Entity alignment (EA) is to discover entities referring to the same object in the real world from different knowledge graphs (KGs). It plays an important role in automatically integrating KGs from multiple sources. Existing knowledge graph embedding (KGE) methods based on Graph Neural Networks (GNNs) have achieved promising results, which enhance entity representation with relation information unidirectionally. Besides, more and more methods introduce semisupervision to ask for more labeled training data. However, two challenges still exist in these methods: (1) Insufficient interaction: The interaction between entities and relations is insufficiently utilized. (2) Low-quality bootstrapping: The generated semi-supervised data is of low quality. In this paper, we propose a novel framework, Echo Entity Alignment (EchoEA), which leverages self-attention mechanism to spread entity information to relations and echo back to entities. The relation representation is dynamically computed from entity representation. Symmetrically, the next entity representation is dynamically calculated from relation representation, which shows sufficient interaction. Furthermore, we propose attribute-combined bidirectional global-filtered strategy (ABGS) to improve bootstrapping, reduce false samples and generate high-quality training data. The experimental results on three real-world cross-lingual datasets are stable at around 96% at hits@1 on average, showing that our approach not only significantly outperforms the state-of-the-art methods, but also is universal and transferable for existing KGE methods.
The pathogenesis of an ovarian disease is connected with PTN and its receptor protein tyrosine phosphatase receptor Z1 (PTPRZ1). Paclitaxel is the first-line drug for the therapy of ovarian cancer. With the increment of paclitaxel chemotherapy, paclitaxel obstruction happens in the late phase of therapy frequently. By treating A2780 and SKOV-3 cells with PTN, we found the development of the two cell lines was enhanced. Different concentrations of PTN were added to A2780 and SKOV-3 cells treated with paclitaxel and the results of MTT showed that the inhibitory effect of paclitaxel on these two cell lines was weakened. The results of apoptosis assays showed that PTN could slow down the rate of apoptosis and its concentration dependence in both cell lines. To further investigate the impact of PTN on the paclitaxel responsiveness of ovarian malignant growth cells, A2780 and SKOV-3 cells were transfected with sh-PTN-1, sh-PTN-2 and sh-NC plasmids. The results of PCR and Western Blot showed that both RNA-interfering plasmids could inhibit PTN in A2780 and SKOV-3 cells. The results of MTT showed that the inhibitory effect of paclitaxel on cells transfected with sh-PTN-1 expanded compared with the benchmark group. Apoptosis assays showed that the complete apoptosis pace of A2780 and SKOV-3 cells with sh-PTN-1 plasmid induced by paclitaxel was accelerated obviously compared with the benchmark group. To summarize, the results suggested that PTN could enhance the resistance to paclitaxel in ovarian cancer cells, which provides a groundwork for studying on drug resistance of cancer cells to paclitaxel and a new perspective for ovarian cancer therapy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.