Essential proteins are an indispensable part of cells and play an extremely significant role in genetic disease diagnosis and drug development.Therefore,the prediction of essential proteins has received extensive atte...Essential proteins are an indispensable part of cells and play an extremely significant role in genetic disease diagnosis and drug development.Therefore,the prediction of essential proteins has received extensive attention from researchers.Many centrality methods and machine learning algorithms have been proposed to predict essential proteins.Nevertheless,the topological characteristics learned by the centrality method are not comprehensive enough,resulting in low accuracy.In addition,machine learning algorithms need sufficient prior knowledge to select features,and the ability to solve imbalanced classification problems needs to be further strengthened.These two factors greatly affect the performance of predicting essential proteins.In this paper,we propose a deep learning framework based on temporal convolutional networks to predict essential proteins by integrating gene expression data and protein-protein interaction(PPI)network.We make use of the method of network embedding to automatically learn more abundant features of proteins in the PPI network.For gene expression data,we treat it as sequence data,and use temporal convolutional networks to extract sequence features.Finally,the two types of features are integrated and put into the multi-layer neural network to complete the final classification task.The performance of our method is evaluated by comparing with seven centrality methods,six machine learning algorithms,and two deep learning models.The results of the experiment show that our method is more effective than the comparison methods for predicting essential proteins.展开更多
Protein–protein interaction(PPI)network analysis is an effective method to identify key proteins during plant development,especially in species for which basic molecular research is lacking,such as apple(Malus domest...Protein–protein interaction(PPI)network analysis is an effective method to identify key proteins during plant development,especially in species for which basic molecular research is lacking,such as apple(Malus domestica).Here,an MdPPI network containing 30806 PPIs was inferred in apple and its quality and reliability were rigorously verified.Subsequently,a rootgrowth subnetwork was extracted to screen for critical proteins in root growth.Because hormone-related proteins occupied the largest proportion of critical proteins,a hormonerelated sub-subnetwork was further extracted from the root-growth subnetwork.Among these proteins,auxin-related M.domestica TRANSPORT INHIBITOR RESISTANT 1(MdTIR1)served as the central,high-degree node,implying that this protein exerts essential roles in root growth.Furthermore,transgenic apple roots overexpressing an MdTIR1 transgene displayed increased primary root elongation.Expression analysis showed that MdTIR1 significantly upregulated auxin-responsive genes in apple roots,indicating that it mediates root growth in an auxin-dependent manner.Further experimental validation revealed that MdTIR1 interacted with and accelerated the degradation of MdIAA28,MdIAA43,andMdIAA46.Thus,MdTIR1-mediated degradation of MdIAAs is critical in auxin signal transduction and root growth regulation in apple.Moreover,our network analysis and high-degree node screening provide a novel research technique for more generally characterizing molecular mechanisms.展开更多
由于PPI网络数据的无尺度和小世界特性,使得目前对此类数据的聚类算法效果不理想.根据PPI网络的拓扑结构特性,本文提出了一种基于连接强度的蚁群优化(Joint Strength based Ant Colony Optimization,JSACO)聚类算法,该算法引入了连接强...由于PPI网络数据的无尺度和小世界特性,使得目前对此类数据的聚类算法效果不理想.根据PPI网络的拓扑结构特性,本文提出了一种基于连接强度的蚁群优化(Joint Strength based Ant Colony Optimization,JSACO)聚类算法,该算法引入了连接强度的概念对蚁群聚类算法中的拾起/放下规则加以改进,以连接强度作为拾起规则,对结点进行聚类,并根据放下规则放弃部分不良数据,产生最终聚类结果.最后采用了MIPS数据库中的PPI数据进行实验,将JSACO算法与PPI网络数据的其他聚类算法进行比较,聚类结果表明JSACO算法正确率高,时间开销低.展开更多
针对蚁群聚类在蛋白质相互作用(protein-protein interaction,PPI)网络中进行功能模块检测问题上时间性能的不足,提出一种快速的基于蚁群聚类的PPI网络功能模块检测(fast ant colony clustering for functional module detection,FACC-F...针对蚁群聚类在蛋白质相互作用(protein-protein interaction,PPI)网络中进行功能模块检测问题上时间性能的不足,提出一种快速的基于蚁群聚类的PPI网络功能模块检测(fast ant colony clustering for functional module detection,FACC-FMD)方法.该算法计算每个蛋白质与核心组蛋白质的相似度,根据拾起放下模型进行聚类,得到的初始聚类结果中功能模块之间相似度很小,省去了原始蚁群聚类算法中的合并和过滤操作,缩短了求解时间.同时该算法根据蛋白质的关键性对蚁群聚类中的拾起放下操作做了更严格的约束,以减少拾起放下的次数,加速了聚类的过程.在多个PPI网络上的实验表明:与原始蚁群聚类方法相比,FACC-FMD大幅度提高了时间性能,同时取得了良好的检测质量,而且与近年来的一些经典算法相比在多项性能指标上也具有一定的优势.展开更多
基金the National Natural Science Foundation of China(Nos.11861045 and 62162040)。
文摘Essential proteins are an indispensable part of cells and play an extremely significant role in genetic disease diagnosis and drug development.Therefore,the prediction of essential proteins has received extensive attention from researchers.Many centrality methods and machine learning algorithms have been proposed to predict essential proteins.Nevertheless,the topological characteristics learned by the centrality method are not comprehensive enough,resulting in low accuracy.In addition,machine learning algorithms need sufficient prior knowledge to select features,and the ability to solve imbalanced classification problems needs to be further strengthened.These two factors greatly affect the performance of predicting essential proteins.In this paper,we propose a deep learning framework based on temporal convolutional networks to predict essential proteins by integrating gene expression data and protein-protein interaction(PPI)network.We make use of the method of network embedding to automatically learn more abundant features of proteins in the PPI network.For gene expression data,we treat it as sequence data,and use temporal convolutional networks to extract sequence features.Finally,the two types of features are integrated and put into the multi-layer neural network to complete the final classification task.The performance of our method is evaluated by comparing with seven centrality methods,six machine learning algorithms,and two deep learning models.The results of the experiment show that our method is more effective than the comparison methods for predicting essential proteins.
基金supported by the National Natural Science Foundation of China(31972357,31901574,and 31772254)the National Key R&D Program of China(2019YFD1000104)。
文摘Protein–protein interaction(PPI)network analysis is an effective method to identify key proteins during plant development,especially in species for which basic molecular research is lacking,such as apple(Malus domestica).Here,an MdPPI network containing 30806 PPIs was inferred in apple and its quality and reliability were rigorously verified.Subsequently,a rootgrowth subnetwork was extracted to screen for critical proteins in root growth.Because hormone-related proteins occupied the largest proportion of critical proteins,a hormonerelated sub-subnetwork was further extracted from the root-growth subnetwork.Among these proteins,auxin-related M.domestica TRANSPORT INHIBITOR RESISTANT 1(MdTIR1)served as the central,high-degree node,implying that this protein exerts essential roles in root growth.Furthermore,transgenic apple roots overexpressing an MdTIR1 transgene displayed increased primary root elongation.Expression analysis showed that MdTIR1 significantly upregulated auxin-responsive genes in apple roots,indicating that it mediates root growth in an auxin-dependent manner.Further experimental validation revealed that MdTIR1 interacted with and accelerated the degradation of MdIAA28,MdIAA43,andMdIAA46.Thus,MdTIR1-mediated degradation of MdIAAs is critical in auxin signal transduction and root growth regulation in apple.Moreover,our network analysis and high-degree node screening provide a novel research technique for more generally characterizing molecular mechanisms.
文摘由于PPI网络数据的无尺度和小世界特性,使得目前对此类数据的聚类算法效果不理想.根据PPI网络的拓扑结构特性,本文提出了一种基于连接强度的蚁群优化(Joint Strength based Ant Colony Optimization,JSACO)聚类算法,该算法引入了连接强度的概念对蚁群聚类算法中的拾起/放下规则加以改进,以连接强度作为拾起规则,对结点进行聚类,并根据放下规则放弃部分不良数据,产生最终聚类结果.最后采用了MIPS数据库中的PPI数据进行实验,将JSACO算法与PPI网络数据的其他聚类算法进行比较,聚类结果表明JSACO算法正确率高,时间开销低.
文摘针对蚁群聚类在蛋白质相互作用(protein-protein interaction,PPI)网络中进行功能模块检测问题上时间性能的不足,提出一种快速的基于蚁群聚类的PPI网络功能模块检测(fast ant colony clustering for functional module detection,FACC-FMD)方法.该算法计算每个蛋白质与核心组蛋白质的相似度,根据拾起放下模型进行聚类,得到的初始聚类结果中功能模块之间相似度很小,省去了原始蚁群聚类算法中的合并和过滤操作,缩短了求解时间.同时该算法根据蛋白质的关键性对蚁群聚类中的拾起放下操作做了更严格的约束,以减少拾起放下的次数,加速了聚类的过程.在多个PPI网络上的实验表明:与原始蚁群聚类方法相比,FACC-FMD大幅度提高了时间性能,同时取得了良好的检测质量,而且与近年来的一些经典算法相比在多项性能指标上也具有一定的优势.
