Disease-related gene module detection based on a multi-label propagation clustering algorithm

• Published in: PloS one Vol. 12; no. 5; p. e0178006
• Main Authors: Jiang, Xue, Zhang, Han, Quan, Xiongwen, Liu, Zhandong, Yin, Yanbin
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 19.05.2017; Public Library of Science (PLoS)
• Subjects: Accuracy; Affinity; Aggregates; Algorithms; Amyotrophic lateral sclerosis; Animals; Bioinformatics; Biological effects; Biology; Biology and Life Sciences; Cancer; Cell migration; Cluster Analysis; Clustering; Computational Biology - methods; Computational neuroscience; Computer and Information Sciences; Computer applications; Computer programs; Computer vision; Construction; Convergence; Data mining; Data processing; Decomposition; Disease; Disease Models, Animal; DNA microarrays; Engineering; Experiments; Feasibility studies; Gene expression; Gene Expression Profiling; Gene Regulatory Networks; Genetic Markers; Genetics; Genomics; Health aspects; Humans; Huntingtin; Huntington Disease - genetics; Information processing; Information retrieval; International conferences; Laboratories; Machine learning; Mathematical analysis; Matrices (mathematics); Medicine and Health Sciences; Methods; Mice; MicroRNAs; miRNA; Models, Theoretical; Modules; Molecular biology; Molecular modelling; Multimedia; Nervous system; Network analysis; Neurodegeneration; Neurosciences; Nodes; Noise reduction; Physical Sciences; Physics; Propagation; Protein transport; Ranking; Research and Analysis Methods; Ribonucleic acid; RNA; Robotics; Similarity measures; Social interactions; Social organization; Sparsity; Statistical analysis; Studies; Systems analysis; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0178006

Detecting disease-related gene modules by analyzing gene expression data is of great significance. It is helpful for exploratory analysis of the interaction mechanisms of genes under complex disease phenotypes. The multi-label propagation algorithm (MLPA) has been widely used in module detection for its fast and easy implementation. The accuracy of MLPA greatly depends on the connections between nodes, and most existing research focuses on measuring the similarity between nodes. However, MLPA does not perform well with loose connections between disease-related genes. Moreover, the biological significance of modules obtained by MLPA has not been demonstrated. To solve these problems, we designed a double label propagation clustering algorithm (DLPCA) based on MLPA to study Huntington's disease. In DLPCA, in addition to category labels, we introduced pathogenic labels to supervise the process of multi-label propagation clustering. The pathogenic labels contain pathogenic information about disease genes and the hierarchical structure of gene expression data. Experimental results demonstrated the superior performance of DLPCA compared with other conventional gene-clustering algorithms.