{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T18:06:26Z","timestamp":1783706786473,"version":"3.55.0"},"reference-count":58,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T00:00:00Z","timestamp":1751155200000},"content-version":"vor","delay-in-days":59,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"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>As the primary messenger RNA (mRNA) delivery vehicles, ionizable lipid nanoparticles (LNPs) exhibit excellent safety, high transfection efficiency, and strong immune response induction. However, the screening process for LNPs is time-consuming and costly. To expedite the identification of high-transfection-efficiency mRNA drug delivery systems, we propose an explainable LNPs transfection efficiency prediction model, called TransMA. TransMA employs a multimodal molecular structure fusion architecture, wherein the fine-grained atomic spatial relationship extractor named molecule 3D Transformer captures three-dimensional spatial features of the molecule, and the coarse-grained atomic sequence extractor named molecule Mamba captures one-dimensional molecular features. We design the mol-attention mechanism block, enabling it to align coarse and fine-grained atomic features and capture relationships between atomic spatial and sequential structures. TransMA achieves state-of-the-art performance in predicting transfection efficiency using the scaffold and cliff data splitting methods on the current largest LNPs dataset, including Hela and RAW cell lines. Moreover, we find that TransMA captures the relationship between subtle structural changes and significant transfection efficiency variations, providing valuable insights for LNPs design. Additionally, TransMA\u2019s predictions on external transfection efficiency data maintain a consistent order with actual transfection efficiencies, demonstrating its robust generalization capability. We hope that high-accuracy transfection prediction models in the future can aid in LNPs design and initial screening, thereby assisting in accelerating the mRNA design process.<\/jats:p>","DOI":"10.1093\/bib\/bbaf307","type":"journal-article","created":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T17:05:06Z","timestamp":1751216706000},"source":"Crossref","is-referenced-by-count":14,"title":["TransMA: an explainable multi-modal deep learning model for predicting properties of ionizable lipid nanoparticles in mRNA delivery"],"prefix":"10.1093","volume":"26","author":[{"given":"Kun","family":"Wu","sequence":"first","affiliation":[{"name":"Shanghai Advanced Research Institute, Chinese Academy of Sciences , 99 Haike Road, Shanghai 201210 ,","place":["China"]},{"name":"University of Chinese Academy of Sciences , No. 1 Yanqihu East Rd, Huairou District, Beijing 101408 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Tsukuba , 1-1-1 Tennodai, Tsukuba, Ibaraki 305-8577 ,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiulong","family":"Yang","sequence":"additional","affiliation":[{"name":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University , 152 Luoyu Road, Hongshan District, Wuhan 430079, Hubei Province ,","place":["China"]},{"name":"School of Computer Science, Central China Normal University , 152 Luoyu Road, Hongshan District, Wuhan 430079, Hubei Province ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Tsukuba , 1-1-1 Tennodai, Tsukuba, Ibaraki 305-8577 ,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fulvio","family":"Mastrogiovanni","sequence":"additional","affiliation":[{"name":"Robotics, Brain, and Cognitive Sciences Unit, Istituto Italiano di Tecnologia , Via Morego 30, 16163 Genoa ,","place":["Italy"]},{"name":"Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genoa , Viaall'Opera Pia 11A, 16145 Genoa ,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Advanced Research Institute, Chinese Academy of Sciences , 99 Haike Road, Shanghai 201210 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Advanced Research Institute, Chinese Academy of Sciences , 99 Haike Road, Shanghai 201210 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"key":"2025062913050212700_ref1","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.1038\/s41578-021-00358-0","article-title":"Lipid nanoparticles for mRNA delivery","volume":"6","author":"Hou","year":"2021","journal-title":"Nat Rev Mater"},{"key":"2025062913050212700_ref2","doi-asserted-by":"publisher","first-page":"3654","DOI":"10.1021\/acs.molpharmaceut.0c00618","article-title":"Nanomedicine-based approaches for mRNA delivery","volume":"17","author":"Uchida","year":"2020","journal-title":"Mol Pharm"},{"key":"2025062913050212700_ref3","doi-asserted-by":"publisher","first-page":"2000099","DOI":"10.1002\/adtp.202000099","article-title":"Nanoplatforms for mRNA therapeutics","volume":"4","author":"Meng","year":"2021","journal-title":"Adv Ther"},{"key":"2025062913050212700_ref4","doi-asserted-by":"publisher","first-page":"1589","DOI":"10.1016\/j.cell.2021.02.030","article-title":"Novel approaches for vaccine development","volume":"184","author":"Gebre","year":"2021","journal-title":"Cell"},{"key":"2025062913050212700_ref5","doi-asserted-by":"publisher","first-page":"107534","DOI":"10.1016\/j.biotechadv.2020.107534","article-title":"The challenge and prospect of mRNA therapeutics landscape","volume":"40","author":"Weng","year":"2020","journal-title":"Biotechnol Adv"},{"key":"2025062913050212700_ref6","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.addr.2020.12.014","article-title":"Self-assembled mRNA vaccines","volume":"170","author":"Kim","year":"2021","journal-title":"Adv Drug Deliv Rev"},{"key":"2025062913050212700_ref7","article-title":"All-trans-retinoic acid-adjuvanted mRNA vaccine induces mucosal anti-tumor immune responses for treating colorectal cancer","volume":"11","author":"Li","year":"2024","journal-title":"Adv Sci"},{"key":"2025062913050212700_ref8","doi-asserted-by":"publisher","first-page":"e2302425","DOI":"10.1002\/advs.202302425","article-title":"Aldolase A accelerates cancer progression by modulating mRNA translation and protein biosynthesis via noncanonical mechanisms","volume":"10","author":"Song","year":"2023","journal-title":"Adv Sci"},{"key":"2025062913050212700_ref9","first-page":"2023","article-title":"Machine learning-guided lipid nanoparticle design for mRNA delivery","volume-title":"ICML 2023 CompBio Workshop","author":"Ding"},{"key":"2025062913050212700_ref10","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1038\/s41392-022-01007-w","article-title":"mRNA-based therapeutics: powerful and versatile tools to combat diseases","volume":"7","author":"Qin","year":"2022","journal-title":"Signal Transduct Target Ther"},{"key":"2025062913050212700_ref11","doi-asserted-by":"crossref","first-page":"16982","DOI":"10.1021\/acsnano.1c04996","article-title":"Lipid nanoparticles-from liposomes to mRNA vaccine delivery, a landscape of research diversity and advancement","volume":"15","author":"Tenchov","year":"2021","journal-title":"ACS Nano"},{"key":"2025062913050212700_ref12","doi-asserted-by":"crossref","first-page":"2205532","DOI":"10.1002\/advs.202205532","article-title":"Lipid nanoparticle delivery system for mRNA encoding b7h3-redirected bispecific antibody displays potent antitumor effects on malignant tumors","volume":"10","author":"Huang","year":"2023","journal-title":"Adv Sci"},{"key":"2025062913050212700_ref13","doi-asserted-by":"crossref","first-page":"3321","DOI":"10.1016\/j.radcr.2021.07.082","article-title":"Acute myocarditis following Comirnaty vaccination in a healthy man with previous SARS-COV-2 infection","volume":"16","author":"Patrignani","year":"2021","journal-title":"Radiol Case Rep"},{"key":"2025062913050212700_ref14","article-title":"A systematic review and meta-analysis of the global prevalence and determinants of Covid-19 vaccine acceptance and uptake in people living with HIV","volume":"8","author":"Sulaiman","journal-title":"Nat Hum Behav"},{"key":"2025062913050212700_ref15","doi-asserted-by":"crossref","first-page":"130638","DOI":"10.1016\/j.ijbiomac.2024.130638","article-title":"Cm-siRPred: predicting chemically modified siRNA efficiency based on multi-view learning strategy","volume":"264","author":"Liu","year":"2024","journal-title":"Int J Biol Macromol"},{"key":"2025062913050212700_ref16","first-page":"eabf4398","article-title":"Engineered ionizable lipid nanoparticles for targeted delivery of RNA therapeutics into different types of cells in the liver. Science","volume":"7","author":"Kim","year":"2021","journal-title":"Advances"},{"key":"2025062913050212700_ref17","doi-asserted-by":"crossref","first-page":"17056","DOI":"10.1038\/natrevmats.2017.56","article-title":"Tools for translation: non-viral materials for therapeutic mRNA delivery","volume":"2","author":"Hajj","year":"2017","journal-title":"Nat Rev Mater"},{"key":"2025062913050212700_ref18","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1016\/j.ymthe.2019.02.012","article-title":"Delivering the messenger: advances in technologies for therapeutic mRNA delivery","volume":"27","author":"Kowalski","year":"2019","journal-title":"Mol Ther"},{"key":"2025062913050212700_ref19","doi-asserted-by":"crossref","first-page":"1174","DOI":"10.1038\/s41587-019-0247-3","article-title":"Delivery of mRNA vaccines with heterocyclic lipids increases anti-tumor efficacy by sting-mediated immune cell activation","volume":"37","author":"Miao","year":"2019","journal-title":"Nat Biotechnol"},{"key":"2025062913050212700_ref20","doi-asserted-by":"crossref","first-page":"1410","DOI":"10.1038\/s41587-023-01679-x","article-title":"Combinatorial design of nanoparticles for pulmonary mRNA delivery and genome editing","volume":"41","author":"Li","year":"2023","journal-title":"Nat Biotechnol"},{"key":"2025062913050212700_ref21","doi-asserted-by":"crossref","DOI":"10.1038\/s41563-024-01867-3","article-title":"Accelerating ionizable lipid discovery for mRNA delivery using machine learning and combinatorial chemistry","volume":"23","author":"Li","year":"2024","journal-title":"Nat Mater"},{"key":"2025062913050212700_ref22","doi-asserted-by":"crossref","first-page":"7233","DOI":"10.1038\/s41467-021-27493-0","article-title":"An ionizable lipid toolbox for RNA delivery","volume":"12","author":"Han","year":"2021","journal-title":"Nat Commun"},{"key":"2025062913050212700_ref23","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1038\/s41392-021-00642-z","article-title":"Membrane-destabilizing ionizable phospholipids: novel components for organ-selective mRNA delivery and CRISPR-Cas gene editing","volume":"6","author":"Meng","year":"2021","journal-title":"Signal Transduct Target Ther"},{"key":"2025062913050212700_ref24","doi-asserted-by":"crossref","first-page":"6305","DOI":"10.1038\/s41467-024-50619-z","article-title":"Agile platform: a deep learning powered approach to accelerate LNP development for mRNA delivery.","volume":"15","author":"Yue","year":"2024","journal-title":"Nat Commun"},{"key":"2025062913050212700_ref25","doi-asserted-by":"crossref","first-page":"bbae186","DOI":"10.1093\/bib\/bbae186","article-title":"Data-balanced transformer for accelerated ionizable lipid nanoparticles screening in mRNA delivery","volume":"25","author":"Wu","year":"2024","journal-title":"Brief Bioinform"},{"key":"2025062913050212700_ref26","article-title":"ChemBERTa: large-scale self-supervised pretraining for molecular property prediction","volume":"abs\/2010.09885","author":"Chithrananda","year":"2020","journal-title":"CoRR"},{"key":"2025062913050212700_ref27","doi-asserted-by":"crossref","first-page":"101243","DOI":"10.1016\/j.cogsys.2024.101243","article-title":"Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists","volume":"86","author":"Retzlaff","year":"2024","journal-title":"Cognit Syst Res"},{"key":"2025062913050212700_ref28","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"2025062913050212700_ref29","first-page":"1135","article-title":"Why Should I Trust You?","volume-title":"Explaining the Predictions of any Classifier. KDD","author":"Ribeiro","year":"2016"},{"key":"2025062913050212700_ref30","doi-asserted-by":"crossref","first-page":"8761","DOI":"10.1021\/acs.jmedchem.9b01101","article-title":"Interpretation of compound activity predictions from complex machine learning models using local approximations and shapley values","volume":"63","author":"Rodr\u00edguez-P\u00e9rez","year":"2020","journal-title":"J Med Chem"},{"key":"2025062913050212700_ref31","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1038\/s42256-020-00236-4","article-title":"Drug discovery with explainable artificial intelligence","volume":"2","author":"Jim\u00e9nez-Luna","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2025062913050212700_ref32","doi-asserted-by":"crossref","first-page":"7166","DOI":"10.1038\/s41598-022-11012-2","article-title":"Interpretability and fairness evaluation of deep learning models on MIMIC-IV dataset","volume":"12","author":"Meng","year":"2022","journal-title":"Sci Rep"},{"key":"2025062913050212700_ref33","doi-asserted-by":"crossref","first-page":"130638","DOI":"10.1016\/j.ijbiomac.2024.130638","article-title":"Cm-siRPred: Predicting chemically modified siRNA efficiency based on multi-view learning strategy","volume":"264","author":"Liu","year":"2024","journal-title":"Int J Biol Macromol"},{"key":"2025062913050212700_ref34","doi-asserted-by":"crossref","first-page":"2400009","DOI":"10.1002\/advs.202400009","article-title":"CodLncScape provides a self-enriching framework for the systematic collection and exploration of coding lncRNAs","volume":"11","author":"Liu","year":"2024","journal-title":"Adv Sci"},{"key":"2025062913050212700_ref35","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Albert","year":"2023"},{"key":"2025062913050212700_ref36","article-title":"U-Mamba: enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024"},{"key":"2025062913050212700_ref37","article-title":"Weak-Mamba-UNet: visual Mamba makes CNN and ViT work better for scribble-based medical image segmentation","author":"Wang","year":"2024"},{"key":"2025062913050212700_ref38","article-title":"VMamba: visual state space model","author":"Liu","year":"2024"},{"key":"2025062913050212700_ref39","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2024.3425540","article-title":"RS-Mamba for large remote sensing image dense prediction","author":"Zhao","year":"2024"},{"key":"2025062913050212700_ref40","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"International Conference on Learning Representations","author":"Albert","year":"2022"},{"key":"2025062913050212700_ref41","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","article-title":"CBAM: convolutional block attention module","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Woo","year":"2018"},{"key":"2025062913050212700_ref42","first-page":"147","article-title":"BAM: bottleneck attention module","volume-title":"British Machine Vision Conference 2018, BMVC 2018","author":"Park","year":"2018"},{"key":"2025062913050212700_ref43","first-page":"7132","article-title":"Squeeze-and-excitation networks","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu"},{"key":"2025062913050212700_ref44","doi-asserted-by":"crossref","DOI":"10.26434\/chemrxiv-2022-jjm0j-v4","article-title":"Uni-Mol: a universal 3D molecular representation learning framework","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhou","year":"2023"},{"key":"2025062913050212700_ref45","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":"2025062913050212700_ref46","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/s42256-021-00438-4","article-title":"Geometry-enhanced molecular representation learning for property prediction","volume":"4","author":"Fang","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2025062913050212700_ref47","doi-asserted-by":"crossref","first-page":"5938","DOI":"10.1021\/acs.jcim.2c01073","article-title":"Exposing the limitations of molecular machine learning with activity cliffs","volume":"62","author":"van Tilborg","year":"2022","journal-title":"J Chem Inf Model"},{"key":"2025062913050212700_ref48","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular representations for property prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2025062913050212700_ref49","doi-asserted-by":"crossref","first-page":"5938","DOI":"10.1021\/acs.jcim.2c01073","article-title":"Exposing the limitations of molecular machine learning with activity cliffs","volume":"62","author":"van Tilborg","year":"2022","journal-title":"J Chem Inf Model"},{"key":"2025062913050212700_ref50","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J Chem Inf Model"},{"key":"2025062913050212700_ref51","doi-asserted-by":"crossref","first-page":"26952","DOI":"10.1021\/acsomega.2c03812","article-title":"Extended connectivity fingerprints as a chemical reaction representation for enantioselective organophosphorus-catalyzed asymmetric reaction prediction","volume":"7","author":"Asahara","year":"2022","journal-title":"ACS Omega"},{"key":"2025062913050212700_ref52","doi-asserted-by":"crossref","first-page":"100026","DOI":"10.1016\/j.apmate.2021.12.002","article-title":"Molecular-fingerprint machine-learning-assisted design and prediction for high-performance MOFs for capture of NMHCs from air","volume":"1","author":"Yuan","year":"2022","journal-title":"Adv Powder Mater"},{"key":"2025062913050212700_ref53","first-page":"4","article-title":"Substructure-based neural machine translation for retrosynthetic prediction","volume":"13","author":"Ucak","year":"2021","journal-title":"J Chem"},{"key":"2025062913050212700_ref54","doi-asserted-by":"crossref","first-page":"3287","DOI":"10.1109\/TIT.2020.2996543","article-title":"Levenshtein distance, sequence comparison and biological database search","volume":"67","author":"Berger","year":"2021","journal-title":"IEEE Trans Inf Theory"},{"key":"2025062913050212700_ref55","volume-title":"Design and synthesis of ionizable cationic lipids and their application in personalized antitumor vaccine","author":"You","year":"2023"},{"key":"2025062913050212700_ref56","article-title":"Tumor-tailored ionizable lipid nanoparticles facilitate IL-12 circular RNA delivery for enhanced lung cancer immunotherapy","volume":"36","author":"Xu","journal-title":"Adv Mater"},{"key":"2025062913050212700_ref57","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1021\/acs.nanolett.2c04479","article-title":"The transcriptional response to lung-targeting lipid nanoparticles in vivo","volume":"23","author":"Radmand","year":"2023","journal-title":"Nano Lett"},{"key":"2025062913050212700_ref58","first-page":"2023","article-title":"Machine learning-guided lipid nanoparticle design for mRNA delivery","volume-title":"ICML 2023 CompBio Workshop","author":"Ding"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/3\/bbaf307\/63617151\/bbaf307.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/3\/bbaf307\/63617151\/bbaf307.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T17:05:14Z","timestamp":1751216714000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf307\/8177287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,1]]},"references-count":58,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf307","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":"bbaf307"}}