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.