An SE(3)-equivariant and dynamic multi-modal engine advancing from PTM site prediction to network understanding
Year: 2026
Type: article
Abstract: Protein post-translational modifications (PTMs) orchestrate complex cellular processes, yet current computational methods predominantly tre at them as isolated sequence events. This reductionist approach—coupled with an inability to model 3D steric constraints and long-tail data scarcity—obscures the cooperative nature of PTM networks. Here, we introduce ProteinNexus, a multimodal deep-learning framework designed to bridge the gap between local site prediction and global network comprehension. By dynamically fusing evolutionary sequence data with a physically grounded, conformal equivariant graph neural network, ProteinNexus rigorously captures the 3D microenvironments of modification sites. Coupled with a reinforcement learning-driven specialization strategy, the framework effectively models crosstalk across 10 diverse PTM types, outperforming state-of-the-art methods by 7.5% (Matthews Correlation Coefficient). Beyond superior predictive accuracy, in silico knockouts and evolutionary analyses reveal that ProteinNexus successfully decodes cooperative PTM dynamics, providing a generalizable, structure-aware computational microscope to unravel the regulatory grammar of the proteome. Protein post-translational modifications (PTMs) enhance proteomic diversity, yet current computational methods fail to integrate site prediction with systemic network comprehension due to data scarcity and model limitations. Here, the authors introduce a three-stage framework, including the ProteinNexus model, advancing PTM analysis from isolated predictions to comprehensive network insights.
Source: Communications Chemistry
Authors: Yiyu Lin, Jiahui Wu, Sen Yang, Yan Wang
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: gold
Estimated APC paid: $3,690
Award: G5046590544
OpenAlex ID: W7160834573