Journal
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
Volume 15, Issue 1, Pages 88-99Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s12539-022-00542-y
Keywords
MiRNA; Disease; Association prediction; Linear neighborhood similarity; Matrix completion
Categories
Ask authors/readers for more resources
This study proposed a space projection model based on block matrix for predicting miRNA-disease associations (BMPMDA). By utilizing matrix completion and linear neighborhood similarity, the model achieved high accuracy in prediction and identified numerous novel associations in existing databases.
With the high-quality development of bioinformatics technology, miRNA-disease associations (MDAs) are gradually being uncovered. At present, convenient and efficient prediction methods, which solve the problem of resource-consuming in traditional wet experiments, need to be further put forward. In this study, a space projection model based on block matrix is presented for predicting MDAs (BMPMDA). Specifically, two block matrices are first composed of the known association matrix and similarity to increase comprehensiveness. For the integrity of information in the heterogeneous network, matrix completion (MC) is utilized to mine potential MDAs. Considering the neighborhood information of data points, linear neighborhood similarity (LNS) is regarded as a measure of similarity. Next, LNS is projected onto the corresponding completed association matrix to derive the projection score. Finally, the AUC and AUPR values for BMPMDA reach 0.9691 and 0.6231, respectively. Additionally, the majority of novel MDAs in three disease cases are identified in existing databases and literature. It suggests that BMPMDA can serve as a reliable prediction model for biological research. [GRAPHICS] .
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available