Application of Machine Learning in the Analysis of Gene Expression in Colorectal Cancer Cells Treated With Chemotherapeutics

Colorectal cancer is a leading cause of cancerrelated deaths, and understanding its molecular mechanisms is key to improving treatments. This study applies machine learning algorithms to analyze the expression of genes related to redox balance, apoptosis, and cell migration in HCT-116 colorectal cancer cells treated with chemotherapeutics (5fluorouracil, oxaliplatin, irinotecan, and leucovorin). The analyzed genes include those for redox homeostasis (GPX1, GPX2, GPX3, GPX4, TXNRD1, GSTP1, NFE2L2, NFKB1, HIF1A), apoptosis (CASP3, CASP8, CASP9, FAS, BCL-2, BAX), and genes coding cytoskeleton proteins (CDH1, CTNNB1, CDH2). Machine learning models, such as decision trees and random forests were used to analyze gene expression changes based on qPCR data. Notably, GPX4 and BAX were linked to chemoresistance, while CDH1 upregulation suggested an effect on cancer cell migration. This study demonstrates the potential of machine learning in identifying gene expression patterns and aiding in the development of personalized CRC treatments.