Poster Presentation 43rd Lorne Genome Conference 2022

Accurate identification of human microRNA-target interaction using machine learning  (#261)

Korawich Uthayopas 1 2 3 , Alex G.C. de Sá 1 2 3 4 , Azadeh Alavi 5 , Douglas E.V. Pires 1 2 3 6 , David B. Ascher 1 2 3 4 7
  1. Structural Biology and Bioinformatics, Department of Biochemistry and Pharmocology, University of Melbourne, Parkville, Victoria, 3052, Australia
  2. Systems and Computational Biology, Bio21 Institute, University of Melbourne, Parkville, Victoria, 3052, Australia
  3. Computational Biology and Clinical Informatics, Baker Heart and Diabetes Institute, Melbourne, Victoria, 3004, Australia
  4. Baker Department of Cardiometabolic Health, Melbourne Medical School, University of Melbourne, Parkville, Victoria, 3010, Australia
  5. AI discipline, School of computational technologies, STEM College, City Campus, RMIT University, Melbourne, Victoria, 3000, Australia
  6. School of Computing and Information Systems, University of Melbourne, Parkville , Victoria, 3052, Australia
  7. Department of Biochemistry, University of Cambridge, 80 Tennis Ct Rd, Cambridge CB2 1GA, England

Extensive research has demonstrated a strong connection between microRNA (miRNA) dysregulation and the progression of several diseases, such as cancers and, neurological and cardiovascular diseases.1,2 Understanding the miRNA functional activity can provide deep insights into disease pathophysiology, allowing the development of precise diagnosis and therapies. MiRNAs play an indispensable role in diverse cellular mechanisms (e.g., cell differentiation and apoptosis) by post-transcriptionally regulating gene expression through complementary base pairing with messenger RNA.3 The limited sensitivity of experimental approaches, however, has made the identification of human miRNA targets challenging. Several computational methods for predicting putative miRNA-mRNA interaction have been developed to fill this gap, but with limited predictive capability.4-6 In this study, we present a predictive model for identification of novel miRNA-target mRNA interactions (PRIMITI), using novel common characteristics extracted from high-throughput CLIP binding7,8 and expression data5. Common characteristics include site type, binding stability, site accessibility, site conservation, 3’-supplementary binding, and site interaction.9,10 PRIMITI has been assessed and validated via both cross-validation and an independent blind test showing consistent predictive performance.11 We will compare the predictive capability of PRIMITI with three other state-of-the-art models, TargetScan,4 miRTarget,5 and DIANA-microT-CDS,6 on external validation datasets of HITS-CLIP12 and microarray13 under different criteria, including recall, Pearson’s correlation, and mean repression of top predicted targets. The model will be made available as a freely accessible web server. PRIMITI will be an invaluable resource for analyzing potential miRNA-mRNA interactions and functional significance in molecular mechanisms.

  1. Deng, S., Calin, G. A., Croce, C. M., Coukos, G., & Zhang, L. (2008). Mechanisms of microRNA deregulation in human cancer. Cell Cycle, 7(17), 2643–2646.
  2. Gurha, P. (2016). MicroRNAs in cardiovascular disease. Current Opinion in Cardiology, 31(3), 249–254.
  3. O’Brien, J., Hayder, H., Zayed, Y., & Peng, C. (2018). Overview of microRNA biogenesis, mechanisms of actions, and circulation. Frontiers in endocrinology, 9, 402.
  4. Agarwal, V., Bell, G. W., Nam, J. W., & Bartel, D. P. (2015). Predicting effective microRNA target sites in mammalian mRNAs. eLife, 4, e05005.
  5. Liu, W., & Wang, X. (2019). Prediction of functional microRNA targets by integrative modeling of microRNA binding and target expression data. Genome biology, 20(1), 18.
  6. Reczko, M., Maragkakis, M., Alexiou, P., Grosse, I., & Hatzigeorgiou, A. G. (2012). Functional microRNA targets in protein coding sequences. Bioinformatics (Oxford, England), 28(6), 771–776.
  7. Helwak, A., Kudla, G., Dudnakova, T., & Tollervey, D. (2013). Mapping the human miRNA interactome by CLASH reveals frequent noncanonical binding. Cell, 153(3), 654–665.
  8. Grosswendt, S., Filipchyk, A., Manzano, M., Klironomos, F., Schilling, M., Herzog, M., Gottwein, E., & Rajewsky, N. (2014). Unambiguous identification of miRNA:target site interactions by different types of ligation reactions. Molecular cell, 54(6), 1042–1054.
  9. Sheu-Gruttadauria, J., Xiao, Y., Gebert, L. F., & MacRae, I. J. (2019). Beyond the seed: structural basis for supplementary microRNA targeting by human Argonaute2. The EMBO journal, 38(13), e101153.
  10. Grimson, A., Farh, K. K., Johnston, W. K., Garrett-Engele, P., Lim, L. P., & Bartel, D. P. (2007). MicroRNA targeting specificity in mammals: determinants beyond seed pairing. Molecular cell, 27(1), 91–105.
  11. Sugiyama, M. (2016). Introduction to Statistical Machine Learning. Amsterdam: Morgan Kaufmann. ISBN: 978-0-12-802121-7
  12. Boudreau, R. L., Jiang, P., Gilmore, B. L., Spengler, R. M., Tirabassi, R., Nelson, J. A., Ross, C. A., Xing, Y., & Davidson, B. L. (2014). Transcriptome-wide discovery of microRNA binding sites in human brain. Neuron, 81(2), 294–305.
  13. Linsley, P. S., Schelter, J., Burchard, J., Kibukawa, M., Martin, M. M., Bartz, S. R., Johnson, J. M., Cummins, J. M., Raymond, C. K., Dai, H., Chau, N., Cleary, M., Jackson, A. L., Carleton, M., & Lim, L. (2007). Transcripts targeted by the microRNA-16 family cooperatively regulate cell cycle progression. Molecular and cellular biology, 27(6), 2240–2252.