DemuxTrans: Transformer and temporal convolution network for accurate barcode demultiplexing in nanopore sequencing

TL;DR

DemuxTrans is a new deep learning method that improves accuracy in nanopore sequencing by better identifying RNA samples using barcodes.

Contribution

DemuxTrans introduces a hybrid deep learning framework combining Transformers and temporal convolution networks for barcode demultiplexing.

Findings

DemuxTrans achieves state-of-the-art performance in barcode demultiplexing metrics like accuracy and F1-score.

The method effectively captures both local patterns and long-range dependencies in nanopore sequencing data.

It enables scalable and efficient identification of multiplexed RNA samples, improving sequencing throughput.

Abstract

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.

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.

The code and datasets are publicly available on https://github.com/LiyuanShu116/Demuxtrans

Figures