Protein-protein interaction prediction method based on deep forest

Abstract

The invention, which belongs to the technical field of biological information, discloses a protein-protein interaction prediction method based on a deep forest. According to the method, pseudo amino acid composition, a mutual information descriptor, composition, and distribution, a conversion descriptor, an amino acid composition position specificity score matrix and a dipeptide composition position specificity score matrix are fused to convert a protein sequence into a numerical vector; sequence information, physicochemical property information and evolution information of the protein pair are fused as initial characteristics of a sample; an elastic network is used for feature selection, and redundant and irrelevant features are removed; and a fused optimal feature vector is inputted intoa constructed multi-granularity cascade depth forest to predict protein-protein interaction. The method is simple and effective, the deep forest can represent the high-level feature information of the protein pair, the results of the training set and the test set are obviously superior to those of other prediction methods, and a certain reference can be provided for drug target prediction and human disease treatment.

Description

technical field [0001] The invention belongs to the technical field of biological information, and relates to a protein-protein interaction prediction method based on deep forest. Background technique [0002] Protein-protein interactions (PPIs) play an important role in the structure and function of cells. The disorder of the network structure will cause abnormalities in the life activities of cells. In-depth study of PPIs is very important for understanding the life activities of cells and elucidating cell life. It is of great significance in terms of function and human disease prevention and treatment. With the advent of the post-genome era and the development of high-throughput sequencing technologies, a large number of experimentally identified PPIs have been generated. Considering that the experimental method to identify and identify PPIs is resource-consuming and takes a long period, how to use machine learning-based prediction of protein-protein interactions is part...

AI Technical Summary

Problems solved by technology

[0005] But deep learning also has its shortcomings. First, before training the deep learning model, the number of layers and nodes of the neural network need to be specified in advance, which requires a lot of energy to adjust the parameters.

Images