Research on predicting the occurrence of hepatocellular carcinoma based on Notch signal-related genes using machine learning algorithms

Abstract

Background:Hepatocellular carcinoma (HCC) is a highly malignant malignant tumor, and is difficult to diagnose, treat and predict the prognosis. Notch signaling pathway can affect HCC. Therefore, our paper aimed to explore the prediction of the occurrence of hepatocellular carcinoma based on Notch signal-related genes using machine learning algorithms.Methods:In our presented study, we downloaded HCC data from TCGA and GEO databases. Firstly, we used machine learning methods to screen the hub Notch signal-related genes. Then, machine learning classification was used to construct a prediction model for the classification and diagnosis of HCC cancer. In our presented study, we also used bioinformatics methods to explore the relationship between the expression of these hub genes in the HCC tumor immune microenvironment to further improve the reliablity of the model.Results:After screening, we identified four hub genes of LAMA4, POLA2, RAD51 and TYMS, which were used as the final variables to construct the model. It was found that AdaBoostClassifie was the best algorithm for the classification and diagnosis model of HCC. The area under curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score of this model in the training set were 0.976, 0.881, 0.877, 0.977, 0.996, 0.500 and 0.932; respectively. The AUC, accuracy, sensitivity, specificity, PPV, NPV and F1 score in the testing set were 0.934, 0.863, 0.881, 0.886, 0.981, 0.489 and 0.926. The AUC in the external validation set was 0.934. In the immune microenvironment, immune cell infiltration played an important role in HCC and was related to the expression of 4 hub genes. Further researches found that patients in the low-risk group of HCC were more likely to have immune escape.Conclusion: Notch signaling pathway were closely related to the occurrence and development of HCC. The HCC classification and diagnosis model established based on this had a high degree of reliability and stability.