Step-by-step Elimination Algorithm Based on Modified Radial Data Visualization to Predict the Response to FOLFOX Treatment of CRC Patients

Abstract

Abstract Background: The application of the FOLFOX chemotherapy scheme to colorectal cancer (CRC) patients often results in the development of resistance to its components, leading to therapeutic failure. This study aimed to develop a functional and easy-to-use algorithm to predict patients’ response to FOLFOX treatment. The transcriptomic data of samples from CRC patients treated with FOLFOX were downloaded from the Gene Expression Omnibus (GEO) database (GSE83129, GSE28702, GSE69657, GSE19860 and GSE41568). By comparing the expression of the top up- and downregulated genes in the FOLFOX responder and nonresponder patient groups, we selected 30 potential markers that were used to create a step-by-step elimination procedure based on modified radial data visualization, which depicts the interplay between the expression levels of chosen attributes (genes) to locate data points in low-dimensional space. Results: Our analysis revealed that FOLFOX-resistant CRC samples are predominantly characterized by upregulated expression of TMEM182and MCM9 and downregulated expression of LRRFIP1. Additionally, we developed a procedure based on the expression levels of TMEM182, MCM9, LRRFIP1, LAMP1, FAM161A, KLHL36, ETV5, RNF168, SRSF11, NCKAP5, CRTAP, VAMP2, ZBTB49 and RIMBP2 that could predict the response to FOLFOX therapy. Conclusion: Our approach can provide unique insight into clinical decision-making regarding therapy scheme administration, potentially increasing patient survival and, as a consequence, medical futility due to incorrect therapy.