UniPTMs: a unified multi-type PTM site prediction model via master–slave architecture-based multi-stage fusion strategy and hierarchical contrastive loss

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. 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. 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.