New Protein Biomarkers to Improve Diagnostic Tools for Colorectal Cancer

This cancer begins when abnormal cells grow uncontrollably in the large bowel, comprising the colon and rectum. Early detection is crucial for effective treatment, underscoring the need for reliable diagnostic tools. Currently, diagnosis involves the removal of tissue from the bowel, which is then tested in the lab to identify cancer and determine suitable treatments. Advances that simplify the detection process and enable earlier identification of colorectal cancer would be highly beneficial. Researchers have now identified three new protein biomarkers that could improve diagnostic tools for the disease.

Researchers at the University of Birmingham (Birmingham, UK) employed machine learning and artificial intelligence (AI) techniques to analyze large health datasets and identify proteins with strong predictive potential for colorectal cancer. In their study published in Frontiers in Oncology, the team analyzed one of the largest UK Biobank datasets, comparing protein profiles from healthy individuals and colorectal cancer patients. They identified three key proteins—TFF3, LCN2, and CEACAM5—associated with cell adhesion and inflammation, processes that are closely linked to cancer development. The next steps include further validating these biomarkers, which may eventually lead to the creation of new diagnostic tools. The team used three machine learning models and AI to recognize patterns in the data.

“In our study, we used advanced machine learning and artificial intelligence (AI) models combined with protein network analysis to identify key protein biomarkers that could aid in diagnosing colorectal cancer,” said Dr. Animesh Acharjee who led the study. “The biomarkers show promise but further large-scale validation study is needed to look into the relationships and mechanistic properties of these potential new biomarkers.”