RNA modifications are essential regulators of gene expression and cellular function, with over 170 distinct types identified to date. Among them, N6-methyladenosine is the most prevalent internal modification in mammalian messenger RNA. Nanopore direct RNA sequencing offers the potential to study RNA modifications at high resolution, but challenges persist for single-molecule resolution detection due to signal noise, low modification frequency, and read-level variability. To address these challenges, we propose MambaNano, a dualbranch deep learning framework designed for direct modeling of raw current signals in m6A detection. The model incorporates a temporal branch to capture long-range signal dependencies and a spatial branch to encode statistical and positional descriptors. These representations are fused through a Mambadriven integration module, followed by an attention-based pooling mechanism that enhances per-site signal summarization. We evaluate MambaNano on nanopore sequencing data from human cell lines. Experimental results demonstrate that the model achieves state-of-the-art detection of$\mathbf{m 6 A}$modifications at the single-molecule level. Visualization further demonstrates that the model responds differently to hypermethylated and hypomethylated modified sequence motifs, confirming its capacity to extract biologically meaningful patterns. Our results highlight the potential of structured state-space models combined with multi-branch processing for accurate and generalizable RNA modification analysis. The source code of MambaNano is available at https://anonymous.4open.science/r/MambaNano-EB62.

MOTIVATION: Oxford Nanopore Technologies (ONT) direct RNA sequencing (dRNA-seq) offers high-resolution, single-molecule analysis but is hindered by the lack of robust multiplex barcoding methods. Existing approaches struggle to accurately demultiplex raw nanopore signals, failing to capture both local patterns and long-range dependencies. This limitation underscores the requirement for advanced solutions to improve accuracy, efficiency, and adaptability in sequencing workflows. We present DemuxTrans, a hybrid deep learning framework that integrates Multi-Layer Feature Fusion, Transformers, and Temporal Convolutional Networks (TCN) for precise barcode demultiplexing. RESULTS: DemuxTrans achieves state-of-the-art performance across multiple datasets by effectively balancing local feature extraction, global context modeling, and long-term dependency capture, excelling in metrics such as accuracy, recall and F1-score. These results demonstrate DemuxTrans as a scalable, efficient solution for barcode demultiplexing in nanopore sequencing, enabling precise identification of multiplexed RNA samples and improving throughput in transcriptomic and epigenomic analyses. AVAILABILITY AND IMPLEMENTATION: The code and datasets are publicly available on https://github.com/LiyuanShu116/Demuxtrans.

Crowd behavior understanding and reconstruction hold significant applications in areas such as public health and urban management. In dense scenes, it is challenging to obtain individual trajectories, which limits the flexibility of traditional trajectory-based methods for generating crowd behavior. To address this issue, we propose a video-based framework for reconstructing crowd behavior. It obtains multimodal group feature representations of the crowd before applying a deep learning network. These features capture the collective movement patterns and we use them to enhance the robustness of reconstruction. Experimental results demonstrate that without relying on precise individual trajectories, our method can produce crowd behavior trajectories that align with the original video’s dynamics, providing a more flexible way of studying crowd behavior.

MOTIVATION: Nanopore sequencing is a new macromolecular recognition and perception technology that enables high-throughput sequencing of DNA, RNA, even protein molecules. The sequences generated by nanopore sequencing span a large time frame, and the labor and time costs incurred by traditional analysis methods are substantial. Recently, research on nanopore data analysis using machine learning algorithms has gained unceasing momentum, but there is often a significant gap between traditional and deep learning methods in terms of classification results. To analyze nanopore data using deep learning technologies, measures such as sequence completion and sequence transformation can be employed. However, these technologies do not preserve the local features of the sequences. To address this issue, we propose a sequence-to-image (S2I) module that transforms sequences of unequal length into images. Additionally, we propose the Transformer-based T-S2Inet model to capture the important information and improve the classification accuracy. RESULTS: Quantitative and qualitative analysis shows that the experimental results have an improvement of around 2% in accuracy compared to previous methods. The proposed method is adaptable to other nanopore platforms, such as the Oxford nanopore. It is worth noting that the proposed method not only aims to achieve the most advanced performance, but also provides a general idea for the analysis of nanopore sequences of unequal length. AVAILABILITY AND IMPLEMENTATION: The main program is available at https://github.com/guanxiaoyu11/S2Inet.

MOTIVATION: As the third-generation sequencing technology, nanopore sequencing has been used for high-throughput sequencing of DNA, RNA, and even proteins. Recently, many studies have begun to use machine learning technology to analyze the enormous data generated by nanopores. Unfortunately, the success of this technology is due to the extensive labeled data, which often suffer from enormous labor costs. Therefore, there is an urgent need for a novel technology that can not only rapidly analyze nanopore data with high-throughput, but also significantly reduce the cost of labeling. To achieve the above goals, we introduce active learning to alleviate the enormous labor costs by selecting the samples that need to be labeled. This work applies several advanced active learning technologies to the nanopore data, including the RNA classification dataset (RNA-CD) and the Oxford Nanopore Technologies barcode dataset (ONT-BD). Due to the complexity of the nanopore data (with noise sequence), the bias constraint is introduced to improve the sample selection strategy in active learning. Results: The experimental results show that for the same performance metric, 50% labeling amount can achieve the best baseline performance for ONT-BD, while only 15% labeling amount can achieve the best baseline performance for RNA-CD. Crucially, the experiments show that active learning technology can assist experts in labeling samples, and significantly reduce the labeling cost. Active learning can greatly reduce the dilemma of difficult labeling of high-capacity nanopore data. We hope active learning can be applied to other problems in nanopore sequence analysis. AVAILABILITY AND IMPLEMENTATION: The main program is available at https://github.com/guanxiaoyu11/AL-for-nanopore. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

In recent years, machine learning has gained increasing traction in the study of molecules, enabling researchers to tackle challenging tasks including molecular property prediction and drug design.Consequently, there remains an open challenge to develop a neural network architecture that can make use of extensive amounts of unlabeled data for training while still providing competitive results in various molecular property prediction tasks. To address this challenge, we propose a Molecule Graph Contrastive Learning approach based on the Transformer framework (T-MGCL). Our approach involves expanding numerous unsupervised molecular graphs and using a contrast estimator to ensure consistency among various graph expansions of the same molecule. Transformer framework is employed to consider the distance between atoms and molecular graph attributes, thereby accounting for structural information that may be overlooked by traditional graph neural networks. Our experimental results demonstrate that the T-MGCL model outperforms other models in several molecular property prediction tasks. Additionally, we observe that the attention weight learned by T-MGCL can be easily explained from a chemical perspective.

Ribonucleic acid (RNA) is a pivotal nucleic acid that plays a crucial role in regulating many biological activities. Recently, one study utilized a machine learning algorithm to automatically classify RNA structural events generated by a Mycobacterium smegmatis porin A nanopore trap. Although it can achieve desirable classification results, compared with deep learning (DL) methods, this classic machine learning requires domain knowledge to manually extract features, which is sophisticated, labor-intensive and time-consuming. Meanwhile, the generated original RNA structural events are not strictly equal in length, which is incompatible with the input requirements of DL models. To alleviate this issue, we propose a sequence-to-sequence (S2S) module that transforms the unequal length sequence (UELS) to the equal length sequence. Furthermore, to automatically extract features from the RNA structural events, we propose a sequence-to-sequence neural network based on DL. In addition, we add an attention mechanism to capture vital information for classification, such as dwell time and blockage amplitude. Through quantitative and qualitative analysis, the experimental results have achieved about a 2% performance increase (accuracy) compared to the previous method. The proposed method can also be applied to other nanopore platforms, such as the famous Oxford nanopore. It is worth noting that the proposed method is not only aimed at pursuing state-of-the-art performance but also provides an overall idea to process nanopore data with UELS.