Protein lysine malonylation site prediction method based on deep learning

Abstract

The invention discloses a protein lysine malonylation site prediction method based on deep learning, and relates to the technical field of biological information. The method comprises the steps: converting the character information of a protein sequence into a numerical vector by adopting an enhanced amino acid composition, a grouped enhanced amino acid composition, a dipeptide deviation expectedaverage value, a K neighbor score and a BLOSUM62 matrix feature extraction algorithm, performing fusion and obtaining a feature space, wherein the influence of each potential feature on a prediction result is fully considered; performing calculating by using a linear convolutional neural network to obtain malonyl site specificity characteristics; selecting related features and reducing feature dimensions through a maximum pooling layer, classifying malonylation sites and non-malonylation sites in combination with a multi-layer deep neural network, constructing a protein malonylation site prediction model DeepMal, and evaluating prediction performance by using 10-fold cross validation and an independent test data set. The model DeepMal is remarkably improved in evaluation indexes, and further promotion of application of deep learning in protein function prediction is facilitated.

Description

technical field [0001] The invention relates to the field of biological information technology, in particular to a method for predicting protein lysine malonylation sites based on deep learning. Background technique [0002] As an important protein post-translational modification site, malonylation was first discovered in 2011, an evolutionarily conserved protein post-translational modification type that occurs on lysine, and its occurrence depends on malonyl-CoA Adds a malonyl group to lysine and changes its charge from +1 to -1. This change has the potential to disrupt the electrostatic interactions of lysine with other amino acids and alter the protein structure, and may even affect its binding to target proteins. It has been shown to exist in a variety of metabolic pathways, such as glucose and fatty acid metabolism, Fatty acid synthesis and oxidation, impaired mitochondrial function, also related to muscle contraction, myocardial ischemia and hypothalamic regulation of...

AI Technical Summary

Problems solved by technology

[0005] i) Existing methods only use limited features, and other potential features will also have an impact on the prediction results

[0006] ii) Redundant features in model building will reduce prediction performance

Images