Colon cancer prognosis assessment gene set and its construction method
A technology of colon cancer and gene sets, applied in the direction of biochemical equipment and methods, instruments, microbial determination/inspection, etc., can solve the problems of incomplete evaluation, affecting protein content and RNA expression, long observation time, etc., and achieve accurate prediction Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0088] Embodiment 1: Lasso regression method builds a model, obtains the selected characteristic gene set
[0089] data processing
[0090] Colon cancer gene expression data and clinical overall survival time data were obtained from The Cancer Genome Atlas project TCGA. Contains RNA-seq data of 471 TCGA colon cancer samples and survival data of 454 TCGA colon cancer samples. First, the samples were cleaned, and samples with both expression data and survival data were selected, and the survival time was longer than 30 days, and 435 colon cancer samples were obtained, and each sample had expression data of 60,488 genes.
[0091] Preliminary screening of related immune genes
[0092] The intersection genes with 547 immune-related genes in CIBERSORT were selected from 60488 genes, and the genes were screened.
[0093] In all the colon cancer sample data after sample screening, the genes with an average expression value 90% of the samples were removed, and 516 immune-relate...
Embodiment 2
[0117] Example 2: Comparison of the predictive power of selected feature gene sets and random gene sets
[0118]In order to further verify the validity of the evaluation gene set of the selected 9 genes, 9 genes were randomly selected from 516 genes (except the above 9 genes) to form a new "random gene set", and compared with the selected A defined "assessment gene set" was used for comparison.
[0119] With reference to the process described in Example 1, patients are also randomly divided into a training set (80%) and a verification set (20%), and the expression values of 9 random genes and the weight coefficients of each gene on survival are summed. As the survival risk score Risk Score of each sample, the calculation formula of Risk Score is the same as that in Example 1.
[0120] The median value of the risk score calculated by the training set is also used as the boundary, and the patients in the training set and validation set are divided into High group and Low grou...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com