{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:04:33Z","timestamp":1780635873126,"version":"3.54.1"},"reference-count":63,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T00:00:00Z","timestamp":1604448000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["21775060"],"award-info":[{"award-number":["21775060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872216"],"award-info":[{"award-number":["61872216"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61472205"],"award-info":[{"award-number":["61472205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81630103"],"award-info":[{"award-number":["81630103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["31871071"],"award-info":[{"award-number":["31871071"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836004"],"award-info":[{"award-number":["61836004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Turing AI Institute of Nanjing"},{"name":"Beijing Brain Science Special","award":["Z181100001518006"],"award-info":[{"award-number":["Z181100001518006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,20]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Motivation<\/jats:title><jats:p>Computational methods accelerate drug discovery and play an important role in biomedicine, such as molecular property prediction and compound\u2013protein interaction (CPI) identification. A key challenge is to learn useful molecular representation. In the early years, molecular properties are mainly calculated by quantum mechanics or predicted by traditional machine learning methods, which requires expert knowledge and is often labor-intensive. Nowadays, graph neural networks have received significant attention because of the powerful ability to learn representation from graph data. Nevertheless, current graph-based methods have some limitations that need to be addressed, such as large-scale parameters and insufficient bond information extraction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In this study, we proposed a graph-based approach and employed a novel triplet message mechanism to learn molecular representation efficiently, named triplet message networks (TrimNet). We show that TrimNet can accurately complete multiple molecular representation learning tasks with significant parameter reduction, including the quantum properties, bioactivity, physiology and CPI prediction. In the experiments, TrimNet outperforms the previous state-of-the-art method by a significant margin on various datasets. Besides the few parameters and high prediction accuracy, TrimNet could focus on the atoms essential to the target properties, providing a clear interpretation of the prediction tasks. These advantages have established TrimNet as a powerful and useful computational tool in solving the challenging problem of molecular representation learning.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability<\/jats:title><jats:p>The quantum and drug datasets are available on the website of MoleculeNet: http:\/\/moleculenet.ai. The source code is available in GitHub: https:\/\/github.com\/yvquanli\/trimnet.<\/jats:p><\/jats:sec><jats:sec><jats:title>Contact<\/jats:title><jats:p>xjyao@lzu.edu.cn, songsen@tsinghua.edu.cn<\/jats:p><\/jats:sec>","DOI":"10.1093\/bib\/bbaa266","type":"journal-article","created":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T20:11:07Z","timestamp":1604002267000},"source":"Crossref","is-referenced-by-count":86,"title":["TrimNet: learning molecular representation from triplet messages for biomedicine"],"prefix":"10.1093","volume":"22","author":[{"given":"Pengyong","family":"Li","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering at Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuquan","family":"Li","sequence":"additional","affiliation":[{"name":"College of Chemistry and Chemical Engineering at Lanzhou University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Yu","family":"Hsieh","sequence":"additional","affiliation":[{"name":"University of Ottawa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer science at Princeton University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianggen","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Lanzhou University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Song","sequence":"additional","affiliation":[{"name":"Brandeis University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Yao","sequence":"additional","affiliation":[{"name":"Lanzhou University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,11,4]]},"reference":[{"key":"2021072112311518300_ref1","article-title":"Neural machine translation by jointly learning to align and translate. In: International Conference on Learning Representations, Banff, Canada: ICLR Press, 2015","author":"Bahdanau"},{"issue":"1","key":"2021072112311518300_ref2","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"issue":"7715","key":"2021072112311518300_ref3","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine learning for molecular and materials science","volume":"559","author":"Butler","year":"2018","journal-title":"Nature"},{"key":"2021072112311518300_ref4","article-title":"Et al.","volume-title":"AAAI Conference on Artificial Intelligence, New York","author":"Chen"},{"issue":"9","key":"2021072112311518300_ref5","doi-asserted-by":"crossref","first-page":"2208","DOI":"10.3390\/molecules23092208","article-title":"Machine learning for drug-target interaction prediction","volume":"23","author":"Chen","year":"2018","journal-title":"Molecules"},{"key":"2021072112311518300_ref6","author":"Chung","year":"2014"},{"issue":"3","key":"2021072112311518300_ref7","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn"},{"issue":"3","key":"2021072112311518300_ref8","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1038\/nmat3568","article-title":"The high-throughput highway to computational materials design","volume":"12","author":"Curtarolo","year":"2013","journal-title":"Nat Mater"},{"key":"2021072112311518300_ref9","first-page":"4171","volume-title":"The North American Chapter of the Association for Computational Linguistics, Minneapolis, Minnesota","author":"Devlin","year":"2019"},{"key":"2021072112311518300_ref10","volume-title":"Pattern Classification","author":"Duda","year":"2012"},{"issue":"11","key":"2021072112311518300_ref11","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1021\/acscentsci.8b00507","article-title":"PotentialNet for molecular property prediction","volume":"4","author":"Feinberg","year":"2018","journal-title":"ACS Cent Sci"},{"key":"2021072112311518300_ref12","volume-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds","author":"Fey","year":"2019"},{"key":"2021072112311518300_ref13","first-page":"1263","volume-title":"International Conference on Machine Learning","author":"Gilmer","year":"2017"},{"issue":"16","key":"2021072112311518300_ref14","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1002\/jcc.24764","article-title":"Deep learning for computational chemistry","volume":"38","author":"Goh","year":"2017","journal-title":"J Comput Chem"},{"key":"2021072112311518300_ref15","author":"Graves","year":"2014"},{"issue":"17","key":"2021072112311518300_ref16","doi-asserted-by":"crossref","first-page":"2241","DOI":"10.1021\/jz200866s","article-title":"The Harvard clean energy project: large-scale computational screening and design of organic photovoltaics on the world community grid","volume":"2","author":"Hachmann","year":"2011","journal-title":"J Phys Chem Lett"},{"key":"2021072112311518300_ref17","first-page":"770","volume-title":"Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"issue":"10","key":"2021072112311518300_ref18","doi-asserted-by":"crossref","first-page":"2520","DOI":"10.3390\/molecules23102520","article-title":"Artificial intelligence in drug design","volume":"23","author":"Hessler","year":"2018","journal-title":"Molecules"},{"issue":"3B","key":"2021072112311518300_ref19","doi-asserted-by":"crossref","first-page":"B864","DOI":"10.1103\/PhysRev.136.B864","article-title":"Inhomogeneous electron gas","volume":"136","author":"Hohenberg","year":"1964","journal-title":"Phys Rev"},{"key":"2021072112311518300_ref20","first-page":"248","volume-title":"Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"issue":"8","key":"2021072112311518300_ref21","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1007\/s10822-016-9938-8","article-title":"Molecular graph convolutions: moving beyond fingerprints","volume":"30","author":"Kearnes","year":"2016","journal-title":"J Comput Aided Mol Des"},{"key":"2021072112311518300_ref22","article-title":"Adam: a method for stochastic optimization","volume-title":"International Conference on Learning Representations","author":"Kingma","year":"2015"},{"key":"2021072112311518300_ref23","volume-title":"International Conference on Learning Representations","author":"Klicpera","year":"2020"},{"key":"2021072112311518300_ref24","article-title":"Open-source cheminformatics","author":"RDKIT","year":"2006"},{"issue":"3","key":"2021072112311518300_ref25","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.drudis.2014.10.012","article-title":"Machine-learning approaches in drug discovery: methods and applications","volume":"20","author":"Lavecchia","year":"2015","journal-title":"Drug Discov Today"},{"issue":"10","key":"2021072112311518300_ref26","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1016\/j.drudis.2019.07.006","article-title":"Deep learning in drug discovery: opportunities, challenges and future prospects","volume":"24","author":"Lavecchia","year":"2019","journal-title":"Drug Discov Today"},{"issue":"7553","key":"2021072112311518300_ref27","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"2021072112311518300_ref28","first-page":"9267","volume-title":"International Conference on Computer Vision","author":"Li","year":"2019"},{"key":"2021072112311518300_ref29","author":"Li","year":"2017"},{"issue":"12","key":"2021072112311518300_ref30","doi-asserted-by":"crossref","first-page":"i221","DOI":"10.1093\/bioinformatics\/btv256","article-title":"Improving compound-protein interaction prediction by building up highly credible negative samples","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"issue":"14","key":"2021072112311518300_ref31","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.3390\/ijms20143389","article-title":"Chemi-net: a molecular graph convolutional network for accurate drug property prediction","volume":"20","author":"Liu","year":"2019","journal-title":"Int J Mol Sci"},{"issue":"6","key":"2021072112311518300_ref32","doi-asserted-by":"crossref","first-page":"2545","DOI":"10.1021\/acs.jcim.9b00266","article-title":"Deep learning in chemistry","volume":"59","author":"Mater","year":"2019","journal-title":"J Chem Inf Model"},{"issue":"9","key":"2021072112311518300_ref33","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1517\/17425255.2014.950222","article-title":"Drug\u2013target interaction prediction via chemogenomic space: learning-based methods","volume":"10","author":"Mousavian","year":"2014","journal-title":"Expert Opin Drug Metab Toxicol"},{"issue":"1","key":"2021072112311518300_ref34","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1038\/nchem.121","article-title":"Towards the computational design of solid catalysts","volume":"1","author":"N\u00f8rskov","year":"2009","journal-title":"Nat Chem"},{"issue":"1","key":"2021072112311518300_ref35","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1146\/annurev-matsci-070214-020823","article-title":"What is high-throughput virtual screening? A perspective from organic materials discovery","volume":"45","author":"Pyzer-Knapp","year":"2015","journal-title":"Annu Rev Mat Res"},{"key":"2021072112311518300_ref36","doi-asserted-by":"crossref","first-page":"140022","DOI":"10.1038\/sdata.2014.22","article-title":"Quantum chemistry structures and properties of 134 kilo molecules","volume":"1","author":"Ramakrishnan","year":"2014","journal-title":"Sci Data"},{"issue":"5","key":"2021072112311518300_ref37","doi-asserted-by":"crossref","first-page":"2087","DOI":"10.1021\/acs.jctc.5b00099","article-title":"Big data meets quantum chemistry approximations: the $\\Delta $-machine learning approach","volume":"11","author":"Ramakrishnan","year":"2015","journal-title":"J Chem Theory Comput"},{"key":"2021072112311518300_ref38","doi-asserted-by":"crossref","first-page":"1878","DOI":"10.1093\/bib\/bby061","article-title":"Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases","volume":"20","author":"Rifaioglu","year":"2019","journal-title":"Brief. Bioinform."},{"issue":"7","key":"2021072112311518300_ref39","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1177\/1087057105281365","article-title":"Using extended-connectivity fingerprints with Laplacian-modified Bayesian analysis in high-throughput screening follow-up","volume":"10","author":"Rogers","year":"2005","journal-title":"J Biomol Screen"},{"issue":"36","key":"2021072112311518300_ref40","doi-asserted-by":"crossref","first-page":"8438","DOI":"10.1039\/C9SC01992H","article-title":"A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification","volume":"10","author":"Ryu","year":"2019","journal-title":"Chem Sci"},{"issue":"1","key":"2021072112311518300_ref41","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans Neural Netw"},{"issue":"2","key":"2021072112311518300_ref42","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1038\/nrd.2017.232","article-title":"Automating drug discovery","volume":"17","author":"Schneider","year":"2018","journal-title":"Nat Rev Drug Discov"},{"key":"2021072112311518300_ref43","first-page":"992","volume-title":"Advances in Neural Information Processing Systems","author":"Sch\u00fctt","year":"2017"},{"key":"2021072112311518300_ref44","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1038\/ncomms13890","article-title":"Quantum-chemical insights from deep tensor neural networks","volume":"8","author":"Sch\u00fctt","year":"2017","journal-title":"Nat Commun"},{"issue":"6","key":"2021072112311518300_ref45","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1021\/ci034160g","article-title":"Random forest: a classification and regression tool for compound classification and QSAR modeling","volume":"43","author":"Svetnik","year":"2003","journal-title":"J Chem Inf Comput Sci"},{"issue":"1","key":"2021072112311518300_ref46","first-page":"1","article-title":"A self-attention based message passing neural network for predicting molecular lipophilicity and aqueous solubility","volume":"12","author":"Tang","year":"2020","journal-title":"J Chem"},{"issue":"2","key":"2021072112311518300_ref47","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1093\/bioinformatics\/bty535","article-title":"Compound-protein interaction prediction with end-to-end learning of neural networks for graphs and sequences","volume":"35","author":"Tsubaki","year":"2019","journal-title":"Bioinformatics"},{"issue":"6","key":"2021072112311518300_ref48","doi-asserted-by":"crossref","first-page":"3678","DOI":"10.1021\/acs.jctc.9b00181","article-title":"PhysNet: a neural network for predicting energies, forces, dipole moments, and partial charges","volume":"15","author":"Unke","year":"2019","journal-title":"J Chem Theory Comput"},{"issue":"6","key":"2021072112311518300_ref49","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1038\/s41573-019-0024-5","article-title":"Applications of machine learning in drug discovery and development","volume":"18","author":"Vamathevan","year":"2019","journal-title":"Nat Rev Drug Discov"},{"key":"2021072112311518300_ref50","first-page":"5999","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2021072112311518300_ref51","volume-title":"International Conference on Learning Representations","author":"Vinyals","year":"2016"},{"issue":"1","key":"2021072112311518300_ref52","doi-asserted-by":"crossref","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"},{"issue":"4","key":"2021072112311518300_ref53","doi-asserted-by":"crossref","first-page":"1401","DOI":"10.1021\/acs.jproteome.6b00618","article-title":"Deep-learning-based drug\u2013target interaction prediction","volume":"16","author":"Wen","year":"2017","journal-title":"J Proteome Res"},{"issue":"6","key":"2021072112311518300_ref54","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1039\/C8SC04175J","article-title":"Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations","volume":"10","author":"Winter","year":"2019","journal-title":"Chem Sci"},{"issue":"1","key":"2021072112311518300_ref55","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13321-019-0407-y","article-title":"Building attention and edge message passing neural networks for bioactivity and physical-chemical property prediction","volume":"12","author":"Withnall","year":"2020","journal-title":"J Chem"},{"issue":"2","key":"2021072112311518300_ref56","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":"Chem Sci"},{"key":"2021072112311518300_ref57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TNNLS.2020.3004626","article-title":"A comprehensive survey on graph neural networks","author":"Wu","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst."},{"key":"2021072112311518300_ref58","article-title":"Pushing the boundaries of molecular representation for drug discovery with graph attention mechanism","author":"Xiong","year":"2019","journal-title":"J Med Chem"},{"key":"2021072112311518300_ref59","first-page":"8676","volume-title":"International Conference on Machine Learning","author":"Xu","year":"2018"},{"issue":"8","key":"2021072112311518300_ref60","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"},{"issue":"35","key":"2021072112311518300_ref61","doi-asserted-by":"crossref","first-page":"8154","DOI":"10.1039\/C9SC00616H","article-title":"Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning","volume":"10","author":"Zhang","year":"2019","journal-title":"Chem Sci"},{"issue":"8","key":"2021072112311518300_ref62","first-page":"1","article-title":"Deep learning on graphs: a survey","volume":"14","author":"Zhang","year":"2020","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2021072112311518300_ref63","article-title":"PairNorm: tackling oversmoothing in GNNs","author":"Zhao","year":"2019"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/22\/4\/bbaa266\/39144778\/bbaa266.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/bib\/article-pdf\/22\/4\/bbaa266\/39144778\/bbaa266.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T16:52:30Z","timestamp":1669395150000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaa266\/5955940"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,4]]},"references-count":63,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,7,20]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaa266","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,7]]},"published":{"date-parts":[[2020,11,4]]},"article-number":"bbaa266"}}