Prediction method for protein sequence disulfide bond connection mode based on forest regression model

Abstract

The invention discloses a prediction method for protein sequence disulfide bond connection mode based on a forest regression model. The method comprises the following steps that step 1, the feature vector of each cysteine residues pair in the protein sequence is obtained through multi-view feature extraction and feature combination; step 2, for the to-be-predicated protein sequence information and training datasets, the feature vectors of all the cysteine residues pairs in the to-be-predicated protein sequence information and training datasets are generated, so that a training sample set and a to-be-predicated sample set are respectively formed; step 3, the distribution rule of cysteine samples in the feature space is studied through the random forest algorithm, so that a random forest regression model is generated; step 4, the feature vector of the to-be-predicated sample set is predicated through the random forest regression model, so that the prone value of each cysteine residues pair forming disulfide bond is obtained, and the disulfide bond connection mode with the highest score is finally-predicated the disulfide bond connection mode in the protein sequence.

Description

technical field [0001] The invention relates to the technical field of disulfide bond prediction in protein sequences of bioinformatics, in particular to a method for predicting disulfide bond connection patterns of protein sequences based on a regression forest model. Background technique [0002] Disulfide bonds are one of the most important structural properties of proteins. Disulfide bonds are the primary covalent bonds formed between two cysteine ​​residues in a protein polypeptide chain, and they can form either interchain or intrachain in the peptide chain. Disulfide bonds play a very important role in protein folding and stability. Therefore, predicting the way cysteine ​​residues in proteins form disulfide bonds plays a pivotal role in predicting protein structure and function. [0003] There are many methods for predicting disulfide bonds, for example, DISULFIND method (A. Ceroni, A. Passerini, A. Vullo et al., "DISULFIND: a disulfide bonding state and cysteine ​...

AI Technical Summary

Problems solved by technology

In summary, although some progress has been made in the prediction of disulfide bond patterns in the prior art, there is still room for improvement in the prediction accuracy.

Images