Grant: Master's Award: Canada Graduate Scholarships
McMaster University
$17,500.00
Artificial intelligence algorithms for in-silico discovery of drug targets in acute myeloid leukemia
FY 2017-18
Summary
The power of modern computing has lent the biological sciences a multitude of computational tools that have been consistently expanding the scale of experiments while driving down their time and financial costs. Over the last decade the use of artificial intelligence algorithms has become more widespread in field of cancer research where clear solutions lie beyond the realm of collective human understanding. This is increasingly evident in the study of cancer stem cells: rare self-renewing populations of cells that continuously give rise to cancer even following a seemingly successful drug treatment. This relapse phenomenon finds a well-studied niche in the aggressive acute myeloid leukemia (AML) disease: a cancer of the bone marrow with often poor clinical outcomes. This proposal describes a new interdisciplinary approach to cancer research: the development of artificial intelligence programs to quickly, affordably, and concisely predict novel drug targets against cancer stem cells, while minimizing potential risk to normal, healthy cells. Assembled from modular genetic algorithm variants, an artificial intelligence program is described herein that has been able to predict highly prognostic gene combinations matching several clinical criteria with little user input, using genome-scale expression data amalgamated from multiple published datasets. The proposed work will delve into its further development, and the in-vivo validation of predicted targets in a mouse model of human AML. A concise, high-confidence gene-knockout screen using the CRISPR-Cas9 genome editing tool will aim to demonstrate the efficacy of this rapid virtual method for drug discovery.
Department
Program
Master's Award: Canada Graduate Scholarships
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
CIHR Funding Decisions Database
As published
Id
386496
Name
Tran Damian V
Region
Ontario
Country
Canada
Orgtype
Institution Paid; Research Institution
Prcname2
Special Cases - Awards Programs
Projecttitle
Artificial intelligence algorithms for in-silico discovery of drug targets in acute myeloid leukemia
Programtype2
Studentship Programs
Orgnameinp2
McMaster University
Cihramount2
$17,500
Cihrequipment2
$0
Programname2
Master's Award: Canada Graduate Scholarships
Keyworddelim
Artificial Intelligence; Bioinformatics; Cancer; Crispr-Cas9; Drug Discovery; Functional Genomics; Interdisciplinary; Leukemia; Software Engineering; Stem Cells
Abstract
The power of modern computing has lent the biological sciences a multitude of computational tools that have been consistently expanding the scale of experiments while driving down their time and financial costs. Over the last decade the use of artificial intelligence algorithms has become more widespread in field of cancer research where clear solutions lie beyond the realm of collective human understanding. This is increasingly evident in the study of cancer stem cells: rare self-renewing populations of cells that continuously give rise to cancer even following a seemingly successful drug treatment. This relapse phenomenon finds a well-studied niche in the aggressive acute myeloid leukemia (AML) disease: a cancer of the bone marrow with often poor clinical outcomes. This proposal describes a new interdisciplinary approach to cancer research: the development of artificial intelligence programs to quickly, affordably, and concisely predict novel drug targets against cancer stem cells, while minimizing potential risk to normal, healthy cells. Assembled from modular genetic algorithm variants, an artificial intelligence program is described herein that has been able to predict highly prognostic gene combinations matching several clinical criteria with little user input, using genome-scale expression data amalgamated from multiple published datasets. The proposed work will delve into its further development, and the in-vivo validation of predicted targets in a mouse model of human AML. A concise, high-confidence gene-knockout screen using the CRISPR-Cas9 genome editing tool will aim to demonstrate the efficacy of this rapid virtual method for drug discovery.
Competitiondate
201712
Approvedterm2
1 yr 0 mth
Pinamesdelim
Tran, Damian V
Approvedterm
1 an 0 mois
Cihrcontribution2
~ $17,500~ $0~