Structure-Based Identification, Characterization, and Disruption of Human Securin-Binding SH3 Domains in Lung Cancer

Integrating node embeddings and biological annotations for genes to predict disease-gene associations

BACKGROUND

Predicting disease causative genes (or simply, disease genes) has played critical roles in understanding the genetic basis of human diseases and further providing disease treatment guidelines. While various computational methods have been proposed for disease gene prediction, with the recent increasing availability of biological information for genes, it is highly motivated to leverage these valuable data sources and extract useful information for accurately predicting disease genes.

RESULTS

We present an integrative framework called N2VKO to predict disease genes. Firstly, we learn the node embeddings from protein-protein interaction (PPI) network for genes by adapting the well-known representation learning method node2vec. Secondly, we combine the learned node embeddings with various biological annotations as rich feature representation for genes, and subsequently build binary classification models for disease gene prediction. Finally, as the data for disease gene prediction is usually imbalanced (i.e. the number of the causative genes for a specific disease is much less than that of its non-causative genes), we further address this serious data imbalance issue by applying oversampling techniques for imbalance data correction to improve the prediction performance. Comprehensive experiments demonstrate that our proposed N2VKO significantly outperforms four state-of-the-art methods for disease gene prediction across seven diseases.

CONCLUSIONS

In this study, we show that node embeddings learned from PPI networks work well for disease gene prediction, while integrating node embeddings with other biological annotations further improves the performance of classification models. Moreover, oversampling techniques for imbalance correction further enhances the prediction performance. In addition, the literature search of predicted disease genes also shows the effectiveness of our proposed N2VKO framework for disease gene prediction.

Overexpression of ubiquitin specific proteases 44 promotes the malignancy of glioma by stabilizing tumor-promoter securin

Ubiquitin specific peptidase 44 (USP44) has been identified as an important component of spindle assemble checkpoint (SAC) to prevent the formation of aneuploidy. However, recent study raised a controversy about the effect of USP44 in tumor. Here, we first confirmed the intranuclear localization of USP44 by testing several specific antibodies to recognize endogenous USP44. Then, data from IHC and qRT-PCR assay indicated that the high expression of USP44 existed in high-grade glioma tissues and signified a poor prognosis. Knockdown of USP44 inhibited proliferation, migration and invasion, induced apoptosis, and arrested cell cycle in G2/M phase in the established glioma cell lines. Down-regulation of oncoprotein securin was detected in USP44 deficient cells, and the interaction of endogenous USP44 and securin was confirmed by immunoprecipitation in U251MG cells, which indicated that securin was a substrate of USP44, and might be stabilized by USP44. In vivo, knockdown of USP44 inhibited the tumorigenicity of U87MG cells significantly. Consequently, our findings suggested that overexpression of USP44 could enhance the malignancy of glioma via securin. USP44 might serve as a predictive biomarker, and the USP44-securin pathway might provide a new therapeutic strategy for the treatment of glioma.