Searching the maximum bicliques or bipartite subgraphs in a graph is a tough question. We proposed a new and efficient method, Searching Quasi-Bicliques (SQB) algorithm, to detect maximum quasi-bicliques from protein-...Searching the maximum bicliques or bipartite subgraphs in a graph is a tough question. We proposed a new and efficient method, Searching Quasi-Bicliques (SQB) algorithm, to detect maximum quasi-bicliques from protein-protein interaction network. As a Divide-and-Conquer method, SQB consists of three steps: first, it divides the protein-protein interaction network into a number of Distance-2-Subgraphs;second, by combining top-down and branch-and-bound methods, SQB seeks quasi-bicliques from every Distance-2-Subgraph;third, all the redundant results are removed. We successfully applied our method on the Saccharomyces cerevisiae dataset and obtained 2754 distinct quasi-bicliques.展开更多
相较于传统药物的研发,药物-靶标的预测方法能够有效降低成本,加快研发进程,但是在实际应用中存在数据集平衡度低、预测精确率不高等问题。基于此,提出一种自适应球形演化的药物-靶标相互作用预测方法ASEKELM(self-Adaptive Spherical E...相较于传统药物的研发,药物-靶标的预测方法能够有效降低成本,加快研发进程,但是在实际应用中存在数据集平衡度低、预测精确率不高等问题。基于此,提出一种自适应球形演化的药物-靶标相互作用预测方法ASEKELM(self-Adaptive Spherical Evolution based on Kernel Extreme Learning Machine)。该方法根据结构相似的药物与靶标更易存在相互作用的原理筛选出高置信度的负样本;并且为了解决球形演化算法易陷入局部最优的问题,利用搜索因子历史记忆的反馈机制及群大小线性递减的策略(LPSR),实现全局搜索和局部搜索的平衡,提高算法的寻优能力;然后利用自适应球形演化算法对核极限学习机(KELM)的参数进行优化。在基于黄金标准的数据集上将ASEKELM与NetLapRLS(Network Laplacian Regularized Least Square)、BLM-NII(Bipartite Local Model with Neighbor-based Interaction profile Inferring)等算法进行对比,验证算法的性能。实验结果表明,在酶(E)、G-蛋白偶联受体(GPCR)、离子通道(IC)和核受体(NR)数据集中,ASE-KELM的ROC曲线下面积(AUC)与PR曲线下面积(AUPR)均优于对比算法;且基于DrugBank等数据库,ASE-KELM在预测新药物-靶标对的验证过程中表现良好。展开更多
A gravitational search algorithm(GSA)uses gravitational force among individuals to evolve population.Though GSA is an effective population-based algorithm,it exhibits low search performance and premature convergence.T...A gravitational search algorithm(GSA)uses gravitational force among individuals to evolve population.Though GSA is an effective population-based algorithm,it exhibits low search performance and premature convergence.To ameliorate these issues,this work proposes a multi-layered GSA called MLGSA.Inspired by the two-layered structure of GSA,four layers consisting of population,iteration-best,personal-best and global-best layers are constructed.Hierarchical interactions among four layers are dynamically implemented in different search stages to greatly improve both exploration and exploitation abilities of population.Performance comparison between MLGSA and nine existing GSA variants on twenty-nine CEC2017 test functions with low,medium and high dimensions demonstrates that MLGSA is the most competitive one.It is also compared with four particle swarm optimization variants to verify its excellent performance.Moreover,the analysis of hierarchical interactions is discussed to illustrate the influence of a complete hierarchy on its performance.The relationship between its population diversity and fitness diversity is analyzed to clarify its search performance.Its computational complexity is given to show its efficiency.Finally,it is applied to twenty-two CEC2011 real-world optimization problems to show its practicality.展开更多
Cocrystallization integrates the merits of high energy and insensitivity between energetic molecules to obtain energetics with satisfying performance.However,how to obtain supramolecular synthons accurately and rapidl...Cocrystallization integrates the merits of high energy and insensitivity between energetic molecules to obtain energetics with satisfying performance.However,how to obtain supramolecular synthons accurately and rapidly for predicting the structure and property of cocrystal remains a challenging problem.In this research,an efficient systematic search approach to predict CL-20/2,4-DNI cocrystal has been proposed that 2,4-DNI revolves around CL-20 with a stoichiometric ratio of 1:1 in accordance with the specified rules(hydrogen bond length:2.2-3.0 Å;search radius:6.5 Å;the number of hydrogen bond:1-3).Eight possible supramolecular synthons were obtained by combining quantum chemistry with molecular mechanics.Crystal structure prediction indicated that there are four structures in cocrystal,namely P21/c,P212121,Pbca and Pna21,and CL-20/2,4-DNI cocrystal is likely to be P21/c and the corresponding cell parameters are Z=4,a=8.28 Å,b=12.17 Å,c=20.42 Å,α=90°,β=96.94°,γ=90°,and ρ=1.9353 g/cm^(3).To further study the intermolecular interaction of CL-20/2,4-DNI cocrystal,a series of theoretical analyses were employed including intermolecular interaction energy,electrostatic potential(ESP),Density of State(DOS),Hirshfeld surface analysis.The C-H…O hydrogen bonds are demonstrated as the predominant driving forces in the cocrystal formation.The mechanical properties and detonation properties of CL-20/2,4-DNI cocrystal implies that the cocrystal shows better ductility and excellent detonation performances(9257 m/s,39.27 GPa)and can serve as a promising energetic material.Cocrystal structure predicted was compared with the experimental one to verify the accuracy of systematic search approach.There is a less than 8.8%error between experiment and predict results,indicating the systematic search approach has extremely high reliability and accuracy.The systematic search approach can be a new strategy to search supramolecular synthons and identify structures effectively and does have the potential to promote the development of energetic cocrystal by theoretical design.展开更多
This paper proposes a new approach for detecting human survivors in destructed environments using an autonomous robot. The proposed system uses a passive infrared sensor to detect the existence of living humans and a ...This paper proposes a new approach for detecting human survivors in destructed environments using an autonomous robot. The proposed system uses a passive infrared sensor to detect the existence of living humans and a low-cost camera to acquire snapshots of the scene. The images are fed into a feed-forward neural network, trained to detect the existence of a human body or part of it within an obstructed environment. This approach requires a relatively small number of images to be acquired and processed during the rescue operation, which considerably reduces the cost of image processing, data transmission, and power consumption. The results of the conducted experiments demonstrated that this system has the potential to achieve high performance in detecting living humans in obstructed environments relatively quickly and cost-effectively. The detection accuracy ranged between 79% and 91% depending on a number of factors such as the body position, the light intensity, and the relative color matching between the body and the surrounding environment.展开更多
文摘Searching the maximum bicliques or bipartite subgraphs in a graph is a tough question. We proposed a new and efficient method, Searching Quasi-Bicliques (SQB) algorithm, to detect maximum quasi-bicliques from protein-protein interaction network. As a Divide-and-Conquer method, SQB consists of three steps: first, it divides the protein-protein interaction network into a number of Distance-2-Subgraphs;second, by combining top-down and branch-and-bound methods, SQB seeks quasi-bicliques from every Distance-2-Subgraph;third, all the redundant results are removed. We successfully applied our method on the Saccharomyces cerevisiae dataset and obtained 2754 distinct quasi-bicliques.
文摘相较于传统药物的研发,药物-靶标的预测方法能够有效降低成本,加快研发进程,但是在实际应用中存在数据集平衡度低、预测精确率不高等问题。基于此,提出一种自适应球形演化的药物-靶标相互作用预测方法ASEKELM(self-Adaptive Spherical Evolution based on Kernel Extreme Learning Machine)。该方法根据结构相似的药物与靶标更易存在相互作用的原理筛选出高置信度的负样本;并且为了解决球形演化算法易陷入局部最优的问题,利用搜索因子历史记忆的反馈机制及群大小线性递减的策略(LPSR),实现全局搜索和局部搜索的平衡,提高算法的寻优能力;然后利用自适应球形演化算法对核极限学习机(KELM)的参数进行优化。在基于黄金标准的数据集上将ASEKELM与NetLapRLS(Network Laplacian Regularized Least Square)、BLM-NII(Bipartite Local Model with Neighbor-based Interaction profile Inferring)等算法进行对比,验证算法的性能。实验结果表明,在酶(E)、G-蛋白偶联受体(GPCR)、离子通道(IC)和核受体(NR)数据集中,ASE-KELM的ROC曲线下面积(AUC)与PR曲线下面积(AUPR)均优于对比算法;且基于DrugBank等数据库,ASE-KELM在预测新药物-靶标对的验证过程中表现良好。
基金supported by National Natural Science Foundation of China(61872271,61673403,61873105,11972115)the Fundamental Research Funds for the Central Universities(22120190208)JSPS KAKENHI(JP17K12751)。
文摘A gravitational search algorithm(GSA)uses gravitational force among individuals to evolve population.Though GSA is an effective population-based algorithm,it exhibits low search performance and premature convergence.To ameliorate these issues,this work proposes a multi-layered GSA called MLGSA.Inspired by the two-layered structure of GSA,four layers consisting of population,iteration-best,personal-best and global-best layers are constructed.Hierarchical interactions among four layers are dynamically implemented in different search stages to greatly improve both exploration and exploitation abilities of population.Performance comparison between MLGSA and nine existing GSA variants on twenty-nine CEC2017 test functions with low,medium and high dimensions demonstrates that MLGSA is the most competitive one.It is also compared with four particle swarm optimization variants to verify its excellent performance.Moreover,the analysis of hierarchical interactions is discussed to illustrate the influence of a complete hierarchy on its performance.The relationship between its population diversity and fitness diversity is analyzed to clarify its search performance.Its computational complexity is given to show its efficiency.Finally,it is applied to twenty-two CEC2011 real-world optimization problems to show its practicality.
基金the support of the National Natural Science Foundation of China(No.22005090)Beijing Institute of Technology Research Fund Program for Young Scholars+2 种基金the National Natural Science Foundation of China(No.11672040 and No.21801016)Open Research Fund Program of Science and Technology on Aerospace Chemical Power Laboratory(STACPL120201B02)the State Key Laboratory of Explosion Science and Technology(No.YB2016-17)。
文摘Cocrystallization integrates the merits of high energy and insensitivity between energetic molecules to obtain energetics with satisfying performance.However,how to obtain supramolecular synthons accurately and rapidly for predicting the structure and property of cocrystal remains a challenging problem.In this research,an efficient systematic search approach to predict CL-20/2,4-DNI cocrystal has been proposed that 2,4-DNI revolves around CL-20 with a stoichiometric ratio of 1:1 in accordance with the specified rules(hydrogen bond length:2.2-3.0 Å;search radius:6.5 Å;the number of hydrogen bond:1-3).Eight possible supramolecular synthons were obtained by combining quantum chemistry with molecular mechanics.Crystal structure prediction indicated that there are four structures in cocrystal,namely P21/c,P212121,Pbca and Pna21,and CL-20/2,4-DNI cocrystal is likely to be P21/c and the corresponding cell parameters are Z=4,a=8.28 Å,b=12.17 Å,c=20.42 Å,α=90°,β=96.94°,γ=90°,and ρ=1.9353 g/cm^(3).To further study the intermolecular interaction of CL-20/2,4-DNI cocrystal,a series of theoretical analyses were employed including intermolecular interaction energy,electrostatic potential(ESP),Density of State(DOS),Hirshfeld surface analysis.The C-H…O hydrogen bonds are demonstrated as the predominant driving forces in the cocrystal formation.The mechanical properties and detonation properties of CL-20/2,4-DNI cocrystal implies that the cocrystal shows better ductility and excellent detonation performances(9257 m/s,39.27 GPa)and can serve as a promising energetic material.Cocrystal structure predicted was compared with the experimental one to verify the accuracy of systematic search approach.There is a less than 8.8%error between experiment and predict results,indicating the systematic search approach has extremely high reliability and accuracy.The systematic search approach can be a new strategy to search supramolecular synthons and identify structures effectively and does have the potential to promote the development of energetic cocrystal by theoretical design.
文摘This paper proposes a new approach for detecting human survivors in destructed environments using an autonomous robot. The proposed system uses a passive infrared sensor to detect the existence of living humans and a low-cost camera to acquire snapshots of the scene. The images are fed into a feed-forward neural network, trained to detect the existence of a human body or part of it within an obstructed environment. This approach requires a relatively small number of images to be acquired and processed during the rescue operation, which considerably reduces the cost of image processing, data transmission, and power consumption. The results of the conducted experiments demonstrated that this system has the potential to achieve high performance in detecting living humans in obstructed environments relatively quickly and cost-effectively. The detection accuracy ranged between 79% and 91% depending on a number of factors such as the body position, the light intensity, and the relative color matching between the body and the surrounding environment.
