{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:03:23Z","timestamp":1765231403146,"version":"3.44.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T00:00:00Z","timestamp":1750809600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T00:00:00Z","timestamp":1750809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100020771","name":"Young Scientists Fund of the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62302328"],"award-info":[{"award-number":["62302328"]}],"id":[{"id":"10.13039\/501100020771","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Jiangsu Province Foundation for Young Scientists","award":["BK20230482"],"award-info":[{"award-number":["BK20230482"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The prominence of 3D molecular property prediction arises from its ability to provide insights into the drug discovery and design, material science and chemical synthesis. Transformer-based models have been widely adopted to autonomously learn long-range atom-to-atom interactions on a global scale, resulting in significant success. However, these models may struggle to capture intricate substructure details (<jats:italic>e<\/jats:italic>.<jats:italic>g<\/jats:italic>.,\u00a0 covalent bond and functional group). In this work, topological simplices defined on nodes, links, triangles are extracted from the atoms\u2019 3D positional information to provide comprehensive representations of the local substructure information, such as atoms, covalent bonds and functional groups. We then propose a topological fusion network, which enhances each atom\u2019s features not only through global atom-to-atom interactions but also by incorporating the fine-grained topological substructure information. In comparison to existing popular methods, our proposed method outperforms the state-of-the-art (SOTA) method by 1.2%, 3.0%, 2.4%, 2.7% on BBBP, BACE, ClinTox, MUV datasets for classification task and 0.048, 0.022, 3.8 on FreeSolv, Lipo and QM7 datasets for regression task, respectively. The code will be released soon.<\/jats:p>","DOI":"10.1007\/s10489-025-06721-w","type":"journal-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T09:41:42Z","timestamp":1750844502000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Topological Fusion Model for Molecular Property Prediction"],"prefix":"10.1007","volume":"55","author":[{"given":"Xia","family":"Rong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Haotian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6155-4259","authenticated-orcid":false,"given":"Wu","family":"Junwei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Shufei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sun","family":"Mingjie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu","family":"Jiejie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhang","family":"Quan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,25]]},"reference":[{"issue":"10","key":"6721_CR1","doi-asserted-by":"publisher","first-page":"7043","DOI":"10.1007\/s10489-021-02195-8","volume":"51","author":"G Jiang","year":"2021","unstructured":"Jiang G, Jiang X, Fang Z et al (2021) An efficient attention module for 3d convolutional neural networks in action recognition. Appl Intell 51(10):7043\u20137057","journal-title":"Appl Intell"},{"issue":"6","key":"6721_CR2","doi-asserted-by":"publisher","first-page":"6844","DOI":"10.1007\/s10489-022-03930-5","volume":"53","author":"A Jhaldiyal","year":"2023","unstructured":"Jhaldiyal A, Chaudhary N (2023) Semantic segmentation of 3d lidar data using deep learning: a review of projection-based methods. Appl Intell 53(6):6844\u20136855","journal-title":"Appl Intell"},{"key":"6721_CR3","doi-asserted-by":"crossref","unstructured":"Wu J, Zhou W, Luo T et al (2021) Multiscale multilevel context and multimodal fusion for rgb-d salient object detection. Signal Process 178:107766","DOI":"10.1016\/j.sigpro.2020.107766"},{"key":"6721_CR4","unstructured":"Sun M, Xiao J, Lim EG, et\u00a0al (2023) Unified multi-modality video object segmentation using reinforcement learning. IEEE Trans Circ Syst Video Technol pp 1\u20131"},{"issue":"1","key":"6721_CR5","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1007\/s10489-020-01801-5","volume":"51","author":"K Bayoudh","year":"2021","unstructured":"Bayoudh K, Hamdaoui F, Mtibaa A (2021) Transfer learning based hybrid 2d\u20133d cnn for traffic sign recognition and semantic road detection applied in advanced driver assistance systems. Appl Intell 51(1):124\u2013142","journal-title":"Appl Intell"},{"key":"6721_CR6","doi-asserted-by":"crossref","unstructured":"Wu J, Sun M, Xu H et al (2025) Class agnostic and specific consistency learning for weakly-supervised point cloud semantic segmentation. Pattern Recogn 158:111067","DOI":"10.1016\/j.patcog.2024.111067"},{"key":"6721_CR7","doi-asserted-by":"crossref","unstructured":"Wu J, Sun M, Jiang C et al (2024) Context-based local-global fusion network for 3d point cloud classification and segmentation. Expert Syst Appl 251:124023","DOI":"10.1016\/j.eswa.2024.124023"},{"key":"6721_CR8","unstructured":"Wu X, Lao Y, Jiang L, et\u00a0al (2022) Point transformer v2: Grouped vector attention and partition-based pooling. In: Advances in Neural Information Processing Systems"},{"key":"6721_CR9","doi-asserted-by":"crossref","unstructured":"Zhou G, Gao Z, Ding Q, et\u00a0al (2023) Uni-mol: a universal 3d molecular representation learning framework","DOI":"10.26434\/chemrxiv-2022-jjm0j-v4"},{"issue":"4","key":"6721_CR10","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10462-024-10710-9","volume":"57","author":"A Zia","year":"2024","unstructured":"Zia A, Khamis A, Nichols J et al (2024) Topological deep learning: a review of an emerging paradigm. Artif Intell Rev 57(4):77","journal-title":"Artif Intell Rev"},{"key":"6721_CR11","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1007\/s00158-021-02881-8","volume":"63","author":"J Wu","year":"2021","unstructured":"Wu J, Sigmund O, Groen JP (2021) Topology optimization of multi-scale structures: a review. Struct Multidiscip Optimiz 63:1455\u20131480","journal-title":"Struct Multidiscip Optimiz"},{"issue":"6","key":"6721_CR12","doi-asserted-by":"publisher","first-page":"2099","DOI":"10.1093\/bib\/bbz125","volume":"21","author":"X Lin","year":"2020","unstructured":"Lin X, Quan Z, Wang ZJ et al (2020) A novel molecular representation with bigru neural networks for learning atom. Brief Bioinf 21(6):2099\u20132111","journal-title":"Brief Bioinf"},{"key":"6721_CR13","unstructured":"Rong Y, Bian Y, Xu T, et\u00a0al (2020) Self-supervised graph transformer on large-scale molecular data. In: Advances in Neural Information Processing Systems"},{"issue":"15","key":"6721_CR14","doi-asserted-by":"publisher","first-page":"4475","DOI":"10.3390\/molecules26154475","volume":"26","author":"A Yoshimori","year":"2021","unstructured":"Yoshimori A (2021) Prediction of molecular properties using molecular topographic map. Molecules 26(15):4475","journal-title":"Molecules"},{"key":"6721_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-020-00456-1","volume":"12","author":"AP Bento","year":"2020","unstructured":"Bento AP, Hersey A, F\u00e9lix E et al (2020) An open source chemical structure curation pipeline using rdkit. J Cheminf 12:1\u201316","journal-title":"J Cheminf"},{"issue":"1","key":"6721_CR16","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","author":"D Weininger","year":"1988","unstructured":"Weininger D (1988) Smiles, a chemical language and information system. J Chem Inf Comput Sci 28(1):31\u201336","journal-title":"J Chem Inf Comput Sci"},{"key":"6721_CR17","doi-asserted-by":"crossref","unstructured":"Kimber TB, Gagnebin M, Volkamer A (2021) Maxsmi: maximizing molecular property prediction performance with confidence estimation using smiles augmentation and deep learning. Artif Intell Life Sci 1:100014","DOI":"10.1016\/j.ailsci.2021.100014"},{"key":"6721_CR18","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1186\/s12859-018-2523-5","volume":"19","author":"M Hirohara","year":"2018","unstructured":"Hirohara M, Saito Y, Koda Y et al (2018) Convolutional neural network based on smiles representation of compounds for detecting chemical motif. BMC Bioinf 19:83\u201394","journal-title":"BMC Bioinf"},{"key":"6721_CR19","doi-asserted-by":"crossref","unstructured":"Li C, Feng J, Liu S, et\u00a0al (2022) A novel molecular representation learning for molecular property prediction with a multiple smiles-based augmentation. Comput Intell Neurosci 2022","DOI":"10.1155\/2022\/8464452"},{"key":"6721_CR20","unstructured":"Liao R, Zhao Z, Urtasun R, et\u00a0al (2019) Lanczosnet: Multi-scale deep graph convolutional networks. In: International Conference on Learning Representations"},{"key":"6721_CR21","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.neucom.2021.02.025","volume":"445","author":"C Shang","year":"2021","unstructured":"Shang C, Liu Q, Tong Q et al (2021) Multi-view spectral graph convolution with consistent edge attention for molecular modeling. Neurocomput 445:12\u201325","journal-title":"Neurocomput"},{"key":"6721_CR22","doi-asserted-by":"crossref","unstructured":"Li XS, Liu X, Lu L, et\u00a0al (2022) Multiphysical graph neural network (mp-gnn) for covid-19 drug design. Brief Bioinf 23(4):bbac231","DOI":"10.1093\/bib\/bbac231"},{"issue":"1","key":"6721_CR23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1758-2946-3-1","volume":"3","author":"NM O\u2019Boyle","year":"2011","unstructured":"O\u2019Boyle NM, Banck M, James CA et al (2011) Open babel: An open chemical toolbox. J Cheminf 3(1):1\u201314","journal-title":"J Cheminf"},{"key":"6721_CR24","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1109\/TMM.2020.3025166","volume":"23","author":"W Zhou","year":"2020","unstructured":"Zhou W, Wu J, Lei J et al (2020) Salient object detection in stereoscopic 3d images using a deep convolutional residual autoencoder. IEEE Trans Multimed 23:3388\u20133399","journal-title":"IEEE Trans Multimed"},{"key":"6721_CR25","doi-asserted-by":"crossref","unstructured":"Wu J, Zhou W, Lei J et al (2022) Lbenet: Lightweight boundary enhancement network for detecting salient objects in rgb-d images. Optik 271:170204","DOI":"10.1016\/j.ijleo.2022.170204"},{"key":"6721_CR26","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, et\u00a0al (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"4","key":"6721_CR27","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1038\/s42256-021-00301-6","volume":"3","author":"WX Shen","year":"2021","unstructured":"Shen WX, Zeng X, Zhu F et al (2021) Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations. Nature Mach Intell 3(4):334\u2013343","journal-title":"Nature Mach Intell"},{"key":"6721_CR28","doi-asserted-by":"crossref","unstructured":"Tchagang AB, Vald\u00e9s JJ (2021) Time frequency representations and deep convolutional neural networks: A recipe for molecular properties prediction. In: 2021 IEEE Canadian Conference on Electrical and Computer Engineering, IEEE","DOI":"10.1109\/CCECE53047.2021.9569072"},{"key":"6721_CR29","unstructured":"Sch\u00fctt K, Kindermans PJ, Sauceda\u00a0Felix HE, et\u00a0al (2017) Schnet: A continuous-filter convolutional neural network for modeling quantum interactions. In: Advances in Neural Information Processing Systems"},{"issue":"17","key":"6721_CR30","doi-asserted-by":"publisher","first-page":"1604","DOI":"10.1002\/cmdc.201900458","volume":"14","author":"H Cho","year":"2019","unstructured":"Cho H, Choi IS (2019) Enhanced deep-learning prediction of molecular properties via augmentation of bond topology. ChemMedChem 14(17):1604\u20131609","journal-title":"ChemMedChem"},{"key":"6721_CR31","doi-asserted-by":"crossref","unstructured":"Lu C, Liu Q, Wang C, et\u00a0al (2019) Molecular property prediction: A multilevel quantum interactions modeling perspective. In: Proceedings of the AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v33i01.33011052"},{"issue":"17","key":"6721_CR32","doi-asserted-by":"publisher","first-page":"7393","DOI":"10.1021\/acs.jmedchem.7b00696","volume":"60","author":"SD Axen","year":"2017","unstructured":"Axen SD, Huang XP, C\u00e1ceres EL et al (2017) A simple representation of three-dimensional molecular structure. J Med Chem 60(17):7393\u20137409","journal-title":"J Med Chem"},{"key":"6721_CR33","unstructured":"Liu Y, Wang L, Liu M, et\u00a0al (2021) Spherical message passing for 3d graph networks. arXiv:2102.05013"},{"issue":"3","key":"6721_CR34","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1021\/acs.jcim.9b01145","volume":"60","author":"J Sunseri","year":"2020","unstructured":"Sunseri J, Koes DR (2020) Libmolgrid: graphics processing unit accelerated molecular gridding for deep learning applications. J Chem Inf Model 60(3):1079\u20131084","journal-title":"J Chem Inf Model"},{"issue":"16","key":"6721_CR35","doi-asserted-by":"publisher","first-page":"4558","DOI":"10.1021\/acs.jpclett.9b01570","volume":"10","author":"S Liu","year":"2019","unstructured":"Liu S, Li J, Bennett KC et al (2019) Multiresolution 3d-densenet for chemical shift prediction in nmr crystallography. The J Phys Chem Lett 10(16):4558\u20134565","journal-title":"The J Phys Chem Lett"},{"issue":"10","key":"6721_CR36","doi-asserted-by":"publisher","first-page":"4378","DOI":"10.1021\/acs.molpharmaceut.7b01134","volume":"15","author":"D Kuzminykh","year":"2018","unstructured":"Kuzminykh D, Polykovskiy D, Kadurin A et al (2018) 3d molecular representations based on the wave transform for convolutional neural networks. Molec Pharma 15(10):4378\u20134385","journal-title":"Molec Pharma"},{"key":"6721_CR37","doi-asserted-by":"crossref","unstructured":"Venkataraman V, Ramamurthy KN, Turaga P (2016) Persistent homology of attractors for action recognition. In: 2016 IEEE International Conference on Image Processing, IEEE","DOI":"10.1109\/ICIP.2016.7533141"},{"key":"6721_CR38","unstructured":"Rieck B, Yates T, Bock C, et\u00a0al (2020) Uncovering the topology of time-varying fmri data using cubical persistence. In: Advances in Neural Information Processing Systems"},{"issue":"12","key":"6721_CR39","doi-asserted-by":"publisher","first-page":"8766","DOI":"10.1109\/TPAMI.2020.3013679","volume":"44","author":"JR Clough","year":"2020","unstructured":"Clough JR, Byrne N, Oksuz I et al (2020) A topological loss function for deep-learning based image segmentation using persistent homology. IEEE Trans Pattern Anal Mach Intell 44(12):8766\u20138778","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6721_CR40","doi-asserted-by":"crossref","unstructured":"Gong W, Wee J, Wu MC, et\u00a0al (2022) Persistent spectral simplicial complex-based machine learning for chromosomal structural analysis in cellular differentiation. Brief Bioinf 23(4):bbac168","DOI":"10.1093\/bib\/bbac168"},{"key":"6721_CR41","doi-asserted-by":"crossref","unstructured":"Wu H, Yip A, Long J, et\u00a0al (2023) Simplicial complex neural networks. IEEE Trans Pattern Anal Mach Intell pp 561\u2013 575","DOI":"10.1109\/TPAMI.2023.3323624"},{"issue":"10","key":"6721_CR42","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1038\/s41567-021-01371-4","volume":"17","author":"F Battiston","year":"2021","unstructured":"Battiston F, Amico E, Barrat A et al (2021) The physics of higher-order interactions in complex systems. Nature Phys 17(10):1093\u20131098","journal-title":"Nature Phys"},{"key":"6721_CR43","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et\u00a0al (2021) An image is worth 16x16 words: Transform Image Recogn Scale"},{"issue":"2","key":"6721_CR44","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","volume":"9","author":"Z Wu","year":"2018","unstructured":"Wu Z, Ramsundar B, Feinberg EN et al (2018) Moleculenet: a benchmark for molecular machine learning. Chem Sci 9(2):513\u2013530","journal-title":"Chem Sci"},{"issue":"2","key":"6721_CR45","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1038\/s42256-021-00438-4","volume":"4","author":"X Fang","year":"2022","unstructured":"Fang X, Liu L, Lei J et al (2022) Geometry-enhanced molecular representation learning for property prediction. Nature Mach Intell 4(2):127\u2013134","journal-title":"Nature Mach Intell"},{"key":"6721_CR46","unstructured":"Ramsundar B, Eastman P, Walters P, et\u00a0al (2019) Deep learning for the life sciences: applying deep learning to genomics, microscopy, drug discovery, and more. \" O\u2019Reilly Media, Inc.\""},{"issue":"3","key":"6721_CR47","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","volume":"4","author":"Y Wang","year":"2022","unstructured":"Wang Y, Wang J, Cao Z et al (2022) Molecular contrastive learning of representations via graph neural networks. Nature Mach Intell 4(3):279\u2013287","journal-title":"Nature Mach Intell"},{"issue":"8","key":"6721_CR48","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","volume":"59","author":"K Yang","year":"2019","unstructured":"Yang K, Swanson K, Jin W et al (2019) Analyzing learned molecular representations for property prediction. J Chem Inf Model 59(8):3370\u20133388","journal-title":"J Chem Inf Model"},{"issue":"16","key":"6721_CR49","doi-asserted-by":"publisher","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","volume":"63","author":"Z Xiong","year":"2019","unstructured":"Xiong Z, Wang D, Liu X et al (2019) Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism. J Med Chem 63(16):8749\u20138760","journal-title":"J Med Chem"},{"issue":"8","key":"6721_CR50","doi-asserted-by":"publisher","first-page":"3105","DOI":"10.1021\/acs.jcim.3c02058","volume":"64","author":"L Song","year":"2024","unstructured":"Song L, Zhu H, Wang K et al (2024) Lgga-mpp: Local geometry-guided graph attention for molecular property prediction. J Chem Inf Model 64(8):3105\u20133113","journal-title":"J Chem Inf Model"},{"key":"6721_CR51","unstructured":"Liu S, Demirel MF, Liang Y (2019) N-gram graph: Simple unsupervised representation for graphs, with applications to molecules"},{"key":"6721_CR52","unstructured":"Hu W, Liu B, Gomes J, et\u00a0al (2020) Strategies for pre-training graph neural networks. In: International Conference on Learning Representations"},{"key":"6721_CR53","unstructured":"Liu S, Wang H, Liu W, et\u00a0al (2022) Pre-training molecular graph representation with 3d geometry. In: International Conference on Learning Representations"},{"key":"6721_CR54","unstructured":"Yu Q, Zhang Y, Ni Y, et\u00a0al (2024) Multimodal molecular pretraining via modality blending. In: The Twelfth International Conference on Learning Representations"},{"key":"6721_CR55","doi-asserted-by":"crossref","unstructured":"Yang J, Zheng K, Long S, et\u00a0al (2024) Mol-ae: Auto-encoder based molecular representation learning with 3d cloze test objective. bioRxiv pp 2024\u201304","DOI":"10.1101\/2024.04.13.589331"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06721-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06721-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06721-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T13:37:53Z","timestamp":1758289073000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06721-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,25]]},"references-count":55,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["6721"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06721-w","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,6,25]]},"assertion":[{"value":"13 June 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"819"}}