Transcription factor binding site prediction method based on depth convolution automatic encoder

Abstract

The invention discloses a transcription factor binding site prediction method based on a depth convolution automatic encoder, is applied to the technical field of computer technology and biological information, and aims to improve the generalization ability of a model while solving the dependence of the model on a negative sequence sample without a binding site. The method comprises the followingsteps: firstly, specifically enriching DNA fragments combined with target protein by virtue of a chromatin co-immunoprecipitation technology, so as to obtain an original data set; preprocessing the original data set to obtain a training data set; secondly, inputting the training data set into a convolution automatic encoder for training; and finally, carrying out binding site identification according to the trained convolutional automatic encoder. Experiments prove that the method can predict different transcription factor binding sites of different cell lines, and has a high-accuracy recognition effect.

Description

technical field [0001] The invention belongs to the fields of computer technology and biological information technology, and particularly relates to a technology for predicting transcription factor binding sites. Background technique [0002] In the early days of studying transcription factor binding sites, the traditional identification problem of transcription factor binding sites was to obtain real transcription factor binding sites from DNA sequences experimentally. Later, with the development of bioinformatics, various methods using mathematical models were developed, and the use of mathematical models enabled researchers not to be limited to the only transcription factor binding site information. The research on transcription factor binding site (TFBS) has been going on for a long time, and it was first widely used to study transcriptional regulators in the upstream promoter region of co-expressed genes. Due to the relatively short sequences of transcription factor bi...

AI Technical Summary

Problems solved by technology

It may contain some noisy data and affect the performance of predictive models in TFBS

(2) Due to the heterogeneity of data samples of different transcription factors, the prediction level of the same model for different transcription factors is limited

Some problems such as insufficient generalization ability of the model

Images