paper-with-me

Papers

VecMol: Vector-Field Representations for 3D Molecule Generation

2026-03-13 · Yuchen Hua, Xingang Peng, Jianzhu Ma, Muhan Zhang arxiv

Generative modeling of three-dimensional (3D) molecules is a fundamental yet challenging problem in drug discovery and materials science. Existing approaches typically represent molecules as 3D graphs and co-generate discrete atom types with continuous atomic coordinates, leading to intrinsic learning difficulties such as heterogeneous modality entanglement and geometry-chemistry coherence constraints. We propose VecMol, a paradigm-shifting framework that reimagines molecular representation by modeling 3D molecules as continuous vector fields over Euclidean space, where vectors point toward nearby atoms and implicitly encode molecular structure. The vector field is parameterized by a neural field and generated using a latent diffusion model, avoiding explicit graph generation and decoupling structure learning from discrete atom instantiation. Experiments on the QM9 and GEOM-Drugs benchmarks validate the feasibility of this novel approach, suggesting vector-field-based representations as a promising new direction for 3D molecular generation.

📄 PDF Abstract BibTeX arXiv:2603.12734

Code (0)

등록된 구현이 없습니다.

Tasks

Graph GenerationDrug Discovery

Similar Papers 제목 키워드 기반

Implicit Neural Representations of Molecular Vector-Valued Functions

2025-02-15 · Jirka Lhotka, Daniel Probst

Molecules have various computational representations, including numerical descriptors, strings, graphs, point clouds, and surfaces. Each representation method enables the application of various machine learning methodolo…

Decoder

HyperDiffusionFields (HyDiF): Diffusion-Guided Hypernetworks for Learning Implicit Molecular Neural Fields

2025-10-20 · Sudarshan Babu, Phillip Lo, Xiao Zhang, Aadi Srivastava 외 arxiv

We introduce HyperDiffusionFields (HyDiF), a framework that models 3D molecular conformers as continuous fields rather than discrete atomic coordinates or graphs. At the core of our approach is the Molecular Directional …

Molecular Property Prediction

Automatic chemical design using a data-driven continuous representation of molecules

2016-10-07 · Rafael Gómez-Bombarelli, Jennifer N. Wei, David Duvenaud, José Miguel Hernández-Lobato 외

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization thro…

DecoderEfficient Exploration

IMG2SMI: Translating Molecular Structure Images to Simplified Molecular-input Line-entry System

2021-09-03 · Daniel Campos, Heng Ji

Like many scientific fields, new chemistry literature has grown at a staggering pace, with thousands of papers released every month. A large portion of chemistry literature focuses on new molecules and reactions between …

Image Captioning

Quadratic Optimization-Based Nonlinear Control for Protein Conformation Prediction

2021-04-27 · Alireza Mohammadi, Mark W. Spong

Predicting the final folded structure of protein molecules and simulating their folding pathways is of crucial importance for designing viral drugs and studying diseases such as Alzheimer's at the molecular level. To thi…

Protein Folding