Analysing Gene Expression Data of Patients with and without Ovarian Cancer using Dynamic Mode Decomposition
No Thumbnail Available
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
Faculty of Engineering and Technology, University of Ilorin, Ilorin.
Abstract
Machine learning (ML) algorithms have been deployed in recent years as models for the analysis of complex data. The ubiquity of ML algorithms stems from their ability to learn the patterns and structures inherent in data. In addition, they are adaptable to a wide range of data types, irrespective of size, which allows them to learn and predict the future pattern of data. In this work, dynamic mode decomposition (DMD), an ML algorithm, is deployed to analyse the pattern of gene expression data from patients with and without ovarian cancer. Ovarian cancer is one of the deadliest gynaecologic cancers in the world. The obscure nature of the symptoms makes early detection of ovarian cancer difficult. If the disease is diagnosed early, the chance of survival increases for patients. In this work, DMD is applied to analyse gene expression data from patients with and without ovarian cancer to understand the spatiotemporal patterns of the data. The DMD modes captured the prevalent structures and predicted the future state of the data. The results obtained show that DMD is a promising algorithm that can predict the features inherent in gene expression for patients with and without ovarian cancer. The DMD modes can further be applied as features to train detection and classification models that can assist health practitioners in the quest for early detection of ovarian cancer through gene expression data.
Description
Proceedings 1st Faculty of Engineering and Technology Conference, University of Ilorin (FETiCON 2023)
Keywords
DMD, eigendecomposition, eigenvalues, eigenvectors, ML, ovarian cancer, SVD
Citation
Usman, A. M., Surajudeen-Bakinde, N. T., Ehiagwina, F. O., Afolabi, A. S., Oloyede, A. A., Zakariya, O. S. (2023). Analysing Gene Expression Data of Patients with and without Ovarian Cancer using Dynamic Mode Decomposition. Proceedings 1st Faculty of Engineering and Technology Conference, University of Ilorin (FETiCON 2023), O. A. A. Eletta, Lasode O. A., & Odusote J. K. (eds.) 559-565. Published by Faculty of Engineering and Technology Conference, University of Ilorin, Ilorin.