Identification of a Prognostic Risk Signature of Kidney Renal Clear Cell Carcinoma Based on Regulating the Immune Response Pathway Exploration

Abstract

Purpose. To construct a survival model for predicting the prognosis of patients with kidney renal clear cell carcinoma (KIRC) based on gene expression related to immune response regulation. Materials and Methods. KIRC mRNA sequencing data and patient clinical data were downloaded from the TCGA database. The pathways and genes involved in the regulation of the immune response were identified from the GSEA database. A single factor Cox analysis was used to determine the association of mRNA in relation to patient prognosis P < 0.05 . The prognostic risk model was further established using the LASSO regression curve. The survival prognosis model was constructed, and the sensitivity and specificity of the model were evaluated using the ROC curve. Results. Compared with normal kidney tissues, there were 28 dysregulated mRNA expressions in KIRC tissues P < 0.05 . Univariate Cox regression analysis revealed that 12 mRNAs were related to the prognosis of patients with renal cell carcinoma. The LASSO regression curve drew a risk signature consisting of six genes: TRAF6, FYN, IKBKG, LAT2, C2, IL4, EREG, TRAF2, and IL12A. The five-year ROC area analysis (AUC) showed that the model has good sensitivity and specificity (AUC >0.712). Conclusion. We constructed a risk prediction model based on the regulated immune response-related genes, which can effectively predict the survival of patients with KIRC.

Facilitating “Omics” for Phenotype Classification Using a User-Friendly AI-Driven Platform: Application in Cancer Prognostics

“…According to a regulatory network model of epithelial-to-mesenchymal transitions, the identified biomarkers are more compatible with mesenchymal than a more invasive hybrid phenotype [23,33]. Thus, our results agree with this idea, but also highlight the complexity and heterogenicity of cancer deregulations and their correlation with survival prognostics [7,25,27,34]. Moreover, our results from the models may be useful as clues for future studies that aim to understand the molecular mechanisms associated with cancer survival, finding therapeutical targets for specific cancers and therapy evaluation metrics.…”

“…Therefore, more studies should be conducted to clarify the potential of the platform AI algorithm as a generic "omics" to phenotype modelling solution. In comparison to other published ML models, our model, for breast cancer prognostics, performed with a superior sensitivity (86%) in comparison to the reported 35-64%, whereas its specificity was inferior (85%) to the 97-99% [25] urthermore, the obtained AUC for the breast cancer prognostic model (86%) was comparable with the 80-92% reported for other models [25] or the lung and renal cancer prognostic models, we obtained in this work slightly superior performances (up to 10%) in comparison to the ones published using other modelling approaches [26,27]. This suggests that our cancer prognostic models are competitive alternatives to the ones already published.…”

Facilitating “Omics” to Phenotype Classification Using a User-Friendly AI-Driven Platform: Application to Cancer Prognostics

“…According to a regulatory network model of epithelial-to-mesenchymal transitions, the identified biomarkers are more compatible with mesenchymal than a more invasive hybrid phenotype [24,34]. Thus, our results agrees with this idea, but also highlights the complexity and heterogenicity of cancer deregulations and its correlation with survival prognostics [7,26,28,35].…”

“…Besides, the obtained AUC for the breast cancer prognostic model (86%) was comparable to the 80-92% reported for other models [26]. For lung and renal cancer prognostic models, we obtained in this work slightly superior (up to 10%) in comparison to the ones published using other modelling approaches [27,28]. This suggests that our cancer prognostic models are competitive alternatives to the ones already published.…”

Construction and Validation of Angiogenesis-Related Prognostic Risk Signature to Facilitate Survival Prediction and Biomarker Excavation of Breast Cancer Patients

“…In addition, in the past few decades, the construction of risk models around cancer-related biological processes or signaling pathway-related genes has succeeded [ 41 – 43 ]. Therefore, inspired by previous research, we used angiogenesis-related genes to construct a risk model for BRCA.…”