Introduction: Cytokines such as Tumor necrosis factor-alpha (TNF-α), Interleukin 6 (IL6), Interferon-gamma (IFN-γ), Interleukin 17-alpha (IL17-α), and Interleukin 33 (IL33), play critical roles in immune responses, and may impact cancer prognosis in future. However, few studies have simultaneously explored the prognostic impact of these cytokines for cancer. In this study, we aim to apply the unsupervised clustering analysis to approach the correlation between the expression of these cytokines and the subsequent prognosis of patients with esophageal squamous cell carcinoma.
Methods: A robust clustering algorithm was used, the Gaussian Mixture Method, through the mclust R package to group patients based on the expression of their cytokines in plasma or tumors. The 324 NTU patients were grouped into 4 clusters, and the 179 GSE53625 patients were grouped into 3 clusters based on expression in plasma and tumors, respectively. Five- and three-year overall survival (OS) and progression free survival (PFS) curves of each cluster were compared. Univariate and multivariate Cox regression analyses were also performed.
Results: We successfully distinguished the multimodal distribution of cytokines through GMM clustering, and discovered the relationship between cytokines and clinical outcomes. We observed that NTU-G3 and NTU-G4 subgroups showed most variation in 5-, 3-year OS, and 5-, 3-year PFS with NTU-G3 being associated with poorer prognosis compared to NTU-G4 (P = 0.016, 0.0052, 0.0575, and 0.0168, respectively). NTU-G3 was characterized with higher TNF-α (median = 3.855, N=78) and lower IL33 (median = 0.000, N = 78), while NTU-G4 showed lower TNF-α (median = 1.76, N = 51) and higher IL33 (median = 1.070, N = 51). The difference was statistically significant for TNF-α and IL33, with P = 0.002 and P <0.0001, respectively. A multivariate Cox-regression analysis revealed that GMM clustering and T/N stage were independent factors for prognosis, suggesting that the prognosis might be dependent on these cytokines.
Conclusions: Our data suggest that expression patterns of IL33 and TNF-α in plasma might serve as a convenient marker to predict the prognosis of ESCC in the future.
The Author(s). Published by S. Karger AG, Basel.