Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Methylation marker and application thereof in diagnosis and classification of tumors

A methylation marker and methylation technology, applied in the field of biomedicine, can solve problems such as the application of unproven markers

Inactive Publication Date: 2019-04-26
EAST CHINA NORMAL UNIV
View PDF6 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Before the present invention, some researchers trained one or four tumors and selected some markers for early diagnosis of tumors. However, the markers they selected could only be used in one or four tumors in the training set. function, did not demonstrate that those markers can be applied to other tumors outside the training set

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
  • Methylation marker and application thereof in diagnosis and classification of tumors
  • Methylation marker and application thereof in diagnosis and classification of tumors
  • Methylation marker and application thereof in diagnosis and classification of tumors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] For the diagnostic methylation markers, the samples of 12 kinds of tumors (paired tumor tissue and normal tissue) in TCGA were first used for feature selection, and the specific steps were as follows:

[0077] (1) Use XGBoost for training. The parameter is to use the GridSearchCV function in sklearn to perform 5-fold cross-validation automatic parameter adjustment. After training, the importance score of each feature (the methylation level of the probe (CpG island)) is obtained. Delete The feature corresponding to the minimum score.

[0078] (2) Repeat step (1) for the data composed of the remaining features until there is only one feature left.

[0079] (3) Too many features lead to high cost of clinical detection, and too few features lead to a decrease in prediction accuracy. Considering this comprehensively, the top 7 CpG islands in the feature importance score were selected as markers for tumor diagnosis.

[0080] (4) Using the methylation levels of the above 7 CpG ...

Embodiment 2

[0086] For the classifier to distinguish different tumors, the tumor samples of TCGA tumors are firstly analyzed according to the following steps:

[0087] In this embodiment, the tumor samples may also come from other data sets.

[0088] In this embodiment, the tumor can also be selected according to actual needs.

[0089] (1) The methyl chip data of tumor patients with 26 kinds of cancers were combined together, including 7605 patient samples; among them, the relevant information of 26 kinds of cancers is shown in Table 3.

[0090] (2) Variance screening: delete probes whose variance (std) in all samples is less than 0.2.

[0091] (3) Differential methylation screening: in each cancer, the top 20 probes that were differentially methylated between this cancer and the remaining 25 cancers (average difference >0.3 & FDR <0.01) were selected. A total of 515 CpG islands were screened out and reserved for further screening. These 515 CpG islands can well distinguish different t...

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 methylation marker for early diagnosis of tumors. The marker comprises CpG islands corresponding to 248 probes in a HumanMethylation450BeadChip Kit and can well separate tumor tissue of the tumors in a training set from pericarcinomatous normal tissue. According to the methylation marker, a machine learning model constructed by adopting the methylation level of the markercan not only be used for clinically predicting the risk of 12 tumors in the training set, but also be applied to other tumors, and has good performance in the other tumors, and the area under the curve reaches 0.94; and it is proved that the methylation level of the screened CpG islands can be used for early diagnosis of almost all TCGA tumors. The invention further provides application of the CpG islands corresponding to 515 methylation markers in the HumanMethylation450BeadChip Kit in classification of the tumors and identification of tumor types.

Description

technical field [0001] The invention belongs to the field of biomedicine, and in particular relates to a methylation marker and its application in tumor diagnosis and classification. Background technique [0002] At present, the early diagnosis of tumors is facing challenges. Compared with the level of gene expression, the level of DNA methylation is more stable, and the methylation level of DNA in circulating tumor cells free in the blood and the methylation level of circulating tumor DNA can be detected from human peripheral blood, so DNA methylation can be used as a marker for tumor diagnosis. Because DNA methylation is a reversible process, DNA methylation can also be used as a drug target. [0003] The previous cancer-related methylation analysis was mainly aimed at the CpG island of the gene promoter region, ignoring the relationship between the abnormal methylation of the gene promoter region and other regions other than the CpG island and the tumor. Moreover, they ...

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): C12Q1/6886C12N15/11
CPCC12Q1/6886C12Q2600/154
Inventor 石铁流丁武斌陈庚
Owner EAST CHINA NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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