Method for predicting protein association graphs on basis of cascade neural network structures

Abstract

The invention relates to a method for predicting protein association graphs on the basis of cascade neural network structures. The method as shown in an attached graph 1 includes steps of A, creating six subnets of neural networks and a cascade neural network; B, reading protein data sets and classifying the data sets according to protein lengths; C, carrying out training and learning on the subnets of the neural networks by the aid of back propagation algorithms; D, carrying out training and learning on the cascade neural network; E, predicting subnets of first-layer neural networks; F, predicting second-layer cascade neural networks to obtain the ultimate protein association graphs. The method has the advantages that the method is implemented by the aid of by the multiple neural networks, the cascade structures are formed, the protein association graphs are predicted, accordingly, the shortcoming that proteins with different lengths cannot be optimally treated by the aid of a method implemented by the aid of a single neural network can be overcome, and the prediction precision and stability can be improved; the method has an inherent concurrent characteristic, accordingly, the various subnets and the cascade network can be concurrently processed, and the computation efficiency can be improved.

Description

technical field [0001] The invention relates to a method for predicting a protein association graph, in particular to a method for predicting a protein association graph based on a cascaded neural network structure. Background technique [0002] The study of protein association map is an important premise and basis for the study of protein spatial structure. Determining protein association maps from amino acid sequences of proteins is a difficult problem both computationally and experimentally. The main reason is that the protein association map has non-local properties, that is, the amino acids at the head of the protein sequence may be connected to the amino acids at the tail. This non-local property makes the prediction of the protein association map complex and requires a large amount of calculation. It will be very time-consuming and uneconomical to determine the protein association map through experimental methods (currently mainly X-ray crystallography and nuclear ma...

AI Technical Summary

Problems solved by technology

[0005] 1. Due to the diversity of proteins, the method based on a single neural network has only one neural network. Obviously, the single neural network structure makes it impossible to optimize the processing of proteins of different lengths, resulting in low prediction accuracy. Large fluctuations due to changes in length

[0006] 2. Since the method based on a single neural network performs calculations on a neural network that cannot be naturally decomposed in both the training and learning link and the calculation and prediction link, parallel computing will inevitably generate a large amount of communication due to tight coupling, resulting in The method based on a single neural network cannot achieve efficient parallel computing in the face of the current huge amount of protein data

Images