MSI prediction model construction method based on immune-related genes

An immune-related and predictive model technology, applied in the field of bioinformatics, can solve the problems of poor clinical performance, high cost, cumbersome operation, etc., and achieve the effect of good prognosis risk and prediction of prognosis risk

CN113921079AActive Publication Date: 2022-01-11SICHUAN CANCER HOSPITAL
9 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2022-01-11

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to an MSI prediction model construction method based on immune-related genes. The method comprises the following steps: collecting and constructing a training set and a verification set of an immune-related MSI prediction model irMSIs from a cancer genome map database; selecting immune related genes from the immunology database, and screening differential genes from the immune related genes; according to the screened differential genes, constructing an immune-related MSI prediction model irMSIs through an LASSO logistic regression algorithm; and verifying the prognosis risk by using the immune-related MSI prediction model irMSIs. The invention provides the application of the immune related gene in MSI state prediction, a group of characteristic genes capable of stably predicting MSI in digestive tract tumors, especially colon cancer, is found in combination with the immune related gene, and the prognosis risk of the colon cancer can be well predicted.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of biological information, in particular to a method for constructing an MSI prediction model related to colon cancer based on immune-related genes. Background technique

[0002] In recent years, tumor immunotherapy for colon cancer has been considered as a treatment method that cannot be ignored, and its focus is to achieve the efficacy of identifying, controlling and eliminating tumors by activating the body's immune system. Drugs targeting immune checkpoint inhibitors (ICIs), such as cytotoxic T-lymphatic system-associated protein 4 (CTLA-4) monoclonal antibody, inhibitor of programmed death protein and its ligand (PD-1 / PD-L1 ) monoclonal antibodies, etc., have brought new hope for the treatment of various tumors, including advanced melanoma, non-small cell lung cancer and bladder cancer. Patients with colon cancer can also benefit from immunotherapy. At present, the US FDA has approved PD-1 immunotherap...

Examples

Embodiment

[0041] The present invention is realized through the following technical solutions, see figure 1 A method for constructing an MSI prediction model based on immune-related genes, comprising the following steps:

[0042] Step S1: Collect the training set and validation set for constructing the immune-related MSI prediction model irMSIs from the Cancer Genome Atlas database.

[0043] Download four cancer cohorts from the Cancer Genome Atlas database TCGA (hereinafter referred to as TCGA), including colon cancer COAD (n=551), rectal cancer READ (n=177), gastric cancer STAD (n=407) , mRNA expression profile and clinical information of esophageal carcinoma ESCA (n=173). The colon cancer COAD cohort was used as the training set for the screening of differential genes and the immune-related MSI prediction model irMSIs, and the other cohorts were used as the validation set for the immune-related MSI prediction model irMSIs.

[0044] Convert the fragments per kilobase per million (FKP...