{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T09:59:30Z","timestamp":1769248770614,"version":"3.49.0"},"reference-count":35,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2022,1,22]],"date-time":"2022-01-22T00:00:00Z","timestamp":1642809600000},"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":["81773632"],"award-info":[{"award-number":["81773632"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of China of Zhejiang Province","award":["LZ19H300001"],"award-info":[{"award-number":["LZ19H300001"]}]},{"name":"Key Research and Development Program of Zhejiang Province","award":["2020C03010"],"award-info":[{"award-number":["2020C03010"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2020QNA7003"],"award-info":[{"award-number":["2020QNA7003"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,3,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Accurate prediction of atomic partial charges with high-level quantum mechanics (QM) methods suffers from high computational cost. Numerous feature-engineered machine learning (ML)-based predictors with favorable computability and reliability have been developed as alternatives. However, extensive expertise effort was needed for feature engineering of atom chemical environment, which may consequently introduce domain bias. In this study, SuperAtomicCharge, a data-driven deep graph learning framework, was proposed to predict three important types of partial charges (i.e. RESP, DDEC4 and DDEC78) derived from high-level QM calculations based on the structures of molecules. SuperAtomicCharge was designed to simultaneously exploit the 2D and 3D structural information of molecules, which was proved to be an effective way to improve the prediction accuracy of the model. Moreover, a simple transfer learning strategy and a multitask learning strategy based on self-supervised descriptors were also employed to further improve the prediction accuracy of the proposed model. Compared with the latest baselines, including one GNN-based predictor and two ML-based predictors, SuperAtomicCharge showed better performance on all the three external test sets and had better usability and portability. Furthermore, the QM partial charges of new molecules predicted by SuperAtomicCharge can be efficiently used in drug design applications such as structure-based virtual screening, where the predicted RESP and DDEC4 charges of new molecules showed more robust scoring and screening power than the commonly used partial charges. Finally, two tools including an online server (http:\/\/cadd.zju.edu.cn\/deepchargepredictor) and the source code command lines (https:\/\/github.com\/zjujdj\/SuperAtomicCharge) were developed for the easy access of the SuperAtomicCharge services.<\/jats:p>","DOI":"10.1093\/bib\/bbab597","type":"journal-article","created":{"date-parts":[[2021,12,24]],"date-time":"2021-12-24T12:07:15Z","timestamp":1640347635000},"source":"Crossref","is-referenced-by-count":13,"title":["Out-of-the-box deep learning prediction of quantum-mechanical partial charges by graph representation and transfer learning"],"prefix":"10.1093","volume":"23","author":[{"given":"Dejun","family":"Jiang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China"},{"name":"Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China"},{"name":"Tencent Quantum Laboratory, Tencent, Shenzhen 518057, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7107-7481","authenticated-orcid":false,"given":"Huiyong","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Medicinal Chemistry, China Pharmaceutical University, Nanjing 210009, Jiangsu, China"}]},{"given":"Jike","family":"Wang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Institute, National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan 430072, Hubei, China"}]},{"given":"Chang-Yu","family":"Hsieh","sequence":"additional","affiliation":[{"name":"Tencent Quantum Laboratory, Tencent, Shenzhen 518057, Guangdong, China"}]},{"given":"Yuquan","family":"Li","sequence":"additional","affiliation":[{"name":"College of Chemistry and Chemical Engineering, Lanzhou University, Lanzhou 730000, China"}]},{"given":"Zhenxing","family":"Wu","sequence":"additional","affiliation":[{"name":"Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3604-3785","authenticated-orcid":false,"given":"Dongsheng","family":"Cao","sequence":"additional","affiliation":[{"name":"Xiangya School of Pharmaceutical Sciences, Central South University, Changsha 410004, Hunan, China"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China"},{"name":"Department of Ophthalmology of the Second Affiliated Hospital School of Medicine, and School of Public Health, Zhejiang University, Hangzhou 310058, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7227-2580","authenticated-orcid":false,"given":"Tingjun","family":"Hou","sequence":"additional","affiliation":[{"name":"Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China"}]}],"member":"286","published-online":{"date-parts":[[2022,1,22]]},"reference":[{"key":"2022031506310363900_ref1","doi-asserted-by":"crossref","DOI":"10.3389\/fgene.2019.00990","article-title":"ContraDRG: automatic partial charge prediction by machine learning","volume":"10","author":"Martin","year":"2019","journal-title":"Front Genet"},{"key":"2022031506310363900_ref2","doi-asserted-by":"crossref","first-page":"W591","DOI":"10.1093\/nar\/gkaa367","article-title":"Atomic charge calculator II: web-based tool for the calculation of partial atomic charges","volume":"48","author":"Racek","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2022031506310363900_ref3","doi-asserted-by":"crossref","first-page":"10269","DOI":"10.1021\/j100142a004","article-title":"A well-behaved electrostatic potential based method using charge restraints for deriving atomic charges: the RESP model","volume":"97","author":"Bayly","year":"1993","journal-title":"J Phys Chem"},{"key":"2022031506310363900_ref4","doi-asserted-by":"crossref","first-page":"8408","DOI":"10.1021\/jp404160y","article-title":"Assessing the performance of MM\/PBSA and MM\/GBSA methods. 3. The impact of force fields and ligand charge models","volume":"117","author":"Xu","year":"2013","journal-title":"J Phys Chem B"},{"key":"2022031506310363900_ref5","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1021\/acs.jcim.7b00663","article-title":"Machine learning of partial charges derived from high-quality quantum-mechanical calculations","volume":"58","author":"Bleiziffer","year":"2018","journal-title":"J Chem Inf Model"},{"key":"2022031506310363900_ref6","doi-asserted-by":"crossref","first-page":"3219","DOI":"10.1016\/0040-4020(80)80168-2","article-title":"Iterative partial equalization of orbital electronegativity\u2014a rapid access to atomic charges","volume":"36","author":"Gasteiger","year":"1980","journal-title":"Tetrahedron"},{"key":"2022031506310363900_ref7","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1002\/jcc.10128","article-title":"Fast, efficient generation of high-quality atomic charges. AM1-BCC model: II. Parameterization and validation","volume":"23","author":"Jakalian","year":"2002","journal-title":"J Comput Chem"},{"key":"2022031506310363900_ref8","article-title":"DeepAtomicCharge: a new graph convolutional network-based architecture for accurate prediction of atomic charges","volume":"22","author":"Wang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2022031506310363900_ref9","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btaa566","article-title":"Fast and accurate prediction of partial charges using atom-path-descriptor-based machine learning","volume":"36","author":"Wang","year":"2020","journal-title":"Bioinformatics"},{"key":"2022031506310363900_ref10","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1002\/cphc.202000040","article-title":"The atomic partial charges arboretum: trying to see the Forest for the trees","volume":"21","author":"Cho","year":"2020","journal-title":"ChemPhysChem"},{"key":"2022031506310363900_ref11","doi-asserted-by":"crossref","first-page":"3361","DOI":"10.1021\/acs.jcim.0c00273","article-title":"High-precision atomic charge prediction for protein systems using fragment molecular orbital calculation and machine learning","volume":"60","author":"Kato","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2022031506310363900_ref12","doi-asserted-by":"crossref","first-page":"1661","DOI":"10.1002\/jcc.23308","article-title":"Fast and accurate generation of ab initio quality atomic charges using nonparametric statistical regression","volume":"34","author":"Rai","year":"2013","journal-title":"J Comput Chem"},{"key":"2022031506310363900_ref13","doi-asserted-by":"crossref","first-page":"4495","DOI":"10.1021\/acs.jpclett.8b01939","article-title":"Discovering a transferable charge assignment model using machine learning","volume":"9","author":"Sifain","year":"2018","journal-title":"J Phys Chem Lett"},{"key":"2022031506310363900_ref14","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1039\/C9RA09337K","article-title":"Atomic partial charge predictions for furanoses by random forest regression with atom type symmetry function","volume":"10","author":"Wang","year":"2020","journal-title":"RSC Adv"},{"key":"2022031506310363900_ref15","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/s13321-020-00479-8","article-title":"Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models","volume":"13","author":"Jiang","year":"2021","journal-title":"J Cheminform"},{"key":"2022031506310363900_ref16","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","author":"Duvenaud","year":"2015","journal-title":"Adv Neural Inform Process Syst"},{"key":"2022031506310363900_ref17","article-title":"InteractionNet: Modeling and explaining of noncovalent protein-ligand interactions with noncovalent graph neural network and layer-wise relevance propagation","volume":"13438","author":"Cho","year":"2020","journal-title":"arXiv preprint arXiv:2005"},{"key":"2022031506310363900_ref18","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/0022-2860(92)85020-H","article-title":"Ab initio Hartree\u2014Fock and post-Hartree\u2014Fock studies on molecular structures and vibrational spectra of formamide and formamidic acid","volume":"270","author":"Kwiatkowski","year":"1992","journal-title":"J Mol Struct"},{"key":"2022031506310363900_ref19","article-title":"TrimNet: learning molecular representation from triplet messages for biomedicine","volume":"22","author":"Li","year":"2021","journal-title":"Brief Bioinform"},{"key":"2022031506310363900_ref20","doi-asserted-by":"crossref","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","volume":"63","author":"Xiong","year":"2019","journal-title":"J Med Chem"},{"key":"2022031506310363900_ref21","doi-asserted-by":"crossref","first-page":"8683","DOI":"10.1021\/acs.jmedchem.9b02147","article-title":"Transfer learning for drug discovery","volume":"63","author":"Cai","year":"2020","journal-title":"J Med Chem"},{"key":"2022031506310363900_ref22","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s13321-020-0413-0","article-title":"Evaluation of deep and shallow learning methods in chemogenomics for the prediction of drugs specificity","volume":"12","author":"Playe","year":"2020","journal-title":"J Chem"},{"key":"2022031506310363900_ref23","first-page":"12265","article-title":"Strategies for pre-training graph neural networks","volume":"1905","author":"Hu","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"2022031506310363900_ref24","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab152","article-title":"MG-BERT: leveraging unsupervised atomic representation learning for molecular property prediction","volume":"22","author":"Zhang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2022031506310363900_ref25","first-page":"12473","article-title":"Pre-training of graph neural network for Modeling effects of mutations on protein-protein binding affinity","volume":"2008","author":"Liu","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"2022031506310363900_ref26","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1021\/acs.accounts.6b00491","article-title":"Forging the basis for developing protein\u2013ligand interaction scoring functions","volume":"50","author":"Liu","year":"2017","journal-title":"Acc Chem Res"},{"key":"2022031506310363900_ref27","doi-asserted-by":"crossref","first-page":"2977","DOI":"10.1021\/jm030580l","article-title":"The PDBbind database: collection of binding affinities for protein\u2212 ligand complexes with known three-dimensional structures","volume":"47","author":"Wang","year":"2004","journal-title":"J Med Chem"},{"key":"2022031506310363900_ref28","doi-asserted-by":"crossref","first-page":"4336","DOI":"10.1021\/acs.molpharmaceut.8b00110","article-title":"Prediction of human cytochrome P450 inhibition using a multitask deep autoencoder neural network","volume":"15","author":"Li","year":"2018","journal-title":"Mol Pharm"},{"key":"2022031506310363900_ref29","first-page":"1","article-title":"ADMET evaluation in drug discovery. 20. Prediction of breast cancer resistance protein inhibition through machine learning, journal of","volume":"12","author":"Jiang","year":"2020","journal-title":"Chem"},{"key":"2022031506310363900_ref30","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1021\/acs.jcim.0c01224","article-title":"Transferable multilevel attention neural network for accurate prediction of quantum chemistry properties via multitask learning","volume":"61","author":"Liu","year":"2021","journal-title":"J Chem Inf Model"},{"key":"2022031506310363900_ref31","doi-asserted-by":"crossref","first-page":"5150","DOI":"10.1021\/acsomega.9b04162","article-title":"graphDelta: MPNN scoring function for the affinity prediction of protein\u2013ligand complexes","volume":"5","author":"Karlov","year":"2020","journal-title":"ACS omega"},{"key":"2022031506310363900_ref32","doi-asserted-by":"crossref","first-page":"3192","DOI":"10.1039\/C6SC05720A","article-title":"ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost","volume":"8","author":"Smith","year":"2017","journal-title":"Chem Sci"},{"key":"2022031506310363900_ref33","doi-asserted-by":"crossref","first-page":"6924","DOI":"10.1021\/acs.jmedchem.1c00421","article-title":"Mining toxicity information from large amounts of toxicity data","volume":"64","author":"Wu","year":"2021","journal-title":"J Med Chem"},{"key":"2022031506310363900_ref34","doi-asserted-by":"crossref","first-page":"8835","DOI":"10.1021\/acs.jmedchem.9b02187","article-title":"Improvement in ADMET prediction with multitask deep Featurization","volume":"63","author":"Feinberg","year":"2020","journal-title":"J Med Chem"},{"key":"2022031506310363900_ref35","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btab389","article-title":"DeepChargePredictor: a web server for predicting QM-based atomic charges via state-of-the-art machine-learning algorithms","volume":"37","author":"Wang","year":"2021","journal-title":"Bioinformatics"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/23\/2\/bbab597\/42806138\/bbab597.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/23\/2\/bbab597\/42806138\/bbab597.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T11:51:20Z","timestamp":1674215480000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbab597\/6513729"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,22]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,3,10]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbab597","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,3]]},"published":{"date-parts":[[2022,1,22]]},"article-number":"bbab597"}}