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

Tumor screening model and construction method and device thereof

A technology for tumor screening and construction methods, applied in character and pattern recognition, instruments, medical automated diagnosis, etc., can solve problems such as difficult to achieve low-cost tumor screening, and achieve the effect of efficient screening and detection

Active Publication Date: 2020-06-05
北京橡鑫生物科技有限公司 +2
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to provide a tumor screening model, its construction method and device, so as to solve the problem that it is difficult to realize low-cost tumor screening in the prior art

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
  • Tumor screening model and construction method and device thereof
  • Tumor screening model and construction method and device thereof
  • Tumor screening model and construction method and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] In a preferred embodiment of the present application, a method for constructing a tumor screening model is provided, figure 1 is a flowchart of a method for constructing a tumor screening model according to an embodiment of the present invention. As shown, the method includes:

[0040] Step S101, obtaining two sets of cell-free DNA sequencing data, the two sets of cell-free DNA sequencing data are respectively from multiple positive samples and multiple control samples;

[0041] Step S103, comparing two sets of cell-free DNA sequencing data and screening out the specific characteristics of ctDNA fragments;

[0042] Step S105, using the specific features of ctDNA fragments to construct a machine learning model to obtain a tumor screening model.

[0043] The above-mentioned method of the present application can be used to greatly improve the detection of ctDNA according to the characteristic distribution of ctDNA fragments which are obviously different from cfDNA, and f...

Embodiment 2

[0069] In a preferred embodiment of the present application, a more specific method for constructing a tumor screening model is provided, the method comprising:

[0070] 1. The input data is the raw data of next-generation sequencing off-machine, and the data format is fastq.

[0071] 1) Preprocess the original off-machine data, including removing adapters and low-quality data.

[0072] 2) Compare and sort the processed original off-machine data with the reference genome, and obtain the comparison results, and the data format is bam.

[0073] 3) Perform duplication reads identification on the bam file, and remove duplication reads.

[0074] 2. Feature selection:

[0075] A) Compare the cell-free DNA sequencing data of the two groups of samples and screen out the specific characteristics of the ctDNA fragments according to the following principles:

[0076] 1) Extract the absolute position of the end of all read pairs in the tumor sample, that is, the physical position corre...

Embodiment 3

[0106] In an optional embodiment, a tumor screening model is also provided, and the tumor screening model is constructed by any of the above methods.

[0107] In another optional embodiment, there is also provided a tumor screening device, which contains the above-mentioned tumor screening model.

[0108] The tumor screening model or tumor screening device can be used to greatly improve the detection of ctDNA according to the characteristic distribution of ctDNA fragments that are significantly different from cfDNA, and further screen out the unique characteristics of ctDNA, and make full use of the specificity of ctDNA in positive samples. Sexual characteristics, constructed by machine learning, can be relatively accurate and efficiently screen the samples to be tested. Moreover, the tumor screening model does not require high sequencing depth of the samples to be tested, and can be realized by conventional low-depth sequencing, providing important research directions and cli...

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 a tumor screening model and a construction method and device thereof. The model construction method comprises the following steps: acquiring two groups of free DNA sequencing data from a plurality of positive samples and a plurality of control samples respectively; comparing the two groups of free DNA sequencing data and screening out specific characteristics of ctDNA fragments; and performing machine learning model construction by utilizing the specific characteristics of the ctDNA fragments to obtain a tumor screening model. According to that characteristic distribution of ctDNA fragments is obviously different from that of cfDNA, the method can be used for greatly improving ctDNA detection, ctDNA specificity characteristics are fully utilized, and the tumor screening model is constructed through machine learning. The tumor screening model has no strict requirement for the sequencing depth of a to-be-detected sample and can be realized by adopting conventionallow-depth sequencing, and thus, has great significance in research direction and clinical guidance for (early) screening of cancers.

Description

technical field [0001] The present invention relates to the field of gene sequencing data analysis, in particular to a tumor screening model, its construction method and device. Background technique [0002] The next-generation sequencing technology is also called massively parallel sequencing. Its core idea is to sequence while synthesizing. It can sequence millions or even billions of DNA molecules at the same time, achieving the goal of large-scale and high-throughput sequencing. Revolutionary advance after Sanger sequencing. In recent years, with the rapid development of next-generation sequencing technology, it has been gradually applied to clinical medical detection and scientific research in the direction of blood tumors. Target sequence capture can selectively isolate or enrich genome-specific fragments, so higher sequencing depth can be obtained at a lower cost, laying a good foundation for low-frequency detection and large data accumulation. At present, in clinic...

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
IPC IPC(8): G16B30/00G16B40/00G16H50/20G06K9/62
CPCG16B30/00G16B40/00G16H50/20G06F18/24323
Inventor 张萌萌郭璟楼峰曹善柏
Owner 北京橡鑫生物科技有限公司
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