{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T22:50:07Z","timestamp":1775170207595,"version":"3.50.1"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371245"],"award-info":[{"award-number":["62371245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Deep graph learning (DGL) has been widely employed in the realm of ligand-based virtual screening. Within this field, a key hurdle is the existence of activity cliffs (ACs), where minor chemical alterations can lead to significant changes in bioactivity. In response, several DGL models have been developed to enhance ligand bioactivity prediction in the presence of ACs. Yet, there remains a largely unexplored opportunity within ACs for optimizing ligand bioactivity, making it an area ripe for further investigation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present a novel approach to simultaneously predict and optimize ligand bioactivities through DGL and ACs (OLB-AC). OLB-AC possesses the capability to optimize ligand molecules located near ACs, providing a direct reference for optimizing ligand bioactivities with the matching of original ligands. To accomplish this, a novel attentive graph reconstruction neural network and ligand optimization scheme are proposed. Attentive graph reconstruction neural network reconstructs original ligands and optimizes them through adversarial representations derived from their bioactivity prediction process. Experimental results on nine drug targets reveal that out of the 667 molecules generated through OLB-AC optimization on datasets comprising 974 low-activity, noninhibitor, or highly toxic ligands, 49 are recognized as known highly active, inhibitor, or nontoxic ligands beyond the datasets\u2019 scope. The 27 out of 49 matched molecular pairs generated by OLB-AC reveal novel transformations not present in their training sets. The adversarial representations employed for ligand optimization originate from the gradients of bioactivity predictions. Therefore, we also assess OLB-AC\u2019s prediction accuracy across 33 different bioactivity datasets. Results show that OLB-AC achieves the best Pearson correlation coefficient (r2) on 27\/33 datasets, with an average improvement of 7.2%\u201322.9% against the state-of-the-art bioactivity prediction methods.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The code and dataset developed in this work are available at github.com\/Yueming-Yin\/OLB-AC.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae365","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T18:20:24Z","timestamp":1718734824000},"source":"Crossref","is-referenced-by-count":3,"title":["OLB-AC: toward optimizing ligand bioactivities through deep graph learning and activity cliffs"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9060-3248","authenticated-orcid":false,"given":"Yueming","family":"Yin","sequence":"first","affiliation":[{"name":"School of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications , Nanjing 210003, China"},{"name":"College of Computing and Data Science, Nanyang Technological University , 639798, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6585-3106","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications , Nanjing 210003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jitao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications , Nanjing 210003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications , Nanjing 210003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3863-7501","authenticated-orcid":false,"given":"Wilson Wen Bin","family":"Goh","sequence":"additional","affiliation":[{"name":"Lee Kong Chian School of Medicine, Nanyang Technological University , 637551, Singapore"},{"name":"School of Biological Sciences, Nanyang Technological University , 637551, Singapore"},{"name":"Center for Biomedical Informatics, Nanyang Technological University , 637551, Singapore"},{"name":"Center for AI in Medicine, Nanyang Technological University , 639798, Singapore"},{"name":"Division of Neurology, Department of Brain Sciences, Faculty of Medicine, Imperial College London , London W12 0NN, U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adams Wai-Kin","family":"Kong","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University , 639798, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7941-9722","authenticated-orcid":false,"given":"Jiansheng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications , Nanjing 210023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,6,18]]},"reference":[{"key":"2024062706312419100_btae365-B1","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1080\/17460441.2017.1353494","article-title":"Representation and identification of activity cliffs","volume":"12","author":"Bajorath","year":"2017","journal-title":"Expert Opin Drug Discov"},{"key":"2024062706312419100_btae365-B2","doi-asserted-by":"crossref","first-page":"3035","DOI":"10.1093\/bioinformatics\/btv302","article-title":"Glass: a comprehensive database for experimentally validated gpcr-ligand associations","volume":"31","author":"Chan","year":"2015","journal-title":"Bioinformatics"},{"key":"2024062706312419100_btae365-B3","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1016\/j.drudis.2014.02.003","article-title":"Activity cliffs in drug discovery: Dr Jekyll or Mr Hyde?","volume":"19","author":"Cruz-Monteagudo","year":"2014","journal-title":"Drug Discov Today"},{"key":"2024062706312419100_btae365-B4","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1186\/s13321-023-00708-w","article-title":"Exploring QSAR models for activity-cliff prediction","volume":"15","author":"Dablander","year":"2023","journal-title":"J Cheminform"},{"key":"2024062706312419100_btae365-B5","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1021\/acs.jcim.8b00173","article-title":"Mmpdb: an open-source matched molecular pair platform for large multiproperty data sets","volume":"58","author":"Dalke","year":"2018","journal-title":"J Chem Inf Model"},{"key":"2024062706312419100_btae365-B6","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1002\/minf.201600023","article-title":"Advances in activity cliff research","volume":"35","author":"Dimova","year":"2016","journal-title":"Mol Inform"},{"key":"2024062706312419100_btae365-B7","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/s13321-018-0283-x","article-title":"Admetlab: a platform for systematic admet evaluation based on a comprehensively collected admet database","volume":"10","author":"Dong","year":"2018","journal-title":"J Cheminform"},{"key":"2024062706312419100_btae365-B8","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume":"28","author":"Duvenaud","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024062706312419100_btae365-B34","author":"EPA","year":"2001","journal-title":"Quality assurance guidance document-model quality assurance project plan for the PM ambient air"},{"key":"2024062706312419100_btae365-B9","first-page":"1263","author":"Gilmer","year":"2017"},{"key":"2024062706312419100_btae365-B10","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/s13321-021-00497-0","article-title":"Molecular optimization by capturing chemist\u2019s intuition using deep neural networks","volume":"13","author":"He","year":"2021","journal-title":"J Cheminform"},{"key":"2024062706312419100_btae365-B11","doi-asserted-by":"crossref","first-page":"796534","DOI":"10.3389\/fphar.2021.796534","article-title":"Machine learning enables accurate and rapid prediction of active molecules against breast cancer cells","volume":"12","author":"He","year":"2021","journal-title":"Front Pharmacol"},{"key":"2024062706312419100_btae365-B12","author":"Hu"},{"key":"2024062706312419100_btae365-B13","doi-asserted-by":"crossref","first-page":"1157","DOI":"10.1007\/s10822-021-00380-y","article-title":"Prediction of activity cliffs on the basis of images using convolutional neural networks","volume":"35","author":"Iqbal","year":"2021","journal-title":"J Comput Aided Mol Des"},{"key":"2024062706312419100_btae365-B14","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.sbi.2019.03.022","article-title":"Applications of machine learning in gpcr bioactive ligand discovery","volume":"55","author":"Jabeen","year":"2019","journal-title":"Curr Opin Struct Biol"},{"key":"2024062706312419100_btae365-B15","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":"2024062706312419100_btae365-B16","doi-asserted-by":"crossref","first-page":"D1388","DOI":"10.1093\/nar\/gkaa971","article-title":"Pubchem in 2021: new data content and improved web interfaces","volume":"49","author":"Kim","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024062706312419100_btae365-B17","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/s10822-014-9719-1","article-title":"Impact of distance-based metric learning on classification and visualization model performance and structure\u2013activity landscapes","volume":"28","author":"Kireeva","year":"2014","journal-title":"J Comput Aided Mol Des"},{"key":"2024062706312419100_btae365-B18","doi-asserted-by":"crossref","first-page":"5044","DOI":"10.1109\/JBHI.2021.3089162","article-title":"3dmol-net: learn 3d molecular representation using adaptive graph convolutional network based on rotation invariance","volume":"26","author":"Li","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"key":"2024062706312419100_btae365-B19","first-page":"857","author":"Li","year":"2022"},{"key":"2024062706312419100_btae365-B20","doi-asserted-by":"crossref","first-page":"103373","DOI":"10.1016\/j.drudis.2022.103373","article-title":"Deep learning methods for molecular representation and property prediction","volume":"27","author":"Li","year":"2022","journal-title":"Drug Discov Today"},{"key":"2024062706312419100_btae365-B21","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1021\/acs.chemrestox.0c00322","article-title":"Deep graph learning with property augmentation for predicting drug-induced liver injury","volume":"34","author":"Ma","year":"2020","journal-title":"Chem Res Toxicol"},{"key":"2024062706312419100_btae365-B22","doi-asserted-by":"crossref","first-page":"D930","DOI":"10.1093\/nar\/gky1075","article-title":"Chembl: towards direct deposition of bioassay data","volume":"47","author":"Mendez","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2024062706312419100_btae365-B23","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1016\/j.bbagen.2017.01.024","article-title":"Tandem application of ligand-based virtual screening and g4-oas assay to identify novel g-quadruplex-targeting chemotypes","volume":"1861","author":"Musumeci","year":"2017","journal-title":"Biochim Biophys Acta Gen Subj"},{"key":"2024062706312419100_btae365-B24","first-page":"3555","author":"Rong","year":"2020"},{"key":"2024062706312419100_btae365-B25","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1038\/s41586-023-05905-z","article-title":"Computational approaches streamlining drug discovery","volume":"616","author":"Sadybekov","year":"2023","journal-title":"Nature"},{"key":"2024062706312419100_btae365-B26","first-page":"100062","article-title":"Deep graph learning in molecular docking: advances and opportunities","volume":"3","author":"S\u00e1nchez-Cruz","year":"2023","journal-title":"Artif Intell Life Sci"},{"key":"2024062706312419100_btae365-B27","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41598-017-18315-9","article-title":"Predicting inhibitory and activatory drug targets by chemically and genetically perturbed transcriptome signatures","volume":"8","author":"Sawada","year":"2018","journal-title":"Sci Rep"},{"key":"2024062706312419100_btae365-B28","article-title":"Online triplet contrastive learning enables efficient cliff awareness in molecular activity prediction","volume-title":"ChemRxiv","author":"Shen","year":"2023"},{"key":"2024062706312419100_btae365-B29","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.3390\/biom12081053","article-title":"Graphsite: ligand binding site classification with deep graph learning","volume":"12","author":"Shi","year":"2022","journal-title":"Biomolecules"},{"key":"2024062706312419100_btae365-B30","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1021\/ci400141w","article-title":"Compound pathway model to capture sar progression: comparison of activity cliff-dependent and-independent pathways","volume":"53","author":"Stumpfe","year":"2013","journal-title":"J Chem Inf Model"},{"key":"2024062706312419100_btae365-B31","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1021\/jm401120g","article-title":"Recent progress in understanding activity cliffs and their utility in medicinal chemistry: miniperspective","volume":"57","author":"Stumpfe","year":"2014","journal-title":"J Med Chem"},{"key":"2024062706312419100_btae365-B32","doi-asserted-by":"crossref","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":"2024062706312419100_btae365-B33","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/s10822-011-9440-2","article-title":"Online chemical modeling environment (ochem): web platform for data storage, model development and publishing of chemical information","volume":"25","author":"Sushko","year":"2011","journal-title":"J Comput Aided Mol Des"},{"key":"2024062706312419100_btae365-B35","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2024062706312419100_btae365-B36","author":"Veli\u010dkovi\u0107"},{"key":"2024062706312419100_btae365-B37","doi-asserted-by":"crossref","first-page":"1600118","DOI":"10.1002\/minf.201600118","article-title":"Performance of deep and shallow neural networks, the universal approximation theorem, activity cliffs, and QSAR","volume":"36","author":"Winkler","year":"2017","journal-title":"Mol Inform"},{"key":"2024062706312419100_btae365-B38","doi-asserted-by":"crossref","first-page":"i324","DOI":"10.1093\/bioinformatics\/btz336","article-title":"Precise modelling and interpretation of bioactivities of ligands targeting g protein-coupled receptors","volume":"35","author":"Wu","year":"2019","journal-title":"Bioinformatics"},{"key":"2024062706312419100_btae365-B39","doi-asserted-by":"crossref","first-page":"W5","DOI":"10.1093\/nar\/gkab255","article-title":"Admetlab 2.0: an integrated online platform for accurate and comprehensive predictions of admet properties","volume":"49","author":"Xiong","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024062706312419100_btae365-B40","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":"2024062706312419100_btae365-B41","author":"Xu"},{"key":"2024062706312419100_btae365-B42","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1093\/bib\/bbaa422","article-title":"Ligand-based approach for predicting drug targets and for virtual screening against covid-19","volume":"22","author":"Yang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024062706312419100_btae365-B43","doi-asserted-by":"crossref","first-page":"4924","DOI":"10.1021\/acs.jcim.1c01021","article-title":"Realvs: toward enhancing the precision of top hits in ligand-based virtual screening of drug leads from large compound databases","volume":"61","author":"Yin","year":"2021","journal-title":"J Chem Inf Model"},{"key":"2024062706312419100_btae365-B44","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.neucom.2021.05.023","article-title":"Metric-learning-assisted domain adaptation","volume":"454","author":"Yin","year":"2021","journal-title":"Neurocomputing"},{"key":"2024062706312419100_btae365-B45","doi-asserted-by":"crossref","first-page":"107315","DOI":"10.1016\/j.knosys.2021.107315","article-title":"Pseudo-margin-based universal domain adaptation","volume":"229","author":"Yin","year":"2021","journal-title":"Knowledge-Based Systems"},{"key":"2024062706312419100_btae365-B46","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac077","article-title":"Afse: towards improving model generalization of deep graph learning of ligand bioactivities targeting gpcr proteins","volume":"23","author":"Yin","year":"2022","journal-title":"Brief Bioinform"},{"key":"2024062706312419100_btae365-B47","doi-asserted-by":"crossref","first-page":"108238","DOI":"10.1016\/j.patcog.2021.108238","article-title":"Universal multi-source domain adaptation for image classification","volume":"121","author":"Yin","year":"2022","journal-title":"Pattern Recognition"},{"key":"2024062706312419100_btae365-B48","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.csbj.2020.02.008","article-title":"Exploring the computational methods for protein-ligand binding site prediction","volume":"18","author":"Zhao","year":"2020","journal-title":"Comput Struct Biotechnol J"},{"key":"2024062706312419100_btae365-B49","author":"Zhou"},{"key":"2024062706312419100_btae365-B50","first-page":"79667","article-title":"Sample-efficient multi-objective molecular optimization with gflownets","volume":"36","author":"Zhu","year":"2024","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae365\/58272252\/btae365.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/6\/btae365\/58343469\/btae365.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/6\/btae365\/58343469\/btae365.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T07:05:54Z","timestamp":1719471954000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae365\/7695868"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":50,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,6,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae365","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,6]]},"published":{"date-parts":[[2024,6]]},"article-number":"btae365"}}