UniPTMs: The First Unified Multi-type PTM Site Prediction Model via Master-Slave Architecture-Based Multi-Stage Fusion Strategy and Hierarchical Contrastive Loss
This work solves the challenge of multi-type PTM site prediction for bioinformatics and epigenetics researchers, representing a novel approach beyond single-type prediction paradigms.
The study tackled the problem of predicting multiple types of protein post-translational modification sites by proposing UniPTMs, a unified framework that addresses limitations in feature fusion and generalization, resulting in performance improvements of 3.2%-11.4% MCC and 4.2%-14.3% AP over state-of-the-art models across five modification types.
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: the first 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 (BGCA) module, while the slave path optimizes feature discrepancies and recalibration between structural and traditional features using a Low-Dimensional Fusion Network (LDFN). Complemented by a Multi-scale Adaptive convolutional Pyramid (MACP) for capturing local feature patterns and a Bidirectional Hierarchical Gated Fusion Network (BHGFN) enabling multi-level feature integration across paths, the framework employs a Hierarchical Dynamic Weighting Fusion (HDWF) 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% MCC and 4.2%-14.3% AP increases) over state-of-the-art models across five modification types and transcends the Single-Type Prediction Paradigm. To strike a balance between model complexity and performance, we have also developed a lightweight variant named UniPTMs-mini.