Deep learning-based ulcerative colitis immune typing classification method and system

A technology for ulcerative colitis and immunophenotyping, applied in the field of precision medicine

Pending Publication Date: 2022-04-22
AFFILIATED HUSN HOSPITAL OF FUDAN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to the patent literature, there is no invention to carry out the immune typing of ulcerative colitis according to the immune pattern to guide the application of clinical biological agents

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Deep learning-based ulcerative colitis immune typing classification method and system
  • Deep learning-based ulcerative colitis immune typing classification method and system
  • Deep learning-based ulcerative colitis immune typing classification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0048] Such as figure 1 As shown, the present invention provides a kind of classification method of the ulcerative colitis immunotype based on artificial intelligence deep learning, comprising:

[0049]Data acquisition step: acquire the ulcerative colitis data set, and divide the ulcerative colitis data set into a training set and a verification set. In the present invention, the ulcerative colitis data set comes from the GEO database and the RNA-Seq transcriptome sequencing of endoscopic biopsy tissue of Huashan Hospital Affiliated to Fudan University, GSE87466 (n=87), GSE73661 (n=64) and GSE75214 (n=74 ) were used as the training set, and GSE16879 (n=24) and Huashan Hospital Affiliated to Fudan University ulcerative colitis cohort (FDUHS cohort) (n=5) were used as the validation set. The GSE73661, GSE16879, and FDUHS cohorts contained information on patients' responsiveness to infliximab or vedelizumab treatment. All data were log2 transformed and only actively diseased ti...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an ulcerative colitis immune typing classification method and system based on deep learning, and the method comprises the steps: obtaining an ulcerative colitis data set, and dividing the ulcerative colitis data set into a training set and a verification set; single sample enrichment analysis is carried out in the training set, and the immune cell infiltration abundance of the sample is evaluated; carrying out immune feature typing through a clustering algorithm, comparing the biological preparation treatment response rates of the two subtypes, and carrying out difference analysis to obtain a feature gene of each subtype; verifying the immune typing in the verification set by using a nearest template prediction algorithm, and comparing the biological agent treatment response rates of the two subtypes; key genes meeting preset conditions are obtained through random forest screening, and a neural network model is constructed; and inputting to-be-classified ulcerative colitis data into the neural network model, and identifying subtype types of the to-be-classified ulcerative colitis data. According to the invention, subtypes with stable immune characteristics can be identified so as to improve clinical medication selection of ulcerative colitis.

Description

technical field [0001] The present invention relates to the technical field of precision medicine, in particular to a deep learning-based classification method and system for the immunophenotyping of ulcerative colitis. Background technique [0002] Ulcerative colitis is an inflammatory disease of the colon with unknown etiology. Ulcerative colitis usually recurs, with persistent lesions. Due to its relapse-prone characteristics, patients need to take drug treatment all year round. As a result, ulcerative colitis places a huge burden on patients and the world's healthcare budgets. [0003] A variety of drugs for ulcerative colitis have been developed, such as aminosalicylic acids, corticosteroids, thiopurines, calcineurin inhibitors, monoclonal antibody biological agents, etc. Among them, the treatment of biological agents is developing rapidly, such as anti-tumor necrosis factor (TNF) drugs (such as infliximab) and anti-integrin drugs (such as Vedelizumab). Although bio...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/08G16B20/00G16H50/20G16H20/10
CPCG06N3/08G16H50/20G16B20/00G16H20/10G06F18/23G06F18/24323
Inventor 莫少聪骆菲菲刘杰
Owner AFFILIATED HUSN HOSPITAL OF FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products