Multi-scale CNN-BiLSTM non-coding RNA interaction relationship prediction method with introducing attention

Abstract

The invention discloses a multi-scale CNN-BiLSTM non-coding RNA interaction relationship prediction method with introducing attention, and belongs to the field of bioinformatics and deep learning. Themethod comprises the following steps: (1) proposing a coding mode k-mers suitable for a gene sequence; (2) using a multi-scale convolution kernel for replacing a single-scale convolution kernel, so that topic features with different lengths between sequences are captured, the feature diversity is enriched, and the model prediction performance is improved; carrying out down-sampling on each convolved feature map by using a plurality of pooling windows with different scales, so as to avoid ignoring potential effective information; (3) fusing a BiLSTM model on the basis of the CNN, so that long-distance information dependence between sequences can be better processed, and feature information is fully learned; and (4) introducing an attention mechanism, and distributing different weights to different words in the text vector by using the attention mechanism to distinguish the importance of the information, so that the attention mechanism pays more attention to the key information, and thepurpose of enhancing learning is achieved.

Description

technical field [0001] The invention belongs to the fields of bioinformatics and deep learning, and relates to a multi-scale CNN-BiLSTM non-coding RNA interaction relationship prediction method that introduces attention, including the design of k-mers coding and the construction of a deep learning prediction model. Background technique [0002] Since deep learning was proposed, its automatic learning features and good learning ability have made it widely used in many fields; for example, convolutional neural network CNN, recurrent neural network RNN ​​and bidirectional long short-term memory neural network BiLSTM have been used In genome research, it solves the problems of motif identification, gene expression inference and interaction relationship prediction. MicroRNA (miRNA) and long non-coding RNA (lncRNA) play an important role in regulating biological life activities, and they play an important role in regulating cell growth, differentiation and proliferation. Therefor...

AI Technical Summary

Problems solved by technology

One-hot encoding will cause dimension disaster and longer sequences will make the feature matrix too large, increasing the burden of memory and calculation; label encoding is only digitally encoded according to the number of nucleotides in the sequence, and only considers Single nucleotide; complementary encoding also only considers complementary features between nucleotides

But in fact, there may be some kind of dependent relationship between adjacent nucleotides

2) As we all know, feature diversity is crucial to improving model performance, while single-scale convolution can only extract a certain local feature, which may lose some potential effective information

Images