{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:07:16Z","timestamp":1782756436461,"version":"3.54.5"},"reference-count":65,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515011213"],"award-info":[{"award-number":["2024A1515011213"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["advanced.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Advanced Intelligent Systems"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>In recent years, the development of large language models (LLMs) has revolutionized various fields of natural science. However, their application in dealing with various molecular data remains constrained due to the reliance on single\u2010modality inputs and outputs. ChatMolData, a novel LLM\u2010based multimodal agent designed to handle diverse molecular data forms, including molecular databases, images, structure\u2010specific files, and unstructured and structured documents, is introduced. ChatMolData integrates the capabilities of LLMs (e.g., GPT\u20104 and GPT\u20103.5) with the robust toolset that supports data retrieval, structuring, prediction, visualization, and search tasks. The agent employs a systematic cycle of reasoning and action to efficiently process complex tasks in molecular science. The evaluation demonstrates that ChatMolData achieves over 90% accuracy for 128 diverse tasks, effectively bridging the gap between experimenters and computational tools. Moreover, it is anticipated that the multimodal\u2010agent strategy provides a pathway to expand data size and improve data accessibility, ultimately promoting molecular research and innovation.<\/jats:p>","DOI":"10.1002\/aisy.202401089","type":"journal-article","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T16:14:46Z","timestamp":1748535286000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ChatMolData: A Multimodal Agent for Automatic Molecular Data Processing"],"prefix":"10.1002","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8360-005X","authenticated-orcid":false,"given":"Yi","family":"Yu","sequence":"first","affiliation":[{"name":"China Resources Pharmaceutical Research Institute (Shenzhen) Co., Ltd.  Shenzhen 518100 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huien","family":"Wang","sequence":"additional","affiliation":[{"name":"China Resources Pharmaceutical Research Institute (Shenzhen) Co., Ltd.  Shenzhen 518100 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Libin","family":"Zong","sequence":"additional","affiliation":[{"name":"China Resources Pharmaceutical Research Institute (Shenzhen) Co., Ltd.  Shenzhen 518100 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Chen","sequence":"additional","affiliation":[{"name":"China Resources Pharmaceutical Group Ltd.  Beijing 100029 China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9207-5778","authenticated-orcid":false,"given":"Yaqin","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Health and Social Sciences The Hong Kong Polytechnic University  Hongkong Hung Hom China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Yu","sequence":"additional","affiliation":[{"name":"China Resources Pharmaceutical Research Institute (Shenzhen) Co., Ltd.  Shenzhen 518100 China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,5,29]]},"reference":[{"key":"e_1_2_9_2_1","volume-title":"Sparks of Artificial General Intelligence: Early Experiments with GPT\u20104","author":"Bubeck S.","year":"2023"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"e_1_2_9_5_1","volume-title":"Igniting Language Intelligence: The Hitchhiker's Guide from Chain\u2010of\u2010Thought Reasoning to Language Agents","author":"Zhang Z.","year":"2023"},{"key":"e_1_2_9_6_1","first-page":"186345","volume-title":"Front. Comput. Sci","author":"Wang L.","year":"2024"},{"key":"e_1_2_9_7_1","volume-title":"Agentmd: Empowering Language Agents for Risk Prediction with Large\u2010Scale Clinical Tool Learning","author":"Jin Q.","year":"2024"},{"key":"e_1_2_9_8_1","volume-title":"Extracting Human Interpretable Structure\u2010Property Relationships in Chemistry Using XAI and Large Language Models","author":"Wellawatte G. P.","year":"2023"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48998-4"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00832-8"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.3c01087"},{"key":"e_1_2_9_12_1","volume-title":"LLaMP: Large Language Model Made Powerful for High\u2010Fidelity Materials Knowledge Retrieval and Distillation","author":"Yuan C.","year":"2024"},{"key":"e_1_2_9_13_1","first-page":"2024","author":"Qu Y.","year":"2024","journal-title":"bioRxiv"},{"key":"e_1_2_9_14_1","volume-title":"Toward a Team Of AI\u2010Made Scientists for Scientific Discovery from Gene Expression Data","author":"Liu H.","year":"2024"},{"key":"e_1_2_9_15_1","doi-asserted-by":"crossref","unstructured":"Y.Ma Z.Gou J.Hao R.Xu S.Wang L.Pan Y.Yang Y.Cao A.Sun H.Awadalla W.Chen in ACL2024 pp.15701\u201015736.","DOI":"10.18653\/v1\/2024.emnlp-main.880"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06792-0"},{"key":"e_1_2_9_17_1","unstructured":"DeepChem https:\/\/github.com\/deepchem\/deepchem (accessed: February 2024)."},{"key":"e_1_2_9_18_1","unstructured":"RDKit www.rdkit.org (accessed: February 2024)."},{"key":"e_1_2_9_19_1","unstructured":"Open Babel https:\/\/github.com\/openbabel\/openbabel (accessed: February 2024)."},{"key":"e_1_2_9_20_1","unstructured":"rxn4Chemistry https:\/\/github.com\/rxn4chemistry\/rxn4chemistry (accessed: February 2024)."},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.analchem.3c05194"},{"key":"e_1_2_9_22_1","volume-title":"LLaSA: Large Multimodal Agent for Human Activity Analysis Through Wearable Sensors","author":"Asif Imran S.","year":"2024"},{"key":"e_1_2_9_23_1","volume-title":"Large Multimodal Agents: A Survey","author":"Xie J.","year":"2024"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41578-025-00772-8"},{"key":"e_1_2_9_25_1","volume-title":"GPT\u2010Driver: Learning to Drive with GPT","author":"Mao J.","year":"2023"},{"key":"e_1_2_9_26_1","volume-title":"ChatVideo: A Tracklet\u2010Centric Multimodal and Versatile Video Understanding System","author":"Wang J.","year":"2023"},{"key":"e_1_2_9_27_1","volume-title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models","author":"Yang Z.","year":"2024"},{"key":"e_1_2_9_28_1","volume-title":"AssistGPT: A General Multi\u2010Modal Assistant that can Plan, Execute, Inspect, and Learn","author":"Gao D.","year":"2023"},{"key":"e_1_2_9_29_1","volume-title":"MuLan: Multimodal\u2010LLM Agent for Progressive and Interactive Multi\u2010Object Diffusion","author":"Li S.","year":"2024"},{"key":"e_1_2_9_30_1","volume-title":"MM\u2010REACT: Prompting ChatGPT For Multimodal Reasoning and Action","author":"Yang Z.","year":"2023"},{"key":"e_1_2_9_31_1","volume-title":"LLaVA\u2010Interactive: An All\u2010In\u2010One Demo for Image Chat, Segmentation, Generation and Editing","author":"Chen W.\u2010G.","year":"2023"},{"key":"e_1_2_9_32_1","volume-title":"Towards Rationality in Language and Multimodal Agents: A Survey","author":"Jiang B.","year":"2024"},{"key":"e_1_2_9_33_1","volume-title":"Building Cooperative Embodied Agents Modularly with Large Language Models","author":"Zhang H.","year":"2023"},{"key":"e_1_2_9_34_1","unstructured":"A.Zhang Y.Chen H.Li Y.Deng X.Wang T.\u2010S.Chua presented at Pro. of the 47th Int. ACM SIGIR Conf. on Research and Development in Information Retrieval Washington DC USA2024."},{"key":"e_1_2_9_35_1","volume-title":"The Rise and Potential of Large Language Model Based Agents: A Survey","author":"Xi Z.","year":"2023"},{"key":"e_1_2_9_36_1","volume-title":"GPT\u20104 Technical Report","author":"OpenAI","year":"2023"},{"key":"e_1_2_9_37_1","unstructured":"ChatGPT https:\/\/openai.com\/index\/chatgpt\/ (accessed: April 2024)."},{"key":"e_1_2_9_38_1","volume-title":"DrugAgent: Automating AI\u2010Aided Drug Discovery Programming Through LLM Multi\u2010Agent Collaboration","author":"Liu S.","year":"2024"},{"key":"e_1_2_9_39_1","first-page":"1","volume":"55","author":"Liu P.","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"e_1_2_9_40_1","volume-title":"ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design","author":"White J.","year":"2023"},{"key":"e_1_2_9_41_1","unstructured":"J.White Q.Fu S.Hays M.Sandborn C.Olea H.Gilbert A.Elnashar J.Spencer\u2010Smith D. C.Schmidt presented at Proc. of the 30th Conf. on Pattern Languages of Programs Monticello IL USA2023."},{"key":"e_1_2_9_42_1","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models","author":"Yao S.","year":"2022"},{"key":"e_1_2_9_43_1","volume-title":"MRKL Systems: A Modular, Neuro\u2010Symbolic Architecture That Combines Large Language Models, External Knowledge Sources and Discrete Reasoning","author":"Karpas E. D.","year":"2022"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad1004"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr777"},{"key":"e_1_2_9_46_1","unstructured":"create_sql_query_chain https:\/\/api.python.langchain.com\/en\/latest\/chains\/langchain.chains.sql_database.query.create_sql_query_chain.html (accessed: February 2024)."},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci00057a005"},{"key":"e_1_2_9_48_1","unstructured":"Schema Questions and SQL Examples https:\/\/chembl.gitbook.io\/chembl\u2010interface\u2010documentation\/frequently\u2010asked\u2010questions\/schema\u2010questions\u2010and\u2010sql\u2010examples (accessed: February 2024)."},{"key":"e_1_2_9_49_1","volume-title":"Hessian QM9: A Quantum Chemistry Database of Molecular Hessians In Implicit Solvents","author":"Williams N. J.","year":"2024"},{"key":"e_1_2_9_50_1","volume-title":"Deformable DETR: Deformable Transformers for End\u2010To\u2010End Object Detection","author":"Zhu X.","year":"2020"},{"key":"e_1_2_9_51_1","doi-asserted-by":"crossref","unstructured":"N.Carion F.Massa G.Synnaeve N.Usunier A.Kirillov S.Zagoruyko inIn European Conf. on Computer Vision Springer Inter. Publishing Cham2020 pp.213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_2_9_52_1","volume-title":"PubTables\u20101M: Towards A Universal Dataset and Metrics for Training and Evaluating Table Extraction Models","author":"Smock B.","year":"2021"},{"key":"e_1_2_9_53_1","volume-title":"GriTS: Grid Table Similarity Metric for Table Structure Recognition","author":"Smock B.","year":"2022"},{"key":"e_1_2_9_54_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00469-w"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50779-y"},{"key":"e_1_2_9_56_1","unstructured":"RDKit QED module https:\/\/www.rdkit.org\/docs\/source\/rdkit.Chem.QED.html#rdkit.Chem (accessed: February 2024)."},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2024.01.004"},{"key":"e_1_2_9_58_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43246-022-00315-6"},{"key":"e_1_2_9_59_1","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"e_1_2_9_60_1","doi-asserted-by":"publisher","DOI":"10.1039\/C8SC04175J"},{"key":"e_1_2_9_61_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.1c00421"},{"key":"e_1_2_9_62_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b00959"},{"key":"e_1_2_9_63_1","unstructured":"Intro to the molecule enumerator https:\/\/greglandrum.github.io\/rdkit\u2010blog\/posts\/2021\u201005\u201013\u2010intro\u2010to\u2010the\u2010molecule\u2010enumerator.html (accessed: February 2024)."},{"key":"e_1_2_9_64_1","unstructured":"Generalized substructure search https:\/\/greglandrum.github.io\/rdkit\u2010blog\/posts\/2021\u201008\u201003\u2010generalized\u2010substructure\u2010search.html (accessed: April 2024)."},{"key":"e_1_2_9_65_1","unstructured":"LangChain https:\/\/github.com\/langchain\u2010ai\/langchain (accessed: February 2024)."},{"key":"e_1_2_9_66_1","first-page":"24824","volume":"35","author":"Wei J.","year":"2022","journal-title":"Adv. Neural Info. Process. Syst."}],"container-title":["Advanced Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202401089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T17:45:36Z","timestamp":1763487936000},"score":1,"resource":{"primary":{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/10.1002\/aisy.202401089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,29]]},"references-count":65,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1002\/aisy.202401089"],"URL":"https:\/\/doi.org\/10.1002\/aisy.202401089","archive":["Portico"],"relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2024-3gdz5","asserted-by":"object"}]},"ISSN":["2640-4567","2640-4567"],"issn-type":[{"value":"2640-4567","type":"print"},{"value":"2640-4567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,29]]},"assertion":[{"value":"2024-12-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2401089"}}