Base substitution, insertion, and deletion errors due to inherent technical constraints inducing unavoidable sequencing inaccuracies, limiting access to high-quality raw data and biological knowledge. To address this, we propose a deep sequence reconstruction model based on the multi-scale attention mechanism and contrastive learning (MACL), designed to enhance DNA sequence reconstruction under highly error rate conditions. The multi-scale attention mechanism includes base scale, inter-sequence and intra-sequence scale. First, the MSA Transformer fully extracts both global and local features of the base scale from the dimensions of the rows and columns. Furthermore, for the errors between sequences and the substitution errors within sequences, MACL proposes Inter-Sequence and Intra-Sequence Multi-Head Attention Mechanisms, respectively, and handles the insertion and deletion errors through the convolution module. In order to maximize the consistency of positive sample pairs in the representation space, we introduce contrastive learning and design a negative sample construction method and data augmentation that are more suitable for substitution errors in sequencing channels. Experiments on real-world DNA storage and viral genome datasets demonstrate that MACL significantly outperforms existing methods in reconstructing the DNA sequence. In particular, when combined with RS codes, MACL can losslessly reconstruct medical images in highly biased sequence (base error rate = 5%) in DNA storage. In summary, the MACL introduces a novel approach to DNA sequence reconstruction in highly error rate conditions, laying a solid foundation for practical applications in DNA storage and genomics research.
Li et al. (Wed,) studied this question.