Review of machine learning methods for RNA secondary structure prediction

Secondary structure plays an important role in determining the function of noncoding RNAs. Hence, identifying RNA secondary structures is of great value to research. Computational prediction is a mainstream approach for predicting RNA secondary structure. Unfortunately, even though new methods have been proposed over the past 40 years, the performance of computational prediction methods has stagnated in the last decade. Recently, with the increasing availability of RNA structure data, new methods based on machine learning (ML) technologies, especially deep learning, have alleviated the issue. In this review, we provide a comprehensive overview of RNA secondary structure prediction methods based on ML technologies and a tabularized summary of the most important methods in this field. The current pending challenges in the field of RNA secondary structure prediction and future trends are also discussed.

Computational modeling of molecular structure of microRNA inhibitors selected against microRNA over-expressed in thyroid cancer

Introduction: Thyroid cancer is the most prevalent malignant neoplasm of endocrine system and advances in thyroid molecular biology studies demonstrate that microRNAs (miRNAs) seem to play a fundamental role in tumor triggering and progression. The miRNAs inhibitors are nucleic acid-based molecules that blockade miRNAs function, making unavailable for develop their usual function, also acting as gene expression controlling molecules. Objective: To develop in silico projection of molecular structure of miRNA inhibitors against miRNA over-expressed in thyroid cancer. Methods: We conducted a search of the nucleotide sequence of 12 miRNAs already defined as inhibitors against miRNA over-expressed in thyroid cancer, realizing in silico projection of the molecular structure of following miRNAs: miRNA-101, miRNA-126, miRNA-126-3p, miRNA-141, miRNA-145, miRNA-146b, miRNA-206, miRNA-3666, miRNA-497, miRNA-539, miRNA-613, and miRNA-618. The nucleotides were selected using GenBank that is the NIH genetic sequence database. The sequences obtained were aligned with the Clustal W multiple alignment algorithms. For the molecular modeling, the structures were generated with the RNAstructure, a fully automated miRNAs structure modelling server, accessible via the Web Servers for RNA Secondary Structure Prediction. Results: We demonstrated a search for nucleotide sequence and the projection of the molecular structure of the following miRNA inhibitors against miRNA over-expressed in thyroid cancer: miRNA-101, miRNA-126, miRNA-126-3p, miRNA-141, miRNA-145, miRNA-146b, miRNA-206, miRNA-3666, miRNA-497, miRNA-539, miRNA-613, and miRNA-618. Conclusion: In this study we show in silico secondary structures projection of selected of 12 miRNA inhibitors against miRNA over-expressed in thyroid cancer through computational biology. Keywords: microRNA; nucleotide analysis; molecular structure; thyroid cancer.

Deep Learning Method for RNA Secondary Structure Prediction with Pseudoknots Based on Large-Scale Data

Traditional machine learning methods are widely used in the field of RNA secondary structure prediction and have achieved good results. However, with the emergence of large-scale data, deep learning methods have more advantages than traditional machine learning methods. As the number of network layers increases in deep learning, there will often be problems such as increased parameters and overfitting. We used two deep learning models, GoogLeNet and TCN, to predict RNA secondary results. And from the perspective of the depth and width of the network, improvements are made based on the neural network model, which can effectively improve the computational efficiency while extracting more feature information. We process the existing real RNA data through experiments, use deep learning models to extract useful features from a large amount of RNA sequence data and structure data, and then predict the extracted features to obtain each base’s pairing probability. The characteristics of RNA secondary structure and dynamic programming methods are used to process the base prediction results, and the structure with the largest sum of the probability of each base pairing is obtained, and this structure will be used as the optimal RNA secondary structure. We, respectively, evaluated GoogLeNet and TCN models based on 5sRNA, tRNA data, and tmRNA data, and compared them with other standard prediction algorithms. The sensitivity and specificity of the GoogLeNet model on the 5sRNA and tRNA data sets are about 16% higher than the best prediction results in other algorithms. The sensitivity and specificity of the GoogLeNet model on the tmRNA dataset are about 9% higher than the best prediction results in other algorithms. As deep learning algorithms’ performance is related to the size of the data set, as the scale of RNA data continues to expand, the prediction accuracy of deep learning methods for RNA secondary structure will continue to improve.