paper-with-me

홈 › Papers

Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling

2026-06-01 · Keyue Qiu, Xintong Wang, Zhilong Zhang, Hao Zhou, Wei-Ying Ma arxiv

Biomolecules such as proteins and small-molecule ligands play a central role in biological systems, arising from the tight interplay between sequence and three-dimensional structure. Recent generative models for biomolecular co-design aim to capture this interplay by jointly modeling coupled modalities. However, existing approaches largely adopt a parallel execution of marginal generative processes, implicitly enforcing fixed synchronous coupling. We argue that a critical but overlooked degree of freedom lies in how these marginal processes are temporally coupled during training and generation, where inappropriate coupling can introduce high-variance supervision and inconsistent intermediate states, affecting modality consistency. To address this, we introduce GeoCoupling, a systematic framework that optimizes for temporal couplings between heterogeneous modalities. Empirical results across structure-based drug design and unconditional protein design demonstrate the learned couplings consistently outperform synchronous and randomly coupled baselines, yielding biomolecules with improved physical validity and diversity.

📄 PDF Abstract BibTeX arXiv:2606.01628

Code (0)

등록된 구현이 없습니다.

Tasks

Protein Design

Similar Papers 제목 키워드 기반

Controlling Peak Sharpness in Multimodal Biomolecular Systems via the Chemical Fokker-Planck Equation

2025-03-18 · Taishi Kotsuka, Enoch Yeung

Intracellular biomolecular systems exhibit intrinsic stochasticity due to low molecular copy numbers, leading to multimodal probability distributions that play a crucial role in probabilistic differentiation and cellular…

Decision Making

Molecular Insights from Conformational Ensembles via Machine Learning

2020-02-04 · Biophys Journal 2020 2 · Fleetwood O, Kasimova MA, Westerlund AM, Delemotte L

Biomolecular simulations are intrinsically high dimensional and generate noisy data sets of ever-increasing size. Extracting important features from the data is crucial for understanding the biophysical properties of mol…

BIG-bench Machine LearningDimensionality ReductionPhysical Simulations

InstructBioMol: Advancing Biomolecule Understanding and Design Following Human Instructions

2024-10-10 · Xiang Zhuang, Keyan Ding, Tianwen Lyu, Yinuo Jiang 외

Understanding and designing biomolecules, such as proteins and small molecules, is central to advancing drug discovery, synthetic biology, and enzyme engineering. Recent breakthroughs in Artificial Intelligence (AI) have…

Data IntegrationDrug Discovery

Active learning of the thermodynamics-dynamics tradeoff in protein condensates

2023-06-06 · Yaxin An, Michael A. Webb, William M. Jacobs

Phase-separated biomolecular condensates exhibit a wide range of dynamical properties, which depend on the sequences of the constituent proteins and RNAs. However, it is unclear to what extent condensate dynamics can be …

Active Learning

Maximizing Information Gain for the Characterization of Biomolecular Circuits

2021-01-08 · Tim Prangemeier, Christian Wildner, Maleen Hanst, Heinz Koeppl

Quantitatively predictive models of biomolecular circuits are important tools for the design of synthetic biology and molecular communication circuits. The information content of typical time-lapse single-cell data for t…

Experimental DesignInformativeness