{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T21:08:06Z","timestamp":1779484086113,"version":"3.53.1"},"reference-count":81,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276044"],"award-info":[{"award-number":["62276044"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.ipm.2026.104771","type":"journal-article","created":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T06:58:24Z","timestamp":1774767504000},"page":"104771","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["From graphs to tokens: Substructure-aware molecular representation for large language models"],"prefix":"10.1016","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7789-3759","authenticated-orcid":false,"given":"Runze","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9390-9478","authenticated-orcid":false,"given":"Zijie","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3321-5373","authenticated-orcid":false,"given":"Xingyue","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9040-4468","authenticated-orcid":false,"given":"Mingqi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3765-483X","authenticated-orcid":false,"given":"Che","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4108-0230","authenticated-orcid":false,"given":"Yanming","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.ipm.2026.104771_bib0001","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1038\/s42256-021-00418-8","article-title":"Geometric deep learning on molecular representations","volume":"3","author":"Atz","year":"2021","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104771_bib0002","unstructured":"Barrault, L., Duquenne, P.-A., Elbayad, M., Kozhevnikov, A., Alastruey, B., Andrews, P., Coria, M., Couairon, G., Costa-juss\u00e0, M. R., Dale, D. et al. (2024). Large concept models: Language modeling in a sentence representation space. 10.48550\/arXiv.2412.08821."},{"key":"10.1016\/j.ipm.2026.104771_bib0003","series-title":"Proceedings of the 31st international conference on computational linguistics","first-page":"354","article-title":"Instructmol: Multi-modal integration for building a versatile and reliable molecular assistant in drug discovery","author":"Cao","year":"2025"},{"issue":"14","key":"10.1016\/j.ipm.2026.104771_bib0004","doi-asserted-by":"crossref","DOI":"10.1063\/5.0193557","article-title":"Molecular hypergraph neural networks","volume":"160","author":"Chen","year":"2024","journal-title":"The Journal of Chemical Physics"},{"key":"10.1016\/j.ipm.2026.104771_bib0005","series-title":"International conference on machine learning","first-page":"7809","article-title":"Llaga: Large language and graph assistant","author":"Chen","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0006","series-title":"Forty-second international conference on machine learning","article-title":"Hierarchical graph tokenization for molecule-language alignment","author":"Chen","year":"2025"},{"key":"10.1016\/j.ipm.2026.104771_bib0007","unstructured":"Chiang, W.-L., Li, Z., Lin, Z., Sheng, Y., Wu, Z., Zhang, H., Zheng, L., Zhuang, S., Zhuang, Y., Gonzalez, J. E. et al. (2023). Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality. See (accessed 14 April 2023), 2, 6. https:\/\/vicuna.lmsys.org, https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/."},{"issue":"1","key":"10.1016\/j.ipm.2026.104771_bib0008","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/s43586-024-00294-7","article-title":"Graph neural networks","volume":"4","author":"Corso","year":"2024","journal-title":"Nature Reviews Methods Primers"},{"issue":"10","key":"10.1016\/j.ipm.2026.104771_bib0009","doi-asserted-by":"crossref","first-page":"1503","DOI":"10.1002\/cmdc.200800178","article-title":"On the art of compiling and using\u2019drug-like\u2019chemical fragment spaces","volume":"3","author":"Degen","year":"2008","journal-title":"ChemMedChem"},{"key":"10.1016\/j.ipm.2026.104771_bib0010","doi-asserted-by":"crossref","first-page":"0740","DOI":"10.34133\/research.0740","article-title":"Molecular merged hypergraph neural network for explainable solvation gibbs free energy prediction","volume":"8","author":"Du","year":"2025","journal-title":"Research"},{"key":"10.1016\/j.ipm.2026.104771_bib0011","first-page":"30039","article-title":"Alpacafarm: A simulation framework for methods that learn from human feedback","volume":"36","author":"Dubois","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104771_bib0012","series-title":"The tenth international conference on learning representations","article-title":"Graph neural networks with learnable structural and positional representations","author":"Dwivedi","year":"2022"},{"key":"10.1016\/j.ipm.2026.104771_bib0013","series-title":"Proceedings of the 2022 conference on empirical methods in natural language processing","first-page":"375","article-title":"Translation between molecules and natural language","author":"Edwards","year":"2022"},{"key":"10.1016\/j.ipm.2026.104771_bib0014","series-title":"The twelfth international conference on learning representations","article-title":"Mol-instructions: A large-scale biomolecular instruction dataset for large language models","author":"Fang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0015","series-title":"The twelfth international conference on learning representations","article-title":"Talk like a graph: Encoding graphs for large language models","author":"Fatemi","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0016","series-title":"The thirteenth international conference on learning representations","article-title":"The foundations of tokenization: Statistical and computational concerns","author":"Gastaldi","year":"2025"},{"key":"10.1016\/j.ipm.2026.104771_bib0017","first-page":"59662","article-title":"What can large language models do in chemistry? A comprehensive benchmark on eight tasks","volume":"36","author":"Guo","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"5","key":"10.1016\/j.ipm.2026.104771_bib0018","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbad305","article-title":"HimGNN: A novel hierarchical molecular graph representation learning framework for property prediction","volume":"24","author":"Han","year":"2023","journal-title":"Briefings in Bioinformatics"},{"issue":"D1","key":"10.1016\/j.ipm.2026.104771_bib0019","doi-asserted-by":"crossref","first-page":"D1214","DOI":"10.1093\/nar\/gkv1031","article-title":"ChEBI in 2016: Improved services and an expanding collection of metabolites","volume":"44","author":"Hastings","year":"2016","journal-title":"Nucleic Acids Research"},{"issue":"1","key":"10.1016\/j.ipm.2026.104771_bib0020","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/1758-2946-5-7","article-title":"Inchi-the worldwide chemical structure identifier standard","volume":"5","author":"Heller","year":"2013","journal-title":"Journal of Cheminformatics"},{"issue":"2, Part A","key":"10.1016\/j.ipm.2026.104771_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104412","article-title":"HT-geogt: A hierarchical twin-stream geometric graph transformer with graph representation learning architecture","volume":"63","author":"Hong","year":"2026","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104771_bib0022","unstructured":"Hu, C., Li, H., Yuan, Y., Li, J., & Tsang, I. (2024). Exploring hierarchical molecular graph representation in multimodal LLMs. 10.48550\/arxiv.2411.04708."},{"key":"10.1016\/j.ipm.2026.104771_bib0023","unstructured":"Jiang, A. Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D. S., de las Casas, D., Bressand, F., Lengyel, G., Lample, G., Saulnier, L., Lavaud, L. R., Lachaux, M.-A., Stock, P., Scao, T. L., Lavril, T., Wang, T., Lacroix, T., & Sayed, W. E. (2023a). Mistral 7b. https:\/\/arxiv.org\/abs\/2310.06825."},{"issue":"1","key":"10.1016\/j.ipm.2026.104771_bib0024","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s42004-023-00857-x","article-title":"Pharmacophoric-constrained heterogeneous graph transformer model for molecular property prediction","volume":"6","author":"Jiang","year":"2023","journal-title":"Communications Chemistry"},{"issue":"4","key":"10.1016\/j.ipm.2026.104771_bib0025","article-title":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","volume":"1","author":"Krenn","year":"2020","journal-title":"Machine Learning: Science and Technology"},{"key":"10.1016\/j.ipm.2026.104771_bib0026","series-title":"Findings of the association for computational linguistics: Acl 2024","first-page":"5848","article-title":"Biomistral: A collection of open-source pretrained large language models for medical domains","author":"Labrak","year":"2024"},{"issue":"1-79","key":"10.1016\/j.ipm.2026.104771_bib0027","first-page":"4","article-title":"Rdkit documentation","volume":"1","author":"Landrum","year":"2013","journal-title":"Release"},{"key":"10.1016\/j.ipm.2026.104771_bib0028","unstructured":"Le, K., Guo, Z., Dong, K., Huang, X., Nan, B., Iyer, R., Zhang, X., Wiest, O., Wang, W., & Chawla, N. V. (2024). Molx: Enhancing large language models for molecular learning with a multi-modal extension. 10.48550\/arXiv.2406.06777."},{"key":"10.1016\/j.ipm.2026.104771_bib0029","unstructured":"Lee, C., Ko, H., Song, Y., Jeong, Y., Hormazabal, R., Han, S., Bae, K., Lim, S., & Kim, S. (2025). Mol-LLM: Multimodal generalist molecular LLM with improved graph utilization. 10.48550\/arXiv.2502.02810."},{"issue":"11","key":"10.1016\/j.ipm.2026.104771_bib0030","doi-asserted-by":"crossref","first-page":"6071","DOI":"10.1109\/TKDE.2024.3393356","article-title":"Empowering molecule discovery for molecule-caption translation with large language models: A chatgpt perspective","volume":"36","author":"Li","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.ipm.2026.104771_bib0031","first-page":"1","article-title":"Kolmogorov\u2013Arnold graph neural networks for molecular property prediction","author":"Li","year":"2025","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104771_bib0032","series-title":"The twelfth international conference on learning representations","article-title":"Towards 3D molecule-text interpretation in language models","author":"Li","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0033","series-title":"Proceedings of the 31st ACM SIGKDD conference on knowledge discovery and data mining v. 2","first-page":"1589","article-title":"Advancing molecular graph-text pre-training via fine-grained alignment","author":"Li","year":"2025"},{"issue":"12","key":"10.1016\/j.ipm.2026.104771_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.drudis.2022.103373","article-title":"Deep learning methods for molecular representation and property prediction","volume":"27","author":"Li","year":"2022","journal-title":"Drug Discovery Today"},{"key":"10.1016\/j.ipm.2026.104771_bib0035","article-title":"Multi-modal large language model enables all-purpose prediction of drug mechanisms and properties","author":"Liang","year":"2024","journal-title":"bioRxiv"},{"key":"10.1016\/j.ipm.2026.104771_bib0036","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104771_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.108073","article-title":"Git-mol: A multi-modal large language model for molecular science with graph, image, and text","volume":"171","author":"Liu","year":"2024","journal-title":"Computers in Biology and Medicine"},{"issue":"2","key":"10.1016\/j.ipm.2026.104771_bib0038","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1038\/s42256-024-00977-6","article-title":"A quantitative analysis of knowledge-learning preferences in large language models in molecular science","volume":"7","author":"Liu","year":"2025","journal-title":"Nature Machine Intelligence"},{"issue":"12","key":"10.1016\/j.ipm.2026.104771_bib0039","doi-asserted-by":"crossref","first-page":"1447","DOI":"10.1038\/s42256-023-00759-6","article-title":"Multi-modal molecule structure\u2013text model for text-based retrieval and editing","volume":"5","author":"Liu","year":"2023","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104771_bib0040","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing","first-page":"15623","article-title":"MolCA: Molecular graph-language modeling with cross-modal projector and uni-modal adapter","author":"Liu","year":"2023"},{"issue":"6","key":"10.1016\/j.ipm.2026.104771_bib0041","doi-asserted-by":"crossref","first-page":"1376","DOI":"10.1021\/acs.jcim.1c01467","article-title":"Unified deep learning model for multitask reaction predictions with explanation","volume":"62","author":"Lu","year":"2022","journal-title":"Journal of Chemical Information and Modeling"},{"key":"10.1016\/j.ipm.2026.104771_bib0042","unstructured":"Luo, Y., Zhang, J., Fan, S., Yang, K., Wu, Y., Qiao, M., & Nie, Z. (2023). BiomedGPT: Open multimodal generative pre-trained transformer for biomedicine. 10.48550\/arxiv.2308.09442."},{"key":"10.1016\/j.ipm.2026.104771_bib0043","series-title":"Proceedings of the 2024\u202fSIAM international conference on data mining (SDM)","first-page":"517","article-title":"Pretraining molecules with explicit substructure information","author":"Ma","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0044","first-page":"131972","article-title":"Llamo: Large language model-based molecular graph assistant","volume":"37","author":"Park","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104771_bib0045","series-title":"Findings of the association for computational linguistics ACL 2024","first-page":"1216","article-title":"Biot5+: Towards generalized biological understanding with IUPAC integration and multi-task tuning","author":"Pei","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0046","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume":"33","author":"Rong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.1016\/j.ipm.2026.104771_bib0047","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1186\/s12859-024-05847-x","article-title":"Can large language models understand molecules?","volume":"25","author":"Sadeghi","year":"2024","journal-title":"BMC Bioinformatics"},{"key":"10.1016\/j.ipm.2026.104771_bib0048","series-title":"International conference on machine learning","first-page":"30458","article-title":"Enhancing activity prediction models in drug discovery with the ability to understand human language","author":"Seidl","year":"2023"},{"issue":"1","key":"10.1016\/j.ipm.2026.104771_bib0049","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1038\/s41597-019-0151-1","article-title":"AqsolDB, a curated reference set of aqueous solubility and 2D descriptors for a diverse set of compounds","volume":"6","author":"Sorkun","year":"2019","journal-title":"Scientific Data"},{"key":"10.1016\/j.ipm.2026.104771_bib0050","first-page":"19870","article-title":"On the scalability of GNNs for molecular graphs","volume":"37","author":"Sypetkowski","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104771_bib0051","series-title":"Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval","first-page":"491","article-title":"GraphGPT: Graph instruction tuning for large language models","author":"Tang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0052","first-page":"5950","article-title":"LLMs as zero-shot graph learners: Alignment of GNN representations with LLM token embeddings","volume":"37","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104771_bib0053","first-page":"30840","article-title":"Can language models solve graph problems in natural language?","volume":"36","author":"Wang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104771_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126484","article-title":"Motif-driven molecular graph representation learning","volume":"269","author":"Wang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.ipm.2026.104771_bib0055","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"21234","article-title":"Bridging molecular graphs and large language models","volume":"vol. 39","author":"Wang","year":"2025"},{"issue":"5","key":"10.1016\/j.ipm.2026.104771_bib0056","first-page":"1","article-title":"Graph machine learning in the era of large language models (LLMs)","volume":"16","author":"Wang","year":"2025","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"issue":"5","key":"10.1016\/j.ipm.2026.104771_bib0057","doi-asserted-by":"crossref","first-page":"3799","DOI":"10.1016\/j.eswa.2009.11.040","article-title":"A novel measure for evaluating classifiers","volume":"37","author":"Wei","year":"2010","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.ipm.2026.104771_bib0058","first-page":"1549","article-title":"A chemical language and information system. 1. introduction to methodology and encoding rules","author":"Weininger","year":"1988","journal-title":"Journal of Chemical Information and Modeling"},{"issue":"9","key":"10.1016\/j.ipm.2026.104771_bib0059","doi-asserted-by":"crossref","first-page":"3790","DOI":"10.1021\/acs.jcim.4c00292","article-title":"Orderly: Data sets and benchmarks for chemical reaction data","volume":"64","author":"Wigh","year":"2024","journal-title":"Journal of Chemical Information and Modeling"},{"key":"10.1016\/j.ipm.2026.104771_bib0060","series-title":"International conference on machine learning","first-page":"53113","article-title":"Expressivity and generalization: Fragment-biases for molecular GNNs","author":"Wollschl\u00e4ger","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0061","series-title":"International conference on machine learning","first-page":"37511","article-title":"Rethinking explaining graph neural networks via non-parametric subgraph matching","author":"Wu","year":"2023"},{"issue":"2","key":"10.1016\/j.ipm.2026.104771_bib0062","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"Moleculenet: A benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chemical Science"},{"key":"10.1016\/j.ipm.2026.104771_bib0063","series-title":"The seventh international conference on learning representations","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2026"},{"issue":"4","key":"10.1016\/j.ipm.2026.104771_bib0064","article-title":"Hierarchical chat-based strategies with MLLMs for spatio-temporal action detection","volume":"62","author":"Xuyang","year":"2025","journal-title":"Information Processing & Management"},{"issue":"4","key":"10.1016\/j.ipm.2026.104771_bib0065","article-title":"GNN-transformer contrastive learning explores homophily","volume":"62","author":"Yangding","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104771_bib0066","series-title":"First conference on language modeling","article-title":"LlaSMol: Advancing large language models for chemistry with a large-scale, comprehensive, high-quality instruction tuning dataset","author":"Yu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0067","unstructured":"Yuan, C., Zhao, K., Kuruoglu, E. E., Wang, L., Xu, T., Huang, W., Zhao, D., Cheng, H., & Rong, Y. (2025). A survey of graph transformers: Architectures, theories and applications. https:\/\/arxiv.org\/abs\/2502.16533."},{"key":"10.1016\/j.ipm.2026.104771_bib0068","series-title":"The eleventh international conference on learning representations","article-title":"GLM-130B: An open bilingual pre-trained model","author":"Zeng","year":"2023"},{"key":"10.1016\/j.ipm.2026.104771_bib0069","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11129","article-title":"Substructure aware graph neural networks","volume":"vol. 37","author":"Zeng","year":"2023"},{"key":"10.1016\/j.ipm.2026.104771_bib0070","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2024.3454328","article-title":"The expressive power of graph neural networks: A survey","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"8","key":"10.1016\/j.ipm.2026.104771_bib0071","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: A survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"10.1016\/j.ipm.2026.104771_bib0072","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3715318","article-title":"Scientific large language models: A survey on biological & chemical domains","volume":"57","author":"Zhang","year":"2025","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.ipm.2026.104771_bib0073","series-title":"Findings of the association for computational linguistics: EMNLP 2024","first-page":"2289","article-title":"Can LLM graph reasoning generalize beyond pattern memorization?","author":"Zhang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104771_bib0074","first-page":"15870","article-title":"Motif-based graph self-supervised learning for molecular property prediction","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104771_bib0075","series-title":"The eleventh international conference on learning representations","article-title":"Molecule generation for target protein binding with structural motifs","author":"Zhang","year":"2023"},{"key":"10.1016\/j.ipm.2026.104771_bib0076","first-page":"5850","article-title":"Gimlet: A unified graph-text model for instruction-based molecule zero-shot learning","volume":"36","author":"Zhao","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2, Part A","key":"10.1016\/j.ipm.2026.104771_bib0077","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104395","article-title":"Over-smoothing problem of heterogeneous graph neural networks: A heterogeneous graph neural network with enhanced node differentiability","volume":"63","author":"Zhao","year":"2026","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104771_bib0078","first-page":"1","article-title":"Large language models for scientific discovery in molecular property prediction","author":"Zheng","year":"2025","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104771_bib0079","unstructured":"Zhong, Z., Zhou, K., & Mottin, D. (2024). Benchmarking large language models for molecule prediction tasks. 10.48550\/arxiv.2403.05075."},{"issue":"22","key":"10.1016\/j.ipm.2026.104771_bib0080","doi-asserted-by":"crossref","first-page":"5363","DOI":"10.1021\/acs.jpcb.4c01875","article-title":"Utility of the Morgan fingerprint in structure-based virtual ligand screening","volume":"128","author":"Zhou","year":"2024","journal-title":"The Journal of Physical Chemistry B"},{"issue":"5","key":"10.1016\/j.ipm.2026.104771_bib0081","article-title":"Multi-SEA: Multi-stage semantic enhancement and aggregation for image-text retrieval","volume":"62","author":"Zijing","year":"2025","journal-title":"Information Processing & Management"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326001627?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326001627?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T20:55:02Z","timestamp":1779483302000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326001627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":81,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["S0306457326001627"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104771","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"From graphs to tokens: Substructure-aware molecular representation for large language models","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104771","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104771"}}