A novel approach to marker genes selection: the case of leukemia

B. Toleva; I. Ivanov

doi:10.1117/12.3011482

19 December 2023 A novel approach to marker genes selection: the case of leukemia

B. Toleva, I. Ivanov

Proceedings Volume 12936, International Conference on Mathematical and Statistical Physics, Computational Science, Education and Communication (ICMSCE 2023); 129361T (2023) https://doi.org/10.1117/12.3011482
Event: International Conference on Mathematical and Statistical Physics, Computational Science, Education and Communication (ICMSCE 2023), 2023, Istanbul, Turkey

Abstract

Machine learning has become a vital part of marker genes selection. Complex machine learning models have been used to select genes that can possibly lead to different types of cancer, e.g. leukemia. Deep learning models have been used to provide deep and sophisticated research of potential gene mutations. Yet, the output from machine learning and deep learning models can be difficult to interpret. They can also be time-consuming. The aim of this research is to propose a fast way to pre-screen large datasets of genes and identify the ones whose mutations have the greatest possibility of causing leukemia. Unlike existing research, the proposed approach is easy to understand and provides insights into the importance of each gene, allowing medical researchers to have prior knowledge when setting up gene combinations for research. The proposed algorithm uses ANOVA ranking to calculate the importance of each gene and then a bootstrapped classification model to check if a selected combination of the genes generates high accuracy. This algorithm can be used as a fast way to select genes for medical tests.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

B. Toleva and I. Ivanov "A novel approach to marker genes selection: the case of leukemia", Proc. SPIE 12936, International Conference on Mathematical and Statistical Physics, Computational Science, Education and Communication (ICMSCE 2023), 129361T (19 December 2023); https://doi.org/10.1117/12.3011482

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available