Using machine learning, a team of Western computer scientists and biologists have identified an underlying genomic signature for 29 different COVID-19 DNA sequences.
This new data discovery tool will allow researchers to quickly and easily classify a deadly virus like COVID-19 in just minutes—a process and pace of high importance for strategic planning and mobilizing medical needs during a pandemic.
The study also supports the scientific hypothesis that COVID-19 (SARS-CoV-2) has its origin in bats as Sarbecovirus, a subgroup of Betacoronavirus.
The findings, Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study, were published today in PLOS ONE.
The “ultra-fast, scalable, and highly accurate” classification system uses a new graphic-based, specialized software and decision-tree approach to illustrate the classification and arrive at a best choice out of all possible outcomes. The entire method uses a new graphic-based, specialized software to illustrate a best choice out of all tested possible outcomes.
Find your dream job in the space industry. Check our Space Job Board »
Biology professor Kathleen Hill co-led the study with Western collaborators in Computer Science and Statistical and Actuarial Sciences, along with others in the University of Waterloo’s Department of Computer Science.
The machine-learning method achieves 100 percent accurate classification of the COVID-19 sequences and more importantly, discovers the most relevant relationships among more than 5,000 viral genomes again within minutes.
“All we needed was the COVID-19 DNA sequence to discover its own intrinsic sequence pattern. We used that signature pattern and a logical approach to match that pattern as close as possible to other viruses and achieved a fine level of classification in minutes—not days, not hours but minutes,” Hill said.
This classification tool has already been used to analyze more than 5,000 unique viral genomic sequences, including the 29 COVID-19 sequences available on Jan. 27.
Hill believes the tool, which is able to classify any newly discovered virus sequence COVID-19 or otherwise, will be an essential component in the toolkit for vaccine and drug developers, front-line health-care workers, researchers and scientists during this global pandemic and beyond.
More information: Gurjit S. Randhawa et al. Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study. PLOS ONE (2020). DOI: 10.1371/journal.pone.0232391
Image: MoDMap3D of (a) 3273 viral sequences from Test-1 representing 11 viral families and realm Riboviria, (b) 2779 viral sequences from Test-2 classifying 12 viral families of realm Riboviria, (c) 208 Coronaviridae sequences from Test-3a classified into genera.
Credit: PLOS ONE (2020). DOI: 10.1371/journal.pone.0232391