Communications of the ACM
Machine Learning Method Differentiates Between Healthy Male, Female Microbiomes
Researchers have used Topological Data Analysis as an unsupervised learning and data exploration tool to identify changes in microbial states.
Credit: University of California, San Diego
Researchers at the University of California, San Diego and the Qualcomm Institute have used Topological Data Analysis (TDA) as an unsupervised learning and data exploration tool to identify changes in microbial states.
The researchers tested the TDA method using a previously published dataset of high-resolution time series of the microbiome from three different sites--the mouth, hands, and gut--and from two healthy subjects, one female and one male.
Previous studies have shown microbial communities of a healthy subject are highly stable over time, so TDA and other methods should have been able to identify six total microbial communities.
The researchers wanted to compare TDA to other well-established methods such as principal component analysis and multidimensional scaling. Although the other methods did identify the clusters for three sites, they did not detect a difference based on the subject's gender.
Meanwhile, the TDA method identified distinct clusters that discriminated between the female and male cut samples, and based on the skin and tongue body sites. "This suggests that TDA is able to identify groups of clusters that other methods may potentially miss," says Qualcomm Institute researcher Mehrdad Yazdani.
From University of California, San Diego
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found