Search

Computational methods including centrality and machine learning-based methods have been proposed to identify essential proteins for understanding the minimum requirements of the survival and evolution of a cell. In centrality methods, researchers are required to design a score function which is based on prior knowledge, yet is usually not sufficient to capture the complexity of biological information. In machine learning-based methods, some selected biological features cannot represent the complete properties of biological information as they lack a computational framework to automatically select features. To tackle these problems, we propose a deep learning framework to automatically learn biological features without prior knowledge. We use node2vec technique to automatically learn a richer representation of protein-protein interaction (PPI) network topologies than a score function. Bidirectional long short term memory cells are applied to capture non-local relationships in gene expression data. For subcellular localization information, we exploit a high dimensional indicator vector to characterize their feature. To evaluate the performance of our method, we tested it on PPI network of S. cerevisiae. Our experimental results demonstrate that the performance of our method is better than traditional centrality methods and is superior to existing machine learning-based methods. To explore which of the three types of biological information is the most vital element, we conduct an ablation study by removing each component in turn. Our results show that the PPI network embedding contributes most to the improvement. In addition, gene expression profiles and subcellular localization information are also helpful to improve the performance in identification of essential proteins. [ABSTRACT FROM AUTHOR]

Rural residential areas are an extensive dispersion with localized concentrations, and the area of land utilization per capita is large in Dazhu village in Hechuan of Chongqing. Inefficient utilization of rural residential areas is an adverse process all over China during the urban-rural transitional period, especially in traditional agricultural areas. The space reconstruction of a rural residential area could be a breakthrough in the rational utilization of land resources, advancing new countryside construction, restructuring village space, and promoting urban-rural integration and development. This paper used the symbiotic theory to establish a rural residential restructuring symbiotic system. The system included rural residential areas as a symbiotic unit, and the policy environment and the village-domain environment as symbiotic environment. Due to the mutual functional differences of symbiotic units, village spatial reconstruction should consider a mutually beneficial symbiotic relationship between the units, namely the mutualism mode. The research analyzed a rural residential restructuring symbiotic system, and made clear the restructuring principles and procedure needed to build the space reconstruction strategy of a rural settlement. The thesis selected the demonstration village of the whole village advancement—Dazhu village in Hechuan of Chongqing as the object of empirical study. It built three kinds of functional groups—productivity-oriented, service-oriented, and living-oriented groups, a space representation of which was already presented in the village, and formed the layout of 'one axis and three groups' at the the village scale. The results showed that: first, adopting the rural residential restructuring symbiotic system analysis accords with the reality of Dazhu village to restructure village space. It further showed that the symbiotic theory has strong applicability to space reconstruction of a rural settlement. Secondly, the results of the empirical study showed that the space reconstruction of a rural settlement, which is based on the symbiotic strategy, can both ensure the inter-operability of a rural settlement and respect the principal position of farmers. It realizes 'shared resources, co-constructed environment' and exploits environmental advantages in the village domain. It can also improve the utilization efficiency of rural residential areas. Through the study of the demonstration village, the paper provides a scientific basis for formulating village space reconstruction and a new approach to the whole village advancement in a hilly area and the beautiful village construction. Due to the fact that the factors which influence rural residential restructuring are very complex, the regional social, economic, and environmental development strategies and resource endowment conditions which are expected to be considered comprehensively, need to be studied further. Different types of household willingness and future livelihoods also require deeper study. [ABSTRACT FROM AUTHOR]