Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Launch Supplement

University of Calgary

$12,500.00

Harnessing AI for Viral Discovery

EF 2024-25

Résumé
Finding viruses in complex environments has traditionally been a challenging task, mainly because there is not a one-size-fits-all "marker" for all viruses. However, with every new viral discovery, our viral reference databases are getting better, helping us identify even more viruses. Some abundant virus groups, nonetheless, still go undetected. This is because the current tools, while advanced, still rely heavily on comparing new potential viruses with sequences of known viruses. This problem led me to a novel idea. Instead of focusing solely on the genetic codes of viruses, what if we also looked at their 3-D structures? Interestingly, many viruses, despite having vastly different genetic make-ups, share similar structural designs, particularly in their protective outer shells. With the advancements in technology, like computer-driven predictions of protein structures through programs such as Alphafold, and decreasing computational costs, I will create a novel approach to viral discovery. By utilizing tools that compare the 3-D structures of proteins, my research team hopes to delve deeper into the viral unknown. I will build a structure-based artificial intelligence (AI) based computational pipeline to identify undiscovered viruses. Overall, this project is significant because it will provide training in the emerging AI field, which is a key area of national importance. Further, it provides new tools for viral discovery, which is critical for ecosystem and disease surveillance, biosecurity and biodefense, and public health preparedness. My team of 6 trainees (2 Undergraduates, 1 Master's, 2 Doctoral, and 1 Postdoctoral) and I will: (1) develop a curated database that catalogs 3-D viral protein structures and explores how they are related, (2) leverage AI to create a powerful tool to discover new viruses, and (3) computationally predict potential viral protein sequences of undiscovered viruses. This project will be the first to take full advantage of 3-D structure-to-structure comparisons for viral discovery. It will also create many standalone tools including a viral 3-D protein structures family database, viral protein interaction database, and computational predictions of undiscovered viral proteins.
Programme
Discovery Launch Supplement
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
DGECR-2024-00150
Name nom
Gregory, Ann
Department département
Biological Sciences
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
12500
Program id
DGECR
Program name en
Discovery Launch Supplement
Program name fr
Supplément Tremplin vers la découverte
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1501
Committee name en
Genes, Cells and Molecules
Committee name fr
Gènes, cellules et molécules
Area of application code
1200
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Advancement of knowledge
Area of application fr
Avancement des connaissances
Research subject code
5202
Research subject group en
Microbiology
Research subject group fr
Microbiologie
Research subject en
Virology
Research subject fr
Virologie
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Harnessing AI for Viral Discovery
Keywords
viruses; viral discovery; bacteriophages; phages; viral capsids; protein structure; structural homology; artificial intelligence; machine learning; protein language models
Application summary
Finding viruses in complex environments has traditionally been a challenging task, mainly because there is not a one-size-fits-all "marker" for all viruses. However, with every new viral discovery, our viral reference databases are getting better, helping us identify even more viruses. Some abundant virus groups, nonetheless, still go undetected. This is because the current tools, while advanced, still rely heavily on comparing new potential viruses with sequences of known viruses. This problem led me to a novel idea. Instead of focusing solely on the genetic codes of viruses, what if we also looked at their 3-D structures? Interestingly, many viruses, despite having vastly different genetic make-ups, share similar structural designs, particularly in their protective outer shells. With the advancements in technology, like computer-driven predictions of protein structures through programs such as Alphafold, and decreasing computational costs, I will create a novel approach to viral discovery. By utilizing tools that compare the 3-D structures of proteins, my research team hopes to delve deeper into the viral unknown. I will build a structure-based artificial intelligence (AI) based computational pipeline to identify undiscovered viruses. Overall, this project is significant because it will provide training in the emerging AI field, which is a key area of national importance. Further, it provides new tools for viral discovery, which is critical for ecosystem and disease surveillance, biosecurity and biodefense, and public health preparedness. My team of 6 trainees (2 Undergraduates, 1 Master's, 2 Doctoral, and 1 Postdoctoral) and I will: (1) develop a curated database that catalogs 3-D viral protein structures and explores how they are related, (2) leverage AI to create a powerful tool to discover new viruses, and (3) computationally predict potential viral protein sequences of undiscovered viruses. This project will be the first to take full advantage of 3-D structure-to-structure comparisons for viral discovery. It will also create many standalone tools including a viral 3-D protein structures family database, viral protein interaction database, and computational predictions of undiscovered viral proteins.