Overlapping protein complex identification method and system based on fuzzy clustering and gene ontology semantic similarity

Abstract

The invention provides an overlapping protein complex identification method and system based on fuzzy clustering and gene ontology semantic similarity. The system comprises a network construction module, a data preprocessing module, a parameter definition module, a model construction module, a model solving module, a protein complex identification module and a result display module. The protein complex recognition is realized by comprehensively considering the interaction relationship between the proteins in the protein interaction network and the gene ontology semantic similarity between the proteins. The method directly acts on the protein interaction network, can identify the overlapping protein complex in the network, is high in effect accuracy, and can effectively solve the protein complex identification problem in the protein interaction network.

Description

technical field [0001] The invention relates to the technical field of computer data processing and the field of computational biology, in particular to a method and system for identifying overlapping protein complexes based on fuzzy clustering and semantic similarity of gene ontology. Background technique [0002] At present, the existing protein complex identification methods are mainly based on the topological structure in the protein interaction network to complete the complex identification work, that is, to identify clusters with certain specific structures according to whether there is an interaction between proteins in the network. as a protein complex. Typical structures describing the topological properties of protein complexes include dense structures, k-cliques, and core-attached structures. However, protein complex identification methods based only on specific topological structures ignore a large amount of Gene Ontology semantic information associated with pro...

AI Technical Summary

Problems solved by technology

However, protein complex identification methods based only on specific topological structures ignore a large amount of Gene Ontology semantic information associated with proteins in protein interaction networks, which describe protein functions from three aspects, namely, molecular function, cellular group analysis and biological process

Neglect of Gene Ontology information prevents discovery of more biologically significant protein complexes

In addition, some known protein complexes overlap with each other, and if the overlapping between protein complexes is not taken into account, the identified protein complexes may be less accurate

[0003] Although some protein complex identification methods considering protein semantic information have been proposed, none of them consider the complete directed acyclic graph relationship inherent in the gene ontology semantic information, so the identified protein complexes perform poorly in accuracy. poor

Images