Lysine succinylation modification prediction method based on bidirectional long-short term memory and convolutional neural network

Abstract

The invention discloses a lysine succinylation modification prediction method based on bidirectional long-short term memory and a convolutional neural network. The method comprises the following steps: segmenting a succinylation protein sequence into fragments which take lysine as a center and each of which comprises 15 amino acid residues at the upstream and the downstream, and processing the balance problem of data by using a random sampling method; and sending known lysine succinylation modification data into an embedded layer of a deep learning classification model, converting amino acids into vectors for expression, then inputting the vectors into a one-dimensional convolutional layer, a pooling layer, a bidirectional long-short term memory network layer, a discarding layer, a flat layer and a full connection layer, and finally outputting information of lysine succinylation modification sites. According to the method, the semantic relationship hidden in the succinylation sequence is absorbed, and lysine succinylation modification can be quickly and effectively predicted; and the invention further develops a network prediction platform which is used for on-line prediction of lysine succinylation modification sites.

Description

technical field [0001] The invention relates to the field of computational biomolecules, in particular to calculation and prediction of lysine succinylation modification using artificial intelligence theory and methods. Background technique [0002] Lysine succinylation is a typical post-translational modification of proteins and plays a crucial regulatory role in cellular processes. Identifying succinylation sites and understanding their mechanisms are crucial for the development of drugs for related diseases. For example, Sreedhar et al. demonstrated that succinylation of proteins causes charge transfer and structural changes that affect protein function; Ye et al. demonstrated that abnormal succinylation is involved in the pathogenesis of cancer; Gibson et al. demonstrated Succinylation has been linked to neurological disorders. [0003] Identifying succinylation is a cyclic iterative process from experiment to calculation and back to experiment, with two main paths: exp...

AI Technical Summary

Problems solved by technology

Existing biotechnology will lead to the loss of information such as the semantic relationship between residues during the conversion process from sequence to feature

Images