Xue Li

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.

Protein-protein interactions (PPIs) are fundamental to many biological processes, including cell signaling, gene expression regulation, immune responses, and protein complex formation. Small molecule inhibitors targeting specific PPIs are expected to treat diseases such as cancer and viral infections by modulating pathophysiological processes. Despite their clinical importance, the development of PPI inhibitors is challenging due to limited experimental validation data, which complicates the accurate prediction of novel inhibitors. Therefore, there is an urgent need for advanced computational methods that can effectively integrate multiple data types and improve prediction accuracy. In this study, we proposed a new framework, PTPPI, to efficiently predict protein-protein interaction inhibitors (PPIIs). PTPPI integrates multiple molecular features, including extended connectivity fingerprints (ECFPs) for structural representation and deep semantic embeddings of SMILES sequences generated by the ChemBERTa pre-trained model. These features are processed by independent encoders and fused using an interactive attention mechanism, which enhances the molecular representation. In addition, PTPPI adopts a multi-task learning approach, enabling the model to both reconstruct input features and accurately predict inhibition scores. Experimental results on eight PPI target families, focusing on inhibitor identification and potency prediction, demonstrate that PTPPI outperforms existing methods. It not only integrates multiple molecular features effectively but also achieves superior prediction performance. This makes PTPPI a valuable and reliable tool for discovering new PPI inhibitors, thus opening up new possibilities for drug discovery and disease treatment.

Modern drug discovery faces significant challenges in optimizing compounds for favorable ADMET properties, notably metabolic stability, as rapid metabolism impacts bioavailability, half-life, and drug-drug interactions. Central to these issues are cytochrome P450 (CYP450) enzymes, which metabolize most approved drugs, with unintended inhibition or accelerated clearance contributing substantially to clinical failures. To address this, we developed DiffMeta-RL, a discrete graph diffusion model enhanced with reinforcement learning, enabling controllable optimization of pharmacological properties. Unlike conventional actor-critic frameworks that require a separate policy network, DiffMeta-RL introduces a streamlined approach by directly optimizing the generative diffusion model itself as the policy, embedding reward-guided updates into the denoising process. Additionally, we proposed MetaCYP, a highly accurate CYP450 inhibition predictor, integrating it into DiffMeta-RL's reward function to guide molecular generation toward reduced CYP450 liability and improved metabolic stability. In benchmark evaluations, DiffMeta-RL outperforms existing models in validity, uniqueness, and novelty. Specifically applied to designing proton pump inhibitors (PPIs) targeting gastric H⁺/K⁺-ATPase, DiffMeta-RL successfully generated candidates exhibiting favorable predicted binding affinity and reduced susceptibility to CYP2C19 and CYP3A4 metabolism, highlighting its practical potential for advancing drug discovery efforts.

Compared with traditional storage media, biological data storage has advanced more rapidly in capacity, diversity, and lifespan, and it also enables continuous data retention. The DNA molecule, as Nature's own archival medium, provides unparalleled density, longevity, and passive durability, making it a compelling foundation for the next generation of "cold" and "deeply cold" archives. Since 2019, progress across the stack—coding for insertion–deletion–missing channels, large-scale random access, enzyme writing, nanopore-native retrieval, and chemically robust expansion—has transformed DNA storage from provocative demonstrations into mature technologies with early end-to-end prototypes. From this perspective, we believe biological data management (BDM) is the first area where DNA storage can have practical impact, including raw sequencing archives, microscopic images, clinical omics data, and compliance-driven retention of de-identified records. We synthesize the latest technology levels, highlight what is actually working in today's labs, distinguish challenges from bottlenecks (particularly write costs/latencies and standardization), and propose a 2025–2030 roadmap with specific milestones in coding, writing, access, and media preservation. Finally, this paper proposes guidelines for integrating DNA archives into biological institutes, biobanks, and hospital systems as a supplementary layer to tape/object storage, and outlines a research agenda covering privacy, chain of custody, and sustainability.

Motivation: Predicting protein–protein interaction (PPI) sites is essential for advancing our understanding of protein interactions, as accurate predictions can significantly reduce experimental costs and time. While considerable progress has been made in identifying binding sites at the level of individual amino acid residues, the prediction accuracy for residue subsequences at transitional boundaries—such as those represented by patterns like singular structures (mutation characteristics of contiguous interacting-residue segments) or edge structures (boundary transitions between interacting/non-interacting residue segments) still requires improvement. Results: we propose a novel PPI site prediction method named MVSO-PPIS. This method integrates two complementary feature extraction modules, a subgraph-based module and an enhanced graph attention module. The extracted features are fused using an attention-based fusion mechanism, producing a composite representation that captures both local protein substructures and global contextual dependencies. MVSO-PPIS is trained to jointly optimize three objectives: overall PPI site prediction accuracy, edge structural consistency, and recognition of unique structural patterns in PPI site sequences. Experimental results on benchmark datasets demonstrate that MVSO-PPIS outperforms existing baseline models in both accuracy and structural interpretability. Availability and implementation: The datasets, source codes, and models of MVSO-PPIS are all available at https://github.com/Edwardblue282/MVSO-PPIS.

Disease is one of the primary factors affecting life activities, with complex etiologies often influenced by gene expression and mutation. Currently, wet lab experiments have analyzed the mechanisms of mutations, but these are usually limited by the costs of wet experiments and constraints in sample types and scales. Therefore, this paper constructs a real-world mutation-induced disease dataset and proposes Capsule and Graph topology networks with multi-head attention (CGM) to predict the mutation-disease associations. CGM can accurately predict protein mutation-disease associations, and to further elucidate the pathogenicity of protein mutations, we also verified that protein mutations lead to protein structural alterations by the model, which suggests that mutation-induced conformational changes may be an important pathogenic factor. Limited by the size of the mutated protein dataset, we also performed experiments on benchmark and imbalanced datasets, where CGM mined 22 unknown protein interaction pairs from the benchmark dataset, better illustrating the potential of CGM in predicting mutation-disease associations. In summary, this paper curates a real dataset. It proposes that CGM predicts protein mutations and disease associations, providing a novel tool for further understanding of biomolecular pathways and disease mechanisms.

Accurate porosity prediction is crucial for evaluating reservoir quality and potential productivity. Traditional laboratory experiments offer reliable porosity measurements but are time-consuming and computationally expensive. Recently, deep learning has been introduced for porosity prediction. However, most existing methods focus on either the relationships among features or deep sequences, neglecting the correlation between them. To better capture these correlations, we propose an adaptive graph convolutional network (GCN) with learning deep sequence and feature correlation graphs. The GCN is applied to well-logging data to capture non-Euclidean characteristics, extracting inherent spatiotemporal relationships. Furthermore, traditional GCNs rely on predefined graphs for feature aggregation, which can vary based on the thresholds for cosine similarity or covariance, potentially affecting accuracy and robustness. To tackle this issue, we introduced an adaptive mechanism for constructing deep sequence and feature correlation graphs, which eliminates the need for predefined thresholds and significantly enhances the accuracy and robustness of predictions. We demonstrated our method on well-logging datasets and comprehensively compared its performance with other deep learning models, showing its superiority in predicting porosity from well-logging data. This work offers geoscientists a more efficient and accurate analytical tool.