Method for improving detection sensitivity of colorectal cancer indicator bacteria by applying support vector machine algorithm

A technology of support vector machine and detection sensitivity, which is applied in computing, computer components, instruments, etc., can solve problems such as abnormal cell proliferation and microsatellite instability, and achieve the effect of high identification accuracy and high accuracy

Active Publication Date: 2020-02-11
SHANGHAI PASSION BIOTECHNOLOGY CO LTD
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Studies have shown that there are a large number of Fusobacterium nucleatum (Fn for short) in the feces and colonic mucosa of patients with colorectal cancer, which can activate the Wnt signal transduction pathway through the combination of FadA antigen and E-cadherin lead to abnormal cell proliferation and microsatellite instability

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
  • Method for improving detection sensitivity of colorectal cancer indicator bacteria by applying support vector machine algorithm
  • Method for improving detection sensitivity of colorectal cancer indicator bacteria by applying support vector machine algorithm
  • Method for improving detection sensitivity of colorectal cancer indicator bacteria by applying support vector machine algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Example 1: SVM algorithm combined with indicator bacteria primer combination and fecal occult blood FIT index combination has higher detection accuracy than fecal occult blood FIT

[0033] 1 Detection of the abundance of 9 intestinal bacteria in feces and the results of fecal occult blood

[0034] 1.1 Sample source

[0035] A total of 1086 fecal samples from patients with colorectal cancer in the Anorectal Department of Liaoning Cancer Hospital and those who were healthy by colonoscopy were collected through cooperation.

[0036] 1.2 Specimen extraction

[0037] Use the feces collection box, tear off the adhesive, put it in a plastic bag; paste the box on the toilet, and excrete the feces into the feces collection box; take a sample (about 5 spoons of feces) into the feces storage tube with a sampling spoon, and then tighten the tube firmly Cover; put the feces preservation tube into the self-sealing tape, and store it at -80°C for later use.

[0038] The bacterial g...

Embodiment 2

[0096] Embodiment 2: Support vector machine method detection model parameter optimization

[0097] 1. Treat the feces

[0098] The specific experimental steps in this example are the same as those in Example 1. The feces of healthy people and patients with colorectal cancer were collected, the bacterial genome was extracted, PCR was performed with 16s rRNA primers, and the values ​​were recorded by the calculation method of the threshold line (Ct) of the amplification curve. Also perform fecal occult blood testing.

[0099] 2. Standardize the results of manure disposal

[0100] The specific result processing in this embodiment is the same as the steps in Embodiment 1. Standardized input reference set data file format, the first column is the sample number, the second to eighth columns are indicator bacteria 1, indicator bacteria 2, indicator bacteria 3, indicator bacteria 4, indicator bacteria 5, indicator bacteria 6, indicator bacteria 7 The ΔCt value, the ninth column is...

Embodiment 3

[0119] Embodiment 3: support vector machine method detects strain combination preferred 1

[0120] 1. Treat the feces

[0121] The specific experimental steps in this example are slightly different from those in Example 1. In this embodiment, 9 combinations of indicator bacteria were detected, and the performance of the 9 combinations of indicator bacteria and the 7 preferred indicator bacteria described in the present invention in identifying colorectal cancer were compared. The rest of the experimental steps are the same as in Example 1.

[0122] The feces of healthy people and colorectal cancer patients were collected in combination, the bacterial genome was extracted, PCR was performed with 16s rRNA primers, and the values ​​were recorded by the calculation method of the threshold line (Ct) of the amplification curve. Also perform fecal occult blood testing.

[0123] The primer sequences of 9 indicator bacteria are as follows:

[0124] Table 7

[0125]

[0126] ...

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 discloses a method for improving the detection sensitivity of colorectal cancer indicator bacteria by applying a support vector machine algorithm, which is characterized by comprising the following steps of: selecting a delta Ct value as a basic numerical value, and selecting a combination of the indicator bacteria and a fecal occult blood FIT (Fitting) index as an indicator index; and a more accurate colorectal cancer recognition method is obtained on the basis of a support vector machine method, parameters of a kernel function, a penalty coefficient and a gamma value and an optimization test of a corresponding model. The method has the beneficial effects that compared with fecal occult blood FIT detection, the SVM optimization algorithm is combined with the optimized indicator primer combination and fecal occult blood FIT index combination, so that the fecal occult blood FIT detection accuracy is higher; the recognition accuracy is higher than that of an unoptimized SVMalgorithm; compared with an unoptimized indicator bacterium primer combination and fecal occult blood FIT index combination, the accuracy is high.

Description

technical field [0001] The invention belongs to the field of gene detection, and in particular relates to a method for improving the detection sensitivity of colorectal cancer indicator bacteria by applying a support vector machine algorithm. Background technique [0002] Colorectal cancer is the fourth most common cancer that endangers people's health, and its death rate ranks second. Studies have shown that people's daily diet and nutritional status can affect the occurrence and development of colorectal cancer. Poor dietary habits can directly affect the host's immune response by damaging the host's DNA, regulating the composition and metabolism of intestinal microorganisms, and interfering with the formation of intestinal functional barriers, leading to intestinal inflammation. In addition, intestinal flora can also directly affect people's susceptibility to intestinal diseases. The huge change of microbial composition in colorectal cancer tissue and adjacent intestina...

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): G06K9/62
CPCG06F18/2411G06F18/214Y02A90/10
Inventor 孙子奎宣涛梁覃斯蔡庆乐
Owner SHANGHAI PASSION BIOTECHNOLOGY CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap