Support Field Neural Representation Learning (SF-NRL), a topology-guided approach that integrates persistent homology(PH), spatial density estimation, and geometric deep learning to infer residue-wise support directly from protein structures, is introduced.
Abstract
We model protein structural stability as a continuous scalar quantity defined over molecular geometry, referred to as the support field. Instead of treating stability as a discrete residue annotation or an empirical score, this representation characterizes protein folds through the combined effects of geometric organization, topological persistence, and local density. Based on this idea, we introduce Support Field Neural Representation Learning (SF-NRL), a topology-guided approach that integrates persistent homology(PH), spatial density estimation, and geometric deep learning to infer residue-wise support directly from protein structures. Persistent topological features are incorporated as structural constraints that modulate local support values across the fold, enabling a continuous description of structural reliability. Across diverse protein families, the inferred support field shows consistent agreement with independent indicators of structural stability and highlights low-support regions associated with conformational flexibility and weak structural integration. By embedding protein structures into a continuous stability landscape, SF-NRL provides an interpretable representation that complements structure prediction models and facilitates systematic identification of structural cores, flexible regions, and functionally relevant motifs. These results demonstrate that topology-informed field representations offer a generalizable and practically useful approach for analyzing protein stability and fold organization.
This review focuses on coordinate- and residue-frame-based diffusion approaches for generating protein structures, paying particular attention to geometric equivariance, conditioning strategies, all-atom modelling and interaction-aware design.
Wen-Ran Li, Xavier F. Cadet, David Medina-Ortiz et al.· International Journal of Mol...· 0 citations
This work proposes a novel approach that learns hierarchical discrete representations of protein structures using vector quantization, and outperforms state-of-the-art models such as ESMDiff across challenging benchmark datasets, including BPTI MD trajectories and conformational-changing pairs.
Seokjun On, Yujin Jeong, Kanghyeon Kim et al.· Bioinformatics· 0 citations
Accurate identification of near-native ligand binding poses is a central challenge in structure-based drug design. From a physical point of view, the successful construction of a protein–ligand complex structure is dependent on whether protein and ligand can form enough atomically pairwise interactions that result in a global energy minimum. In this work, we report a machine learning scoring strategy for protein–ligand screening which explicitly considers the Native Contact Ratio (NCR), a topology inspired metric that quantifies the preservation of protein–ligand interfacial contacts as well as interaction energy. This physics-awared supervision strategy provides a simple but efficient gradient field that faithfully reflects the complicated protein energy landscape than conventional 3D coordinate-based objectives. Building on this principle, we present DeepNCR, an energy-informed Transformer framework that encodes approximate Coulombic and dispersive interaction potentials across the protein–ligand binding interface. Furthermore, we introduce a feature pruning step that compresses the interaction tensor from 1470 to 868 dimensions, further improving signal-to-noise ratio and directing model attention toward the interaction motifs critical for binding specificity. The model optimizes topological objectives and at inference drives pose refinement through a differentiable hybrid gradient field integrating predicted NCR and AutoDock Vina energetics. Extensive evaluation on the CASF-2016 benchmark and the 3D-DISCO cross-docking data set demonstrates consistently high performance: a Top-1 docking success rate of 94.7%, a 1% Enrichment Factor of 21.21 in virtual screening, and a Top-1 cross-docking success rate of 34.8%. Mechanistic analysis reveals that NCR-guided optimization enables decoy escaping from local energy minima and drives the recovery of disrupted native interactions, confirming that NCR captures the physical determinants of binding rather than mere geometric proximity.
Zhenqiang Zhang, Zhihao Wang, Yang Liu et al.· Journal of Chemical Informat...· 0 citations
This work introduces mathematical topology metrics that quantify the entanglement complexity of a tertiary protein structure while respecting uncrossability constraints and results indicate that these metrics efficiently encode structural features linked to protein function and provide a more informative description than conventional metrics.
P. Malatesta, Roshita S. Chandnani, J. Yalim et al.· bioRxiv· 0 citations
Accurate identification of enzyme active sites is a prerequisite for elucidating protein functions and guiding enzyme engineering. Driven by the exponential growth of protein sequence data from next-generation sequencing, numerous novel enzymes with low sequence similarity have been discovered. While protein structure prediction models have provided highly accurate 3D structural data for these novel enzymes, the precise identification of their active sites remains a significant challenge for existing computational methods. Existing methods are constrained by static geometric representations, limited local receptive fields of graph encoders, and evolutionary semantic dilution. To address these limitations, this study presents Evo-EquiGPS, a multimodal graph neural network framework that synergizes multidimensional features for precise enzyme active site prediction. The model incorporates a three-branch parallel encoding architecture consisting of a dynamic geometric flow, a global topological flow, and an explicit evolutionary flow. It comprehensively integrates sequence semantics, 3D structures, and explicit evolutionary constraints of enzymes. Empirical evaluations demonstrate that Evo-EquiGPS exhibits superior performance across data sets with high structural diversity. On the TS124 data set, its area under the precision-recall curve (AUPRC) surpassed that of leading models such as SCREEN and GraphEC by a significant margin (exceeding SCREEN by 13.1% and GraphEC by 15.1%). Furthermore, the model demonstrated strong generalization capabilities on the highly diverse independent test set CSA112. Overall, the Evo-EquiGPS framework significantly enhances the precision of enzyme active site prediction. This provides a solid foundation for computational protein functional annotation.
Xinyu Fei, Jiali Gu, Cheng Zhou et al.· Journal of Chemical Informat...· 0 citations
DHST is proposed, a deep hybrid structure–topology framework that integrates sequence semantics from a pretrained protein language model with local structural information learned by a residual graph convolutional network and introduces site-specific persistent homology to encode multi-scale topological invariants and a topology-guided residue-wise gated fusion module to modulate structure–semantics representations using local topological embeddings.
Bin Lu, Fujun Xiang, Hai-Long Wang et al.· Applied Sciences· 0 citations