A semi-supervised learning approach for RNA secondary structure prediction

Machine learning for RNA 2D structure prediction benchmarked on experimental data

Since the 1980s, dozens of computational methods have addressed the problem of predicting RNA secondary structure. Among them are those that follow standard optimization approaches and, more recently, machine learning (ML) algorithms. The former were repeatedly benchmarked on various datasets. The latter, on the other hand, have not yet undergone extensive analysis that could suggest to the user which algorithm best fits the problem to be solved. In this review, we compare 15 methods that predict the secondary structure of RNA, of which 6 are based on deep learning (DL), 3 on shallow learning (SL) and 6 control methods on non-ML approaches. We discuss the ML strategies implemented and perform three experiments in which we evaluate the prediction of (I) representatives of the RNA equivalence classes, (II) selected Rfam sequences and (III) RNAs from new Rfam families. We show that DL-based algorithms (such as SPOT-RNA and UFold) can outperform SL and traditional methods if the data distribution is similar in the training and testing set. However, when predicting 2D structures for new RNA families, the advantage of DL is no longer clear, and its performance is inferior or equal to that of SL and non-ML methods.

Secondary structure prediction of long noncoding RNA: review and experimental comparison of existing approaches

MOTIVATION

In contrast to messenger RNAs, the function of the wide range of existing long noncoding RNAs (lncRNAs) largely depends on their structure, which determines interactions with partner molecules. Thus, the determination or prediction of the secondary structure of lncRNAs is critical to uncover their function. Classical approaches for predicting RNA secondary structure have been based on dynamic programming and thermodynamic calculations. In the last 4 years, a growing number of machine learning (ML)-based models, including deep learning (DL), have achieved breakthrough performance in structure prediction of biomolecules such as proteins and have outperformed classical methods in short transcripts folding. Nevertheless, the accurate prediction for lncRNA still remains far from being effectively solved. Notably, the myriad of new proposals has not been systematically and experimentally evaluated.

RESULTS

In this work, we compare the performance of the classical methods as well as the most recently proposed approaches for secondary structure prediction of RNA sequences using a unified and consistent experimental setup. We use the publicly available structural profiles for 3023 yeast RNA sequences, and a novel benchmark of well-characterized lncRNA structures from different species. Moreover, we propose a novel metric to assess the predictive performance of methods, exclusively based on the chemical probing data commonly used for profiling RNA structures, avoiding any potential bias incorporated by computational predictions when using dot-bracket references. Our results provide a comprehensive comparative assessment of existing methodologies, and a novel and public benchmark resource to aid in the development and comparison of future approaches.

AVAILABILITY

Full source code and benchmark datasets are available at: https://github.com/sinc-lab/lncRNA-folding.

CONTACT

lbugnon@sinc.unl.edu.ar.

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.

ATTfold: RNA Secondary Structure Prediction With Pseudoknots Based on Attention Mechanism

Accurate RNA secondary structure information is the cornerstone of gene function research and RNA tertiary structure prediction. However, most traditional RNA secondary structure prediction algorithms are based on the dynamic programming (DP) algorithm, according to the minimum free energy theory, with both hard and soft constraints. The accuracy is particularly dependent on the accuracy of soft constraints (from experimental data like chemical and enzyme detection). With the elongation of the RNA sequence, the time complexity of DP-based algorithms will increase geometrically, as a result, they are not good at coping with relatively long sequences. Furthermore, due to the complexity of the pseudoknots structure, the secondary structure prediction method, based on traditional algorithms, has great defects which cannot predict the secondary structure with pseudoknots well. Therefore, few algorithms have been available for pseudoknots prediction in the past. The ATTfold algorithm proposed in this article is a deep learning algorithm based on an attention mechanism. It analyzes the global information of the RNA sequence via the characteristics of the attention mechanism, focuses on the correlation between paired bases, and solves the problem of long sequence prediction. Moreover, this algorithm also extracts the effective multi-dimensional features from a great number of RNA sequences and structure information, by combining the exclusive hard constraints of RNA secondary structure. Hence, it accurately determines the pairing position of each base, and obtains the real and effective RNA secondary structure, including pseudoknots. Finally, after training the ATTfold algorithm model through tens of thousands of RNA sequences and their real secondary structures, this algorithm was compared with four classic RNA secondary structure prediction algorithms. The results show that our algorithm significantly outperforms others and more accurately showed the secondary structure of RNA. As the data in RNA sequence databases increase, our deep learning-based algorithm will have superior performance. In the future, this kind of algorithm will be more indispensable.

Sequence-to-function deep learning frameworks for engineered riboregulators

While synthetic biology has revolutionized our approaches to medicine, agriculture, and energy, the design of completely novel biological circuit components beyond naturally-derived templates remains challenging due to poorly understood design rules. Toehold switches, which are programmable nucleic acid sensors, face an analogous design bottleneck; our limited understanding of how sequence impacts functionality often necessitates expensive, time-consuming screens to identify effective switches. Here, we introduce Sequence-based Toehold Optimization and Redesign Model (STORM) and Nucleic-Acid Speech (NuSpeak), two orthogonal and synergistic deep learning architectures to characterize and optimize toeholds. Applying techniques from computer vision and natural language processing, we 'un-box' our models using convolutional filters, attention maps, and in silico mutagenesis. Through transfer-learning, we redesign sub-optimal toehold sensors, even with sparse training data, experimentally validating their improved performance. This work provides sequence-to-function deep learning frameworks for toehold selection and design, augmenting our ability to construct potent biological circuit components and precision diagnostics.

DMfold: A Novel Method to Predict RNA Secondary Structure With Pseudoknots Based on Deep Learning and Improved Base Pair Maximization Principle

While predicting the secondary structure of RNA is vital for researching its function, determining RNA secondary structure is challenging, especially for that with pseudoknots. Typically, several excellent computational methods can be utilized to predict the secondary structure (with or without pseudoknots), but they have their own merits and demerits. These methods can be classified into two categories: the multi-sequence method and the single-sequence method. The main advantage of the multi-sequence method lies in its use of the auxiliary sequences to assist in predicting the secondary structure, but it can only successfully predict in the presence of multiple highly homologous sequences. The single-sequence method is associated with the major merit of easy operation (only need the target sequence to predict secondary structure), but its folding parameters are the common features of diversity RNA, which cannot describe the unique characteristics of RNA, thus potentially resulting in the low prediction accuracy in some RNA. In this paper, "DMfold," a method based on the Deep Learning and Improved Base Pair Maximization Principle, is proposed to predict the secondary structure with pseudoknots, which fully absorbs the advantages and avoids some disadvantages of those two methods. Notably, DMfold could predict the secondary structure of RNA by learning similar RNA in the known structures, which uses the similar RNA sequences instead of the highly homogeneous sequences in the multi-sequence method, thereby reducing the requirement for auxiliary sequences. In DMfold, it only needs to input the target sequence to predict the secondary structure. Its folding parameters are fully extracted automatically by deep learning, which could avoid the lack of folding parameters in the single-sequence method. Experiments show that our method is not only simple to operate, but also improves the prediction accuracy compared to multiple excellent prediction methods. A repository containing our code can be found at https://github.com/linyuwangPHD/RNA-Secondary-Structure-Database.

Research on folding diversity in statistical learning methods for RNA secondary structure prediction

How to improve the prediction accuracy of RNA secondary structure is currently a hot topic. The existing prediction methods for a single sequence do not fully consider the folding diversity which may occur among RNAs with different functions or sources. This paper explores the relationship between folding diversity and prediction accuracy, and puts forward a new method to improve the prediction accuracy of RNA secondary structure. Our research investigates the following: 1. The folding feature based on stochastic context-free grammar is proposed. By using dimension reduction and clustering techniques, some public data sets are analyzed. The results show that there is significant folding diversity among different RNA families. 2. To assign folding rules to RNAs without structural information, a classification method based on production probability is proposed. The experimental results show that the classification method proposed in this paper can effectively classify the RNAs of unknown structure. 3. Based on the existing prediction methods of statistical learning models, an RNA secondary structure prediction framework is proposed, namely "Cluster - Training - Parameter Selection - Prediction". The results show that, with information on folding diversity, prediction accuracy can be significantly improved.

Empirical evaluation of a virtual laboratory approach to teach lactate dehydrogenase enzyme kinetics

Background

Personalised instruction is increasingly recognised as crucial for efficacious learning today. Our seminal work delineates and elaborates on the principles, development and implementation of a specially-designed adaptive, virtual laboratory.

Aims

We strived to teach laboratory skills associated with lactate dehydrogenase (LDH) enzyme kinetics to 2nd-year biochemistry students using our adaptive learning platform. Pertinent specific aims were to:(1)

design/implement a web-based lesson to teach lactate dehydrogenase(LDH) enzyme kinetics to 2nd-year biochemistry students

(2)

determine its efficacious in improving students' comprehension of enzyme kinetics

(3)

assess their perception of its usefulness/manageability(vLab versus Conventional Tutorial)

Methods

Our tools were designed using HTML5 technology. We hosted the program on an adaptive e-learning platform (AeLP). Provisions were made to interactively impart informed laboratory skills associated with measuring LDH enzyme kinetics. A series of e-learning methods were created. Tutorials were generated for interactive teaching and assessment.

Results

The learning outcomes herein were on par with that from a conventional classroom tutorial. Student feedback showed that the majority of students found the vLab learning experience “valuable”; and the vLab format/interface “well-designed”. However, there were a few technical issues with the 1st roll-out of the platform.

Conclusions

Our pioneering effort resulted in productive learning with the vLab, with parity with that from a conventional tutorial. Our contingent discussion emphasises not only the cornerstone advantages, but also the shortcomings of the AeLP method utilised. We conclude with an astute analysis of possible extensions and applications of our methodology.

•

We developed & implemented a specially-designed adaptive virtual-laboratory [vLab].

•

Laboratory lactate dehydrogenase kinetics were taught to 2nd-year biochem students.

•

The vLab was designed using HTML5 and hosted on an adaptive e-learning platform.

•

The learning outcomes were on par with that from a conventional classroom tutorial.