MAGs to include all sequencing reads in analysis, and thus provide versatility in studying SVs across diverse and poorly characterized microbial communities for more comprehensive insights into microbial genome dynamics.

show abstract

“…Although this might be a limitation derived from our small sample size, it should be noted that there is controversy over whether metagenomic data is enough to separate obese and lean patients [79]. Some authors argue that additional information, such as metabolomic or host genomic data, might be necessary [79,81].…”

Section: Discussionmentioning

confidence: 99%

Bioinformatic methods for stratification of obese patients and identification of cancer susceptibility biomarkers based on the analysis of the gut microbiome

Lacruz-Pleguezuelos

Fernández

Molina

et al. 2022

Preprint

View full text Add to dashboard Cite

Obesity has an impact on health by increasing the risk of various diseases. However, these risks might also depend on the metabolic health status, as it seems that metabolically healthy obese subjects are under a reduced risk of suffering comorbidities such as colorectal cancer. The gut microbiome has an effect on obesity and metabolic disorders through several integration pathways, making it a potential therapeutic target for these diseases. In this study, we characterized the gut microbiota of 356 obese and non-obese European individuals with different comorbidities associated with obesity. Using approaches based on supervised machine learning and network biology, we found a set of biomarkers of interest for differentiating metabolically healthy from unhealthy subjects. Then, we performed a linear discriminant analysis of effect size on a population of 1593 colorectal cancer, adenoma and control subjects assembled by the COST Action ML4Microbiome to investigate their role in colorectal cancer risk. Four of our biomarkers appeared in both approaches, suggesting their possible role in colorectal cancer development, prognosis and follow up: Clostridium leptum, Gordonibacter pamelaeae, Eggerthella lenta and Collinsella intestinalis. Further research via longitudinal studies or experimental validation of these microbial species would be necessary to confirm this association.

show abstract

It takes guts to learn: machine learning techniques for disease detection from the gut microbiome

Cited by 18 publications

References 135 publications

Uncovering the link between gut microbiome, highly processed food consumption and diet quality through bioinformatics methods

Uncovering the link between gut microbiome, highly processed food consumption and diet quality through bioinformatics methods

Reference-free Structural Variant Detection in Microbiomes via Long-read Coassembly Graphs

Bioinformatic methods for stratification of obese patients and identification of cancer susceptibility biomarkers based on the analysis of the gut microbiome

Contact Info

Product

Resources

About