Grant: Discovery Grants Program - Individual
University of Calgary
$31,000.00
Representation learning of complex networks for the analysis of biological systems
FY 2024-25
Summary
My proposed research program will focus on the representation and analysis of complex networks. Networks are made up of a set of nodes and edges, where each edge connects two nodes. Nodes represent different entities, and edges convey information about the relationship or information shared between the nodes. Complex networks commonly occur when representing real--world systems. They are characterized by non-trivial structures and informative patterns of connection between their nodes as opposed to forming simpler structures such as a sequence, lattices, or random connections between nodes. Biological networks such as gene correlation networks and protein--protein interaction networks are examples of complex networks. However, analyzing biological networks poses challenges regarding making interpretations strictly from the graphical representations of these networks. Many methods of analyzing biological entities like genes or proteins disregard, summarize, or aggregate information to simplify analyses. However, in the process, biologically relevant information can be lost. Representing the structure of biological networks in a low-dimensional numerical form and developing techniques to compare them on a massive scale enables further research on the visualization, characterization, and quantification of conservation and adaptation of biological processes within organisms. Representations of these networks would also facilitate their integration into multi-modal learning strategies where the understanding of biological processes can be enhanced by learning from different data types, such as a combination of biological imaging and network data.
My research program will develop new network representations of gene sets, i.e., groups of genes responsible for some biological process or function, so we can analyse biological networks using a more holistic systems-level approach. This research program has the anticipated outcomes of developing novel strategies to 1) represent complex networks, 2) analyse and identify areas of similarity and differences between these networks, and 3) combine information from biological imaging and networks into multi-modal learning frameworks.
This program will also provide students with essential training and skills in artificial intelligence, a fast-growing area in both academia and industry in Canada requiring skilled personnel.
Program
Discovery Grants Program - Individual
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2023-04245
Name nom
Ovens, Katie
Department département
Computer Science
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
2023
Award amount
31000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
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
2803
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Knowledge representation
Research subject fr
Répresentation des connaissances
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
Representation learning of complex networks for the analysis of biological systems
Keywords
complex network analysis; machine learning; deep learning; biological network analysis; graph neural networks; computational biology; imaging analysis; multi-modal learning; representation learning
Application summary
My proposed research program will focus on the representation and analysis of complex networks. Networks are made up of a set of nodes and edges, where each edge connects two nodes. Nodes represent different entities, and edges convey information about the relationship or information shared between the nodes. Complex networks commonly occur when representing real--world systems. They are characterized by non-trivial structures and informative patterns of connection between their nodes as opposed to forming simpler structures such as a sequence, lattices, or random connections between nodes. Biological networks such as gene correlation networks and protein--protein interaction networks are examples of complex networks. However, analyzing biological networks poses challenges regarding making interpretations strictly from the graphical representations of these networks. Many methods of analyzing biological entities like genes or proteins disregard, summarize, or aggregate information to simplify analyses. However, in the process, biologically relevant information can be lost. Representing the structure of biological networks in a low-dimensional numerical form and developing techniques to compare them on a massive scale enables further research on the visualization, characterization, and quantification of conservation and adaptation of biological processes within organisms. Representations of these networks would also facilitate their integration into multi-modal learning strategies where the understanding of biological processes can be enhanced by learning from different data types, such as a combination of biological imaging and network data.
My research program will develop new network representations of gene sets, i.e., groups of genes responsible for some biological process or function, so we can analyse biological networks using a more holistic systems-level approach. This research program has the anticipated outcomes of developing novel strategies to 1) represent complex networks, 2) analyse and identify areas of similarity and differences between these networks, and 3) combine information from biological imaging and networks into multi-modal learning frameworks.
This program will also provide students with essential training and skills in artificial intelligence, a fast-growing area in both academia and industry in Canada requiring skilled personnel.