Method for predicting the direction and regulation of protein interactions

A prediction method and protein technology, applied in special data processing applications, instruments, biological neural network models, etc., can solve problems such as restrictive research, lack of interaction direction, etc., and achieve the effect of efficient prediction

Active Publication Date: 2018-12-25
南京深佰科技有限公司
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the existing high-throughput protein interaction detection methods can only detect simple physical interaction relationships (chemical bonds) between proteins, and lack the reflection of interaction directionality (upstream or downstream) and regulatory relationships (activation or inhibition). However, most of the interactions between proteins in real life systems have obvious biological functions such as signal transduction, activation, or inhibition.

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
  • Method for predicting the direction and regulation of protein interactions
  • Method for predicting the direction and regulation of protein interactions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] This embodiment provides a method for predicting the direction of action and regulatory relationship of Arabidopsis protein interaction, including the following steps:

[0053] S1, use Modeller software to carry out homology modeling on the spatial structure of interacting proteins, and the screening criteria for the stable structure of homologous proteins meet one of the following conditions: E value of sequence similarity comparison BLAST<10-5, or MPQS value ≥0.5, or GA341 value ≥0.5, or z-DOPE value <0. If there are multiple homologous structures that meet the screening conditions, the one with the highest MPQS score is selected as the representative structure of the target protein.

[0054] S2. Collect the spatial structure data of homologous or heterologous protein complexes from the PDB database, separate and extract the structural data of each subunit of the protein complex, and use TM-align software to align the homologous structure of the interacting protein wi...

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 prediction method of protein interaction direction and regulation relationship, which comprises the following steps: homologous modeling of the interaction protein; comparing and superposing the homologous spatial structure of each interacting protein and each subunit of the protein complex, according to the structure of the stable complex, a protein-protein interactionmodel with spatial structure resolution being constructed, and the interaction direction and frequency of amino acid residues in the protein-protein interaction interface being calculated, and the directional contact map of amino acid residues in the protein-protein interaction interface being generated; a convolution neural network being used to extract the target characteristics of the directional contact map, and the recognition model being trained to obtain the training model, and the protein interaction direction and regulation relationship being predicted. The prediction method of protein interaction direction and regulation relationship is a prediction method based on depth learning, which can achieve accurate and efficient prediction of protein interaction direction and regulationrelationship.

Description

technical field [0001] The invention relates to the field of biotechnology, in particular to a method for predicting protein interaction direction and regulation relationship. Background technique [0002] Protein-protein interactions are essential to almost all cellular processes, and most genes perform biological functions by interacting with other proteins at the protein level. [0003] At present, some high-throughput experimental methods have been developed to analyze the interaction relationship between proteins, which can deepen people's understanding of how proteins form functional complexes through interactions and participate in cell responses to environmental stimuli. [0004] However, the existing high-throughput protein interaction detection methods can only detect simple physical interaction relationships (chemical bonds) between proteins, and lack the reflection of interaction directionality (upstream or downstream) and regulatory relationships (activation or ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F19/18G06N3/04
CPCG06N3/045
Inventor 张利达曹应龙时振英
Owner 南京深佰科技有限公司
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