Method for predicting disease association relationship in biological association network
A technology of association network and association relationship, which is applied in the field of biological association network prediction algorithm, can solve the problems of expensive and time-consuming experimental methods, achieve the effect of excellent prediction accuracy, improve prediction accuracy, and promote research
Inactive Publication Date: 2021-09-03
TIANJIN UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, traditional techniques are only applied to one non-coding RNA or one specific disease, the two are performed separately, and the experimental method is time-consuming and expensive
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0038] The present invention is described in detail below in conjunction with accompanying drawing:
[0039] Such as figure 1 As shown, the present invention realizes the accurate identification of the relationship between non-coding RNA and diseases, which is of great help to the treatment of diseases in human biomedical research. However, traditional techniques are only applied to one non-coding RNA or one specific disease, and experimental methods are time-consuming and expensive. Numerous computational tools have been proposed to detect novel associations based on known ncRNA and disease-associated information. Since ncRNAs (circRNAs, miRNAs, and lncRNAs) are closely related to the progression of various human diseases, the development of effective computational methods is crucial for ncRNA-disease association prediction.
[0040] The basic idea of the present invention is: multiple nuclei of non-coding RNAs and multiple nuclei of diseases are fused by center core alig...
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
Login to View More Abstract
The invention discloses a method for predicting a disease association relationship in a biological association network. The method comprises the following steps: S1, establishing multi-core representation of non-coding RNA and multi-core representation of a disease; S2, using calculation method of center-core alignment to fuse the multi-core of non-coding RNA and the multi-core of disease respectively to obtain the optimal core; S3, decomposing the fused optimal core into two matrixes by adopting the calculation method of singular value decomposition; S4, calculating the sum of the matrixes by using a three-matrix decomposition method of a hypergraph regular term to obtain a hypergraph Laplacian matrix; and S5, calculating the sum of the hypergraph Laplacian matrix by using a cross validation method, and obtaining a new incidence relation matrix, wherein Y * = A[theta]BT. According to the method, the problem of predicting the incidence relation between the non-coding RNA and the disease is solved, a hypergraph Laplacian regular term is added into three-matrix decomposition calculation, and the prediction precision is obviously improved by adopting a multi-core fusion method of center core alignment.
Description
technical field [0001] The invention belongs to the field of biological association network prediction algorithm in bioinformatics, and in particular relates to a method for predicting disease association relationship in the biological association network. Background technique [0002] Accurate correlations between non-coding RNAs and diseases are of great help to the treatment of human biomedical research. However, traditional techniques are only applied to one non-coding RNA or one specific disease, and the two are performed separately, and the experimental method is time-consuming and expensive. A number of computational tools have been proposed to detect novel associations based on known noncoding RNA and disease-associated information. Since noncoding RNAs (ncRNAs), including circular RNAs (circRNAs), microRNAs (miRNAs), and long noncoding RNAs (lncRNAs), are closely associated with the progression of various human diseases, developing efficient computational methods t...
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
Login to View More IPC IPC(8): G16H50/70G16B5/00
CPCG16H50/70G16B5/00
Inventor 郭菲王浩唐继军丁漪杰
Owner TIANJIN UNIV