Tokenizing Electron Cloud in Protein-Ligand Interaction Learning

• URL: http://arxiv.org/abs/2505.19014v2
• Date: Sat, 31 May 2025 08:00:35 GMT
• Title: Tokenizing Electron Cloud in Protein-Ligand Interaction Learning
• Authors: Haitao Lin, Odin Zhang, Jia Xu, Yunfan Liu, Zheng Cheng, Lirong Wu, Yufei Huang, Zhifeng Gao, Stan Z. Li,
• Abstract summary: ECBind is a method for tokenizing electron cloud signals into quantized embeddings.<n>It helps uncover binding modes that cannot be fully represented by atom-level models.<n>To extend its applicability to a wider range of scenarios, we utilize knowledge distillation to develop an electron-cloud-agnostic prediction model.
• Score: 51.74909649330779
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The affinity and specificity of protein-molecule binding directly impact functional outcomes, uncovering the mechanisms underlying biological regulation and signal transduction. Most deep-learning-based prediction approaches focus on structures of atoms or fragments. However, quantum chemical properties, such as electronic structures, are the key to unveiling interaction patterns but remain largely underexplored. To bridge this gap, we propose ECBind, a method for tokenizing electron cloud signals into quantized embeddings, enabling their integration into downstream tasks such as binding affinity prediction. By incorporating electron densities, ECBind helps uncover binding modes that cannot be fully represented by atom-level models. Specifically, to remove the redundancy inherent in electron cloud signals, a structure-aware transformer and hierarchical codebooks encode 3D binding sites enriched with electron structures into tokens. These tokenized codes are then used for specific tasks with labels. To extend its applicability to a wider range of scenarios, we utilize knowledge distillation to develop an electron-cloud-agnostic prediction model. Experimentally, ECBind demonstrates state-of-the-art performance across multiple tasks, achieving improvements of 6.42\% and 15.58\% in per-structure Pearson and Spearman correlation coefficients, respectively.

Related papers

• Exploring structure diversity in atomic resolution microscopy with graph neural networks [18.903519247639355]
  Deep learning is a powerful tool to explore structure diversity in a fast, accurate, and intelligent manner. This work provides a powerful tool to explore structure diversity in a fast, accurate, and intelligent manner.
  arXiv  Detail & Related papers  (2024-10-23T07:48:35Z)
• Electronic Correlations in Multielectron Silicon Quantum Dots [0.3793387630509845]
  Silicon metal-oxide-semiconductor based quantum dots present a promising pathway for realizing practical quantum computers. Hartree-Fock theory is an imperative tool for the electronic structure modelling of multi-electron quantum dots. We present a Hartree-Fock-based method that accounts for these complexities for the modelling of silicon quantum dots.
  arXiv  Detail & Related papers  (2024-07-05T06:46:38Z)
• Striking the Right Balance of Encoding Electron Correlation in the Hamiltonian and the Wavefunction Ansatz [0.0]
  Multi-configurational electronic structure theory delivers the most versatile approximations to many-electron wavefunctions. We argue in favor of simple electrons-only correlator expressions that may allow one to define transcorrelated models.
  arXiv  Detail & Related papers  (2024-04-30T00:34:34Z)
• Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge [69.80471117520719]
  Re-Dock is a novel diffusion bridge generative model extended to geometric manifold. We propose energy-to-geometry mapping inspired by the Newton-Euler equation to co-model the binding energy and conformations. Experiments on designed benchmark datasets including apo-dock and cross-dock demonstrate our model's superior effectiveness and efficiency over current methods.
  arXiv  Detail & Related papers  (2024-02-18T05:04:50Z)
• Modeling Non-Covalent Interatomic Interactions on a Photonic Quantum Computer [50.24983453990065]
  We show that the cQDO model lends itself naturally to simulation on a photonic quantum computer. We calculate the binding energy curve of diatomic systems by leveraging Xanadu's Strawberry Fields photonics library. Remarkably, we find that two coupled bosonic QDOs exhibit a stable bond.
  arXiv  Detail & Related papers  (2023-06-14T14:44:12Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Neural Upscaling from Residue-level Protein Structure Networks to Atomistic Structure [2.087827281461409]
  "neural upscaling" is able to effectively recapitulate detailed structural information for intrinsically disordered proteins. Results suggest that scalable network-based models for protein structure and dynamics may be used in settings where atomistic detail is desired.
  arXiv  Detail & Related papers  (2021-08-25T23:43:57Z)
• Distance-aware Molecule Graph Attention Network for Drug-Target Binding Affinity Prediction [54.93890176891602]
  We propose a diStance-aware Molecule graph Attention Network (S-MAN) tailored to drug-target binding affinity prediction. As a dedicated solution, we first propose a position encoding mechanism to integrate the topological structure and spatial position information into the constructed pocket-ligand graph. We also propose a novel edge-node hierarchical attentive aggregation structure which has edge-level aggregation and node-level aggregation.
  arXiv  Detail & Related papers  (2020-12-17T17:44:01Z)
• ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution [57.635467829558664]
  We introduce a structural regularization across convolutional kernels in a CNN. We show that CNNs now maintain performance with dramatic reduction in parameters and computations.
  arXiv  Detail & Related papers  (2020-09-04T20:41:47Z)
• Graph Neural Network for Hamiltonian-Based Material Property Prediction [56.94118357003096]
  We present and compare several different graph convolution networks that are able to predict the band gap for inorganic materials. The models are developed to incorporate two different features: the information of each orbital itself and the interaction between each other. The results show that our model can get a promising prediction accuracy with cross-validation.
  arXiv  Detail & Related papers  (2020-05-27T13:32:10Z)

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.