{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T06:15:19Z","timestamp":1788243319687,"version":"build-2803163510"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32470687"],"award-info":[{"award-number":["32470687"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225109"],"award-info":[{"award-number":["62225109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62522106"],"award-info":[{"award-number":["62522106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["ZD2024F001"],"award-info":[{"award-number":["ZD2024F001"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Chem."],"abstract":"<jats:p>Structure-Based Drug Design (SBDD) is a key computational paradigm that uses protein structural information to design and optimize small molecules with desired binding properties. Existing SBDD methods mainly focus on molecular design and often lack the capability to independently conduct downstream evaluation and optimize workflows. Meanwhile, directly applying large language models (LLMs) to molecular design faces challenges such as fragmented execution, limited tool coordination, and insufficient traceability of intermediate decision-making processes. To address these limitations, we propose a Drug Discovery Agent (DDA), a traceable and auditable multi-agent biomedical informatics framework for automating SBDD. DDA uses a role-specific multi-agent architecture to transform natural-language drug-discovery goals into actionable scientific workflows. Through a unified tool-calling protocol, this framework seamlessly integrates bioinformatics, molecular modeling, and molecular docking modules, enabling autonomous workflow execution from target preparation and molecular generation to multi-objective evaluation, candidate prioritization, and trajectory tracking. We systematically evaluated DDA on the CrossDocked2020 benchmark. Under the closed-loop delivery protocol, the framework produced 2,000 final candidate records, with a joint screen-pass rate 20 percentage points higher than that of the strongest specialized baseline. These results indicate that DDA provides a scalable, executable, and traceable computational framework that reduces manual coordination in structure-based automated drug discovery and delivers prioritized candidate sets with minimal human intervention.<\/jats:p>","DOI":"10.3389\/fchem.2026.1914886","type":"journal-article","created":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T05:35:57Z","timestamp":1788240957000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DDA: a traceable multi-agent framework for automated structure-based drug design"],"prefix":"10.3389","volume":"14","author":[{"given":"Yutao","family":"Yu","sequence":"first","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Northeast Forestry University","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sicheng","family":"Tian","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Northeast Forestry University","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohua","family":"Wang","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Northeast Forestry University","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","article-title":"Quantifying the chemical beauty of drugs","volume":"4","author":"Bickerton","year":"2012","journal-title":"Nat. Chem."},{"key":"B2","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1038\/s42256-024-00832-8","article-title":"Augmenting large language models with chemistry tools","volume":"6","author":"Bran","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"B3","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1038\/nbt.3820","article-title":"Nextflow enables reproducible computational workflows","volume":"35","author":"Di Tommaso","year":"2017","journal-title":"Nat. Biotechnol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1038\/s42256-024-00843-5","article-title":"Machine learning-aided generative molecular design","volume":"6","author":"Du","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"B5","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1758-2946-1-8","article-title":"Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions","volume":"1","author":"Ertl","year":"2009","journal-title":"J. Cheminformatics"},{"key":"B6","doi-asserted-by":"publisher","first-page":"4200","DOI":"10.1021\/acs.jcim.0c00411","article-title":"Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design","volume":"60","author":"Francoeur","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"B7","doi-asserted-by":"publisher","first-page":"W422","DOI":"10.1093\/nar\/gkae236","article-title":"Admetlab 3.0: an updated comprehensive online ADMET prediction platform enhanced with broader coverage, improved performance, API functionality and decision support","volume":"52","author":"Fu","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41586-026-10652-y","article-title":"A multi-agent system for automating scientific discovery","volume":"655","author":"Ghareeb","year":"2026","journal-title":"Nature"},{"key":"B9","author":"Grattafiori","year":"2024","journal-title":"The Llama 3 Herd of ModelsarXiv preprint arXiv:2407.21783"},{"key":"B10","article-title":"3D equivariant diffusion for target-aware molecule generation and affinity prediction","author":"Guan","year":"2023","journal-title":"arXiv preprint Arxiv2303.03543. Present. A. T. ICLR"},{"key":"B11","article-title":"Decompdiff: diffusion models with decomposed priors for structure-based drug design","author":"Guan","year":"2024"},{"key":"B12","doi-asserted-by":"publisher","first-page":"nwaf028","DOI":"10.1093\/nsr\/nwaf028","article-title":"Foundation models in bioinformatics","volume":"12","author":"Guo","year":"2025","journal-title":"Natl. Sci. Rev."},{"key":"B13","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1016\/j.bmcl.2018.12.065","article-title":"Shape-based virtual screen for the discovery of novel cdk8 inhibitor chemotypes","volume":"29","author":"He","year":"2019","journal-title":"Bioorg. and Med. Chem. Lett."},{"key":"B14","doi-asserted-by":"publisher","first-page":"7928","DOI":"10.1038\/s41467-025-63245-0","article-title":"Target-aware 3D molecular generation based on guided equivariant diffusion","volume":"16","author":"Hu","year":"2025","journal-title":"Nat. Commun."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2026.3677444","article-title":"Medsegagent: a universal and scalable multi-agent system for instructive medical image segmentation","author":"Huang","year":"2026","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B16","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"B17","doi-asserted-by":"crossref","first-page":"79410","DOI":"10.52202\/079017-2522","article-title":"Mdagents: an adaptive collaboration of LLMs for medical decision-making","volume":"37","author":"Kim","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B18","doi-asserted-by":"crossref","first-page":"2520","DOI":"10.1093\/bioinformatics\/bts480","article-title":"Snakemake\u2014a scalable bioinformatics workflow engine","volume":"28","author":"K\u00f6ster","year":"2012","journal-title":"Bioinformatics"},{"key":"B19","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s10994-025-06955-2","article-title":"Automated scientific discovery: from equation discovery to autonomous discovery systems","volume":"115","author":"Kramer","year":"2026","journal-title":"Mach. Learn."},{"key":"B20","article-title":"RDKit: open-Source cheminformatics","author":"Landrum","year":"2006"},{"key":"B21","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1186\/s13321-025-01028-x","article-title":"Equivariant diffusion for structure-based de novo ligand generation with latent-conditioning","volume":"17","author":"Le","year":"2025","journal-title":"J. Cheminformatics"},{"key":"B22","author":"Li","year":"2024","journal-title":"AUTODIFF: Autoregressive Diffusion Modeling for Structure-based Drug DesignarXiv preprint arXiv:2404.02003"},{"key":"B23","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/s0169-409x(00)00129-0","article-title":"Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings","volume":"23","author":"Lipinski","year":"1997","journal-title":"Adv. Drug Deliv. Rev."},{"key":"B24","doi-asserted-by":"publisher","first-page":"4174","DOI":"10.1039\/d2sc06860e","article-title":"Discovery of a photoactivatable dimerized sting agonist based on the benzo [b] selenophene scaffold","volume":"14","author":"Liu","year":"2023","journal-title":"Chem. Sci."},{"key":"B25","first-page":"15692","author":"Liu","year":"2024","journal-title":"Drugagent: Automating AI-aided Drug Discovery Programming Through LLM multi-agent CollaborationarXiv preprint arXiv:2411"},{"key":"B26","doi-asserted-by":"crossref","first-page":"56","DOI":"10.25080\/Majora-92bf1922-00a","article-title":"Data structures for statistical computing in python","volume-title":"Proceedings of the 9th Python in Science Conference","author":"McKinney","year":"2010"},{"key":"B27","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1038\/s41551-025-01363-2","article-title":"Coordinated AI agents for advancing healthcare","volume":"9","author":"Moritz","year":"2025","journal-title":"Nat. Biomed. Eng."},{"key":"B28","first-page":"38","article-title":"The blackboard model of problem solving and the evolution of blackboard architectures","volume":"7","author":"Nii","year":"1986","journal-title":"AI Mag."},{"key":"B29","first-page":"17644","article-title":"Pocket2mol: efficient molecular sampling based on 3D protein pockets","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Peng","year":"2022"},{"key":"B30","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1021\/acs.jmedchem.3c01093","article-title":"Discovery of novel aminobutanoic acid-based asct2 inhibitors for the treatment of non-small-cell lung cancer","volume":"67","author":"Qin","year":"2024","journal-title":"J. Med. Chem."},{"key":"B31","first-page":"12141","author":"Qu","year":"2024","journal-title":"Molcraft: Structure-Based Drug Design in Continuous Parameter SpacearXiv preprint arXiv:2404"},{"key":"B32","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1021\/acs.jcim.4c01385","article-title":"Diffint: a diffusion model for structure-based drug design with explicit hydrogen bond interaction guidance","volume":"65","author":"Sako","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"B33","doi-asserted-by":"crossref","first-page":"68539","DOI":"10.52202\/075280-2997","article-title":"Toolformer: language models can teach themselves to use tools","volume":"36","author":"Schick","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B34","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1038\/s43588-024-00737-x","article-title":"Structure-based drug design with equivariant diffusion models","volume":"4","author":"Schneuing","year":"2024","journal-title":"Nat. Comput. Sci."},{"key":"B35","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1038\/s42256-024-00809-7","article-title":"Generative AI for designing and validating easily synthesizable and structurally novel antibiotics","volume":"6","author":"Swanson","year":"","journal-title":"Nat. Mach. Intell."},{"key":"B36","doi-asserted-by":"publisher","first-page":"btae416","DOI":"10.1093\/bioinformatics\/btae416","article-title":"Admet-ai: a machine learning ADMET platform for evaluation of large-scale chemical libraries","volume":"40","author":"Swanson","year":"","journal-title":"Bioinformatics"},{"key":"B37","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"Autodock vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J. Comput. Chem."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1016\/j.bmcl.2019.04.009","article-title":"Discovery of an egfr tyrosine kinase inhibitor from ilex latifolia in breast cancer therapy","volume":"29","author":"Wang","year":"2019","journal-title":"Bioorg. and Med. Chem. Lett."},{"key":"B39","doi-asserted-by":"publisher","first-page":"9360","DOI":"10.1038\/s41467-024-53632-4","article-title":"Tamgen: drug design with target-aware molecule generation through a chemical language model","volume":"15","author":"Wu K","year":"2024","journal-title":"Nat. Commun."},{"key":"B40","article-title":"Autogen: enabling next-gen LLM applications via multi-agent conversations","volume-title":"First Conference on Language Modeling","author":"Wu Q","year":"2024"},{"key":"B41","doi-asserted-by":"publisher","first-page":"121101","DOI":"10.1007\/s11432-024-4222-0","article-title":"The rise and potential of large language model based agents: a survey","volume":"68","author":"Xi","year":"2025","journal-title":"Sci. China Inf. Sci."},{"key":"B42","article-title":"Cellagent: an LLM-driven multi-agent framework for automated single-cell data analysis","author":"Xiao","year":"2024","journal-title":"arXiv Preprint arXiv:2407.09811"},{"key":"B43","doi-asserted-by":"publisher","first-page":"4588","DOI":"10.1021\/acs.jmedchem.0c02044","article-title":"Structure-enabled discovery of novel macrocyclic inhibitors targeting glutaminase 1 allosteric binding site","volume":"64","author":"Xu","year":"2021","journal-title":"J. Medicinal Chemistry"},{"key":"B44","article-title":"Drugmcts: a drug repurposing framework combining multi-agent, RAG and monte carlo tree search","author":"Yang","year":"2025","journal-title":"arXiv preprint arXiv:2507.07426"},{"key":"B45","article-title":"React: Synergizing Reasoning and Acting in Language Models","author":"Yao","year":"2022","journal-title":"arXiv preprint arXiv:2210.03629"},{"key":"B46","doi-asserted-by":"publisher","first-page":"114846","DOI":"10.1016\/j.ejmech.2022.114846","article-title":"The sar and action mechanisms of autophagy inhibitors that eliminate drug resistance","volume":"244","author":"Ye","year":"2022","journal-title":"Eur. J. Med. Chem."},{"key":"B47","doi-asserted-by":"publisher","first-page":"3336","DOI":"10.1021\/acs.jctc.2c01145","article-title":"Uni-dock: GPU-accelerated docking enables ultralarge virtual screening","volume":"19","author":"Yu","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"B48","doi-asserted-by":"publisher","first-page":"114860","DOI":"10.1016\/j.ejmech.2022.114860","article-title":"Discovery of novel hydroxyamidine based indoleamine 2, 3-dioxygenase 1 (ido1) and thioredoxin reductase 1 (trxr1) dual inhibitors","volume":"245","author":"Zhou","year":"2023","journal-title":"Eur. J. Med. Chem."},{"key":"B49","doi-asserted-by":"publisher","first-page":"140125","DOI":"10.1016\/j.molstruc.2024.140125","article-title":"Discovery of novel thiophene [2, 3-d] pyrimidine\u2013thiazole derivative as promising mnk inhibitor to treat breast cancer","volume":"1321","author":"Zhu","year":"2025","journal-title":"J. Mol. Struct."}],"container-title":["Frontiers in Chemistry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fchem.2026.1914886\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T05:36:00Z","timestamp":1788240960000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fchem.2026.1914886\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":49,"alternative-id":["10.3389\/fchem.2026.1914886"],"URL":"https:\/\/doi.org\/10.3389\/fchem.2026.1914886","relation":{},"ISSN":["2296-2646"],"issn-type":[{"value":"2296-2646","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,1]]},"article-number":"1914886"}}