Machine Learning-Derived Neddylation Gene Signature for Predicting Prognosis and Immunotherapy Benefits in Colorectal...

Area of Science:

• Oncology
• Molecular Biology
• Bioinformatics

Background:

• Colorectal cancer (CRC) poses a significant global health challenge due to treatment resistance.
• Neddylation, a post-translational modification, influences tumor progression and immune responses, but its role in CRC remains underexplored.

Purpose of the Study:

• To investigate the role of neddylation-related genes (NRGs) in colorectal cancer subtypes.
• To develop and validate a neddylation-related gene signature (NRGS) for predicting CRC patient prognosis and treatment response.

Main Methods:

• Analysis of CRC single-cell RNA sequencing (scRNA-seq) and bulk RNA-seq data from TCGA and GEO databases.
• Development of an NRGS using ten machine-learning algorithms and external validation.
• Comparative analysis of biofunctions, immune cell infiltration, genomic mutations, and treatment responses between high- and low-risk groups.

Main Results:

• High neddylation scores in CRC are associated with increased malignant and diverse immune/stromal cells, promoting tumor growth and spread.
• Two distinct neddylation patterns were identified, with Cluster B linked to poorer survival, immunosuppression, and tumor progression.
• The developed NRGS accurately predicted overall survival (OS) with high AUC values and correlated with advanced disease stage, recurrence, and metastasis.

Conclusions:

• The NRGS effectively predicts prognosis and potential resistance to immunotherapy and chemotherapy in CRC patients.
• This signature can aid in developing personalized treatment strategies for colorectal cancer.
• Further validation is recommended to confirm the clinical utility of the NRGS.