Biomarker Could Foretell Success of Colon Cancer Chemo

MIAMI, FLORIDA (July 25, 2024) - A study published in Cell Reports Medicine has identified a novel 10-gene biomarker that could potentially predict whether patients with stage II or III colon cancer will benefit from adjuvant chemotherapy. This treatment is often used after surgery to kill any remaining cancer cells and prevent recurrence. However, not all patients show improved survival rates with this therapy. 

The research was spearheaded by Steven Chen, Ph.D., at the Sylvester Comprehensive Cancer Center at the University of Miami Miller School of Medicine. The team's findings may pave the way for personalized treatment plans based on individual patient data. 

Chen explains: "When we talk about precision oncology, it means using an individual patient's information -- specifically their biomarkers -- to guide clinical decisions about what kind of treatment is best for them." He emphasizes that ideally adjuvant chemotherapy should only be applied to those who will respond positively to it while finding other effective treatments for non-responders. 

As a data scientist specializing in colorectal and breast cancers research, Chen applies machine learning and artificial intelligence techniques. His current focus is to identify gene signatures – specific sets of genes whose combined expression patterns can serve as a biomarker guiding treatment options.  

To achieve this goal, the team curated one of the largest gene expression datasets for stage 2 and 3 colon cancer consisting of aggregated gene expression profiles from six publicly available sources totaling up to 933 patients' data. 

After creating an initial network from thousands of relevant genes via machine learning algorithms; they were able to narrow down first into an18-gene network then finally into ten genes which formed a biologically relevant signature predicting responses towards chemotherapy. 

Following obtaining confidence over their discovery; they built a model analyzing this gene signature aiming at determining which patients would benefit most from adjuvant chemotherapy through comparing outcomes against random five-to fifteen-gene networks with significantly better results. 

In order to further validate their model, the team collected tumor tissue samples from 109 stage 2 and 3 colon cancer patients along with data on their responses to adjuvant chemotherapy. The tests confirmed that patients predicted by the gene signature to benefit from chemotherapy had significantly better survival outcomes than those predicted not to benefit. 

Despite these promising results, Chen stresses that more steps are needed before this biomarker can be used in clinical practice. "To make it clinically applicable, we need prospective clinical trials where we recruit patients and apply this biomarker to see its effectiveness," he said. 

This study was supported by funding from Sylvester and is part of Chen's larger goal of translating data science into real-world benefits for cancer patients. He hopes that every research finding his team uncovers will improve clinical decisions and ultimately help those battling cancer. 

/Public Release. This material from the originating organization/author(s) might be subject to editing for clarity, style, length or accuracy at any time after publication by Mirage.News which does not take institutional positions or sides; all views expressed herein are solely those of the author(s).