{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T21:33:50Z","timestamp":1776202430426,"version":"3.50.1"},"reference-count":57,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:00:00Z","timestamp":1745625600000},"content-version":"vor","delay-in-days":56,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372314"],"award-info":[{"award-number":["62372314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The accurate categorization of compounds within the anatomical therapeutic chemical (ATC) system is fundamental for drug development and fundamental research. Although this area has garnered significant research focus for over a decade, the majority of prior studies have concentrated solely on the Level 1 labels defined by the World Health Organization (WHO), neglecting the labels of the remaining four levels. This narrow focus fails to address the true nature of the task as a multilevel, multi-label classification challenge. Moreover, existing benchmarks like Chen-2012 and ATC-SMILES have become outdated, lacking the incorporation of new drugs or updated properties of existing ones that have emerged in recent years and have been integrated into the WHO ATC system. To tackle these shortcomings, we present a comprehensive approach in this paper. Firstly, we systematically cleanse and enhance the drug dataset, expanding it to encompass all five levels through a rigorous cross-resource validation process involving KEGG, PubChem, ChEMBL, ChemSpider, and ChemicalBook. This effort culminates in the creation of a novel benchmark termed ATC-GRAPH. Secondly, we extend the classification task to encompass Level 2 and introduce graph-based learning techniques to provide more accurate representations of drug molecular structures. This approach not only facilitates the modeling of Polymers, Macromolecules, and Multi-Component drugs more precisely but also enhances the overall fidelity of the classification process. The efficacy of our proposed framework is validated through extensive experiments, establishing a new state-of-the-art methodology. To facilitate the replication of this study, we have made the benchmark dataset, source code, and web server openly accessible.<\/jats:p>","DOI":"10.1093\/bib\/bbaf194","type":"journal-article","created":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T04:30:54Z","timestamp":1745641854000},"source":"Crossref","is-referenced-by-count":1,"title":["GraphATC: advancing multilevel and multi-label anatomical therapeutic chemical classification via atom-level graph learning"],"prefix":"10.1093","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2347-4183","authenticated-orcid":false,"given":"Wengyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science, Sichuan University , Chengdu 610065 ,","place":["China"]},{"name":"Department of Computing, The Hong Kong Polytechnic University , Kowloon ,","place":["Hong Kong"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Sichuan University , Chengdu 610065 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Sichuan University , Chengdu 610065 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqi","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computing , The Hong Kong Polytechnic University, Kowloon,","place":["Hong Kong"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory , Shenzhen 518000 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory , Shenzhen 518000 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University , Kowloon ,","place":["Hong Kong"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5706-5177","authenticated-orcid":false,"given":"Xiao-Yong","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Sichuan University , Chengdu 610065 ,","place":["China"]},{"name":"Department of Computing, The Hong Kong Polytechnic University , Kowloon ,","place":["Hong Kong"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,4,26]]},"reference":[{"key":"2025042600304487500_ref1","doi-asserted-by":"crossref","first-page":"W55","DOI":"10.1093\/nar\/gkn307","article-title":"Superpred: drug classification and target prediction","volume":"36","author":"Dunkel","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2025042600304487500_ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0035254","article-title":"Predicting anatomical therapeutic chemical (ATC) classification of drugs by integrating chemical\u2013chemical interactions and similarities","volume":"7","author":"Chen","year":"2012","journal-title":"PloS One"},{"key":"2025042600304487500_ref3","doi-asserted-by":"publisher","first-page":"W26","DOI":"10.1093\/nar\/gku477","article-title":"Superpred: update on drug classification and target prediction","volume":"42","author":"Nickel","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2025042600304487500_ref4","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1039\/c3mb70490d","article-title":"A hybrid method for prediction and repositioning of drug anatomical therapeutic chemical classes","volume":"10","author":"Chen","year":"2014","journal-title":"Mol Biosyst"},{"key":"2025042600304487500_ref5","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1093\/bioinformatics\/btw644","article-title":"iATC-mISF: a multi-label classifier for predicting the classes of anatomical therapeutic chemicals","volume":"33","author":"Cheng","year":"2017","journal-title":"Bioinformatics"},{"key":"2025042600304487500_ref6","doi-asserted-by":"publisher","first-page":"58494","DOI":"10.18632\/oncotarget.17028","article-title":"iATC-mHyb: a hybrid multi-label classifier for predicting the classification of anatomical therapeutic chemicals","volume":"8","author":"Cheng","year":"2017","journal-title":"Oncotarget"},{"key":"2025042600304487500_ref7","doi-asserted-by":"publisher","first-page":"2837","DOI":"10.1093\/bioinformatics\/btx278","article-title":"Multi-label classifier based on histogram of gradients for predicting the anatomical therapeutic chemical class\/classes of a given compound","volume":"33","author":"Nanni","year":"2017","journal-title":"Bioinformatics"},{"key":"2025042600304487500_ref8","doi-asserted-by":"crossref","first-page":"4007","DOI":"10.2174\/1381612824666181112113438","article-title":"Convolutional neural networks for ATC classification","volume":"24","author":"Lumini","year":"2018","journal-title":"Curr Pharm Des"},{"key":"2025042600304487500_ref9","doi-asserted-by":"publisher","first-page":"2228","DOI":"10.1016\/j.bbadis.2017.12.019","article-title":"Inferring anatomical therapeutic chemical (ATC) class of drugs using shortest path and random walk with restart algorithms","volume":"1864","author":"Chen","year":"2018","journal-title":"Biochim Biophys Acta, Mol Basis Dis"},{"key":"2025042600304487500_ref10","doi-asserted-by":"publisher","first-page":"971","DOI":"10.3389\/fphar.2019.00971","article-title":"ATC-NLSP: prediction of the classes of anatomical therapeutic chemicals using a network-based label space partition method","volume":"10","author":"Wang","year":"2019","journal-title":"Front Pharmacol"},{"key":"2025042600304487500_ref11","first-page":"117","article-title":"Ensemble of deep learning approaches for ATC classification","volume-title":"Smart Intelligent Computing and Applications: Proceedings of the Third International Conference on Smart Computing and Informatics","author":"Nanni","year":":  , 2019"},{"key":"2025042600304487500_ref12","doi-asserted-by":"crossref","first-page":"153","DOI":"10.4236\/abb.2020.115012","article-title":"iATC_Deep-mISF: a multi-label classifier for predicting the classes of anatomical therapeutic chemicals by deep learning","volume":"11","author":"Zhe","year":"2020","journal-title":"Advances in Bioscience and Biotechnology"},{"key":"2025042600304487500_ref13","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.1093\/bioinformatics\/btz757","article-title":"iATC-NRAKEL: an efficient multi-label classifier for recognizing anatomical therapeutic chemical classes of drugs","volume":"36","author":"Zhou","year":"2020","journal-title":"Bioinformatics"},{"key":"2025042600304487500_ref14","doi-asserted-by":"publisher","first-page":"3568","DOI":"10.1093\/bioinformatics\/btaa166","article-title":"iATC-FRAKEL: a simple multi-label web server for recognizing anatomical therapeutic chemical classes of drugs with their fingerprints only","volume":"36","author":"Zhou","year":"2020","journal-title":"Bioinformatics"},{"key":"2025042600304487500_ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbadis.2020.165910","article-title":"Recognizing novel chemicals\/drugs for anatomical therapeutic chemical classes with a heat diffusion algorithm","volume":"1866","author":"Liang","year":"2020","journal-title":"Biochim Biophys Acta, Mol Basis Dis"},{"key":"2025042600304487500_ref16","doi-asserted-by":"publisher","first-page":"2841","DOI":"10.1093\/bioinformatics\/btab204","article-title":"A convolutional neural network and graph convolutional network-based method for predicting the classification of anatomical therapeutic chemicals","volume":"37","author":"Zhao","year":"2021","journal-title":"Bioinformatics"},{"key":"2025042600304487500_ref17","doi-asserted-by":"crossref","first-page":"bbab289","DOI":"10.1093\/bib\/bbab289","article-title":"Deep fusion learning facilitates anatomical therapeutic chemical recognition in drug repurposing and discovery","volume":"22","author":"Wang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025042600304487500_ref18","article-title":"DACPGTN: drug ATC code prediction method based on graph transformer network for drug discovery","volume":"13","author":"Yan","year":"2022","journal-title":"Front Pharmacol"},{"key":"2025042600304487500_ref19","article-title":"Neural networks for anatomical therapeutic chemical (ATC) classification","author":"Nanni","year":"2022","journal-title":"Appl Comput Inf"},{"key":"2025042600304487500_ref20","doi-asserted-by":"crossref","first-page":"bbac346","DOI":"10.1093\/bib\/bbac346","article-title":"Identifying the kind behind smiles\u2013anatomical therapeutic chemical classification using structure-only representations","volume":"23","author":"Cao","year":"2022","journal-title":"Brief Bioinform"},{"key":"2025042600304487500_ref21","doi-asserted-by":"publisher","first-page":"1986","DOI":"10.1021\/ci9000844","article-title":"Concept-based semi-automatic classification of drugs","volume":"49","author":"Gurulingappa","year":"2009","journal-title":"J Chem Inf Model"},{"key":"2025042600304487500_ref22","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.1021\/ci400155x","article-title":"Relating anatomical therapeutic indications by the ensemble similarity of drug sets","volume":"53","author":"Leihong","year":"2013","journal-title":"J Chem Inf Model"},{"key":"2025042600304487500_ref23","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1093\/bioinformatics\/btt158","article-title":"Network predicting drug\u2019s anatomical therapeutic chemical code","volume":"29","author":"Wang","year":"2013","journal-title":"Bioinformatics"},{"key":"2025042600304487500_ref24","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.jbi.2015.09.016","article-title":"Prediction of drug\u2019s anatomical therapeutic chemical (ATC) code by integrating drug\u2013domain network","volume":"58","author":"Chen","year":"2015","journal-title":"J Biomed Inform"},{"key":"2025042600304487500_ref25","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1093\/bioinformatics\/btv055","article-title":"Similarity-based prediction for anatomical therapeutic chemical classification of drugs by integrating multiple data sources","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"key":"2025042600304487500_ref26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-017-1660-6","article-title":"Predicting anatomic therapeutic chemical classification codes using tiered learning","volume":"18","author":"Olson","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2025042600304487500_ref27","article-title":"RNPredATC: a deep residual learning-based model with applications to the prediction of drug-ATC code association","volume":"20","author":"Zhao","year":"2021","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2025042600304487500_ref28","doi-asserted-by":"publisher","first-page":"2058","DOI":"10.1093\/bib\/bbaa027","article-title":"Drug repositioning by prediction of drug\u2019s anatomical therapeutic chemical code via network-based inference approaches","volume":"22","author":"Peng","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025042600304487500_ref29","doi-asserted-by":"publisher","first-page":"107862","DOI":"10.1016\/j.compbiomed.2023.107862","article-title":"PDATC-NCPMKL: predicting drug\u2019s anatomical therapeutic chemical (ATC) codes based on network consistency projection and multiple kernel learning","volume":"169","author":"Chen","year":"2024","journal-title":"Comput Biol Med"},{"key":"2025042600304487500_ref30","doi-asserted-by":"publisher","first-page":"D380","DOI":"10.1093\/nar\/gkv1277","article-title":"STITCH 5: augmenting protein\u2013chemical interaction networks with tissue and affinity data","volume":"44","author":"Szklarczyk","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2025042600304487500_ref31","volume-title":"RDKit: Open-Source Cheminformatics","author":"European Bioinformatics Institute","year":"2024"},{"key":"2025042600304487500_ref32","doi-asserted-by":"crossref","first-page":"W652","DOI":"10.1093\/nar\/gkq367","article-title":"SIMCOMP\/SUBCOMP: chemical structure search servers for network analyses","volume":"38","author":"Hattori","year":"2010","journal-title":"Nucleic Acids Res"},{"key":"2025042600304487500_ref33","volume-title":"Simplified Molecular-Input Line-Entry System","author":"Wikipedia contributors","year":"2024"},{"key":"2025042600304487500_ref34","doi-asserted-by":"publisher","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"},{"key":"2025042600304487500_ref35","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume":"28","author":"Duvenaud","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"2025042600304487500_ref36","doi-asserted-by":"publisher","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":"2025042600304487500_ref37","volume-title":"Chemical Table File","author":"Wikipedia contributors","year":"2024"},{"key":"2025042600304487500_ref38","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1093\/nar\/27.1.29","article-title":"KEGG: Kyoto encyclopedia of genes and genomes","volume":"27","author":"Ogata","year":"1999","journal-title":"Nucleic Acids Res"},{"key":"2025042600304487500_ref39","doi-asserted-by":"publisher","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","article-title":"Pubchem 2023 update","volume":"51","author":"Kim","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2025042600304487500_ref40","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL: a large-scale bioactivity database for drug discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2025042600304487500_ref41","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.jtbi.2010.12.024","article-title":"Some remarks on protein attribute prediction and pseudo amino acid composition","volume":"273","author":"Chou","year":"2011","journal-title":"J Theor Biol"},{"key":"2025042600304487500_ref42","author":"Internet Archive","year":"2024"},{"key":"2025042600304487500_ref43","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"2025042600304487500_ref44","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Advances in Neural Information Processing Systems, NIPS\u201917","author":"Hamilton","year":"2017"},{"key":"2025042600304487500_ref45","article-title":"Graph attention networks","volume-title":"International Conference on Learning Representations","author":"Velickovic","year":"2018"},{"key":"2025042600304487500_ref46","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1021\/acspolymersau.1c00050","article-title":"Prediction and interpretation of polymer properties using the graph convolutional network","volume":"2","author":"Park","year":"2022","journal-title":"ACS Polymers Au"},{"key":"2025042600304487500_ref47","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1038\/s41524-023-01034-3","article-title":"Polymer graph neural networks for multitask property learning","volume":"9","author":"Queen","year":"2023","journal-title":"npj Comput Mater"},{"key":"2025042600304487500_ref48","doi-asserted-by":"publisher","first-page":"2908","DOI":"10.1021\/acs.jctc.3c01385","article-title":"Polymer-unit graph: advancing interpretability in graph neural network machine learning for organic polymer semiconductor materials","volume":"20","author":"Zhang","year":"2024","journal-title":"J Chem Theory Comput"},{"key":"2025042600304487500_ref49","volume-title":"DeeperGCN: all you need to train deeper GCNs","author":"Li","year":"2020"},{"key":"2025042600304487500_ref50","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1039\/c3mb25555g","article-title":"Some remarks on predicting multi-label attributes in molecular biosystems","volume":"9","author":"Chou","year":"2013","journal-title":"Mol Biosyst"},{"key":"2025042600304487500_ref51","first-page":"10","volume":"1050","author":"Velickovic","year":"2017","journal-title":"Graph attention networks stat"},{"key":"2025042600304487500_ref52","article-title":"How powerful are graph neural networks","author":"Xu","year":"2018"},{"key":"2025042600304487500_ref53","article-title":"Deep graph library: a graph-centric, highly performant package for graph neural networks","author":"Wang","year":"2019"},{"key":"2025042600304487500_ref54","first-page":"21618","article-title":"Rethinking graph transformers with spectral attention","volume":"34","author":"Kreuzer","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025042600304487500_ref55","first-page":"14501","article-title":"Recipe for a general, powerful, scalable graph transformer","volume":"35","author":"Ramp\u00e1\u0161ek","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025042600304487500_ref56","first-page":"31613","article-title":"Exphormer: sparse transformers for graphs","volume-title":"International Conference on Machine Learning","author":"Shirzad","year":"2023"},{"key":"2025042600304487500_ref57","volume-title":"Graph-Mamba: towards long-range graph sequence modeling with selective state spaces","author":"Wang","year":"2024"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf194\/63012495\/bbaf194.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/2\/bbaf194\/63012495\/bbaf194.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T04:31:00Z","timestamp":1745641860000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf194\/8120240"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":57,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf194","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2025,3]]},"article-number":"bbaf194"}}