PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies

• URL: http://arxiv.org/abs/2605.01625v1
• Date: Sat, 02 May 2026 22:31:50 GMT
• Title: PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies
• Abstract summary: PRIME (Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies) is a unified framework that models proteins as a nested family of five structural graphs spanning surface, atomic, residue, secondary-structure, and protein levels.<n> Experiments on standard protein representation learning benchmarks demonstrate strong and competitive performance across diverse tasks.
• Score: 6.086602240954416
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Proteins are inherently multiscale physical systems whose functional properties emerge from coordinated structural organization across multiple spatial resolutions, ranging from atomic interactions to global fold topology. However, existing protein representation learning methods typically operate at a single structural level or treat different sources of structural information as parallel modalities, without explicitly modeling their hierarchical relationships. We introduce PRIME (Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies), a unified framework that models proteins as a nested family of five physically grounded structural graphs spanning surface, atomic, residue, secondary-structure, and protein levels. Adjacent levels are connected through deterministic, physics-informed assignment operators, enabling bidirectional information exchange via bottom-up aggregation and top-down contextual refinement. Experiments on standard protein representation learning benchmarks demonstrate strong and competitive performance across diverse tasks, with particularly notable gains on the Fold Classification benchmark, where PRIME outperforms the strongest geometric GNN baseline by margins of 13.80 and 18.30 points on the harder Superfamily and Fold splits, and achieves a state-of-the-art accuracy of 84.10% on Reaction Class prediction, surpassing all baseline methods, including ESM. Ablation studies confirm that each structural level contributes complementary and non-redundant information, and adaptive cross-attention analysis reveals that PRIME autonomously identifies the most task-relevant structural resolutions at prediction time. Our source code is publicly available at https://github.com/HySonLab/PRIME

Related papers

• Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition [13.468392186646382]
  ProtDiS is a knowledge-guided framework that decomposes pretrained protein micro-environment embeddings into biologically grounded dimensions.<n>Inspired by the information bottleneck principle, ProtDiS learns representations that balance informativeness and compression.<n>Protein- and residue-level analyses show that ProtDiS differentiates proteins with similar folds but divergent functions and captures fine-grained biophysical signals critical.
  arXiv  Detail & Related papers  (2026-05-12T07:12:12Z)
• Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles [74.32932832937618]
  We introduce $textbfRigidSSL$ ($textitRigidity-Aware Self-Supervised Learning$), a geometric pretraining framework that front-loads geometry learning prior to finetuning.<n>Phase I (RigidSSL-Perturb) learns geometric priors from 432K structures from the AlphaFold Protein Structure Database with simulated perturbations.<n>Phase II (RigidSSL-MD) refines these representations on 1.3K molecular dynamics trajectories to capture physically realistic transitions.
  arXiv  Detail & Related papers  (2026-03-02T21:32:30Z)
• Protein Autoregressive Modeling via Multiscale Structure Generation [51.92004892768298]
  We present protein autoregressive modeling (PAR), the first multi-scale autoregressive framework for protein backbone generation.<n>We adopt noisy context learning and scheduled sampling, enabling robust backbone generation.<n>On the unconditional generation benchmark, PAR effectively learns protein distributions and produces backbones of high design quality.
  arXiv  Detail & Related papers  (2026-02-04T18:59:49Z)
• Topotein: Topological Deep Learning for Protein Representation Learning [16.907805137005845]
  We introduce Topotein, a comprehensive framework that applies topological deep learning to protein representation learning (PRL)<n>PCC represents proteins at multiple hierarchical levels -- from residues to secondary structures to complete proteins -- while preserving geometric information at each level.<n> TCPNet employs SE(3)-equivariant message passing across these hierarchical structures, enabling more effective capture of multi-scale structural patterns.
  arXiv  Detail & Related papers  (2025-09-04T04:58:20Z)
• AlphaFold Database Debiasing for Robust Inverse Folding [58.792020809180336]
  We introduce a Debiasing Structure AutoEncoder (DeSAE) that learns to reconstruct native-like conformations from intentionally corrupted backbone geometries.<n>At inference, applying DeSAE to AFDB structures produces debiased structures that significantly improve inverse folding performance.
  arXiv  Detail & Related papers  (2025-06-10T02:25:31Z)
• Bidirectional Hierarchical Protein Multi-Modal Representation Learning [4.682021474006426]
  Protein language models (pLMs) pretrained on large scale protein sequences have demonstrated significant success in sequence-based tasks.<n> graph neural networks (GNNs) designed to leverage 3D structural information have shown promising generalization in protein-related prediction tasks.<n>We propose a bidirectional and hierarchical (Bi-Hierarchical) fusion approach to capture richer and more comprehensive protein representations.
  arXiv  Detail & Related papers  (2025-04-07T06:47:49Z)
• Multi-Scale Representation Learning for Protein Fitness Prediction [31.735234482320283]
  Previous methods have primarily relied on self-supervised models trained on vast, unlabeled protein sequence or structure datasets.<n>We introduce the Sequence-Structure-Surface Fitness (S3F) model - a novel multimodal representation learning framework that integrates protein features across several scales.<n>Our approach combines sequence representations from a protein language model with Geometric Vector Perceptron networks encoding protein backbone and detailed surface topology.
  arXiv  Detail & Related papers  (2024-12-02T04:28:10Z)
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model [68.28309982199902]
  We present NeuralPLexer, a computational approach that can directly predict protein-ligand complex structures. Our study suggests that a data-driven approach can capture the structural cooperativity between proteins and small molecules, showing promise in accelerating the design of enzymes, drug molecules, and beyond.
  arXiv  Detail & Related papers  (2022-09-30T01:46:38Z)
• Multi-Scale Representation Learning on Proteins [78.31410227443102]
  This paper introduces a multi-scale graph construction of a protein -- HoloProt. The surface captures coarser details of the protein, while sequence as primary component and structure captures finer details. Our graph encoder then learns a multi-scale representation by allowing each level to integrate the encoding from level(s) below with the graph at that level.
  arXiv  Detail & Related papers  (2022-04-04T08:29:17Z)
• PersGNN: Applying Topological Data Analysis and Geometric Deep Learning to Structure-Based Protein Function Prediction [0.07340017786387766]
  In this work, we isolate protein structure to make functional annotations for proteins in the Protein Data Bank. We present PersGNN - an end-to-end trainable deep learning model that combines graph representation learning with topological data analysis.
  arXiv  Detail & Related papers  (2020-10-30T02:24:35Z)
• Transfer Learning for Protein Structure Classification at Low Resolution [124.5573289131546]
  We show that it is possible to make accurate ($geq$80%) predictions of protein class and architecture from structures determined at low ($leq$3A) resolution. We provide proof of concept for high-speed, low-cost protein structure classification at low resolution, and a basis for extension to prediction of function.
  arXiv  Detail & Related papers  (2020-08-11T15:01:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.