ISPRF: A Machine Learning Model to Predict the Immune Subtype of Kidney Cancer Samples by Four Genes

Abstract

Background Clear cell renal cell carcinoma (ccRCC) is the most common type of renal cell carcinoma. Immunotherapy, especially anti-PD-1, is becoming a pillar of ccRCC treatment. However, precise biomarkers and robust models are needed to select the appropriate patients for immunotherapy.MethodsA total of 831 ccRCC transcriptomic profiles were obtained from 6 datasets. Unsupervised clustering was performed to identify the immune subtypes among ccRCC samples based on immune cell enrichment scores. Weighted correlation network analysis (WGCNA) was used to identify hub genes distinguishing subtypes and related to prognosis. A machine learning model was established by random forest algorithm, and employed to an open and free online website to predict the immune subtype. ResultsIn the identified immune subtypes, subtype2 was enriched in immune cell enrichment scores and immunotherapy biomarkers. WGCNA analysis identified 4 hub genes related to immune subtype, CTLA4, FOXP3, IFNG, and CD19. The random forest model was constructed by mRNA expression of these four hub genes, and the value of areas under the curve of the receiver operating characteristic (AUC) was 0.78. Subtype2 patients in the independent validation cohort had a better drug response and prognosis for immunotherapy treatment. Moreover, an open and free website was developed by the random forest model (https://immunotype.shinyapps.io/ISPRF/). ConclusionsThe current study constructs a model and provides a free online website that could identify suitable ccRCC patients for immunotherapy, and it is an important step forward to personalized treatment.