Protein subcellular localization method and device based on deep convolutional neural network

Abstract

The invention discloses a protein subcellular localization method and device based on a deep convolutional neural network. The method comprises the steps of receiving sequence information of a known protein subcellular location, and establishing and storing a reference protein sequence database; conducting feature extraction on protein sequences in the reference protein sequence database, and conducting feature fusion on extracted feature data; with the fused feature data as input of the deep convolutional neural network, training the deep convolutional neural network to obtain a deep convolutional neural network classifier; receiving protein sequences to be predicted, conducting feature extraction and corresponding feature fusion, and inputting the protein sequences to the trained deep convolutional neural network classifier to conduct predicating localization on the protein subcellular localization of the protein sequences. The protein subcellular localization method and device solvethe problem of difficult selection of advantageous features in current protein subcellular localization research and further improve the accuracy at the same time.

Description

technical field [0001] The invention belongs to the technical field of protein subcellular localization in bioinformatics, and in particular relates to a protein subcellular localization method and device based on a deep convolutional neural network. Background technique [0002] With the development of information technology and the initiation of the Human Genome Project, bioinformatics has gradually become a hot research field in recent years. Its main purpose is to reveal the laws of biological systems by analyzing and counting various biological data. In the process of studying thousands of biological data and disorganized gene sequences or protein sequences, many new research directions have been generated, and one of the very important directions is the subcellular localization of proteins. [0003] The cell is the most basic unit in biology, but its structure is highly complex. According to the position of each structure inside the cell and the function it undertakes,...

AI Technical Summary

Problems solved by technology

[0011] Aiming at the deficiencies in the existing technology and solving the problem that the positioning accuracy of the protein subcellular localization method based on machine learning in the prior art needs to be further improved and the superior features cannot be independently selected, the present invention proposes a method based on deep convolutional neural network The protein subcellular localization method and device, using the deep convolutional neural network to achieve the purpose of expanding the superior characteristics through multi-layer nonlinear changes, designed it as a classifier for protein subcellular localization, in order to further improve the localization accuracy, in the feature When extracting, the method of feature fusion is adopted

Images