Data Mining Analysis Of Prognostic Risk Genes Of Liver Cancer Based On LASSO

At present,hepatocellular carcinoma(HCC)is one of the most common malignant tumors in our country and even in the world.Its mortality rate is very high,which seriously endangers people's life and health,and brings great economic and mental pressure to families.Because of the limitations of traditional drug treatment,it is difficult to achieve the desired therapeutic effect.Targeted gene therapy is a new approach for the treatment of hepatocellular carcinoma,which is more targeted and has a good therapeutic prospect.However,targeted gene therapy requires the selection of appropriate genes,that is,We need to extract appropriate genetic markers from complex genetic data through data mining.In this paper,we first use LASSO regression analysis method with 10-fold cross-validation to reduce the dimension of gene data of hepatocellular carcinoma patients.Finally,we screened 26 genetic markers.Then we constructed a prognostic model using 26 genetic markers.what's more,Experiments on training set and verification set show that the model has good performance.Finally,we analyzed these 26 gene markers by the online gene function,and verified the relevant literature.The results show that the gene markers excavated in this paper have certain reference value for the follow-up clinical treatment of hepatocellular carcinoma.