Plant protein interaction network constructing method based on deep learning

A plant protein and deep learning technology, which is applied in informatics, biological systems, bioinformatics, etc., can solve the problems of large number of deep learning model parameters, training overfitting, and large training data, so as to reduce the workload of parameter adjustment , the effect of reliable predictors

Inactive Publication Date: 2019-08-16
SHANGHAI JIAO TONG UNIV
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most studies on the construction of plant-protein interaction networks use traditional machine learning methods such as decision trees, naive Bayesian, support vector machines, and random forests for modeling, and few studies use deep learning methods to build protein interaction classifi...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Plant protein interaction network constructing method based on deep learning
  • Plant protein interaction network constructing method based on deep learning
  • Plant protein interaction network constructing method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] Such as figure 1 As shown, taking the construction of the protein interaction network at the whole genome level of Arabidopsis thaliana as an example, the present invention provides a method for constructing a protein interaction network based on deep learning, which specifically includes the following steps:

[0032] (1) Homologous modeling, spatial structure comparison and structural feature calculation

[0033] Homologous structural templates of Arabidopsis proteins were collected from the ModBase database and screened according to the following criteria: MPQS (ModPipe Quality Score)>=0.5; or GA341>=0.5; or E-value<0.0001; or Z-DOPE<0 . In addition, the spatial structure data of homologous or heterologous protein complexes were collected from the two databases of PDB and PISA, and the structure of the interaction interface between each chain of the protein complex and the corresponding interaction residues were calculated by using the PIBASE software package. Subse...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a plan protein interaction network constructing method based on deep learning. The method comprises the following steps of 1), acquiring 11 characteristic data of a protein interaction pair; 2), performing screening for obtaining a training set and a testing set; 3), constructing a deep learning classification model; 4), performing batch optimization on the parameter of the deep learning classification model, and obtaining a classification model of an optimal optimization parameter combination; 5), performing interaction relation predicting on all possible two-to-two interaction proteins of the whole genome according the classification model of the optimal optimization parameter combination; and 6), predicting the protein interaction network according to an interaction relation predicting result. Compared with the prior art, the method has advantages of high predicting accuracy, high modeling efficiency, etc.

Description

technical field [0001] The invention relates to deep learning technology in the field of biotechnology, in particular to a method for building a plant protein interaction network based on deep learning. Background technique [0002] Protein interaction is essential in the biological process of cells, and most genes perform their biological functions by interacting with other proteins at the protein level. The advent of the post-genome era has provided abundant data information for predicting protein interactions on a genome-wide scale, and with the development of high-throughput experimental technology and bioinformatics, the research progress of complex biological networks has been greatly improved. [0003] Building a classification model requires the use of statistics, machine learning, and other methods to extract valuable information from a large amount of data. This process includes data preprocessing, classification, and anomaly detection. With the explosive growth o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G16B5/00
CPCG16B5/00
Inventor 赵佳薇张利达雷雨郑存俭洪剑伟
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products