IncRNA-disease association prediction method and system based on Laplacian regularization least square and network projection

Abstract

The invention discloses an lncRNA-disease association prediction method and system based on Laplacian regularization least square and network projection, and the method comprises the steps: introducing disease Gaussian kernel spectrum similarity and lncRNA Gaussian kernel spectrum similarity to construct a comprehensive disease similarity matrix and a comprehensive lncRNA similarity matrix; respectively implementing a Laplacian regularization least square method in the comprehensive disease similarity matrix and the comprehensive lncRNA similarity matrix, integrating two obtained pre-estimation score matrixes to obtain a lncRNA and disease association composite pre-estimation score matrix, and through a network projection means, respectively projecting the comprehensive disease similarity matrix and the comprehensive lncRNA similarity matrix on the lncRNA and disease association composite estimation score matrix, and finally obtaining an lncRNA and disease association prediction result. Compared with an existing prediction method, the correlation between all diseases and the lncRNA can be predicted at the same time, the method can be used for predicting isolated diseases and new lncRNA, and the method has the advantages that a negative sample is not needed, only one parameter is needed, and the prediction accuracy is higher.

Description

technical field [0001] The present invention relates to the technical field of biological information, in particular to a lncRNA-disease association prediction method and system based on Laplacian regularized least squares and network projection. Background technique [0002] Long non-coding RNA (lncRNA) is a non-coding RNA longer than 200 nucleotides. In recent years, a large amount of evidence has shown that many lncRNAs are closely related to human diseases, and lncRNA mutations and disorders can cause a variety of diseases, including cervical cancer, ovarian cancer, etc. Therefore, identifying and predicting the relationship between lncRNAs and diseases is helpful In order to explore the pathogenesis of diseases, the identification and confirmation of the correlation between lncRNA and diseases has become an important topic in the field of biological research in recent years. However, it is very time-consuming and laborious to determine the association between lncRNA an...

AI Technical Summary

Problems solved by technology

However, it is very time-consuming and laborious to determine the association between lncRNA and disease through biological experiments, and the use of computer technology to predict potential disease-associated lncRNA can greatly reduce the work intensity, thereby saving cost and time. Currently, the leading prediction model There are IIRWR and LDAI-ISPS, but the above calculation and prediction models involve many parameters, need more negative sample data support, have high dependence on data resources, are difficult to implement, and have weak generalization ability. Accuracy also needs to be improved

Images