Clustering, which explores the visualization and distribution of data, has recently been widely studied. Although current clustering algorithms such as DBSCAN, can detect the arbitrary-shape clusters and work well, the parameters involved in these methods are often difficult to determine. Clustering using a fast search of density peaks is a promising technique for solving this problem. However, the current methods suffer from the problem of uneven distribution within local clusters. To solve this problem, we propose a new density peak based clustering algorithm employing a hierarchical strategy, namely, HCFS, which consists mainly of two stages. In the first stage, the HCFS estimates the density and distance of each point. The points with higher density and distance are selected as candidate centers, and then subclusters centered on them are further obtained. In the second stage, considering that adjacent subclusters based on certain candidate centers are highly similar and connected within the same cluster, we propose a new mechanism for measuring dissimilarity and connectivity between the subclusters. Those highly similar and connected subclusters are merged to increase the dissimilarity between different clusters and to obtain the final clustering results. The experiments conducted on a large number of datasets show that our method can effectively identify unevenly distributed clusters and yield better or comparable performance for different datasets.INDEX TERMS Cluster, candidate center, density peak based, hierarchical, merge, subclusters, two-stage algorithm, uneven distribution within local clusters.

The long non-coding RNA (lncRNA)–protein interaction plays an important role in the post-transcriptional gene regulation, such as RNA splicing, translation, signaling, and the development of complex diseases. The related research on the prediction of lncRNA–protein interaction relationship is beneficial in the excavation and the discovery of the mechanism of lncRNA function and action occurrence, which are important. Traditional experimental methods for detecting lncRNA–protein interactions are expensive and time-consuming. Therefore, computational methods provide many effective strategies to deal with this problem. In recent years, most computational methods only use the information of the lncRNA–lncRNA or the protein–protein similarity and cannot fully capture all features to identify their interactions. In this paper, we propose a novel computational model for the lncRNA–protein prediction on the basis of machine learning methods. First, a feature method is proposed for representing the information of the network topological properties of lncRNA and protein interactions. The basic composition feature information and evolutionary information based on protein, the lncRNA sequence feature information, and the lncRNA expression profile information are extracted. Finally, the above feature information is fused, and the optimized feature vector is used with the recursive feature elimination algorithm. The optimized feature vectors are input to the support vector machine (SVM) model. Experimental results show that the proposed method has good effectiveness and accuracy in the lncRNA–protein interaction prediction.

No abstract

Noncoding RNAs (ncRNAs) have recently attracted considerable attention due to their key roles in biology. The ncRNA–proteins interaction (NPI) is often explored to reveal some biological activities that ncRNA may affect, such as biological traits, diseases, etc. Traditional experimental methods can accomplish this work but are often labor-intensive and expensive. Machine learning and deep learning methods have achieved great success by exploiting sufficient sequence or structure information. Graph Neural Network (GNN)-based methods consider the topology in ncRNA–protein graphs and perform well on tasks like NPI prediction. Based on GNN, some pairwise constraint methods have been developed to apply on homogeneous networks, but not used for NPI prediction on heterogeneous networks. In this paper, we construct a pairwise constrained NPI predictor based on dual Graph Convolutional Network (GCN) called NPI-DGCN. To our knowledge, our method is the first to train a heterogeneous graph-based model using a pairwise learning strategy. Instead of binary classification, we use a rank layer to calculate the score of an ncRNA–protein pair. Moreover, our model is the first to predict NPIs on the ncRNA–protein bipartite graph rather than the homogeneous graph. We transform the original ncRNA–protein bipartite graph into two homogenous graphs on which to explore second-order implicit relationships. At the same time, we model direct interactions between two homogenous graphs to explore explicit relationships. Experimental results on the four standard datasets indicate that our method achieves competitive performance with other state-of-the-art methods. And the model is available at https://github.com/zhuoninnin1992/NPIPredict

No abstract