arXiv subjects

Gang Du

Publications and source records attributed to Gang Du.

6 recordsLinked to original sources

arXiv2026

EpiBench: Can LLMs Understand Epitopes for Antibody Drug Discovery?

Epitopes determine where antibodies bind antigens and shape downstream therapeutic properties such as functional blockade and escape resistance, making epitope understanding central to antibody drug discovery. Although large language models (LLMs) have shown strong biomedical reasoning ability, it remains unclear whether they can infer epitope information directly from antigen and antibody sequences. Existing epitope resources typically focus on isolated prediction tasks or rely on specialized structural settings, while general protein benchmarks do not evaluate epitope-centered decisions across the antibody development workflow. To address this gap, we introduce EpiBench, a closed-book, sequence-based, and automatically scorable benchmark for evaluating epitope reasoning in LLMs. EpiBench contains 1,609 curated samples grounded in structural antibody--antigen contacts, curated functional B-cell assays, and deep mutational scanning escape measurements. It covers five connected tasks: targetable region discovery, antibody-conditioned epitope identification, epitope binning, functional epitope assessment, and antibody escape assessment, with controlled sampling to reduce shortcut-based evaluation artifacts. We evaluate nine general-purpose LLMs and analyze their behavior through task-specific baselines, antigen length stratification, explicit-reasoning comparison, and failure-mode inspection. The results show that current LLMs capture partial epitope-related signals but remain limited in antibody-specific sequence grounding, long-context residue localization, and biologically grounded reasoning. Therefore, EpiBench provides a diagnostic testbed for measuring and improving sequence-aware biomedical LLMs toward reliable LLM-assisted antibody discovery.

cs.CL↗

arXiv2026

A few-shot and physically restorable symbolic regression turbulence model based on normalized general effective-viscosity hypothesis

Turbulence is a complex, irregular flow phenomenon ubiquitous in natural processes and engineering applications. The Reynolds-averaged Navier-Stokes (RANS) method, owing to its low computational cost, has become the primary approach for rapid simulation of engineering turbulence problems. However, the inaccuracy of classical turbulence models constitutes the main drawback of the RANS framework. With the rapid development of data-driven approaches, many data-driven turbulence models have been proposed, yet they still suffer from issues of generalizability and accuracy. In this work, we propose a few-shot, physically restorable, symbolic regression turbulence model based on the normalized general effective-viscosity hypothesis. Few-shot indicates that our model is trained on limited flow configurations spanning only a narrow subset of turbulent flow physics, yet can still outperform the baseline model in substantially different turbulent flows. Physically restorable means our model can nearly revert to the baseline model in regimes satisfying specific physical conditions, using only the symbolic regression training results. The normalized general effective-viscosity hypothesis was proposed in our previous study. Specifically, we first formalize the concept of few-shot data-driven turbulence models. Second, we train our symbolic regression turbulence models using only direct numerical simulation (DNS) data for three-dimensional periodic hill flow slices. Third, we evaluate our models on periodic hill flows, zero pressure gradient flat plate flow, NACA0012 airfoil flows, and NASA Rotor 37 transonic axial compressor flows. One of our symbolic regression turbulence models consistently outperforms the baseline model, and we further demonstrate that this model can nearly revert to baseline behavior in certain flow regimes.

physics.flu-dyn↗

arXiv2025

ODesign: A World Model for Biomolecular Interaction Design

Biomolecular interactions underpin almost all biological processes, and their rational design is central to programming new biological functions. Generative AI models have emerged as powerful tools for molecular design, yet most remain specialized for individual molecular types and lack fine-grained control over interaction details. Here we present ODesign, an all-atom generative world model for all-to-all biomolecular interaction design. ODesign allows scientists to specify epitopes on arbitrary targets and generate diverse classes of binding partners with fine-grained control. Across entity-, token-, and atom-level benchmarks in the protein modality, ODesign demonstrates superior controllability and performance to modality-specific baselines. Extending beyond proteins, it generalizes to nucleic acid and small-molecule design, enabling interaction types such as protein-binding RNA/DNA and RNA/DNA-binding ligands that were previously inaccessible. By unifying multimodal biomolecular interactions within a single generative framework, ODesign moves toward a general-purpose molecular world model capable of programmable design. ODesign is available at https://odesign.lglab.ac.cn ,

q-bio.BM↗

arXiv2025

A symbolic regression-based implicit algebraic stress turbulence model: incorporating the production of non-dimensional Reynolds stress deviatoric tensor

Turbulence constitutes an exceptionally complex and irregular flow phenomenon that manifests in liquids, gases, and plasma, making it ubiquitous in both natural processes and engineering applications. Given the relatively modest advancements in classical turbulence models over the past half-century, data-driven approaches, such as machine learning, have recently gained considerable traction in turbulence model research. In this study, we introduce a symbolic regression-based implicit algebraic stress turbulence model that incorporates the production of non-dimensional Reynolds stress deviatoric tensor, thereby capturing the contribution of the shape of local turbulence produced by the mean flow field. We rigorously evaluate our model across five distinct characteristic flow cases and benchmark it against three alternative turbulence models. Our comprehensive analysis demonstrates that the proposed model exhibits robust performance and substantial generalizability across all test cases while manifesting notable advantages when compared with the reference turbulence models.

physics.flu-dyn↗

arXiv2025

Learning Non-Ideal Vortex Flows Using the Differentiable Vortex Particle Method

Vortex flows are ubiquitous in both natural processes and engineering applications, including phenomena such as typhoons, water currents, and aerospace fluid dynamics. The vortex particle method, a computational approach grounded in vortex dynamics, has been extensively applied in aerodynamics, oceanography, turbulence, and aeroacoustics. With the recent introduction of machine learning into computational fluid dynamics, a hybrid framework known as the differentiable vortex particle method (DVPM) has been proposed, which integrates the vortex particle method with deep learning to enable efficient learning and prediction. However, the original formulation of DVPM is limited to ideal vortex flow conditions, such as inviscid flows without non-conservative body forces, which significantly restricts its practical applicability. In this study, we extend the differentiable vortex particle method beyond idealized flow scenarios to encompass more realistic, non-ideal conditions, including viscous flow and flow subjected to non-conservative body forces. We establish the Lamb-Oseen vortex as a benchmark case, representing a fundamental viscous vortex flow in fluid mechanics. This selection offers significant analytical advantages, as the Lamb-Oseen vortex possesses an exact analytical solution derived from the Navier-Stokes (NS) equations, thereby providing definitive ground truth data for training and validation purposes. Through rigorous evaluation across a spectrum of Reynolds numbers, we demonstrate that DVPM achieves superior accuracy in modeling the Lamb-Oseen vortex compared to conventional convolutional neural networks (CNNs) and physics-informed neural networks (PINNs). Our results substantiate DVPM's robust capabilities in modeling non-ideal vortex flows, establishing its distinct advantages over contemporary deep learning methodologies in fluid dynamics applications.

physics.flu-dyn↗

arXiv2024

Enhancing generalizability of machine learning general effective-viscosity turbulence model via tensor basis normalization

With the rapid advancement of machine learning techniques, the development and study of machine learning turbulence models have become increasingly prevalent. As a critical component of turbulence modeling, the constitutive relationship between the Reynolds stress tensor and the mean flow quantities, modeled using machine learning methods, faces a pressing challenge: the lack of generalizability. To address this issue, we propose a novel tensor basis normalization technique to improve machine learning turbulence models, grounded in the general effective-viscosity hypothesis. In this study, we utilize direct numerical simulation (DNS) results of periodic hill flows as training data to develop a symbolic regression-based turbulence model based on the general effective-viscosity hypothesis. Furthermore, we construct a systematic validation dataset to evaluate the generalizability of our symbolic regression-based turbulence model. This validation set includes periodic hills with different aspect ratios from the training dataset, zero pressure gradient flat plate flows, three-dimensional incompressible flows over a NACA0012 airfoil, and transonic axial compressor rotor flows. These validation cases exhibit significant flow characteristics and geometrical variations, progressively increasing their differences from the training dataset. Such a diverse validation set is a robust benchmark to assess the generalizability of the proposed turbulence model. Finally, we demonstrate that our symbolic regression-based turbulence model performs effectively across validation cases, encompassing various separation features, geometries, and Reynolds numbers.

physics.flu-dyn↗