{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T20:16:36Z","timestamp":1782245796088,"version":"3.54.5"},"reference-count":53,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"vor","delay-in-days":29,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Research Project of Anhui Educational Committee","award":["RZ2300001813"],"award-info":[{"award-number":["RZ2300001813"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Accurately predicting the pharmacological and toxicological properties of molecules is a critical step in the drug development process. Owing to the heterogeneity of molecular property prediction tasks, most of the current methods rely on building a base model and fine-tuning it to address specific properties. However, constructing a high-quality base model is a time-consuming procedure and requires a carefully designed network architecture; in addition, in certain rare molecular property prediction tasks, the base model often does not transfer well to new tasks. In this work, we adopt a meta-learning-based training framework that enables our model to adapt to diverse tasks with limited data, thereby preventing data scarcity from impacting certain molecular property predictions. Additionally, this framework leverages the correlations between different tasks, allowing the constructed model to quickly adapt to new prediction tasks. Moreover, we propose a multimodal fusion framework that combines two-dimensional molecular graphs with molecular images. In the molecular graphs, node-, motif-, and graph-level features are hierarchically guided from low to high levels, fully exploiting the molecular representation and more efficiently conducting hierarchical fusion. Experimental results indicate that our model outperforms the baseline models across various performance indicators, thereby validating the effectiveness of our approach.<\/jats:p>","DOI":"10.1093\/bib\/bbaf251","type":"journal-article","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T11:20:54Z","timestamp":1748604054000},"source":"Crossref","is-referenced-by-count":3,"title":["Integrated multimodal hierarchical fusion and meta-learning for enhanced molecular property prediction"],"prefix":"10.1093","volume":"26","author":[{"given":"Xianjun","family":"Han","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology , Anhui University, Jiulong Road 111, Hefei 230601,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenglong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology , Anhui University, Jiulong Road 111, Hefei 230601,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Acupuncture and Tuina , Anhui University of Chinese Medicine, Longzihu Road 350, Hefei 230012,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijian","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Acupuncture and Tuina , Anhui University of Chinese Medicine, Longzihu Road 350, Hefei 230012,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,5,30]]},"reference":[{"key":"2025053008014678600_ref1","doi-asserted-by":"publisher","first-page":"108344","DOI":"10.1016\/j.jmgm.2022.108344","article-title":"MolRoPE-BERT: an enhanced molecular representation with rotary position embedding for molecular property prediction","volume":"118","author":"Liu","year":"2023","journal-title":"J Mol Graph Model"},{"key":"2025053008014678600_ref2","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":""},{"key":"2025053008014678600_ref3","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J Chem Inf Comput Sci"},{"key":"2025053008014678600_ref4","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1145\/3307339.3342186","article-title":"SMILES-BERT: large scale unsupervised pre-training for molecular property prediction","volume-title":"Proceedings of the 10th ACM international conference on bioinformatics, computational biology and health informatics","author":"Wang","year":"2019"},{"key":"2025053008014678600_ref5","first-page":"045024","article-title":"Self-referencing embedded strings (selfies): a 100% robust molecular string representation","volume":"1","author":"Krenn","year":"2020","journal-title":"Mach Learn: Sci Technol"},{"key":"2025053008014678600_ref6","doi-asserted-by":"publisher","first-page":"13167","DOI":"10.1007\/s00521-023-08403-5","article-title":"Few-shot learning via graph embeddings with convolutional networks for low-data molecular property prediction","volume":"35","author":"Torres","year":"2023","journal-title":"Neural Comput Appl"},{"key":"2025053008014678600_ref7","article-title":"How powerful are graph neural networks?","volume-title":"7th International Conference on Learning Representations","author":"Xu"},{"key":"2025053008014678600_ref8","article-title":"Inductive representation learning on large graphs","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17)","author":"Hamilton"},{"key":"2025053008014678600_ref9","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1016\/j.drudis.2021.02.011","article-title":"Graph neural networks for automated de novo drug design","volume":"26","author":"Xiong","year":"2021","journal-title":"Drug Discov Today"},{"key":"2025053008014678600_ref10","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1093\/bib\/bbz042","article-title":"Graph convolutional networks for computational drug development and discovery","volume":"21","author":"Sun","year":"2020","journal-title":"Brief Bioinform"},{"key":"2025053008014678600_ref11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-021-04298-y","article-title":"A neural network-based method for polypharmacy side effects prediction","volume":"22","author":"Masumshah","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2025053008014678600_ref12","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular contrastive learning of representations via graph neural networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2025053008014678600_ref13","first-page":"56","article-title":"MolPROP: molecular property prediction with multimodal language and graph fusion","volume":"16","author":"Rollins","year":"2024","journal-title":"J Chem"},{"key":"2025053008014678600_ref14","doi-asserted-by":"publisher","first-page":"3948","DOI":"10.1021\/acs.jcim.2c00521","article-title":"SMICLR: contrastive learning on multiple molecular representations for semisupervised and unsupervised representation learning","volume":"62","author":"Pinheiro","year":"2022","journal-title":"J Chem Inf Model"},{"key":"2025053008014678600_ref15","first-page":"vbad110","article-title":"DPSP: a multimodal deep learning framework for polypharmacy side effects prediction","volume":"3","author":"Masumshah","year":"2023","journal-title":"Bioinf Adv"},{"key":"2025053008014678600_ref16","article-title":"Contrastive learning of image-and structure-based representations in drug discovery","volume-title":"Proceedings of the Machine Learning for Drug Discovery (MLDD) Workshop at the International Conference on Learning Representations (ICLR)","author":"Sanchez-Fernandez"},{"key":"2025053008014678600_ref17","doi-asserted-by":"publisher","DOI":"10.5376\/bm.2024.15.0004","article-title":"New methods for predicting drug molecule activity using deep learning","volume":"15","author":"White","year":"2024","journal-title":"Biosci Methods"},{"key":"2025053008014678600_ref18","doi-asserted-by":"crossref","first-page":"2779","DOI":"10.1109\/BIBM49941.2020.9313553","article-title":"Improving molecular property prediction on limited data with deep multi-label learning","volume-title":"2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Ma","year":"2020"},{"key":"2025053008014678600_ref19","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab109","article-title":"An effective self-supervised framework for learning expressive molecular global representations to drug discovery","volume":"22","author":"Li","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025053008014678600_ref20","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular contrastive learning of representations via graph neural networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2025053008014678600_ref21","doi-asserted-by":"crossref","first-page":"3585","DOI":"10.1145\/3447548.3467186","article-title":"MoCL: data-driven molecular fingerprint via knowledge-aware contrastive learning from molecular graph","volume-title":"Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining","author":"Sun","year":"2021"},{"key":"2025053008014678600_ref22","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1038\/s42004-023-00825-5","article-title":"Hierarchical molecular graph self-supervised learning for property prediction","volume":"6","author":"Zang","year":"2023","journal-title":"Commun Chem"},{"key":"2025053008014678600_ref23","first-page":"5715","article-title":"EmotiEffNets for facial processing in video-based valence-arousal prediction, expression classification and action unit detection","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Savchenko","year":"2023"},{"key":"2025053008014678600_ref24","article-title":"Predicting molecule toxicity via descriptor-based graph self-supervised learning","volume":"11","author":"Li","journal-title":"IEEE Access"},{"key":"2025053008014678600_ref25","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"2025053008014678600_ref26","doi-asserted-by":"publisher","first-page":"12e0005","DOI":"10.1016\/j.eswa.2023.120005","article-title":"Few-shot learning with transformers via graph embeddings for molecular property prediction","volume":"225","author":"Torres","year":"2023","journal-title":"Expert Syst Appl"},{"key":"2025053008014678600_ref27","first-page":"4","volume":"2","author":"Nichol","year":"2018","journal-title":"Reptile: a scalable metalearning algorithm"},{"key":"2025053008014678600_ref28","doi-asserted-by":"publisher","first-page":"100022","DOI":"10.1016\/j.ailsci.2021.100022","article-title":"Learning functional group chemistry from molecular images leads to accurate prediction of activity cliffs","volume":"1","author":"Iqbal","year":"2021","journal-title":"Artif Intell Life Sci"},{"key":"2025053008014678600_ref29","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1038\/s42256-022-00557-6","article-title":"Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework","volume":"4","author":"Zeng","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2025053008014678600_ref30","article-title":"rdkit\/rdkit: 2020_03_1 (Q1 2020) Release","author":"Landrum","year":"2020"},{"key":"2025053008014678600_ref31","article-title":"PLANET: a multi-objective graph neural network model for protein\u2013ligand binding affinity prediction","author":"Zhang","year":"2023","journal-title":"J Chem Inf Model"},{"key":"2025053008014678600_ref32","first-page":"15870","article-title":"Motif-based graph self-supervised learning for molecular property prediction","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang","year":"2021"},{"key":"2025053008014678600_ref33","doi-asserted-by":"publisher","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":"2025053008014678600_ref34","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2023\/396","article-title":"Graph propagation transformer for graph representation learning","volume-title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI-23)","author":"Chen"},{"key":"2025053008014678600_ref35","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1007\/978-3-031-43901-8_61","article-title":"ConvFormer: plug-and-play CNN-style transformers for improving medical image segmentation","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Lin","year":"2023"},{"key":"2025053008014678600_ref36","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","volume-title":"Proceedings of the 9th International Conference on Learning Representations (ICLR 2021)","author":"Dosovitskiy"},{"key":"2025053008014678600_ref37","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s13636-024-00335-9","article-title":"DeepDet: YAMNnet with bottleneck attention module (BAM) for TTS synthesis detection","volume":"2024","author":"Mahum","year":"2024","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"2025053008014678600_ref38","doi-asserted-by":"crossref","first-page":"bbad461","DOI":"10.1093\/bib\/bbad461","article-title":"KinomeMETA: meta-learning enhanced kinome-wide polypharmacology profiling","volume":"25","author":"Ren","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025053008014678600_ref39","doi-asserted-by":"publisher","first-page":"4849","DOI":"10.1109\/TNNLS.2024.3359657","article-title":"Meta-MolNet: a cross-domain benchmark for few examples drug discovery","volume":"36","author":"Lv","year":"2025","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"2025053008014678600_ref40","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: a benchmark for molecular machine learning","volume":"9","author":"Zhenqin","year":"2018","journal-title":"Chem Sci"},{"key":"2025053008014678600_ref41","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1021\/acs.chemrestox.6b00135","article-title":"ToxCast chemical landscape: paving the road to 21st century toxicology","volume":"29","author":"Richard","year":"2016","journal-title":"Chem Res Toxicol"},{"key":"2025053008014678600_ref42","doi-asserted-by":"publisher","first-page":"e79568","DOI":"10.1371\/journal.pone.0079568","article-title":"SWEETLEAD: an in silico database of approved drugs, regulated chemicals, and herbal isolates for computer-aided drug discovery","volume":"8","author":"Novick","year":"2013","journal-title":"PloS One"},{"key":"2025053008014678600_ref43","article-title":"Strategies for pre-training graph neural networks","author":"Hu","year":"2019"},{"key":"2025053008014678600_ref44","doi-asserted-by":"crossref","DOI":"10.1145\/3394486.3403237","article-title":"GPT-GNN: generative pre-training of graph neural networks","volume-title":"Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining","author":"Hu"},{"key":"2025053008014678600_ref45","article-title":"InfoGraph: unsupervised and semi-supervised graph-level representation learning via mutual information maximization","volume-title":"International Conference on Learning Representations","author":"Sun","year":"2019"},{"key":"2025053008014678600_ref46","article-title":"Self-supervised graph-level representation learning with local and global structure","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML 2021)","author":"Xu"},{"key":"2025053008014678600_ref47","article-title":"Graph contrastive learning with augmentations","volume-title":"Advances in Neural Information Processing Systems","author":"You","year":"2020"},{"key":"2025053008014678600_ref48","article-title":"Graph contrastive learning automated","volume-title":"International Conference on Machine Learning","author":"You","year":"2021"},{"key":"2025053008014678600_ref49","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular contrastive learning of representations via graph neural networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2025053008014678600_ref50","article-title":"Self-supervised graph transformer on large-scale molecular data","volume-title":"Advances in neural information processing systems","author":"Rong"},{"key":"2025053008014678600_ref51","doi-asserted-by":"crossref","first-page":"195912","DOI":"10.1007\/s11704-024-3784-y","article-title":"MetaGIN: a lightweight framework for molecular property prediction","volume":"19","author":"Wang","year":"2025","journal-title":"Front Comp Sci"},{"key":"2025053008014678600_ref52","doi-asserted-by":"publisher","first-page":"152","DOI":"10.4236\/jcc.2025.131011","article-title":"MMGCF: generating counterfactual explanations for molecular property prediction via motif rebuild","volume":"13","author":"Zhang","year":"2025","journal-title":"J Comput Commun"},{"key":"2025053008014678600_ref53","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J Mach Learn Res"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/3\/bbaf251\/63405334\/bbaf251.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/3\/bbaf251\/63405334\/bbaf251.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T12:02:00Z","timestamp":1748606520000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf251\/8153688"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,1]]},"references-count":53,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf251","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,5]]},"published":{"date-parts":[[2025,5,1]]},"article-number":"bbaf251"}}