Subspace fusion-based protein-vitamin binding location point predicting method

A technology of binding sites and prediction methods, which is applied in the fields of instruments, calculations, electrical digital data processing, etc., and can solve problems such as large gaps and poor interpretability

CN103955628AInactive Publication Date: 2014-07-30NANJING UNIV OF SCI & TECH
5 Cites 19 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2014-07-30
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides a subspace fusion-based protein-vitamin binding location point predicting method. The method comprises the steps of feature extracting and feature combining: extracting evolution information, secondary-level structural information the binding tendency information of a protein by respectively using a PSI-BLAST, a PSIPRED and a protein-vitamin binding location point tendency table, and converting amino acid residues in a protein sequence into a vector presentation mode by a sliding window and serial combination; using a multi-feature selection algorithm to perform feature selection on an original feature space for multiple times; forming a feature subspace by feature subsets obtained from feature selection every time and establishing multiple feature subspaces; training one SVM (support vector machine) classifier for each obtained feature subspace; fusing multiple SVM classifiers which are trained by a weighted average classifier fusing mode; performing protein-vitamin binding location prediction on the protein to be predicted based on a fused SVM predictor. The prediction method is fast in prediction sped and high in prediction precision.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of bioinformatics protein-vitamin interaction, in particular to a method for predicting protein-vitamin binding sites based on subspace fusion. Background technique

[0002] The interaction between proteins and vitamins plays a vital role in metabolism and is ubiquitous and indispensable in life activities. Determining the binding sites between proteins and vitamins through biological experiments takes a lot of time and money, and is inefficient. With the rapid development of sequencing technology and the continuous advancement of human structural genome, proteomics has accumulated a large number of protein sequences that have not been labeled with vitamin binding sites. Therefore, there is an urgent need to develop a fast and accurate intelligent prediction method for protein-vitamin binding sites directly from the protein sequence by applying the relevant knowledge of bioinformatics, and it is of great significance...

Examples

Embodiment Construction

[0085] In order to better understand the technical content of the present invention, specific embodiments are given together with the attached drawings for description as follows.

[0086] Such as figure 1 As shown, according to a preferred embodiment of the present invention, the protein-vitamin binding site prediction method based on subspace fusion, first, use PSI-BLAST and PSIPRED to obtain the PSSM matrix (ie evolutionary information matrix) and secondary structure probability matrix, and the binding propensity matrix of the protein generated from the protein-vitamin binding site propensity table; secondly, from the PSSM matrix, the secondary structure probability matrix, and the protein-vitamin binding site Point propensity table to construct the feature vector of each amino acid residue; then, use the three feature selection algorithms of Joint Laplacian Feature Weights Learning (Algorithm 1), Fisher Score (Algorithm 2) and Laplacian Score (Algorithm 3) to construct fea...