Splicing-Based Predictive Learning for Individual Chemotherapy Evaluation in Colorectal Cancer (SPLICE)

What this Trial Is About

Colorectal cancer (CRC) is a major cause of cancer-related death worldwide, and responses to adjuvant chemotherapy after surgery vary greatly among patients. This research aims to develop a machine learning model that predicts how individuals will respond to chemotherapy by analyzing tumor-specific alternative splicing patterns, which may better indicate treatment outcomes than traditional gene expression methods. The study seeks to identify molecular markers that can guide personalized treatment and assess recurrence risk after surgery. The study involves analyzing RNA sequencing data from tumor tissue samples to detect alternative splicing features linked to chemotherapy response. Researchers will develop an assay called SPLICE, based on reverse transcription-quantitative polymerase chain reaction (RT-qPCR), and use machine learning to create a predictive model. This model will be validated independently in separate patient groups, tracking disease-free survival up to five years after treatment. Participants will provide tumor tissue samples and clinical data for analysis. The study will evaluate outcomes such as recurrence-free survival and overall survival for up to 60 months following treatment. By combining molecular data with clinical outcomes, researchers aim to produce a tool that helps predict chemotherapy effectiveness and supports personalized care decisions for colorectal cancer patients.

Splicing-based Predictive Learning for Individual Chemotherapy Evaluation in Colorectal Cancer