Parallel drug-target correlation prediction method based on sorting learning

Abstract

The invention discloses a parallel drug-target correlation prediction method based on sorting learning, and belongs to the field of bioinformatics. According to the method, multiple types of similarity, correlation characteristics, chemical spatial characteristics and gene spatial characteristics are extracted through multiple characteristic extraction methods; then, due to the fact that a characteristic set with high dimensionality can be obtained through multi-angle characteristic extraction and samples do not have conventional positive and negative example labels, dimensionality reduction processing is conducted through a principal component analysis method, then, the dimensionality reduced characteristic set is input into a sorting learning algorithm, and finally the drug-target correlation degree under each query can be predicted and output. By utilizing sorting learning, the drug-target correlation is no longer simply divided into correlation or uncorrelation, and sorting is performed according to the correlation degree of the drug and the target, so that research and development of a new drug are facilitated, and redirection of the drug is also facilitated.

Description

technical field [0001] The invention belongs to the field of biological information systems, and in particular relates to a parallel drug-target correlation prediction method based on ranking learning. Background technique [0002] There are many methods and techniques for predicting drug-protein correlations. Traditional prediction methods are divided into two types: ligand-based and target-based: the ligand-based method requires the correlation information of the known ligand of the target protein, and uses this to define a pharmacophore model to describe the binding of the ligand. shared features, which means that this type of method is not suitable for situations where there is little known ligand information; target-based methods need to obtain the 3-dimensional structure of the target in advance, but the 3-dimensional structure of some protein sequences is unknown and difficult Obtain. [0003] Although traditional forecasting methods can guarantee high accuracy, the...

AI Technical Summary

Problems solved by technology

The introduction of machine learning has indeed made great progress in terms of speed, but both feature-based methods and similarity-based methods have certain shortcomings: on the one hand, similarity-based methods only rely on unilateral (drug or target), the second is that when the number of known ligands (or targets) that can act on the target (or ligand) is small, the similarity between the analyte and only a few samples can be drawn It is obviously not convincing enough; when using feature-based methods, drug information and protein sequence information may not be well represented in digital form due to the algorithm used

[0004] In addition, when using machine learning to predict drug-protein correlation, many researchers simply predict whether the drug is related to the protein, and classify the research into two Classification problem, no further exploration of the degree of drug-protein correlation, that is, no further exploration of which protein (drug) has the strongest correlation with a given drug (protein)

Images