{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T22:04:16Z","timestamp":1774044256542,"version":"3.50.1"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T00:00:00Z","timestamp":1655164800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Alibaba Innovative Research Program"},{"name":"Alibaba-NTU Singapore Joint Research Institute","award":["AN-GC-2020-002"],"award-info":[{"award-number":["AN-GC-2020-002"]}]},{"name":"Singapore Ministry of Education Academic Research Fund Tier 1","award":["RG109\/19"],"award-info":[{"award-number":["RG109\/19"]}]},{"name":"Singapore Ministry of Education Academic Research Fund Tier 2","award":["MOE-T2EP20220-0010"],"award-info":[{"award-number":["MOE-T2EP20220-0010"]}]},{"name":"Singapore Ministry of Education Academic Research Fund Tier 2","award":["MOE-T2EP20120-0013"],"award-info":[{"award-number":["MOE-T2EP20120-0013"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Graph neural networks (GNNs) are the most promising deep learning models that can revolutionize non-Euclidean data analysis. However, their full potential is severely curtailed by poorly represented molecular graphs and features. Here, we propose a multiphysical graph neural network (MP-GNN) model based on the developed multiphysical molecular graph representation and featurization. All kinds of molecular interactions, between different atom types and at different scales, are systematically represented by a series of scale-specific and element-specific graphs with distance-related node features. From these graphs, graph convolution network (GCN) models are constructed with specially designed weight-sharing architectures. Base learners are constructed from GCN models from different elements at different scales, and further consolidated together using both one-scale and multi-scale ensemble learning schemes. Our MP-GNN has two distinct properties. First, our MP-GNN incorporates multiscale interactions using more than one molecular graph. Atomic interactions from various different scales are not modeled by one specific graph (as in traditional GNNs), instead they are represented by a series of graphs at different scales. Second, it is free from the complicated feature generation process as in conventional GNN methods. In our MP-GNN, various atom interactions are embedded into element-specific graph representations with only distance-related node features. A unique GNN architecture is designed to incorporate all the information into a consolidated model. Our MP-GNN has been extensively validated on the widely used benchmark test datasets from PDBbind, including PDBbind-v2007, PDBbind-v2013 and PDBbind-v2016. Our model can outperform all existing models as far as we know. Further, our MP-GNN is used in coronavirus disease 2019 drug design. Based on a dataset with 185 complexes of inhibitors for severe acute respiratory syndrome coronavirus (SARS-CoV\/SARS-CoV-2), we evaluate their binding affinities using our MP-GNN. It has been found that our MP-GNN is of high accuracy. This demonstrates the great potential of our MP-GNN for the screening of potential drugs for SARS-CoV-2. Availability: The Multiphysical graph neural network (MP-GNN) model can be found in https:\/\/github.com\/Alibaba-DAMO-DrugAI\/MGNN. Additional data or code will be available upon reasonable request.<\/jats:p>","DOI":"10.1093\/bib\/bbac231","type":"journal-article","created":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T20:09:57Z","timestamp":1655150997000},"source":"Crossref","is-referenced-by-count":56,"title":["Multiphysical graph neural network (MP-GNN) for COVID-19 drug design"],"prefix":"10.1093","volume":"23","author":[{"given":"Xiao-Shuang","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University , China , 200240"},{"name":"Healthcare Intelligence, AI Center, Alibaba Group DAMO Academy , China , 310000"}]},{"given":"Xiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Chern Institute of Mathematics and LPMC, Nankai University , Tianjin, China , 300071"},{"name":"Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University , Singapore 637371"}]},{"given":"Le","family":"Lu","sequence":"additional","affiliation":[{"name":"Healthcare Intelligence, AI Center, Alibaba Group DAMO Academy , China , 310000"}]},{"given":"Xian-Sheng","family":"Hua","sequence":"additional","affiliation":[{"name":"Healthcare Intelligence, AI Center, Alibaba Group DAMO Academy , China , 310000"}]},{"given":"Ying","family":"Chi","sequence":"additional","affiliation":[{"name":"Healthcare Intelligence, AI Center, Alibaba Group DAMO Academy , China , 310000"}]},{"given":"Kelin","family":"Xia","sequence":"additional","affiliation":[{"name":"Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University , Singapore 637371"}]}],"member":"286","published-online":{"date-parts":[[2022,6,14]]},"reference":[{"issue":"11","key":"2022071906092919300_ref1","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.1016\/j.drudis.2017.08.010","article-title":"From machine learning to deep learning: progress in machine intelligence for rational drug discovery","volume":"22","author":"Zhang","year":"2017","journal-title":"Drug Discov Today"},{"issue":"7","key":"2022071906092919300_ref2","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1021\/ci400187y","article-title":"Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules","volume":"53","author":"Lusci","year":"2013","journal-title":"J Chem Inf Model"},{"issue":"12","key":"2022071906092919300_ref3","doi-asserted-by":"crossref","first-page":"2495","DOI":"10.1021\/acs.jcim.6b00355","article-title":"Boosting docking-based virtual screening with deep learning","volume":"56","author":"Pereira","year":"2016","journal-title":"J Chem Inf Model"},{"issue":"8","key":"2022071906092919300_ref4","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":"2022071906092919300_ref5","article-title":"Atomic convolutional networks for predicting protein-ligand binding affinity","author":"Gomes","year":"2017"},{"issue":"11","key":"2022071906092919300_ref6","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 central science"},{"issue":"2","key":"2022071906092919300_ref7","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1093\/bioinformatics\/bty535","article-title":"Compound\u2013protein interaction prediction with end-to-end learning of neural networks for graphs and sequences","volume":"35","author":"Tsubaki","year":"2019","journal-title":"Bioinformatics"},{"issue":"3","key":"2022071906092919300_ref8","doi-asserted-by":"crossref","first-page":"1044","DOI":"10.1021\/acs.jcim.8b00672","article-title":"Deepchemstable: chemical stability prediction with an attention-based graph convolution network","volume":"59","author":"Li","year":"2019","journal-title":"J Chem Inf Model"},{"issue":"9","key":"2022071906092919300_ref9","doi-asserted-by":"crossref","first-page":"3817","DOI":"10.1021\/acs.jcim.9b00410","article-title":"Molecule property prediction based on spatial graph embedding","volume":"59","author":"Wang","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2022071906092919300_ref10","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.104460","article-title":"AweGNN: Auto-parametrized weighted element-specific graph neural networks for molecules","volume":"134","author":"Szocinski","year":"2021","journal-title":"Comput Biol Med"},{"key":"2022071906092919300_ref11","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1145\/3447548.3467311","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","author":"Li","year":"2021"},{"issue":"8","key":"2022071906092919300_ref12","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"GraphDTA: Predicting drug\u2013target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"2022071906092919300_ref13","article-title":"DeepGS: Deep representation learning of graphs and sequences for drug-target binding affinity prediction","author":"Lin","year":"2020"},{"issue":"35","key":"2022071906092919300_ref14","doi-asserted-by":"crossref","first-page":"20701","DOI":"10.1039\/D0RA02297G","article-title":"Drug-target affinity prediction using graph neural network and contact maps","volume":"10","author":"Jiang","year":"2020","journal-title":"RSC Adv"},{"key":"2022071906092919300_ref15","doi-asserted-by":"crossref","first-page":"267","DOI":"10.3389\/fbioe.2020.00267","article-title":"Dipeptide frequency of word frequency and graph convolutional networks for DTA prediction","volume":"8","author":"Wang","year":"2020","journal-title":"Front Bioeng Biotechnol"},{"issue":"4","key":"2022071906092919300_ref16","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"Zohar Bloom-Ackermann, et al. A deep learning approach to antibiotic discovery","volume":"180","author":"Stokes","year":"2020","journal-title":"Cell"},{"issue":"8","key":"2022071906092919300_ref17","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1009284","article-title":"Deep geometric representations for modeling effects of mutations on protein-protein binding affinity","volume":"17","author":"Liu","year":"2021","journal-title":"PLoS Comput Biol"},{"key":"2022071906092919300_ref18","article-title":"Utilising graph machine learning within drug discovery and development","author":"Gaudelet","year":"05 2021","journal-title":"Brief Bioinform"},{"key":"2022071906092919300_ref19","first-page":"276","article-title":"Persistent homology analysis of biomolecular data","volume":"305","author":"Wei","year":"2017","journal-title":"J Comput Phys"},{"issue":"1","key":"2022071906092919300_ref20","doi-asserted-by":"crossref","DOI":"10.1515\/mlbmb-2017-0009","article-title":"Mathematics at the eve of a historic transition in biology","volume":"5","author":"Wei","year":"2017","journal-title":"Computational and Mathematical Biophysics"},{"issue":"7","key":"2022071906092919300_ref21","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1005690","article-title":"TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions","volume":"13","author":"Cang","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"2022071906092919300_ref22","volume-title":"International journal for numerical methods in biomedical engineering","author":"Cang","year":"2017"},{"issue":"7","key":"2022071906092919300_ref23","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.1021\/acs.jcim.7b00226","article-title":"Rigidity strengthening: A mechanism for protein\u2013ligand binding","volume":"57","author":"Nguyen","year":"2017","journal-title":"J Chem Inf Model"},{"issue":"2","key":"2022071906092919300_ref24","doi-asserted-by":"crossref","DOI":"10.1002\/cnm.2914","article-title":"Integration of element specific persistent homology and machine learning for protein-ligand binding affinity prediction","volume":"34","author":"Cang","year":"2018","journal-title":"International journal for numerical methods in biomedical engineering"},{"issue":"1","key":"2022071906092919300_ref25","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1005929","article-title":"Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening","volume":"14","author":"Cang","year":"2018","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"2022071906092919300_ref26","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/s10822-018-0146-6","article-title":"Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges","volume":"33","author":"Nguyen","year":"2019","journal-title":"J Comput Aided Mol Des"},{"issue":"7","key":"2022071906092919300_ref27","doi-asserted-by":"crossref","first-page":"3291","DOI":"10.1021\/acs.jcim.9b00334","article-title":"AGL-Score: Algebraic graph learning score for protein-ligand binding scoring, ranking, docking, and screening","volume":"59","author":"Nguyen","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2022071906092919300_ref28","article-title":"MathDL: Mathematical deep learning for D3R Grand Challenge 4","volume":"1\u201317","author":"Nguyen","year":"2019","journal-title":"Journal of computer-aided molecular design, pages"},{"key":"2022071906092919300_ref29","article-title":"A review of mathematical representations of biomolecular data","author":"Nguyen","year":"2020","journal-title":"Phys Chem Chem Phys"},{"key":"2022071906092919300_ref30","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4020-9783-6","volume-title":"Recent advances in QSAR studies: methods and applications","author":"Puzyn","year":"2010"},{"issue":"8","key":"2022071906092919300_ref31","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1016\/j.drudis.2018.05.010","article-title":"Machine learning in chemoinformatics and drug discovery","volume":"23","author":"Lo","year":"2018","journal-title":"Drug Discov Today"},{"key":"2022071906092919300_ref32","doi-asserted-by":"crossref","DOI":"10.1385\/1592598021","volume-title":"Chemoinformatics: concepts, methods, and tools for drug discovery","author":"Bajorath","year":"2004"},{"issue":"44","key":"2022071906092919300_ref33","doi-asserted-by":"crossref","first-page":"12036","DOI":"10.1039\/D0SC04641H","article-title":"Unveiling the molecular mechanism of SARS-CoV-2 main protease inhibition from 137 crystal structures using algebraic topology and deep learning","volume":"11","author":"Nguyen","year":"2020","journal-title":"Chem Sci"},{"issue":"3","key":"2022071906092919300_ref34","doi-asserted-by":"crossref","DOI":"10.1002\/cnm.3179","article-title":"DG-GL: Differential geometry-based geometric learning of molecular datasets","volume":"35","author":"Nguyen","year":"2019","journal-title":"International journal for numerical methods in biomedical engineering"},{"issue":"3","key":"2022071906092919300_ref35","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1093\/bioinformatics\/btu626","article-title":"PDB-wide collection of binding data: current status of the PDBbind database","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"key":"2022071906092919300_ref36","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab136","article-title":"Forman persistent ricci curvature (FPRC) based machine learning models for protein-ligand binding affinity prediction","author":"Wee","year":"2021","journal-title":"Briefings in Bioinformatics, in press"},{"key":"2022071906092919300_ref37","first-page":"652","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi","year":"2017"},{"key":"2022071906092919300_ref38","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017"},{"issue":"4","key":"2022071906092919300_ref39","article-title":"Ensemble learning: A survey","volume":"8","author":"Sagi","year":"2018","journal-title":"Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/advance-article-pdf\/doi\/10.1093\/bib\/bbac231\/45017442\/bbac231.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/advance-article-pdf\/doi\/10.1093\/bib\/bbac231\/45017442\/bbac231.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T06:16:17Z","timestamp":1658211377000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbac231\/6607747"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,14]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,7,18]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbac231","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,7,18]]},"published":{"date-parts":[[2022,6,14]]},"article-number":"bbac231"}}