AUTHOR=Zhan Zhao-Hui , You Zhu-Hong , Li Li-Ping , Zhou Yong , Yi Hai-Cheng 

TITLE=Accurate Prediction of ncRNA-Protein Interactions From the Integration of Sequence and Evolutionary Information

JOURNAL=Frontiers in Genetics

VOLUME=Volume 9 - 2018

YEAR=2018

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2018.00458

DOI=10.3389/fgene.2018.00458

ISSN=1664-8021

ABSTRACT=The interaction between ncRNA and protein plays a crucial role in biological processes including gene expression and post-transcriptional gene regulation. The biological function of ncRNA is mostly realized by binding with proteins. Therefore, an accurate understanding of the interaction between ncRNA and protein has a significant impact on biology research. However, the existing computational prediction models need spending a lot of time on classification training and the resource consumed requires for classification is too large. Fortunately, an efficient classifier named LightGBM can solve the problem of long time consumption. In this study, we proposed a novel computational model for predicting ncRNA and protein interactions by using improved gradient boosting decision tree classifier. More specifically, the pseudo-Zernike Moment and singular value decomposition algorithm are employed to extract the discriminative features from protein and ncRNA sequence, respectively. The performance of our proposed method is evaluated on four datasets including RPI369, RPI488, RPI1807 and RPI2241. The experimental results of 10-fold cross-validation shown that the proposed method performs much better than existing methods in predicting ncRNA-protein interactions, which could be used as a useful tool in proteomics research.