Communications of the ACM
Learning to Look
A new algorithm could improve the accuracy of searches in microbial and metagenomic databases.
Credit: J. Driver, P. Secor/University of Montana)
Researchers at the U.S. Department of Energy's Joint Genome Institute (JGI) have developed an algorithm that could improve the accuracy of searches in microbial and metagenomic databases.
The algorithm "learned" to identify a certain type of bacterial viruses or phages called inoviruses.
The search tool first worked on a reference dataset that included genome sequences known to be affiliated with these inoviruses.
The team manually curated the results and refined the algorithm, and then the search tool analyzed more than 70,000 microbial and metagenome datasets, ultimately identifying more than 10,000 inovirus-like sequences.
Said JGI's Simon Roux, "The machine learning approach allows you to quickly scale up once you've found the right features that you can use to identify the inoviruses."
From Joint Genome Institute
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found