A method for ATP docking of proteins assisted by contact probability

Abstract

A protein ATP docking method based on contact probability. First, use five protein binding residue prediction servers such as ATPbind to predict the binding residue information of protein-ATP, and use the voting method to select the residue with the most occurrences as Binding residues to improve the accuracy of binding residues; secondly, extracting the contact probability matrix between specific types of binding residues and ATP atoms from the PDB database, and scoring the generated conformations as an energy function to improve docking accuracy; Finally, computational efficiency is improved by using an improved differential evolution algorithm to search for optimal individuals. The invention provides a contact probability-assisted protein ATP docking method with low calculation cost and high prediction accuracy.

Description

technical field [0001] The invention relates to the fields of bioinformatics, intelligent optimization and computer application, and in particular to a protein ATP docking method assisted by contact probability. Background technique [0002] With the continuous research of proteomics, it is more and more common to find that proteins combine with some ligands and small molecules to play a role in organisms as a whole. Throughout life, the protein-ligand mutual recognition process, including substrate-enzyme, antigen-antibody, hormone-receptor recognition, is an important basis for the molecular mechanisms and regulatory processes of various biological functions. The mutual recognition and interaction between proteins and ligands is an important way for proteins to exert their biological functions, and plays a very important role in various life activities, such as gene regulation, signal transduction, and immune response, etc., are inseparable from proteins and ligands Inter...

AI Technical Summary

Problems solved by technology

However, there is no energy function that can perfectly judge the energy of the complex. In addition, the inaccurate prediction of protein binding residues will also lead to errors in the energy function, resulting in inaccurate predicted complex structures. Some intelligent algorithms also exist problems with long search times or inaccurate search results

[0005] Therefore, existing protein-ligand molecular docking methods have shortcomings in terms of prediction accuracy and computational cost, and need to be improved

Images