piRNA-disease incidence relation prediction method based on convolution denoising autoencoder

Abstract

The invention discloses a piRNA-disease incidence relation prediction method based on a convolution denoising autoencoder. The method comprises the following steps: selecting and establishing a data set; generating the similarity characteristics of the Piwi protein interaction RNA sequences; generating semantic similarity features of the diseases; generating nuclear similar characteristics of Piwi protein interaction RNA and a disease Gaussian interaction spectrum; mining deep hidden features; constructing a training set and a test set; and constructing a classifier model. According to the method, excellent performance expression is achieved under a five-fold cross validation experiment, and the effectiveness of the convolutional denoising self-encoding neural network in prediction of Piwi protein interaction RNA and disease association is proved. Case research proves that the practical application capability of the method in discovering the incidence relation between potential Piwi protein interaction RNA and diseases is better proved.

Description

technical field [0001] The present invention relates to the technical fields of deep learning and bioinformatics, and more specifically, to a method for predicting piRNA-disease associations based on convolutional denoising autoencoders. Background technique [0002] In recent years, Piwi protein-interacting RNAs have been recognized as important mediators in cell biology and become the latest members of the small non-coding RNA family. Piwi protein-interacting RNA is a single-stranded RNA containing 21-30 nucleotides, which mainly interacts with Argonaute family PIWI protein members (Argonaute3, Piwi, Aubergine) in different organisms to form and epigenetic regulation , spermatogenesis, transposon silencing, mRNA regulation and development, and the piRNA / PIWI complex associated with genome rearrangement. This complex can cause heterochromatin modification and transposon silencing by recognizing piRNA sequences, and has become a model of highly conserved small molecule RNA-...

AI Technical Summary

Problems solved by technology

These known association data provide a solid foundation for the construction of efficient and fast computational methods for predicting potential associations, thus solving the time-consuming, expensive and labor-intensive problems of traditional biological experimental methods to a certain extent

At present, most computational prediction methods only consider the similarity features of Piwi protein interaction RNA sequence features and diseases, without further denoising the features and extracting deep hidden features. Therefore, it is necessary to design a method that can take advantage of Piwi protein interaction RNA sequence information, Gaussian interaction spectrum nuclear similarity information and disease semantic similarity information, disease Gaussian interaction spectrum nuclear similarity information, can fuse multiple features, denoise and extract deep hidden features to achieve higher prediction accuracy method of prediction

Images