Gene function prediction method based on r-svm and tpr rules

A technology of gene function and prediction method, applied in the field of data mining of bioinformatics, can solve problems such as hierarchical constraints, and achieve the effect of reducing expenses, saving experimental costs, and shortening time

Active Publication Date: 2018-10-02
黑龙江鉴成医学检验实验室有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The invention can realize the prediction of gene function, and can solve the multi-label problem and hierarchical constraint problem existing when the classification algorithm is used to realize the prediction of gene function

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
  • Gene function prediction method based on r-svm and tpr rules
  • Gene function prediction method based on r-svm and tpr rules
  • Gene function prediction method based on r-svm and tpr rules

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0032]Since in the GO annotation scheme, the function is gradually refined from top to bottom, for some genes, it may not have the function represented by the bottom node, which makes for these nodes, the number of samples with this function is very small , the number of samples that do not have this function is large, and this situation is known as the dataset imbalance problem. The existence of this kind of problem will reduce the accuracy of classification. Therefore, when constructing positive and negative sample sets for nodes, certain strategies need to be adopted to solve this problem.

[0033] Since a gene sample is represented by a multi-dimensional vector, a sample has many attribute values, and processing these attribute values ​​at the same time will introduce a large number of calculations. For different functional nodes, the attributes related to the function may be different, and some attributes may be irrelevant attributes, and processing irrelevant attributes ...

specific Embodiment approach 2

[0053] The specific process of constructing positive sample sets and negative sample sets according to the improved sibling principle described in step 2 of this embodiment is as follows:

[0054] For each node in the GO annotation scheme, in the training set, the samples belonging to the node are used as positive samples, and the samples belonging to the sibling nodes of the node are used as initial negative samples, and at the same time, the negative samples that belong to the positive sample set are eliminated in the initial negative sample set. , and take it as the final negative sample set, that is, the negative sample set; among them, if a node has no sibling nodes, trace upwards and select samples belonging to the sibling nodes of its parent node as negative samples;

[0055] Specific symbols indicate:

[0056] Tr + (c j )=*(c j )

[0057]

[0058] Among them, Tr represents the training set containing all samples; node c j Represents the corresponding class labe...

specific Embodiment approach 3

[0060] The specific implementation process of step 3 of this embodiment is as follows:

[0061] Step 3.1,

[0062] First, use the concept of information gain in the C4.5 decision tree algorithm to calculate the information gain of each attribute, and at the same time calculate the gain ratio of each attribute;

[0063] For a certain node, let D be the sample set, Gain(R) be the information gain, and Gainratio be the information gain ratio for attribute R, then its calculation formula is:

[0064]

[0065]

[0066] Gain(R)=Info(D)-Info R (D)

[0067]

[0068]

[0069] Among them, p i Indicates the proportion of samples belonging to category i in the sample set, m is the number of categories contained in the sample set, Info(·) indicates the entropy value of the sample set, that is, the amount of information required to separate different categories of the sample set; k indicates The attribute R has k different values, D j is a sample set composed of samples who...

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

A method for predicting gene function based on R-SVM and TPR rules relates to a method for predicting gene function. The invention can realize the prediction of the gene function, and can solve the multi-label problem and the hierarchical constraint problem existing when the classification algorithm is used to realize the prediction of the gene function. The present invention firstly uses genes with known functions as training samples to form a training set; for each node in the GO annotation scheme, a positive sample set and a negative sample set are constructed; for each node in the GO annotation scheme, select the node The attribute that contributes a lot to the classification of the function; through training, a set of R-SVM classifiers is obtained and the unknown samples are classified and predicted, and a set of preliminary R-SVM classification results are obtained; the classification results are converted into posterior probability values, using A weighted TPR ensemble algorithm for directed acyclic graph hierarchy to realize gene function prediction. The invention is applicable to the prediction of gene function.

Description

technical field [0001] The invention relates to the data mining field of bioinformatics, in particular to a gene function prediction method. Background technique [0002] Genes are segments of DNA that have hereditary effects. Genes support the basic structure and performance of life, and store all the information about the race, blood type, conception, growth, and apoptosis process of life. It is also an internal factor that determines the health of life. All life phenomena such as the birth, growth, decline, disease, old age, and death of organisms are related to genes. Therefore, clarifying the biological function of genes is of great significance in understanding biological processes in organisms, analyzing disease mechanisms, developing new drugs, and many other aspects. [0003] At present, the functions of many genes in many organisms such as mice and humans are still unknown, and there is a lot of work to be done for gene function annotation. How to predict and fin...

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 Patents(China)
IPC IPC(8): G06F19/18G06K9/62
CPCG16B20/00G06F18/2411
Inventor 冯收付平徐明珠郑文斌石金龙邱传良于鸿杰阳彬
Owner 黑龙江鉴成医学检验实验室有限公司
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