Structural deep clustering network for stratification of breast cancer patients through integration of somatic mutation profiles

• Published in: Computer methods and programs in biomedicine Vol. 242; p. 107808
• Main Authors: Su, Dongqing, Xiong, Yuqiang, Wang, Shiyuan, Wei, Haodong, Ke, Jiawei, Li, Honghao, Wang, Tao, Zuo, Yongchun, Yang, Lei
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01-12-2023
• Subjects: Deep clustering; Graph convolutional network; Heterogeneity; Somatic mutation; Somatic mutation; Heterogeneity; Graph convolutional network; Deep clustering
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2023.107808

•A structural deep clustering algorithm was employed to classify a total of 2526 breast cancer samples.•This study offers an intriguing classification of breast cancer patients using solely somatic mutation data.•Each subtype of breast cancer was found to be linked with distinct prognosis, biological features, immunogenomic landscape, as well as immunotherapy and chemotherapy implications.
Breast cancer is among of the most malignant tumor that occurs in women and is one of the leading causes of death from gynecologic malignancy worldwide. The high degree of heterogeneity that characterizes breast cancer makes it challenging to devise effective therapeutic strategies. Accumulating evidence highlights the crucial role of stratifying breast cancer patients into clinically significant subtypes to achieve better prognoses and treatments. The structural deep clustering network is a graph convolutional network-based clustering algorithm that integrates structural information and has achieved state-of-the-art performance in various applications.
In this study, we employed structural deep clustering network to integrate somatic mutation profiles for stratifying 2526 breast cancer patients from the Memorial Sloan Kettering Cancer Center into two clinically differentiable subtypes.
Breast cancer patients in cluster 1 exhibited better prognosis than breast cancer patients in cluster 2, and the difference between them was statistically significant. The immunogenomic landscape further demonstrated that cluster 1 was associated with remarkable infiltration of the tumor infiltrating lymphocytes. The clustering subtype could be used to evaluate the therapeutic benefit of immunotherapy and chemotherapy in breast cancer patients. Furthermore, our approach effectively classified patients from eight different cancer types, demonstrating its generalizability.
Our study represents a step towards a generic methodology for classifying cancer patients using only somatic mutation data and structural deep clustering network approaches. Employing structural deep clustering network to identify breast cancer subtypes is promising and can inform the development of more accurate and personalized therapies.