23 Study on mirnas prediction and co-expression patterns of the human intronic mirnas with their host genes. (5th December 2017)

• Record Type: Journal Article
• Authors: Wang, HC; Li, B; Wu, M
• Is Part Of: Journal of investigative medicine. Volume 65(2017)Supplement 7
• Page Start: A8
• Page End: A8
• Publication Date: 2017-12-05
• Subjects: Clinical medicine -- Periodicals; Medicine -- Research -- Periodicals; Medicine; Research -- United States; Clinical medicine; Medicine -- Research; Periodicals; 616.075
• DOI: 10.1136/jim-2017-MEBabstracts.23
• Languages: English
• ISSNs: 1081-5589

Abstract

Abstract : Objectives: MiRNAs are a set of endogenous non-coding RNAs with a length of about 22nt. They regulate the expression of the target mRNAs and are involved in many important biological processes including metabolism, defense against viruses, apoptosis and proliferation. In this paper we focus on two hotspot issues related to miRNAs, namely miRNAs prediction and the co-expression patterns prediction of the intronic ?miRNAs with their host genes. Methods: Firstly, a new method based on machine learning techniques is proposed to recognise the miRNAs. Couplet-syntax is introduced to depict local structure-sequence of pre-miRNA which is able to represent the most robust and intrinsic features of pre-miRNA. Feature selection algorithms based on filter models are proposed to achieve good comprehensive performance. Secondly, a new method based on multiple features extraction techniques is proposed to recognise the co-expression patterns of the intronic miRNAs with their host genes. The feature vectors were calculated from the genome coordinates data of human miRNAs which includes intronic miRNAs, miRNA-hosting introns, and miRNA-hosting genes. The ensemble features selection algorithm is used to obtain a subset of features with high correlation and stability. Results: The analysis and comparison of multi-group experiments show that we achieved the best features and models to predict miRNAs and the co-expression patterns of the intronic miRNAs with their host genes which are verified with promising results. Conclusions: This study not only provides some effective means for research on miRNAs prediction and co-expression prediction of intronic miRNAs with their host genes, but also gives some solid foundation for future research in this field. Acknowledgements: Supported by the National Natural Science Foundation of China (Grant No. 61402099).