Aysegul Bumin, a Ph.D. student in the University of Florida Department of Computer & Information Science & Engineering (CISE), along with her team recently received the best student paper award at the 13th Association for Computing Machinery Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB) for her research on fiber-based tensor completion for drug repurposing.
The paper titled, “FiT : Fiber-based tensor completion for drug repurposing,” was co-authored by Anna Ritz, Ph.D., an associate professor in the Biology Department at Reed College; Donna Slonim, Ph.D., a professor in the Department of Computer Science at Tufts University; Tamer Kahveci, Ph.D., a CISE professor; and Kejun Huang, Ph.D., a CISE assistant professor. The research focuses on the problem of missing data in fiber structure, and the method proposed provides fast and accurate imputations compared to existing algorithms. The imputed values are used for solving an important problem: drug repurposing.
Drug repurposing is the process of finding new uses for drugs or compounds already in development. Repurposing existing drugs for novel indications reduces drug development time and cost, and can decrease the risk of failure, as developing new drugs and compounds for different disease-affected cells with unique traits is costly and can take decades, making drug repurposing a necessity.
“This research provides a novel method for data imputation for more accurate and faster drug repurposing,” Dr. Kahveci said.
When asked about the team’s next steps, Dr. Huang replied, “We plan to develop new algorithms to adapt to specific bioinformatics applications and bring new aspects to bioinformatics problems by using machine learning.”
ACM-BCB is the premier conference covering all aspects of bioinformatics research, including design, analysis, specification, verification, implementation and performance.
Allison Logan
Communications Manager
Herbert Wertheim College of Engineering