A protein saccharification site identification method

Abstract

The invention provides a protein saccharification site identification method. The method includes: collecting a saccharification site training data set; extracting a peptide chain from the saccharification site training data set; encoding and characterizing protein by using Digital vectors of peptide chains, the accessible surface area of amino acid in a peptide chain, the secondary structure probability of amino acid in the peptide chain and the grey correlation degree of the peptide chain; selecting a maximum correlation and minimum redundancy (mRMR) feature selection algorithm to find an optimal feature set, and training on a support vector machine to obtain a predictor, so as to identify the protein saccharification site. According to the protein saccharification site identification method provided by the invention, the amino acid sequence in the peptide chain, the accessible surface area of the amino acid in the peptide chain, the secondary structure probability of the amino acidin the peptide chain and the grey correlation degree of the peptide chain are fully considered, and the accuracy of protein saccharification site identification is improved.

Description

technical field [0001] The present application relates to the technical field of protein function prediction, in particular to a method for identifying protein glycosylation sites. Background technique [0002] Without the participation of enzymes, the process of covalently bonding reducing sugar molecules to proteins is called glycation. Glycation is one of the most important post-translational modification processes (PTMs) of proteins and involves a two-step reaction. First, the unstable Schiff bases are rearranged to form more stable Amadori products; then, advanced glycation endproducts (AGEs) are generated. AGEs themselves or their cross-linked products lead to direct changes in protein structure and function. When AGEs accumulate to a certain extent, they will damage various organs of the body. More and more studies have shown that AGEs exist in eyeball proteins, plasma, red blood cells, arteries and kidneys, and immunochemical methods have also found that the amoun...

AI Technical Summary

Problems solved by technology

First of all, some protein peptide chains in the data set used in the previous article have been updated in Uniprot. If they continue to be used, unnecessary noise will be introduced during training.

Secondly, the researchers only used the features of a single peptide chain and ignored the relationship between peptide chains. The extracted feature information is not perfect, which will affect the accuracy of the results.

Images