arXiv subjects

Xujun Zhang

Publications and source records attributed to Xujun Zhang.

18 recordsLinked to original sources

arXiv2026

AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design

Scientific LLM agents have shown promise in literature reasoning, tool use, and experiment planning, but it remains unclear whether they can autonomously improve large, tightly coupled scientific machine-learning systems through executable code changes and computationally expensive validation. We study this question in protein folding, where progress requires coordinated architectural modifications, multi-objective evaluation, and domain-aware interpretation. We present AgentFold, a multi-agent framework that formulates folding-model development as a closed-loop search over executable code variants. Starting from ESMFold, AgentFold proposes hypotheses, implements and debugs code-level modifications, evaluates model variants, analyzes experimental outcomes, and stores both successful and failed interventions in structured memory. An MCTS-style policy allocates computational resources across high-scoring search branches. On an engineering-scale protein-folding codebase comprising more than 2,000 lines of code, AgentFold explores approximately 80 model variants using approximately 5,000 GPU-hours and 170 million LLM tokens. Under a matched computational budget, AgentFold improves the best lDDT by 7.5% over independent Codex proposals and outperforms a random-search control. Beyond model improvement, the resulting intervention traces reveal recurring empirical design patterns: stable gains tend to arise from early, soft, learnable priors and gated refinement, whereas direct geometric perturbations and geometry-conditioned feedback often destabilize training. The code and experimental resources are publicly available at https://github.com/lmqfly/AgentFold.

cs.AI↗

arXiv2026

Navigating committor landscape of biomolecules with a general pairwise interaction model

Sampling rare conformation transitions between metastable states is a central challenge in atomistic simulations. While the committor function serve as an ideal reaction coordinate for driving enhanced sampling, their high-dimensional inputs and complex functional forms limit the efficacy of standard feedforward neural networks in modeling them. Inspired by recent breakthroughs in biomolecular structure prediction, we propose a novel committor learning framework grounded in the AlphaFold 3 paradigm. By integrating a lightweight, differentiable atom-level embedding with a simplified Pairformer architecture, our method inherently captures intricate dynamical features of diverse biosystems without requiring specialized prior knowledge. We demonstrate the superior expressiveness and accuracy of the proposed framework across multiple atomistic processes. For the folding of the chignolin mini-protein, our model reveals the finer-grained structure of its transition state ensemble (TSE) and a detailed bifurcated reaction mechanism. Furthermore, for calixarene host-guest systems, we develop a unified committor model that elucidates how ligand substituents regulate the ratio between distinct binding pathways, offering new perspectives for structure-based drug design.

physics.comp-ph↗

arXiv2026

An accurate nucleic acid-small molecule docking framework via geometric deep learning with large-scale pretraining

Nucleic acids are increasingly recognized as therapeutic targets beyond conventional protein-centered drug discovery, yet accurate and efficient docking of small molecules to nucleic acid structures remains challenging. Physics-based docking methods often show limited accuracy and efficiency, whereas deep learning approaches are constrained by the scarcity of experimentally resolved nucleic acid-ligand complexes. Here, we present NucleoDock, a deep learning framework for nucleic acid-small molecule docking. To address data scarcity, NucleoDock combines physics-guided large-scale pretraining on millions of docking-generated synthetic complexes with fine-tuning on curated experimental co-crystal structures. It further integrates sequence- and structure-informed nucleotide representations with atomistic three-dimensional features to capture both biological context and binding-site geometry. A mixture density network-based geometric scoring head is used to model conditional interaction-distance distributions for pose ranking. On an external benchmark of 125 nucleic acid-ligand complexes, NucleoDock achieved a top-1 success rate of 56 percent at an RMSD cutoff of 2.0 Angstrom, outperforming rDock with 29 percent, while generating 100 poses in approximately 5 seconds per complex. Retrospective virtual screening on the ROBIN benchmark further showed improved early enrichment. NucleoDock represents a step toward bridging the methodological gap between protein- and nucleic acid-directed computational drug discovery.

q-bio.BM↗

arXiv2026

Skoda's $L^2$ division theorem for $L^2$-optimal pairs

We establish a Skoda-type $L^2$ division theorem for $L^2$-optimal pairs, using a technique that combines a new Bochner-type inequality derived from the $L^2$-optimal conditions and Skoda's basic inequality. As applications, we provide some new characterizations of domains of holomorphy.

math.CV↗

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

BioScore: A Foundational Scoring Function For Diverse Biomolecular Complexes

Structural assessment of biomolecular complexes is vital for translating molecular models into functional insights, shaping our understanding of biology and aiding drug discovery. However, current structure-based scoring functions often lack generalizability across diverse biomolecular systems. We present BioScore, a foundational scoring function that addresses key challenges -- data sparsity, cross-system representation, and task compatibility -- through a dual-scale geometric graph learning framework with tailored modules for structure assessment and affinity prediction. BioScore supports a wide range of tasks, including affinity prediction, conformation ranking, and structure-based virtual screening. Evaluated on 16 benchmarks spanning proteins, nucleic acids, small molecules, and carbohydrates, BioScore consistently outperforms or matches 70 traditional and deep learning methods. Our newly proposed PPI Benchmark further enables comprehensive evaluation of protein-protein complex scoring. BioScore demonstrates broad applicability: (1) pretraining on mixed-structure data boosts protein-protein affinity prediction by up to 40% and antigen-antibody binding correlation by over 90%; (2) cross-system generalizability enables zero- and few-shot prediction with up to 71% correlation gain; and (3) its unified representation captures chemically challenging systems such as cyclic peptides, improving affinity prediction by over 60%. BioScore establishes a robust and generalizable framework for structural assessment across complex biomolecular landscapes.

physics.chem-ph↗

arXiv2025

Graph Neural Networks in Modern AI-aided Drug Discovery

Graph neural networks (GNNs), as topology/structure-aware models within deep learning, have emerged as powerful tools for AI-aided drug discovery (AIDD). By directly operating on molecular graphs, GNNs offer an intuitive and expressive framework for learning the complex topological and geometric features of drug-like molecules, cementing their role in modern molecular modeling. This review provides a comprehensive overview of the methodological foundations and representative applications of GNNs in drug discovery, spanning tasks such as molecular property prediction, virtual screening, molecular generation, biomedical knowledge graph construction, and synthesis planning. Particular attention is given to recent methodological advances, including geometric GNNs, interpretable models, uncertainty quantification, scalable graph architectures, and graph generative frameworks. We also discuss how these models integrate with modern deep learning approaches, such as self-supervised learning, multi-task learning, meta-learning and pre-training. Throughout this review, we highlight the practical challenges and methodological bottlenecks encountered when applying GNNs to real-world drug discovery pipelines, and conclude with a discussion on future directions.

q-bio.BM↗

arXiv2025

AutoLoop: a novel autoregressive deep learning method for protein loop prediction with high accuracy

Protein structure prediction is a critical and longstanding challenge in biology, garnering widespread interest due to its significance in understanding biological processes. A particular area of focus is the prediction of missing loops in proteins, which are vital in determining protein function and activity. To address this challenge, we propose AutoLoop, a novel computational model designed to automatically generate accurate loop backbone conformations that closely resemble their natural structures. AutoLoop employs a bidirectional training approach while merging atom- and residue-level embedding, thus improving robustness and precision. We compared AutoLoop with twelve established methods, including FREAD, NGK, AlphaFold2, and AlphaFold3. AutoLoop consistently outperforms other methods, achieving a median RMSD of 1.12 Angstrom and a 2-Angstrom success rate of 73.23% on the CASP15 dataset, while maintaining strong performance on the HOMSTARD dataset. It demonstrates the best performance across nearly all loop lengths and secondary structural types. Beyond accuracy, AutoLoop is computationally efficient, requiring only 0.10 s per generation. A post-processing module for side-chain packing and energy minimization further improves results slightly, confirming the reliability of the predicted backbone. A case study also highlights AutoLoop's potential for precise predictions based on dominant loop conformations. These advances hold promise for protein engineering and drug discovery.

q-bio.BM↗

arXiv2025

The union problem for domains with partial pseudoconvex boundaries

We show that a smooth bounded domain in $\mathbb{C}^n$ admitting partial pseudoconvex exhaustion remains partial pseudoconvex. The main ingredient of the proof is based on a new characterization of hyper-$q$-convex domains. Furthermore, we get several convex analogies.

math.CV↗

arXiv2025

Discovery of novel antimicrobial peptides with notable antibacterial potency by a LLM-based foundation model

Large language models (LLMs) have shown remarkable advancements in chemistry and biomedical research, acting as versatile foundation models for various tasks. We introduce AMP-Designer, an LLM-based approach for swiftly designing novel antimicrobial peptides (AMPs) with desired properties. Within 11 days, AMP-Designer achieved the de novo design of 18 AMPs with broad-spectrum activity against Gram-negative bacteria. In vitro validation revealed a 94.4% success rate, with two candidates demonstrating exceptional antibacterial efficacy, minimal hemotoxicity, stability in human plasma, and low potential to induce resistance, as evidenced by significant bacterial load reduction in murine lung infection experiments. The entire process, from design to validation, concluded in 48 days. AMP-Designer excels in creating AMPs targeting specific strains despite limited data availability, with a top candidate displaying a minimum inhibitory concentration of 2.0 μg/ml against Propionibacterium acnes. Integrating advanced machine learning techniques, AMP-Designer demonstrates remarkable efficiency, paving the way for innovative solutions to antibiotic resistance.

q-bio.BM↗

arXiv2024

Token-Mol 1.0: Tokenized drug design with large language model

Significant interests have recently risen in leveraging sequence-based large language models (LLMs) for drug design. However, most current applications of LLMs in drug discovery lack the ability to comprehend three-dimensional (3D) structures, thereby limiting their effectiveness in tasks that explicitly involve molecular conformations. In this study, we introduced Token-Mol, a token-only 3D drug design model. This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in drug discovery into probabilistic prediction problems, thereby enabling learning through a unified paradigm. Token-Mol is built on the transformer decoder architecture and trained using random causal masking techniques. Additionally, we proposed the Gaussian cross-entropy (GCE) loss function to overcome the challenges in regression tasks, significantly enhancing the capacity of LLMs to learn continuous numerical values. Through a combination of fine-tuning and reinforcement learning (RL), Token-Mol achieves performance comparable to or surpassing existing task-specific methods across various downstream tasks, including pocket-based molecular generation, conformation generation, and molecular property prediction. Compared to existing molecular pre-trained models, Token-Mol exhibits superior proficiency in handling a wider range of downstream tasks essential for drug design. Notably, our approach improves regression task accuracy by approximately 30% compared to similar token-only methods. Token-Mol overcomes the precision limitations of token-only models and has the potential to integrate seamlessly with general models such as ChatGPT, paving the way for the development of a universal artificial intelligence drug design model that facilitates rapid and high-quality drug design by experts.

q-bio.BM↗

arXiv2024

A new characterization of $L^2$-domains of holomorphy with null thin complements via $L^2$-optimal conditions

In this paper, we show that the $L^2$-optimal condition implies the $L^2$-divisibility of $L^2$-integrable holomorphic functions. As an application, we offer a new characterization of bounded $L^2$-domains of holomorphy with null thin complements using the $L^2$-optimal condition, which appears to be advantageous in addressing a problem proposed by Deng-Ning-Wang. Through this characterization, we show that a domain in a Stein manifold with a null thin complement, admitting an exhaustion of complete Kähler domains, remains Stein. By the way, we construct an $L^2$-optimal domain that does not admit any complete Kähler metric.

math.CV↗

arXiv2024

Deep Geometry Handling and Fragment-wise Molecular 3D Graph Generation

Most earlier 3D structure-based molecular generation approaches follow an atom-wise paradigm, incrementally adding atoms to a partially built molecular fragment within protein pockets. These methods, while effective in designing tightly bound ligands, often overlook other essential properties such as synthesizability. The fragment-wise generation paradigm offers a promising solution. However, a common challenge across both atom-wise and fragment-wise methods lies in their limited ability to co-design plausible chemical and geometrical structures, resulting in distorted conformations. In response to this challenge, we introduce the Deep Geometry Handling protocol, a more abstract design that extends the design focus beyond the model architecture. Through a comprehensive review of existing geometry-related models and their protocols, we propose a novel hybrid strategy, culminating in the development of FragGen - a geometry-reliable, fragment-wise molecular generation method. FragGen marks a significant leap forward in the quality of generated geometry and the synthesis accessibility of molecules. The efficacy of FragGen is further validated by its successful application in designing type II kinase inhibitors at the nanomolar level.

physics.chem-ph↗

arXiv2023

Positivity of Riemannian metric and the existence theorem of $L^2$ estimates for $d$ operator

Apply the $L^2$ technique developed by Deng-Ning-Wang-Zhou,we give a new characterization of Nakano $q$-positivity for Riemannian flat vector bundle in the sense of $L^2 $ estimate for the $d$ operator. We also give a new characterization of the positivity of the curvature operator associated to the Riemannian metric on manifold in a local version in the sense of $L^2$ estimate. Then we prove two results parallel to Liu-Yang-Zhou's answer to Lempert's question to Hermitian holomorphic vector bundle. We also study the boundary convexity of relative compact domain in certain Riemannian manifold with convexity restrictions.

math.DG↗

arXiv2023

Delete: Deep Lead Optimization Enveloped in Protein Pocket through Unified Deleting Strategies and a Structure-aware Network

Drug discovery is a highly complicated process, and it is unfeasible to fully commit it to the recently developed molecular generation methods. Deep learning-based lead optimization takes expert knowledge as a starting point, learning from numerous historical cases about how to modify the structure for better drug-forming properties. However, compared with the more established de novo generation schemes, lead optimization is still an area that requires further exploration. Previously developed models are often limited to resolving one (or few) certain subtask(s) of lead optimization, and most of them can only generate the two-dimensional structures of molecules while disregarding the vital protein-ligand interactions based on the three-dimensional binding poses. To address these challenges, we present a novel tool for lead optimization, named Delete (Deep lead optimization enveloped in protein pocket). Our model can handle all subtasks of lead optimization involving fragment growing, linking, and replacement through a unified deleting (masking) strategy, and is aware of the intricate pocket-ligand interactions through the geometric design of networks. Statistical evaluations and case studies conducted on individual subtasks demonstrate that Delete has a significant ability to produce molecules with superior binding affinities to protein targets and reasonable drug-likeness from given fragments or atoms. This feature may assist medicinal chemists in developing not only me-too/me-better products from existing drugs but also hit-to-lead for first-in-class drugs in a highly efficient manner.

q-bio.BM↗

arXiv2023

Highly accurate and efficient deep learning paradigm for full-atom protein loop modeling with KarmaLoop

Protein loop modeling is the most challenging yet highly non-trivial task in protein structure prediction. Despite recent progress, existing methods including knowledge-based, ab initio, hybrid and deep learning (DL) methods fall significantly short of either atomic accuracy or computational efficiency. Moreover, an overarching focus on backbone atoms has resulted in a dearth of attention given to side-chain conformation, a critical aspect in a host of downstream applications including ligand docking, molecular dynamics simulation and drug design. To overcome these limitations, we present KarmaLoop, a novel paradigm that distinguishes itself as the first DL method centered on full-atom (encompassing both backbone and side-chain heavy atoms) protein loop modeling. Our results demonstrate that KarmaLoop considerably outperforms conventional and DL-based methods of loop modeling in terms of both accuracy and efficiency, with the average RMSD improved by over two-fold compared to the second-best baseline method across different tasks, and manifests at least two orders of magnitude speedup in general. Consequently, our comprehensive evaluations indicate that KarmaLoop provides a state-of-the-art DL solution for protein loop modeling, with the potential to hasten the advancement of protein engineering, antibody-antigen recognition, and drug design.

q-bio.BM↗

arXiv2020

Characterization of Curvature positivity of Riemannian metrics on flat vector bundles

We give a characterization of Nakano positivity of Riemannian flat vector bundles over bounded domains $D\subset\mathbb{R}^n$ in terms of solvability of the $d$ equation with certain good $L^2$ estimate condition. As an application, we give an alternative proof of the matrix-valued Prekopa's theorem that is originally proved by Raufi. Our methods are inspired by the recent works of Deng-Ning-Wang-Zhou on characterization of Nakano positivity of Hermitian holomorphic vector bundles and positivity of direct image sheaves associated to holomorphic fibrations.

math.CV↗

arXiv2018

Fridman's invariant, squeezing functions, and exhausting domains

We show that if a bounded domain $Ω$ is exhausted by a bounded strictly pseudoconvex domain $D$ with $C^2$ boundary, then $Ω$ is holomorphically equivalent to $D$ or the unit ball, and show that a bounded domain has to be holomorphically equivalent to the unit ball if its Fridman's invariant has certain growth condition near the boundary.

math.CV↗