Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

G protein-coupled receptor topology calculation prediction method based on feedback type conditional random field

A technology of conditional random field and coupled receptors, which is applied in computing, special data processing applications, instruments, etc.

Inactive Publication Date: 2015-06-24
SUZHOU UNIV OF SCI & TECH
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The joint probability model based on the conditional random field does not need to assume the independence of the observation sequence, thereby solving the local optimal problem of the hidden Markov model; secondly, the present invention improves the basic conditional random field method and introduces a feedback mechanism. Continuous feedback self-improves the modeling ability of conditional random fields, thereby ultimately improving the prediction accuracy of GPCR topology

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
  • G protein-coupled receptor topology calculation prediction method based on feedback type conditional random field
  • G protein-coupled receptor topology calculation prediction method based on feedback type conditional random field
  • G protein-coupled receptor topology calculation prediction method based on feedback type conditional random field

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] This embodiment discloses a method for predicting the topological calculation of G protein-coupled receptors based on feedback conditional random fields. The prediction method includes:

[0054] (1) Data set preparation: Prepare two data sets, TMPDB_FB and PDBTM_FB, the TMPDB_FB contains 106 different α-helix chains selected from TMPB, and the PDBTM_FB contains 472 non-redundant α-helix chains selected from PDBTM chain.

[0055] (2) Data preprocessing: normalize the data set, and map the value ranges of the physical attribute values ​​and contour feature attribute values ​​of the residues to the [0,1] interval.

[0056] (3) Feedback conditional random field, including three stages:

[0057] (31) Basic conditional random field model: conditional random field theory, the conditional probability distribution between the marker sequence Y and the given observation sequence X is shown in formula (1):

[0058] P ( Y | ...

Embodiment 2

[0114] In this embodiment, the feedback CRF in Embodiment 1 is compared with the non-feedback CRF. Correct protein helix position and protein helix number are two very important indicators for studying GPCR. The correct rate of protein helical positions is equal to the ratio of the number of amino acid chains with correct helical positions to the total number of amino acid chains, and the correct rate of protein helical numbers is equal to the ratio of the number of amino acid chains with correct helical numbers to the total ratio of numbers.

[0115] In the data set PDBTM_FB, the relationship between the above two indicators and the window size and the number of feedbacks is shown in Table 2 and 3. In the two tables, the size of the window is (11,13,15), no feedback means no feedback, because when the basic conditional random field model is first constructed, there is no low-level prediction result to generate feedback features , feedback 1 means the first feedback.

[011...

Embodiment 3

[0122] This embodiment compares the feedback type conditional random field in embodiment 1 with the existing method. In order to further verify the performance of the feedback type basic conditional random field model, in this embodiment, the accuracy of this method is compared with other methods. Ten well-known GPCR topology prediction methods are compared. They are MEMSATS-SVM, OCTOPUS, MEMSAT3, ENSEMBLE, PHOBIUS, HMMTOP, PRODIV, SVMTOP, TMHMM, PHDhtm, the data set used is TMPDB_FB, the results are as follows Figure 4 shown.

[0123] Figure 4 "Correct protein helix count" in the table indicates the correct rate of protein helix number, and "Correct helix location" indicates the correct rate of helix position. The correct rate of helix position here is different from the correct rate of protein helix position. The correct rate of helix position It refers to the ratio of the correct number of helices predicted by the helix position in the entire data set to the total numbe...

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 G protein-coupled receptor topology calculation prediction method based on a feedback type conditional random field. The prediction method comprises the steps of 1, data set preparation, 2, data preprocessing, and 3, the feedback type conditional random field which comprises 31 a basic conditional random field model, 32, a feedback type conditional random field frame and 33, a feedback mechanism and algorithm. The GPCR topology structure prediction method is based on the FCRF; the joint probability model based on the conditional random field does not need to carry out independence assumption on an observation sequence, so that the local optimum problem of a hidden Markov model is solved; in addition, the basic conditional random field is improved, the feedback mechanism is introduced, and the modeling ability of the conditional random field is improved in the uninterrupted feedback, so that finally, GPCR topology prediction precision is improved.

Description

technical field [0001] The invention belongs to the field of prediction of G protein-coupled receptors, and in particular relates to a topological calculation and prediction method of G protein EUN receptors based on a feedback conditional random field. Background technique [0002] G Protein-Coupled Receptor (GPCR) is a kind of receptor protein with 7 transmembrane helices, and the topology of its transmembrane region is shown as figure 1 shown. GPCR is named for its ability to bind and regulate the activity of G protein. GPCR is responsible for the transmission of information between cells and the external environment. It is a very important class of signaling molecule receptors and plays an important role in biological and drug research. However, since the classical X-ray diffraction method and nuclear magnetic resonance (NMR) experimental method are ineffective for GPCRs, as of March 2015, only 24 high-precision three-dimensional structures of GPCRs and their ligands ha...

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): G06F19/18
Inventor 陈石敏吴宏杰陆卫忠王坤胡伏原付保川
Owner SUZHOU UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com