Dataset Information

Pet-Human Gut Microbiome Host Classifier Using Data from Different Studies.

ABSTRACT: (1) Background: microbiome host classification can be used to identify sources of contamination in environmental data. However, there is no ready-to-use host classifier. Here, we aimed to build a model that would be able to discriminate between pet and human microbiomes samples. The challenge of the study was to build a classifier using data solely from publicly available studies that normally contain sequencing data for only one type of host. (2) Results: we have developed a random forest model that distinguishes human microbiota from domestic pet microbiota (cats and dogs) with 97% accuracy. In order to prevent overfitting, samples from several (at least four) different projects were necessary. Feature importance analysis revealed that the model relied on several taxa known to be key components in domestic cat and dog microbiomes (such as Fusobacteriaceae and Peptostreptococcaeae), as well as on some taxa exclusively found in humans (as Akkermansiaceae). (3) Conclusion: we have shown that it is possible to make a reliable pet/human gut microbiome classifier on the basis of the data collected from different studies.

SUBMITTER: Bykova N

PROVIDER: S-EPMC7602744 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Pet-Human Gut Microbiome Host Classifier Using Data from Different Studies.

Bykova Nadia N Litovka Nikita N Popenko Anna A Musienko Sergey S

Microorganisms 20201015 10

(1) Background: microbiome host classification can be used to identify sources of contamination in environmental data. However, there is no ready-to-use host classifier. Here, we aimed to build a model that would be able to discriminate between pet and human microbiomes samples. The challenge of the study was to build a classifier using data solely from publicly available studies that normally contain sequencing data for only one type of host. (2) Results: we have developed a random forest model ...[more]

PMID: 33076521

Similar Datasets

Project description:Human lifestyle and its relationship with the human microbiome has been a line of research widely studied. This is because, throughout human history, civilizations have experienced different environments and lifestyles that could have promoted changes in the human microbiome. The comparison between industrialized and non-industrialized human populations in several studies has allowed to observe variation in the microbiome structure due to the population lifestyle. Nevertheless, the lifestyle of human populations is a gradient where several subcategories can be described. Yet, it is not known how these different lifestyles of human populations affect the microbiome structure on a large scale. Therefore, the main goal of this work was the collection and comparison of 16S data from the gut microbiome of populations that have different lifestyles around the world. With the data obtained from 14 studies, it was possible to compare the gut microbiome of 568 individuals that represent populations of hunter-gatherers, agricultural, agropastoral, pastoral, and urban populations. Results showed that industrialized populations present less diversity than those from non-industrialized populations, as has been described before. However, by separating traditional populations into different categories, we were able to observe patterns that cannot be appreciated by encompassing the different traditional lifestyles in a single category. In this sense, we could confirm that different lifestyles exhibit distinct alpha and beta diversity. In particular, the gut microbiome of pastoral and agropastoral populations seems to be more similar to those of urban populations according to beta diversity analysis. Beyond that, beta diversity analyses revealed that bacterial composition reflects the different lifestyles, representing a transition from hunters-gatherers to industrialized populations. Also, we found that certain groups such as Bacteoidaceae, Lanchospiraceae, and Rickenellaceae have been favored in the transition to modern societies, being differentially abundant in urban populations. Thus, we could hypothesize that due to adaptive/ecological processes; multifunctional bacterial groups (e.g., Bacteroidaceae) could be replacing some functions lost in the transition to modern lifestyle.

Dataset Information

Pet-Human Gut Microbiome Host Classifier Using Data from Different Studies.

Publications

Pet-Human Gut Microbiome Host Classifier Using Data from Different Studies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets