Biological network clustering method and system based on high-order structure

Abstract

The invention relates to a biological network clustering method and system based on a high-order structure. The system comprises a network construction module, a model construction module, a network clustering module, a redundancy deletion module and a result display module. Rich high-order structure information in a biological network is utilized to identify functional modules in the biological network, and clustering analysis can be performed on various types of network motifs by combining the advantages of a high-order Markov random process. The method has excellent performance; based onthe clustering result of the high-order structure information, a new thought is provided for biological network analysis, such as recognition of overlapping protein complexes and inference of new signal paths; and meanwhile, abundant organization structures presented in the biological network are disclosed. The biological network clustering method and system directly act on biological networks such as a protein interaction network and a gene co-expression network, are high in effect accuracy, and are a very reliable biological network clustering method and system.

Description

technical field [0001] The invention relates to the technical field of computer data processing, in particular to a high-order structure-based biological network clustering method and system. Background technique [0002] Cluster analysis in biological networks involves identifying biologically meaningful functional modules, providing valuable insights into understanding complex biological systems. Most clustering algorithms only use low-order connection patterns at the level of individual biological entities and their connections for cluster analysis. Although links are the basic units of networks, considering low-order connectivity patterns may not be sufficient to fully exploit the structural information available in biological networks, thus limiting further improvements in clustering accuracy. Existing clustering techniques exploit low-order connectivity patterns at the level of individual biomolecules and their connections, but few techniques consider higher-order con...

AI Technical Summary

Problems solved by technology

Although links are the basic unit of networks, considering low-order connectivity patterns may not be sufficient to fully exploit the structural information available in biological networks, limiting further improvements in clustering accuracy

Existing clustering techniques exploit low-order connectivity patterns at the level of individual biomolecules and their connections, but few techniques take into account higher-order connectivity patterns at the level of small networks or motif structures

Images