\u00a9 https:\/\/phil.cdc.gov\/Details.aspx?pid=23312<\/figcaption><\/figure>\nChallenges with identifying new COVID-19 variants<\/h3>\n
Like other RNA viruses, COVID-19 has a high mutation rate and short time between generations. This means that it evolves extremely rapidly.<\/p>\n
Identifying new strains that are likely to be problematic, therefore, requires considerable effort.<\/p>\n
The GISAID database, which provides access to genomic data of influenza viruses, currently has almost 16 million sequences available.<\/p>\n
Mapping the evolution and history of all COVID-19 genomes from this data requires large amounts of computer and human time.<\/p>\n
Human expert time is limited<\/h3>\n
The new method allows for the automation of these tasks.<\/p>\n
The researchers processed 5.7 million high-coverage sequences in only one to two days on a standard modern laptop.<\/p>\n
Existing methods would not be able to do this, as more researchers would need to identify pathogen strains.<\/p>\n
Thomas House, Professor of Mathematical Sciences at The University of Manchester, said: \u201cThe unprecedented amount of genetic data generated during the pandemic demands improvements to our methods to analyse it thoroughly.<\/p>\n
\u201cThe data is continuing to grow rapidly, but without showing a benefit to curating this data, there is a risk that it will be removed or deleted.<\/p>\n
\u201cWe know that human expert time is limited, so our approach should not replace human work altogether but work alongside it to enable the job to be done much quicker and free our experts for other vital developments.\u201d<\/p>\n
How does the new method work?<\/h3>\n
The new method is set to identify new COVID-19 variants by breaking down the virus’s genetic sequences into smaller words, represented as numbers, and counting them.<\/p>\n
It then groups similar sequences together based on their word patterns using Machine Learning techniques.<\/p>\n
Cahuantzi concluded: \u201cOur analysis serves as a proof of concept, demonstrating the potential use of machine learning methods as an alert tool for the early discovery of emerging major variants without relying on the need to generate phylogenies.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"
Scientists at the Universities of Manchester and Oxford have developed an AI framework that can track new COVID-19 variants.<\/p>\n","protected":false},"author":18,"featured_media":45187,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[10551],"tags":[570,16871],"acf":[],"yoast_head":"\n
Emerging COVID-19 variants identified with AI<\/title>\n\n\n\n\n\n\n\n\n\n\n\n\n\t\n\t\n\t\n\n\n\n\n\n\t\n\t\n\t\n