RESUMEN
OBJECTIVE@#To propose a new method for mining complexes in dynamic protein network using spatiotemporal convolution neural network.@*METHODS@#The edge strength, node strength and edge existence probability are defined for modeling of the dynamic protein network. Based on the time series information and structure information on the graph, two convolution operators were designed using Hilbert-Huang transform, attention mechanism and residual connection technology to represent and learn the characteristics of the proteins in the network, and the dynamic protein network characteristic map was constructed. Finally, spectral clustering was used to identify the protein complexes.@*RESULTS@#The simulation results on several public biological datasets showed that the F value of the proposed algorithm exceeded 90% on DIP dataset and MIPS dataset. Compared with 4 other recognition algorithms (DPCMNE, GE-CFI, VGAE and NOCD), the proposed algorithm improved the recognition efficiency by 34.5%, 28.7%, 25.4% and 17.6%, respectively.@*CONCLUSION@#The application of deep learning technology can improve the efficiency in analysis of dynamic protein networks.
Asunto(s)
Algoritmos , Análisis por Conglomerados , Simulación por Computador , Redes Neurales de la Computación , Proyectos de InvestigaciónRESUMEN
The microenvironment in the seminiferous tubules of buffalo changes with age, which affects the self-renewal and growth of spermatogonial stem cells (SSCs) and the process of spermatogenesis, but the mechanism remains to be elucidated. RNA-seq was performed to compare the transcript profiles of pre-pubertal buffalo (PUB) and adult buffalo (ADU) seminiferous tubules. In total, 17,299 genes from PUB and ADU seminiferous tubules identified through RNA-seq, among which 12,271 were expressed in PUB and ADU seminiferous tubules, 4,027 were expressed in only ADU seminiferous tubules, and 956 were expressed in only PUB seminiferous tubules. Of the 17,299 genes, we identified 13,714 genes that had significant differences in expression levels between PUB and ADU through GO enrichment analysis. Among these genes, 5,342 were significantly upregulated and possibly related to the formation or identity of the surface antigen on SSCs during self-renewal; 7,832 genes were significantly downregulated, indicating that genes in PUB seminiferous tubules do not participate in the biological processes of sperm differentiation or formation in this phase compared with those in ADU seminiferous tubules. Subsequently, through the combination with KEGG analysis, we detected enrichment in a number of genes related to the development of spermatogonial stem cells, providing a reference for study of the development mechanism of buffalo spermatogonial stem cells in the future. In conclusion, our data provide detailed information on the mRNA transcriptomes in PUB and ADU seminiferous tubules, revealing the crucial factors involved in maintaining the microenvironment and providing a reference for further in vitro cultivation of SSCs.