Protein-DNA binding residue prediction method based on sampling and integrated learning

Abstract

The invention discloses a protein-DNA binding residue prediction method based on sampling and integrated learning. The method comprises the steps of (1) feature extraction and training sample set construction, (2) sampling and model training, (3) model integration, and (4) online prediction. The method is used for solving the shortcomings of low prediction precision caused by the problems of few feature types and class imbalance in protein-DNA binding residue prediction problems and has the advantages of high prediction precision and high generalization ability.

Description

technical field [0001] The invention relates to the field of bioinformatics prediction of protein-ligand binding residues, specifically, a protein with high precision and strong generalization ability based on a downsampling algorithm based on hyperplane distance and an improved self-adaptive lifting algorithm - DNA-binding residue prediction method. Background technique [0002] In cells, proteins often need to bind with DNA molecules to participate in various life activities, such as DNA replication, DNA repair and virus infection. Accurate identification of protein-DNA binding residues facilitates analysis of protein function and design of new drugs. Traditionally, researchers have utilized biochemical methods such as EMSAs, Fast ChIP, and X-ray crystallography to identify protein-DNA binding residues. However, such methods are time-consuming and expensive, and cannot meet the urgent needs of related research in the post-gene era where protein-DNA complexes are rapidly ...

AI Technical Summary

Problems solved by technology

However, due to discarding unselected negative samples, random downsampling can easily cause information loss, resulting in low prediction accuracy of the final model

Images