BACKGROUND: As a core mechanism of epigenetic regulation in eukaryotes, protein post-translational modifications (PTMs) require precise prediction to decipher dynamic life activity networks. To address the limitations of existing deep learning models in cross-modal feature fusion, domain generalization, and architectural optimization, this study proposes UniPTMs: a unified framework for multi-type PTM prediction. RESULTS: The framework innovatively establishes a "Master-Slave" dual-path collaborative architecture: the master path dynamically integrates high-dimensional representations of protein sequences, structures, and evolutionary information through a bidirectional gated cross-attention module, while the slave path optimizes feature discrepancies and recalibration between structural and traditional features using a low-dimensional fusion network. Complemented by a multi-scale adaptive convolutional pyramid for capturing local feature patterns and a bidirectional hierarchical gated fusion network enabling multi-level feature integration across paths, the framework employs a hierarchical dynamic weighting fusion mechanism to intelligently aggregate multimodal features. Enhanced by a novel hierarchical contrastive loss function for feature consistency optimization, UniPTMs demonstrates significant performance improvements (3.2-11.4% Matthews correlation coefficient and 4.2-14.3% average precision increases) over state-of-the-art models across five modification types. Additionally, to strike a balance between model complexity and performance, we have developed a lightweight variant named UniPTMs-mini. CONCLUSIONS: UniPTMs successfully transcends the single-type prediction paradigm, providing a unified and highly accurate approach for multi-type PTM prediction. This robust architecture, alongside its lightweight variant, offers a powerful and practical tool for advancing epigenetic research and further deciphering dynamic life activity networks.

The prediction of post-translational modifications (PTMs), a critical regulatory mechanism, is hindered by data sparsity and the challenge of integrating 3D structural information into computational models. We introduce UniProNet, a universal PTM prediction framework that overcomes these limitations using an E(3) equivariant graph neural network with multi-modal fusion. To address data scarcity for rare PTMs, UniProNet incorporates a generative evolutionary network, PTM-AGEN. Its core dual-stream architecture processes parallel sequence and structural data, integrating them through a synergistic fusion strategy that combines a Dominant-Stream Fusion Network, a Symmetric Hierarchical-flow Graph Network for multi-scale geometric representation, and a Kronecker-Hyper-Transport-Refiner based on Gromov-Wasserstein optimal transport theory. A hierarchical contrastive loss function ensures multi-modal consistency. Benchmarked on$\mathbf{1 0}$distinct PTM types, UniProNet substantially outperforms state-of-the-art models, with average improvements of$\mathbf{4. 3 2 \%}$in AUC,$\mathbf{8. 1 1 \%}$in MCC, and$\mathbf{5. 9 4 \%}$in AP. Furthermore, its excellent generalization to other tasks, such as protein-protein interaction prediction, highlights its broad applicability and potential as a foundational tool in computational proteomics.

BACKGROUND: Accurately identifying RNA 2'-O-methylation (2OM) sites is a crucial step in gaining an in-depth understanding of RNA regulatory mechanisms. Although there are currently multiple prediction tools available, they still suffer from limited prediction accuracy and an inability to fully capture the associations between sequences and sites. RESULTS: This study constructs a novel low-redundancy dataset and innovatively proposes the KN-PairMatrix encoding scheme, effectively addressing the research gap in sequence-site association analysis. Based on this foundation, we developed the deep learning framework OMetaNet, which integrates residual and downsampling-optimized CNN modules, Mamba network, and a proprietary cross-modal interactive fusion module. The framework incorporates a contrastive learning-driven adaptive hybrid loss function. Employing a progressive feature disentanglement strategy, it enhances the learning capability for 2OM site-specific patterns. Independent evaluation results demonstrate that OMetaNet significantly outperforms existing methods in predicting 2OM sites across all four nucleotide types. CONCLUSIONS: We proposed a novel computational model, OMetaNet. Its unique design structure may potentially reshape the paradigm of transcriptome analysis, open up new directions for extracting modification site information, and show significant potential in biomarker research and cross-species generalization studies.

Bioactive peptides are beneficial or have physiological effects on the life activities of biological organisms. The functions of bioactive peptides are diverse, usually with one or more, so accurately detecting the multiple functions of multi-functional peptides is extremely important. Traditional experimental identification methods are time-consuming, laborious and costly. To overcome these problems, we adopt a computational biology approach and propose a new model BPFun based on deep learning, which can predict seven functions including anticancer, antibacterial, antihypertensive and so on. In BPFun, we obtained the features of bioactive peptides from different aspects, including biological and physicochemical features. Meanwhile, adopting data augmentation to solve the problem of data imbalance. We combine convolutional networks of different scales and Bi-LSTM layers to obtain high-level feature vectors of different features. Finally, the prediction performance is improved by combining these fused features and combining the self-attention mechanism and the Bi-LSTM layer. Our experiments show that BPFun based on five types of sequence features significantly improves the prediction performance of bioactive peptides. Experiments on the test dataset showed that BPFun gets the accuracy and absolute truth value of 0.6577 and 0.6573 on the dataset of seven functional classifications and was superior to other methods. Codes and data are available at https://github.com/291357657/BPFun .