Colorectal cancer metabolic gene prognosis prediction model
A colorectal cancer, predictive model technology, applied in the field of biomedicine, to reduce the occurrence of ineffective treatment, reduce costs and discomfort experience, and achieve good specificity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0021] 1 method
[0022] 1) Determine the candidate list of metabolism-related genes: Metabolism-related genes inclusion criteria: (A) have the same expression pattern in TCGA database and GEO database; (B) enriched in KEGG metabolism-related pathways. At the same time, for the metabolic genes that appeared multiple times in the cohort, the mean value was taken. (C) Differential expression (LIMMA) in the TCGA training set. The screening criteria were set as |with |logFC|>1.5, and fdr value<0.05. (D) Univariate Cox regression analysis P<0.05 for OS correlation in TCGA training set. Exclusion criteria: not meeting any of the above.
[0023] 2) Use lasso regression to establish a model: and evaluate: use the metabolism-related genes screened out by the above method to establish a Lasso Cox regression model. Penalized maximum likelihood estimation was performed with the bootstrap method, repeated 1000 times. The optimal weighting coefficients are determined by the 1-SE criter...
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