Development of Computational to ols to Target Microrna

<p>MicroRNAs (a.k.a, miRNAs) play an important role in disease development. However, few of their structures have been determined and structure-based computational methods remain challenging in accurately predicting their interactions with small molecules. To address this issue, my thesis is to develop integrated approaches to screening for novel inhibitors by targeting specific structure motifs in miRNAs. The project starts with implementing a tool to find potential miRNA targets with desired motifs. I combined both sequence information of miRNAs and known RNA structure data from Protein Data Bank (PDB) to predict the miRNA structure and identify the motif to target, then I conducted intensive molecular dynamics simulations and RNA ensemble docking studies. In order to better evaluate the binding affinity of miRNA ligands, a new scoring function for molecular docking is devised. RNAs, as negatively charged molecules, tend to be more dependent on electrostatic interaction. To obtain a more accurate predictions, I have introduced the combination of Yukawa and Coulomb potentials. I curated a large RNA dataset to train my program to build robust models, using both convolutional neural networks (CNNs) and long short-term memory (LSTM) neural networks. The result shows that these latest machine learning algorithms have high predictive power, with the correlation coefficient R² as high as 0.97 and the root mean standard error (RMSE) as low as 1.42 kJ/mol. I envision that the combination of these different strategies can be used as a powerful tool to target specific miRNA motifs for therapeutics discovery and development.</p>

Name thesis:degree_name

Masters of Science (MS)

Level thesis:degree_level

Thesis (MS)

Year dc:date.available

2020

Authors dc:creator

• Song, Luo
• <p>https://orcid.org/0000-0003-3906-6042</p>

Contributors dc:contributor

• Shuxing Zhang
• Gabriel Lopez-Berestein, M.D.
• George A Calin, M.D. Ph.D.

• microRNA
• bioinformatics
• chemoinformatics
• database
• docking
• motif
• machine learing
• deep learing
• AI
• Artificial Intelligence and Robotics
• Biophysics
• Medicine and Health Sciences
• Other Chemistry
• Structural Biology

Repository record dc:identifier

https://digitalcommons.library.tmc.edu/utgsbs_dissertations/1051

OAI identifier oai:identifier

oai:digitalcommons.library.tmc.edu:utgsbs_dissertations-2106