New software tool could provide answers to some of life's most intriguing questions

April 17, 2019

A University of Waterloo researcher has spearheaded the development of a software tool that can provide conclusive answers to some of the world's most fascinating questions.

The tool, which combines supervised machine learning with digital signal processing (ML-DSP), could for the first time make it possible to definitively answer questions such as how many different species exist on Earth and in the oceans. How are existing, newly-discovered, and extinct species related to each other? What are the bacterial origins of human mitochondrial DNA? Do the DNA of a parasite and its host have a similar genomic signature?

The tool also has the potential to positively impact the personalized medicine industry by identifying the specific strain of a virus and thus allowing for precise drugs to be developed and prescribed to treat it.

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

"With this method even if we only have small fragments of DNA we can still classify DNA sequences, regardless of their origin, or whether they are natural, synthetic, or computer-generated," said Lila Kari, a professor in Waterloo's Faculty of Mathematics. "Another important potential application of this tool is in the healthcare sector, as in this era of personalized medicine we can classify viruses and customize the treatment of a particular patient depending on the specific strain of the virus that affects them."

In the study, 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. "Our results show that ML-DSP overwhelmingly outperforms alignment-based software in terms of processing time, while having classification accuracies that are comparable in the case of small datasets and superior in the case of large datasets," Kari said. "Compared with other alignment-free software, ML-DSP has significantly better classification accuracy and is overall faster."

The authors 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 per cent accuracy, and 4,710 bacterial genomes into divisions with 95.5 per cent accuracy.
A paper detailing the new software tool, titled ML-DSP: Machine Learning with Digital Signal Processing for ultrafast, accurate, and scalable genome classification at all taxonomic levels, which was authored by Kari together with Western University PhD candidate Gurjit Randhawa and Dr Kathleen Hill, an Associate Professor in the Department of Biology at We

University of Waterloo

Related DNA Articles from Brightsurf:

A new twist on DNA origami
A team* of scientists from ASU and Shanghai Jiao Tong University (SJTU) led by Hao Yan, ASU's Milton Glick Professor in the School of Molecular Sciences, and director of the ASU Biodesign Institute's Center for Molecular Design and Biomimetics, has just announced the creation of a new type of meta-DNA structures that will open up the fields of optoelectronics (including information storage and encryption) as well as synthetic biology.

Solving a DNA mystery
''A watched pot never boils,'' as the saying goes, but that was not the case for UC Santa Barbara researchers watching a ''pot'' of liquids formed from DNA.

Junk DNA might be really, really useful for biocomputing
When you don't understand how things work, it's not unusual to think of them as just plain old junk.

Designing DNA from scratch: Engineering the functions of micrometer-sized DNA droplets
Scientists at Tokyo Institute of Technology (Tokyo Tech) have constructed ''DNA droplets'' comprising designed DNA nanostructures.

Does DNA in the water tell us how many fish are there?
Researchers have developed a new non-invasive method to count individual fish by measuring the concentration of environmental DNA in the water, which could be applied for quantitative monitoring of aquatic ecosystems.

Zigzag DNA
How the cell organizes DNA into tightly packed chromosomes. Nature publication by Delft University of Technology and EMBL Heidelberg.

Scientists now know what DNA's chaperone looks like
Researchers have discovered the structure of the FACT protein -- a mysterious protein central to the functioning of DNA.

DNA is like everything else: it's not what you have, but how you use it
A new paradigm for reading out genetic information in DNA is described by Dr.

A new spin on DNA
For decades, researchers have chased ways to study biological machines.

From face to DNA: New method aims to improve match between DNA sample and face database
Predicting what someone's face looks like based on a DNA sample remains a hard nut to crack for science.

Read More: DNA News and DNA Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to