Background: As the RNA secondary structure is highly related to its stability and functions, the structure prediction is of great value to biological research. The traditional computational prediction for RNA secondary prediction is mainly based on the thermodynamic model with dynamic programming to find the optimal structure. However, the prediction performance based on the traditional approach is unsatisfactory for further research. Besides, the computational complexity of the structure prediction using dynamic programming is $$O(N^3)$$O ( N 3 ) ; it becomes $$O(N^6)$$O ( N 6 ) for RNA structure with pseudoknots, which is computationally impractical for large-scale analysis. Results: In this paper, we propose REDfold, a novel deep learning-based method for RNA secondary prediction. REDfold utilizes an encoder-decoder network based on CNN to learn the short and long range dependencies among the RNA sequence, and the network is further integrated with symmetric skip connections to efficiently propagate activation information across layers. Moreover, the network output is post-processed with constrained optimization to yield favorable predictions even for RNAs with pseudoknots. Experimental results based on the ncRNA database demonstrate that REDfold achieves better performance in terms of efficiency and accuracy, outperforming the contemporary state-of-the-art methods.

With the rise of modern healthcare monitoring, heart rate (HR) estimation using remote photoplethysmography (rPPG) has gained attention for its non-contact, continuous tracking capabilities. However, most HR estimation methods rely on stable, fixed sampling intervals, while practical image capture often involves irregular frame rates and missing data, leading to inaccuracies in HR measurements. This study addresses these issues by introducing low-complexity timing correction methods, including linear, cubic, and filter interpolation, to improve HR estimation from rPPG signals under conditions of irregular sampling and data loss. Through a comparative analysis, this study offers insights into efficient timing correction techniques for enhancing HR estimation from rPPG, particularly suitable for edge-computing applications where low computational complexity is essential. Cubic interpolation can provide robust performance in reconstructing signals but requires higher computational resources, while linear and filter interpolation offer more efficient solutions. The proposed low-complexity timing correction methods improve the reliability of rPPG-based HR estimation, making it a more robust solution for real-world healthcare applications.

Piwi-interacting RNAs (piRNAs) are a new class of small, non-coding RNAs, crucial in the regulation of gene expression. Recent research has revealed links between piRNAs, viral defense mechanisms, and certain human cancers. Due to their clinical potential, there is a great interest in identifying piRNAs from large genome databases through efficient computational methods. However, piRNAs lack conserved structure and sequence homology across species, which makes piRNA detection challenging. Current detection algorithms heavily rely on manually crafted features, which may overlook or improperly use certain features. Furthermore, there is a lack of suitable computational tools for analyzing large-scale databases and accurately identifying piRNAs. To address these issues, we propose LSTM4piRNA, a highly efficient deep learning-based method for predicting piRNAs in large-scale genome databases. LSTM4piRNA utilizes a compact LSTM network that can effectively analyze RNA sequences from extensive datasets to detect piRNAs. It can automatically learn the dependencies among RNA sequences, and regularization is further integrated to reduce the generalization error. Comprehensive performance evaluations based on piRNAs from the piRBase database demonstrate that LSTM4piRNA outperforms current advanced methods and is well-suited for analysis with large-scale databases.

Electrolyte balance is essential for the proper functioning of the body, and imbalances can lead to various health issues, some of which may be life-threatening. Therefore, measuring electrolyte concentrations is becoming increasingly important, particularly for athletes engaged in high-intensity and prolonged physical activity. In this project, we developed a highly sensitive sensing device capable of accurately and rapidly measuring electrolyte concentrations in mixed solutions, providing precise analysis of trace electrolyte levels. The sensor device requires no complex operational procedures and can quickly complete measurements, making it well-suited for point-of-care applications. Integration of regression models further enhances the device’s ability to estimate concentrations in mixed electrolyte solutions. The test results demonstrate that the device can detect subtle concentration variations, with a precision as low as $0.5$ mM. This proposed sensing device offers a cost-effective and efficient solution for real-time monitoring of electrolyte levels in healthcare.

RNA secondary structural alignment serves as a foundational procedure in identifying conserved structural motifs among RNA sequences, crucially advancing our understanding of novel RNAs via comparative genomic analysis. While various computational strategies for RNA structural alignment exist, they often come with high computational complexity. Specifically, when addressing a set of RNAs with unknown structures, the task of simultaneously predicting their consensus secondary structure and determining the optimal sequence alignment requires an overwhelming computational effort of $$O(L^6)$$ for each RNA pair. Such an extremely high computational complexity makes these methods impractical for large-scale analysis despite their accurate alignment capabilities. In this paper, we introduce REDalign, an innovative approach based on deep learning for RNA secondary structural alignment. By utilizing a residual encoder-decoder network, REDalign can efficiently capture consensus structures and optimize structural alignments. In this learning model, the encoder network leverages a hierarchical pyramid to assimilate high-level structural features. Concurrently, the decoder network, enhanced with residual skip connections, integrates multi-level encoded features to learn detailed feature hierarchies with fewer parameter sets. REDalign significantly reduces computational complexity compared to Sankoff-style algorithms and effectively handles non-nested structures, including pseudoknots, which are challenging for traditional alignment methods. Extensive evaluations demonstrate that REDalign provides superior accuracy and substantial computational efficiency. REDalign presents a significant advancement in RNA secondary structural alignment, balancing high alignment accuracy with lower computational demands. Its ability to handle complex RNA structures, including pseudoknots, makes it an effective tool for large-scale RNA analysis, with potential implications for accelerating discoveries in RNA research and comparative genomics.