Related Experiment Video
Updated: Oct 12, 2025
Predictive Immune Modeling of Solid Tumors
Published on: February 25, 2020
ISPRF: a machine learning model to predict the immune subtype of kidney cancer samples by four genes
Zhifeng Wang1, Zihao Chen2, Hongfan Zhao2
1Department of Urology, Henan Provincial People's Hospital, Zhengzhou University People's Hospital, Zhengzhou, China.
Background:
Clear cell renal cell carcinoma (ccRCC) is the most common type of renal cell carcinoma (RCC). Immunotherapy, especially anti-PD-1, is becoming a pillar of ccRCC treatment. However, precise biomarkers and robust models are needed to select the proper patients for immunotherapy.
Methods:
A 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 a random forest (RF) algorithm and used on an open and free online website to predict the immune subtype.
Results:
In the identified immune subtypes, subtype2 was enriched in immune cell enrichment scores and immunotherapy biomarkers. WGCNA analysis identified four hub genes related to immune subtypes, CTLA4, FOXP3, IFNG, and CD19. The RF model was constructed by mRNA expression of these four hub genes, and the value of area under the receiver operating characteristic curve (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 RF model (https://immunotype.shinyapps.io/ISPRF/).
Conclusions:
The 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.
Insights
This study identifies immune subtypes in clear cell renal cell carcinoma (ccRCC) and develops a predictive model for immunotherapy response. The findings aid in selecting patients for personalized treatment strategies.
Area of Science:
- Oncology
- Immunology
- Bioinformatics
Background:
- Clear cell renal cell carcinoma (ccRCC) is the most prevalent kidney cancer subtype.
- Immunotherapy, particularly anti-PD-1, is a key treatment for ccRCC, but patient selection remains a challenge.
- Accurate biomarkers and predictive models are crucial for optimizing immunotherapy efficacy in ccRCC.
Purpose of the Study:
- To identify distinct immune subtypes within ccRCC.
- To develop a machine learning model for predicting immunotherapy response.
- To provide a tool for personalized ccRCC treatment selection.
Main Methods:
- Analysis of 831 ccRCC transcriptomic profiles from six datasets.
- Unsupervised clustering based on immune cell enrichment scores to define subtypes.
- Weighted gene co-expression network analysis (WGCNA) to identify prognostic hub genes.
- Random Forest (RF) model development using four key genes (CTLA4, FOXP3, IFNG, CD19) for subtype prediction.
Main Results:
- Two immune subtypes were identified, with subtype 2 showing enrichment in immune cell markers and immunotherapy biomarkers.
- Four hub genes (CTLA4, FOXP3, IFNG, CD19) were found to be associated with immune subtypes and prognosis.
- The RF model achieved an AUC of 0.78 for predicting immune subtypes.
- Subtype 2 patients demonstrated improved immunotherapy response and prognosis in validation cohorts.
Conclusions:
- A novel model and an accessible online tool were developed to identify ccRCC patients likely to benefit from immunotherapy.
- This work represents a significant advancement towards personalized immunotherapy for ccRCC.
- The developed tool facilitates precise patient stratification for targeted treatment.
