Label noise and long-tailed distributions are two major challenges in distantly supervised relation extraction. Recent studies have shown great progress on denoising, but paid little attention to the problem of long-tailed relations. In this paper, we introduce a constraint graph to model the dependencies between relation labels. On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously. CGRE employs graph convolution networks to propagate information from data-rich relation nodes to data-poor relation nodes, and thus boosts the representation learning of long-tailed relations. To further improve the noise immunity, a constraint-aware attention module is designed in CGRE to integrate the constraint information. Extensive experimental results indicate that CGRE achieves significant improvements over the previous methods for both denoising and long-tailed relation extraction.

Measures of gene functional similarity are essential tools for gene clustering, gene function prediction, evaluation of protein-protein interaction, disease gene prioritization and other applications. In recent years, many gene functional similarity methods have been proposed based on the semantic similarity of GO terms. However, these leading approaches may make errorprone judgments especially when they measure the specificity of GO terms as well as the IC of a term set. Therefore, how to estimate the gene functional similarity reliably is still a challenging problem. We propose WIS, an effective method to measure the gene functional similarity. First of all, WIS computes the IC of a term by employing its depth, the number of its ancestors as well as the topology of its descendants in the GO graph. Secondly, WIS calculates the IC of a term set by means of considering the weighted inherited semantics of terms. Finally, WIS estimates the gene functional similarity based on the IC overlap ratio of term sets. WIS is superior to some other representative measures on the experiments of functional classification of genes in a biological pathway, collaborative evaluation of GO-based semantic similarity measures, protein-protein interaction prediction and correlation with gene expression. Further analysis suggests that WIS takes fully into account the specificity of terms and the weighted inherited semantics of terms between GO terms. The proposed WIS method is an effective and reliable way to compare gene function. The web service of WIS is freely available at http://nclab.hit.edu.cn/WIS/ .

In discovering disease etiology and pathogenesis, the associations between MicroRNAs (miRNAs) and diseases play a critical role. Given known miRNA-disease associations (MDAs), how to uncover potential MDAs is an important problem. To solve this problem, most of the existing methods regard known MDAs as positive samples and unknown ones as negative samples, and then predict possible MDAs by iteratively revising the negative samples. However, simply viewing unknown MDAs as negative samples introduces erroneous information, which may result in poor predication performance. To avoid such defects, we present a novel method using only positive samples to predict MDAs by latent features extraction (LFEMDA). We design a new approach to construct the miRNAs similarity matrix. LFEMDA integrates the disease similarity matrix, the known MDAs and the miRNAs similarity matrix to identify potential MDAs. By introducing miRNAs and diseases knowledge as the auxiliary variables, the method can converge to give the optimal solution in each iteration. We conduct experiments on high-association diseases and new diseases datasets, in which our method shows better performance than that of other methods. We also carry out a case study on breast neoplasms to further demonstrate the capacity of our method in uncovering potential MDAs.