Sign In

Communications of the ACM

ACM TechNews

Software Tool Could Provide Answers to Some of Life's Most Intriguing Questions


The tool could answer questions such as how many different species exist on Earth and in the oceans.

University of Waterloo researchers have developed a software tool that purportedly can provide conclusive answers to some of the worlds most fascinating questions.

Credit: University of Waterloo News

Researchers at the University of Waterloo in Canada have developed a software tool that combines machine learning with digital signal processing (ML-DSP) to make it possible to definitively answer challenging questions.

ML-DSP is an alignment-free software tool that works by transforming a DNA sequence into a digital signal, then uses digital signal processing methods to process and distinguish these signals from each other.

The researchers performed a quantitative comparison with other state-of-the-art classification software tools on two small benchmark datasets and one large 4,322 vertebrate mitochondrial genome dataset. The results showed that ML-DSP outperformed alignment-based software in terms of processing time, while being comparable in terms of classification accuracy.

The researchers also conducted preliminary experiments indicating the potential of ML-DSP to be used for other datasets, by classifying 4,271 complete dengue virus genomes into subtypes with 100% accuracy, and 4,710 bacterial genomes into divisions with 95.5% accuracy.

From University of Waterloo News
View Full Article

 

Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA


 

No entries found