{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T05:52:17Z","timestamp":1777269137608,"version":"3.51.4"},"reference-count":87,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T00:00:00Z","timestamp":1706572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T00:00:00Z","timestamp":1706572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["81973241"],"award-info":[{"award-number":["81973241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"crossref","award":["2020A1515010548"],"award-info":[{"award-number":["2020A1515010548"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Conventional machine learning (ML) and deep learning (DL) play a key role in the selectivity prediction of kinase inhibitors. A number of models based on available datasets can be used to predict the kinase profile of compounds, but there is still controversy about the advantages and disadvantages of ML and DL for such tasks. In this study, we constructed a comprehensive benchmark dataset of kinase inhibitors, involving in 141,086 unique compounds and 216,823 well-defined bioassay data points for 354 kinases. We then systematically compared the performance of 12 ML and DL methods on the kinase profiling prediction task. Extensive experimental results reveal that (1) Descriptor-based ML models generally slightly outperform fingerprint-based ML models in terms of predictive performance. RF as an ensemble learning approach displays the overall best predictive performance. (2) Single-task graph-based DL models are generally inferior to conventional descriptor- and fingerprint-based ML models, however, the corresponding multi-task models generally improves the average accuracy of kinase profile prediction. For example, the multi-task FP-GNN model outperforms the conventional descriptor- and fingerprint-based ML models with an average AUC of 0.807. (3) Fusion models based on voting and stacking methods can further improve the performance of the kinase profiling prediction task, specifically, RF::AtomPairs\u2009+\u2009FP2\u2009+\u2009RDKitDes fusion model performs best with the highest average AUC value of 0.825 on the test sets. These findings provide useful information for guiding choices of the ML and DL methods for the kinase profiling prediction tasks. Finally, an online platform called KIPP (<jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/kipp.idruglab.cn\">https:\/\/kipp.idruglab.cn<\/jats:ext-link>) and python software are developed based on the best models to support the kinase profiling prediction, as well as various kinase inhibitor identification tasks including virtual screening, compound repositioning and target fishing.<\/jats:p>","DOI":"10.1186\/s13321-023-00799-5","type":"journal-article","created":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T17:02:42Z","timestamp":1706634162000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Large-scale comparison of machine learning methods for profiling prediction of kinase inhibitors"],"prefix":"10.1186","volume":"16","author":[{"given":"Jiangxia","family":"Wu","sequence":"first","affiliation":[]},{"given":"Yihao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jingxing","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Duancheng","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jindi","family":"Huang","sequence":"additional","affiliation":[]},{"given":"MuJie","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Ling","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,30]]},"reference":[{"key":"799_CR1","doi-asserted-by":"publisher","first-page":"1912","DOI":"10.1126\/science.1075762","volume":"298","author":"G Manning","year":"2002","unstructured":"Manning G, Whyte DB, Martinez R et al (2002) The protein kinase complement of the human genome. Science 298:1912\u20131934. https:\/\/doi.org\/10.1126\/science.1075762","journal-title":"Science"},{"key":"799_CR2","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.tips.2013.11.004","volume":"35","author":"M Huang","year":"2014","unstructured":"Huang M, Shen A, Ding J, Geng M (2014) Molecularly targeted cancer therapy: some lessons from the past decade. Trends Pharmacol Sci 35:41\u201350. https:\/\/doi.org\/10.1016\/j.tips.2013.11.004","journal-title":"Trends Pharmacol Sci"},{"key":"799_CR3","doi-asserted-by":"publisher","first-page":"111","DOI":"10.3322\/caac.20003","volume":"59","author":"WW Ma","year":"2009","unstructured":"Ma WW, Adjei AA (2009) Novel agents on the horizon for cancer therapy. CA Cancer J Clin 59:111\u2013137. https:\/\/doi.org\/10.3322\/caac.20003","journal-title":"CA Cancer J Clin"},{"key":"799_CR4","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/j.tibs.2014.08.010","volume":"39","author":"C Sun","year":"2014","unstructured":"Sun C, Bernards R (2014) Feedback and redundancy in receptor tyrosine kinase signaling: relevance to cancer therapies. Trends Biochem Sci 39:465\u2013474. https:\/\/doi.org\/10.1016\/j.tibs.2014.08.010","journal-title":"Trends Biochem Sci"},{"key":"799_CR5","doi-asserted-by":"publisher","first-page":"5023","DOI":"10.1021\/jm401490p","volume":"57","author":"JD Clark","year":"2014","unstructured":"Clark JD, Flanagan ME, Telliez J-B (2014) Discovery and development of janus kinase (JAK) inhibitors for inflammatory diseases: miniperspective. J Med Chem 57:5023\u20135038. https:\/\/doi.org\/10.1021\/jm401490p","journal-title":"J Med Chem"},{"key":"799_CR6","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1038\/nrd4025","volume":"12","author":"PJ Barnes","year":"2013","unstructured":"Barnes PJ (2013) New anti-inflammatory targets for chronic obstructive pulmonary disease. Nat Rev Drug Discov 12:543\u2013559. https:\/\/doi.org\/10.1038\/nrd4025","journal-title":"Nat Rev Drug Discov"},{"key":"799_CR7","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1021\/jm501557a","volume":"58","author":"F Muth","year":"2015","unstructured":"Muth F, G\u00fcnther M, Bauer SM et al (2015) Tetra-substituted pyridinylimidazoles as dual inhibitors of p38\u03b1 mitogen-activated protein kinase and c-Jun N-terminal kinase 3 for potential treatment of neurodegenerative diseases. J Med Chem 58:443\u2013456. https:\/\/doi.org\/10.1021\/jm501557a","journal-title":"J Med Chem"},{"key":"799_CR8","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.1038\/nm.3703","volume":"20","author":"R Kikuchi","year":"2014","unstructured":"Kikuchi R, Nakamura K, MacLauchlan S et al (2014) An antiangiogenic isoform of VEGF-A contributes to impaired vascularization in peripheral artery disease. Nat Med 20:1464\u20131471. https:\/\/doi.org\/10.1038\/nm.3703","journal-title":"Nat Med"},{"key":"799_CR9","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1038\/nature13887","volume":"517","author":"AS Banks","year":"2015","unstructured":"Banks AS, McAllister FE, Camporez JPG et al (2015) An ERK\/Cdk5 axis controls the diabetogenic actions of PPAR\u03b3. Nature 517:391\u2013395. https:\/\/doi.org\/10.1038\/nature13887","journal-title":"Nature"},{"key":"799_CR10","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/alzrt238","volume":"6","author":"HB Nygaard","year":"2014","unstructured":"Nygaard HB, van Dyck CH, Strittmatter SM (2014) Fyn kinase inhibition as a novel therapy for Alzheimer\u2019s disease. Alzheimers Res Ther 6:8. https:\/\/doi.org\/10.1186\/alzrt238","journal-title":"Alzheimers Res Ther"},{"key":"799_CR11","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-021-00303-4","author":"MM Attwood","year":"2021","unstructured":"Attwood MM, Fabbro D, Sokolov AV et al (2021) Author correction: trends in kinase drug discovery: targets, indications and inhibitor design. Nat Rev Drug Discov. https:\/\/doi.org\/10.1038\/s41573-021-00303-4","journal-title":"Nat Rev Drug Discov"},{"key":"799_CR12","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1038\/nrd2541","volume":"7","author":"DM Goldstein","year":"2008","unstructured":"Goldstein DM, Gray NS, Zarrinkar PP (2008) High-throughput kinase profiling as a platform for drug discovery. Nat Rev Drug Discov 7:391\u2013397. https:\/\/doi.org\/10.1038\/nrd2541","journal-title":"Nat Rev Drug Discov"},{"key":"799_CR13","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.jmgm.2017.11.003","volume":"79","author":"D-D Li","year":"2018","unstructured":"Li D-D, Meng X-F, Wang Q et al (2018) Consensus scoring model for the molecular docking study of mTOR kinase inhibitor. J Mol Graph Model 79:81\u201387. https:\/\/doi.org\/10.1016\/j.jmgm.2017.11.003","journal-title":"J Mol Graph Model"},{"key":"799_CR14","doi-asserted-by":"publisher","first-page":"4283","DOI":"10.1021\/acs.jcim.9b01204","volume":"60","author":"L Burggraaff","year":"2020","unstructured":"Burggraaff L, Lenselink EB, Jespers W et al (2020) Successive statistical and structure-based modeling to identify chemically novel kinase inhibitors. J Chem Inf Model 60:4283\u20134295. https:\/\/doi.org\/10.1021\/acs.jcim.9b01204","journal-title":"J Chem Inf Model"},{"key":"799_CR15","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.3390\/molecules22091576","volume":"22","author":"S Kothiwale","year":"2017","unstructured":"Kothiwale S, Borza C, Pozzi A, Meiler J (2017) Quantitative structure-activity relationship modeling of kinase selectivity profiles. Molecules 22:1576. https:\/\/doi.org\/10.3390\/molecules22091576","journal-title":"Molecules"},{"key":"799_CR16","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/j.chemolab.2017.06.011","volume":"167","author":"Y Kong","year":"2017","unstructured":"Kong Y, Yan A (2017) QSAR models for predicting the bioactivity of Polo-like kinase 1 inhibitors. Chemom Intell Lab Syst 167:214\u2013225. https:\/\/doi.org\/10.1016\/j.chemolab.2017.06.011","journal-title":"Chemom Intell Lab Syst"},{"key":"799_CR17","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1021\/ci800138n","volume":"48","author":"S Sciabola","year":"2008","unstructured":"Sciabola S, Stanton RV, Wittkopp S et al (2008) Predicting kinase selectivity profiles using free-Wilson QSAR analysis. J Chem Inf Model 48:1851\u20131867. https:\/\/doi.org\/10.1021\/ci800138n","journal-title":"J Chem Inf Model"},{"key":"799_CR18","doi-asserted-by":"publisher","first-page":"1974","DOI":"10.1021\/ci900176y","volume":"49","author":"RP Sheridan","year":"2009","unstructured":"Sheridan RP, Nam K, Maiorov VN et al (2009) QSAR models for predicting the similarity in binding profiles for pairs of protein kinases and the variation of models between experimental data sets. J Chem Inf Model 49:1974\u20131985. https:\/\/doi.org\/10.1021\/ci900176y","journal-title":"J Chem Inf Model"},{"key":"799_CR19","doi-asserted-by":"publisher","first-page":"1958","DOI":"10.1002\/cmdc.201500346","volume":"10","author":"A Hillisch","year":"2015","unstructured":"Hillisch A, Heinrich N, Wild H (2015) Computational chemistry in the pharmaceutical industry: from childhood to adolescence. ChemMedChem 10:1958\u20131962. https:\/\/doi.org\/10.1002\/cmdc.201500346","journal-title":"ChemMedChem"},{"key":"799_CR20","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1038\/nbt1284","volume":"25","author":"MJ Keiser","year":"2007","unstructured":"Keiser MJ, Roth BL, Armbruster BN et al (2007) Relating protein pharmacology by ligand chemistry. Nat Biotechnol 25:197\u2013206. https:\/\/doi.org\/10.1038\/nbt1284","journal-title":"Nat Biotechnol"},{"key":"799_CR21","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1038\/nature08506","volume":"462","author":"MJ Keiser","year":"2009","unstructured":"Keiser MJ, Setola V, Irwin JJ et al (2009) Predicting new molecular targets for known drugs. Nature 462:175\u2013181. https:\/\/doi.org\/10.1038\/nature08506","journal-title":"Nature"},{"key":"799_CR22","doi-asserted-by":"publisher","first-page":"1942","DOI":"10.1021\/ci1005004","volume":"51","author":"E Martin","year":"2011","unstructured":"Martin E, Mukherjee P, Sullivan D, Jansen J (2011) Profile-QSAR: a novel meta-qsar method that combines activities across the kinase family to accurately predict affinity, selectivity, and cellular activity. J Chem Inf Model 51:1942\u20131956. https:\/\/doi.org\/10.1021\/ci1005004","journal-title":"J Chem Inf Model"},{"key":"799_CR23","doi-asserted-by":"publisher","first-page":"4463","DOI":"10.1021\/jm0303195","volume":"47","author":"X Xia","year":"2004","unstructured":"Xia X, Maliski EG, Gallant P, Rogers D (2004) Classification of kinase inhibitors using a bayesian model. J Med Chem 47:4463\u20134470. https:\/\/doi.org\/10.1021\/jm0303195","journal-title":"J Med Chem"},{"key":"799_CR24","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1021\/ci300403k","volume":"53","author":"SC Sch\u00fcrer","year":"2013","unstructured":"Sch\u00fcrer SC, Muskal SM (2013) Kinome-wide activity modeling from diverse public high-quality data sets. J Chem Inf Model 53:27\u201338. https:\/\/doi.org\/10.1021\/ci300403k","journal-title":"J Chem Inf Model"},{"key":"799_CR25","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1186\/1471-2105-11-339","volume":"11","author":"M Lapins","year":"2010","unstructured":"Lapins M, Wikberg JE (2010) Kinome-wide interaction modelling using alignment-based and alignment-independent approaches for kinase description and linear and non-linear data analysis techniques. BMC Bioinformatics 11:339. https:\/\/doi.org\/10.1186\/1471-2105-11-339","journal-title":"BMC Bioinformatics"},{"key":"799_CR26","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1021\/ci200607f","volume":"52","author":"S Niijima","year":"2012","unstructured":"Niijima S, Shiraishi A, Okuno Y (2012) Dissecting kinase profiling data to predict activity and understand cross-reactivity of kinase inhibitors. J Chem Inf Model 52:901\u2013912. https:\/\/doi.org\/10.1021\/ci200607f","journal-title":"J Chem Inf Model"},{"key":"799_CR27","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1021\/ci200615h","volume":"52","author":"B Chen","year":"2012","unstructured":"Chen B, Sheridan RP, Hornak V, Voigt JH (2012) Comparison of random forest and pipeline pilot na\u00efve bayes in prospective QSAR predictions. J Chem Inf Model 52:792\u2013803. https:\/\/doi.org\/10.1021\/ci200615h","journal-title":"J Chem Inf Model"},{"key":"799_CR28","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.aca.2013.07.003","volume":"792","author":"D-S Cao","year":"2013","unstructured":"Cao D-S, Zhou G-H, Liu S et al (2013) Large-scale prediction of human kinase\u2013inhibitor interactions using protein sequences and molecular topological structures. Anal Chim Acta 792:10\u201318. https:\/\/doi.org\/10.1016\/j.aca.2013.07.003","journal-title":"Anal Chim Acta"},{"key":"799_CR29","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1021\/acs.jcim.5b00646","volume":"56","author":"A Bora","year":"2016","unstructured":"Bora A, Avram S, Ciucanu I et al (2016) Predictive models for fast and effective profiling of kinase inhibitors. J Chem Inf Model 56:895\u2013905. https:\/\/doi.org\/10.1021\/acs.jcim.5b00646","journal-title":"J Chem Inf Model"},{"key":"799_CR30","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1021\/acs.jmedchem.6b01611","volume":"60","author":"B Merget","year":"2017","unstructured":"Merget B, Turk S, Eid S et al (2017) Profiling prediction of kinase inhibitors: toward the virtual assay. J Med Chem 60:474\u2013485. https:\/\/doi.org\/10.1021\/acs.jmedchem.6b01611","journal-title":"J Med Chem"},{"key":"799_CR31","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1038\/msb.2011.5","volume":"7","author":"H Yabuuchi","year":"2011","unstructured":"Yabuuchi H, Niijima S, Takematsu H et al (2011) Analysis of multiple compound\u2013protein interactions reveals novel bioactive molecules. Mol Syst Biol 7:472. https:\/\/doi.org\/10.1038\/msb.2011.5","journal-title":"Mol Syst Biol"},{"key":"799_CR32","unstructured":"Unterthiner T, Mayr A, Klambauer G, et al. Deep Learning as an Opportunity in Virtual Screening. In: Workshop on Deep Learning and Representation Learning (NIPS2014). 2014."},{"key":"799_CR33","doi-asserted-by":"publisher","first-page":"8723","DOI":"10.1021\/acs.jmedchem.9b00855","volume":"63","author":"X Li","year":"2020","unstructured":"Li X, Li Z, Wu X et al (2020) Deep learning enhancing kinome-wide polypharmacology profiling: model construction and experiment validation. J Med Chem 63:8723\u20138737. https:\/\/doi.org\/10.1021\/acs.jmedchem.9b00855","journal-title":"J Med Chem"},{"key":"799_CR34","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1021\/acs.jcim.7b00729","volume":"58","author":"S Avram","year":"2018","unstructured":"Avram S, Bora A, Halip L, Curp\u0103n R (2018) Modeling kinase inhibition using highly confident data sets. J Chem Inf Model 58:957\u2013967. https:\/\/doi.org\/10.1021\/acs.jcim.7b00729","journal-title":"J Chem Inf Model"},{"key":"799_CR35","doi-asserted-by":"publisher","first-page":"bbad398","DOI":"10.1093\/bib\/bbad398","volume":"24","author":"B Li","year":"2023","unstructured":"Li B, Lin M, Chen T, Wang L (2023) FG-BERT: a generalized and self-supervised functional group-based molecular representation learning framework for properties prediction. Brief Bioinform 24:bbad398. https:\/\/doi.org\/10.1093\/bib\/bbad398","journal-title":"Brief Bioinform"},{"key":"799_CR36","doi-asserted-by":"publisher","first-page":"bbab112","DOI":"10.1093\/bib\/bbab112","volume":"22","author":"Z Wu","year":"2021","unstructured":"Wu Z, Jiang D, Hsieh C-Y et al (2021) Hyperbolic relational graph convolution networks plus: a simple but highly efficient QSAR-modeling method. Brief Bioinform 22:bbab112. https:\/\/doi.org\/10.1093\/bib\/bbab112","journal-title":"Brief Bioinform"},{"key":"799_CR37","doi-asserted-by":"publisher","first-page":"bbab068","DOI":"10.1093\/bib\/bbab068","volume":"22","author":"Q Ye","year":"2021","unstructured":"Ye Q, Chai X, Jiang D et al (2021) Identification of active molecules against Mycobacterium tuberculosis through machine learning. Brief Bioinform 22:bbab068. https:\/\/doi.org\/10.1093\/bib\/bbab068","journal-title":"Brief Bioinform"},{"key":"799_CR38","doi-asserted-by":"publisher","first-page":"3688","DOI":"10.1021\/acs.jcim.3c00132","volume":"63","author":"S Luukkonen","year":"2023","unstructured":"Luukkonen S, Meijer E, Tricarico GA et al (2023) Large-scale modeling of sparse protein kinase activity data. J Chem Inf Model 63:3688\u20133696. https:\/\/doi.org\/10.1021\/acs.jcim.3c00132","journal-title":"J Chem Inf Model"},{"key":"799_CR39","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","volume":"13","author":"T Cover","year":"1967","unstructured":"Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13:21\u201327. https:\/\/doi.org\/10.1109\/TIT.1967.1053964","journal-title":"IEEE Trans Inf Theory"},{"key":"799_CR40","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-0285-4","volume-title":"Pattern classification and scene analysis","author":"RO Duda","year":"1973","unstructured":"Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, Hoboken. https:\/\/doi.org\/10.1007\/978-1-4471-0285-4"},{"key":"799_CR41","doi-asserted-by":"publisher","first-page":"2048","DOI":"10.1021\/ci0340916","volume":"43","author":"VV Zernov","year":"2003","unstructured":"Zernov VV, Balakin KV, Ivaschenko AA et al (2003) Drug discovery using support vector machines. the case studies of drug-likeness, agrochemical-likeness, and enzyme inhibition predictions. J Chem Inf Comput Sci 43:2048\u20132056. https:\/\/doi.org\/10.1021\/ci0340916","journal-title":"J Chem Inf Comput Sci"},{"key":"799_CR42","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1021\/ci034160g","volume":"43","author":"V Svetnik","year":"2003","unstructured":"Svetnik V, Liaw A, Tong C et al (2003) Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci 43:1947\u20131958. https:\/\/doi.org\/10.1021\/ci034160g","journal-title":"J Chem Inf Comput Sci"},{"key":"799_CR43","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. Xgboost: A scalable tree boosting system\/\/Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016: 785\u2013794. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"799_CR44","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/BF02478259","volume":"5","author":"WS McCulloch","year":"1943","unstructured":"McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115\u2013133. https:\/\/doi.org\/10.1007\/BF02478259","journal-title":"Bull Math Biophys"},{"key":"799_CR45","unstructured":"Kipf TN, Welling M. Semi-Supervised Classification with Graph Convolutional Networks. arXiv. 2017; 160902907"},{"key":"799_CR46","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, et al. Graph Attention Networks. arXiv. 2018; 171010903"},{"key":"799_CR47","unstructured":"Gilmer J, Schoenholz SS, Riley PF, et al. Neural message passing for Quantum chemistry. In: Proceedings of the 34th International Conference on Machine Learning - Volume 70. JMLR.org, Sydney, NSW, Australia, pp 1263\u20131272. 2017."},{"key":"799_CR48","doi-asserted-by":"publisher","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","volume":"63","author":"Z Xiong","year":"2020","unstructured":"Xiong Z, Wang D, Liu X et al (2020) Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism. J Med Chem 63:8749\u20138760. https:\/\/doi.org\/10.1021\/acs.jmedchem.9b00959","journal-title":"J Med Chem"},{"key":"799_CR49","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","volume":"59","author":"K Yang","year":"2019","unstructured":"Yang K, Swanson K, Jin W et al (2019) Analyzing learned molecular representations for property prediction. J Chem Inf Model 59:3370\u20133388. https:\/\/doi.org\/10.1021\/acs.jcim.9b00237","journal-title":"J Chem Inf Model"},{"issue":"6","key":"799_CR50","doi-asserted-by":"publisher","first-page":"bbac408","DOI":"10.1093\/bib\/bbac408","volume":"23","author":"H Cai","year":"2022","unstructured":"Cai H, Zhang H, Zhao D et al (2022) FP-GNN: a versatile deep learning architecture for enhanced molecular property prediction. Brief Bioinform 23(6):bbac408","journal-title":"Brief Bioinform"},{"key":"799_CR51","doi-asserted-by":"publisher","first-page":"D930","DOI":"10.1093\/nar\/gky1075","volume":"47","author":"D Mendez","year":"2019","unstructured":"Mendez D, Gaulton A, Bento AP et al (2019) ChEMBL: towards direct deposition of bioassay data. Nucleic Acids Res 47:D930\u2013D940. https:\/\/doi.org\/10.1093\/nar\/gky1075","journal-title":"Nucleic Acids Res"},{"key":"799_CR52","doi-asserted-by":"publisher","first-page":"D1388","DOI":"10.1093\/nar\/gkaa971","volume":"49","author":"S Kim","year":"2021","unstructured":"Kim S, Chen J, Cheng T et al (2021) PubChem in 2021: new data content and improved web interfaces. Nucleic Acids Res 49:D1388\u2013D1395. https:\/\/doi.org\/10.1093\/nar\/gkaa971","journal-title":"Nucleic Acids Res"},{"key":"799_CR53","doi-asserted-by":"publisher","first-page":"D198","DOI":"10.1093\/nar\/gkl999","volume":"35","author":"T Liu","year":"2007","unstructured":"Liu T, Lin Y, Wen X et al (2007) BindingDB: a web-accessible database of experimentally determined protein\u2013ligand binding affinities. Nucleic Acids Res 35:D198\u2013D201. https:\/\/doi.org\/10.1093\/nar\/gkl999","journal-title":"Nucleic Acids Res"},{"key":"799_CR54","doi-asserted-by":"publisher","first-page":"2324","DOI":"10.1021\/acs.jcim.5b00559","volume":"55","author":"T Sterling","year":"2015","unstructured":"Sterling T, Irwin JJ (2015) ZINC 15\u2014ligand discovery for everyone. J Chem Inf Model 55:2324\u20132337. https:\/\/doi.org\/10.1021\/acs.jcim.5b00559","journal-title":"J Chem Inf Model"},{"key":"799_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.106189","volume":"32","author":"O Laufk\u00f6tter","year":"2020","unstructured":"Laufk\u00f6tter O, Laufer S, Bajorath J (2020) Kinase inhibitor data set for systematic analysis of representative kinases across the human kinome. Data Brief 32:106189. https:\/\/doi.org\/10.1016\/j.dib.2020.106189","journal-title":"Data Brief"},{"key":"799_CR56","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","volume":"50","author":"D Rogers","year":"2010","unstructured":"Rogers D, Hahn M (2010) Extended-connectivity fingerprints. J Chem Inf Model 50:742\u2013754. https:\/\/doi.org\/10.1021\/ci100050t","journal-title":"J Chem Inf Model"},{"key":"799_CR57","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1021\/ci010132r","volume":"42","author":"JL Durant","year":"2002","unstructured":"Durant JL, Leland BA, Henry DR, Nourse JG (2002) Reoptimization of MDL keys for use in drug discovery. J Chem Inf Comput Sci 42:1273\u20131280. https:\/\/doi.org\/10.1021\/ci010132r","journal-title":"J Chem Inf Comput Sci"},{"key":"799_CR58","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1021\/ci00046a002","volume":"25","author":"RE Carhart","year":"1985","unstructured":"Carhart RE, Smith DH, Venkataraghavan R (1985) Atom pairs as molecular features in structure-activity studies: definition and applications. J Chem Inf Comput Sci 25:64\u201373. https:\/\/doi.org\/10.1021\/ci00046a002","journal-title":"J Chem Inf Comput Sci"},{"key":"799_CR59","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/1758-2946-3-33","volume":"3","author":"NM O\u2019Boyle","year":"2011","unstructured":"O\u2019Boyle NM, Banck M, James CA et al (2011) Open babel: an open chemical toolbox. J Cheminform 3:33. https:\/\/doi.org\/10.1186\/1758-2946-3-33","journal-title":"J Cheminform"},{"key":"799_CR60","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1002\/(SICI)1097-0290(199824)61:1<47::AID-BIT9>3.0.CO;2-Z","volume":"61","author":"A Gobbi","year":"1998","unstructured":"Gobbi A, Poppinger D (1998) Genetic optimization of combinatorial libraries. Biotechnol Bioeng 61:47\u201354. https:\/\/doi.org\/10.1002\/(SICI)1097-0290(199824)61:1%3c47::AID-BIT9%3e3.0.CO;2-Z","journal-title":"Biotechnol Bioeng"},{"key":"799_CR61","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/s10822-016-9938-8","volume":"30","author":"S Kearnes","year":"2016","unstructured":"Kearnes S, McCloskey K, Berndl M et al (2016) Molecular graph convolutions: moving beyond fingerprints. J Comput Aided Mol Des 30:595\u2013608. https:\/\/doi.org\/10.1007\/s10822-016-9938-8","journal-title":"J Comput Aided Mol Des"},{"key":"799_CR62","unstructured":"Duvenaud D, Maclaurin D, Aguilera-Iparraguirre J, et al. Convolutional Networks on Graphs for Learning Molecular Fingerprints. arXiv. 2015; 150909292"},{"key":"799_CR63","doi-asserted-by":"publisher","first-page":"3186","DOI":"10.1021\/ci500253q","volume":"54","author":"L Wang","year":"2014","unstructured":"Wang L, Le X, Li L et al (2014) Discovering new agents active against methicillin-resistant staphylococcus aureus with ligand-based approaches. J Chem Inf Model 54:3186\u20133197. https:\/\/doi.org\/10.1021\/ci500253q","journal-title":"J Chem Inf Model"},{"key":"799_CR64","doi-asserted-by":"publisher","first-page":"18987","DOI":"10.1038\/srep18987","volume":"6","author":"L Wang","year":"2016","unstructured":"Wang L, Chen L, Yu M et al (2016) Discovering new mTOR inhibitors for cancer treatment through virtual screening methods and in vitro assays. Sci Rep 6:18987. https:\/\/doi.org\/10.1038\/srep18987","journal-title":"Sci Rep"},{"key":"799_CR65","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1039\/c8ob02193g","volume":"17","author":"Y Luo","year":"2019","unstructured":"Luo Y, Zeng R, Guo Q et al (2019) Identifying a novel anticancer agent with microtubule-stabilizing effects through computational cell-based bioactivity prediction models and bioassays. Org Biomol Chem 17:1519\u20131530. https:\/\/doi.org\/10.1039\/c8ob02193g","journal-title":"Org Biomol Chem"},{"key":"799_CR66","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmech.2020.112328","volume":"196","author":"Q Guo","year":"2020","unstructured":"Guo Q, Zhang H, Deng Y et al (2020) Ligand- and structural-based discovery of potential small molecules that target the colchicine site of tubulin for cancer treatment. Eur J Med Chem 196:112328. https:\/\/doi.org\/10.1016\/j.ejmech.2020.112328","journal-title":"Eur J Med Chem"},{"key":"799_CR67","doi-asserted-by":"crossref","unstructured":"Joachims T. Text categorization with support vector machines\u202f: learning with many relevant features. Proceedings of the ECML-98. 1998.","DOI":"10.1007\/BFb0026683"},{"key":"799_CR68","doi-asserted-by":"publisher","first-page":"2000105","DOI":"10.1002\/minf.202000105","volume":"40","author":"S Li","year":"2021","unstructured":"Li S, Ding Y, Chen M et al (2021) HDAC3i-finder: a machine learning-based computational tool to screen for HDAC3 inhibitors. Mol Inform 40:2000105. https:\/\/doi.org\/10.1002\/minf.202000105","journal-title":"Mol Inform"},{"key":"799_CR69","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13321-020-00479-8","volume":"13","author":"D Jiang","year":"2021","unstructured":"Jiang D, Wu Z, Hsieh C-Y et al (2021) Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models. J Cheminformatics 13:12. https:\/\/doi.org\/10.1186\/s13321-020-00479-8","journal-title":"J Cheminformatics"},{"key":"799_CR70","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1002\/minf.201501008","volume":"35","author":"E Gawehn","year":"2016","unstructured":"Gawehn E, Hiss JA, Schneider G (2016) Deep learning in drug discovery. Mol Inform 35:3\u201314. https:\/\/doi.org\/10.1002\/minf.201501008","journal-title":"Mol Inform"},{"key":"799_CR71","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1021\/ci500747n","volume":"55","author":"J Ma","year":"2015","unstructured":"Ma J, Sheridan RP, Liaw A et al (2015) Deep neural nets as a method for quantitative structure-activity relationships. J Chem Inf Model 55:263\u2013274. https:\/\/doi.org\/10.1021\/ci500747n","journal-title":"J Chem Inf Model"},{"key":"799_CR72","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107920","volume":"115","author":"L Zhu","year":"2021","unstructured":"Zhu L, Wan B, Li C et al (2021) Dyadic relational graph convolutional networks for skeleton-based human interaction recognition. Pattern Recognit 115:107920. https:\/\/doi.org\/10.1016\/j.patcog.2021.107920","journal-title":"Pattern Recognit"},{"key":"799_CR73","doi-asserted-by":"crossref","unstructured":"Flam-Shepherd D, Wu T, Friederich P, Aspuru-Guzik A. Neural message passing on high order paths. arXiv. 2020; 200210413","DOI":"10.1088\/2632-2153\/abf5b8"},{"key":"799_CR74","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-019-0407-y","volume":"12","author":"M Withnall","year":"2020","unstructured":"Withnall M, Lindel\u00f6f E, Engkvist O, Chen H (2020) Building attention and edge message passing neural networks for bioactivity and physical\u2013chemical property prediction. J Cheminform 12:1. https:\/\/doi.org\/10.1186\/s13321-019-0407-y","journal-title":"J Cheminform"},{"key":"799_CR75","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s13321-020-0414-z","volume":"12","author":"B Tang","year":"2020","unstructured":"Tang B, Kramer ST, Fang M et al (2020) A self-attention based message passing neural network for predicting molecular lipophilicity and aqueous solubility. J Cheminform 12:15. https:\/\/doi.org\/10.1186\/s13321-020-0414-z","journal-title":"J Cheminform"},{"key":"799_CR76","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","volume":"180","author":"JM Stokes","year":"2020","unstructured":"Stokes JM, Yang K, Swanson K et al (2020) A deep learning approach to antibiotic discovery. Cell 180:688-702.e13. https:\/\/doi.org\/10.1016\/j.cell.2020.01.021","journal-title":"Cell"},{"key":"799_CR77","first-page":"2825","volume":"12","author":"A Swami","year":"2013","unstructured":"Swami A, Jain R (2013) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"799_CR78","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1002\/cmdc.201700180","volume":"13","author":"FA Sorgenfrei","year":"2018","unstructured":"Sorgenfrei FA, Fulle S, Merget B (2018) Kinome-wide profiling prediction of small molecules. ChemMedChem 13:495\u2013499. https:\/\/doi.org\/10.1002\/cmdc.201700180","journal-title":"ChemMedChem"},{"key":"799_CR79","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1038\/s41598-020-80758-4","volume":"11","author":"I Abdelbaky","year":"2021","unstructured":"Abdelbaky I, Tayara H, Chong KT (2021) Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets. Sci Rep 11:706. https:\/\/doi.org\/10.1038\/s41598-020-80758-4","journal-title":"Sci Rep"},{"key":"799_CR80","doi-asserted-by":"publisher","first-page":"8208","DOI":"10.1021\/acs.jmedchem.1c00020","volume":"64","author":"N S\u00e1nchez-Cruz","year":"2021","unstructured":"S\u00e1nchez-Cruz N, Medina-Franco JL (2021) Epigenetic target fishing with accurate machine learning models. J Med Chem 64:8208\u20138220. https:\/\/doi.org\/10.1021\/acs.jmedchem.1c00020","journal-title":"J Med Chem"},{"key":"799_CR81","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1038\/s42256-021-00335-w","volume":"3","author":"GB Kc","year":"2021","unstructured":"Kc GB, Bocci G, Verma S et al (2021) A machine learning platform to estimate anti-SARS-CoV-2 activities. Nat Mach Intell 3:527\u2013535. https:\/\/doi.org\/10.1038\/s42256-021-00335-w","journal-title":"Nat Mach Intell"},{"key":"799_CR82","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","volume":"9","author":"Z Wu","year":"2018","unstructured":"Wu Z, Ramsundar B, Feinberg EN et al (2018) MoleculeNet: a benchmark for molecular machine learning. Chem Sci 9:513\u2013530. https:\/\/doi.org\/10.1039\/C7SC02664A","journal-title":"Chem Sci"},{"key":"799_CR83","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-016-1433-7","volume":"18","author":"S Eid","year":"2017","unstructured":"Eid S, Turk S, Volkamer A et al (2017) KinMap: a web-based tool for interactive navigation through human kinome data. BMC Bioinformatics 18:1\u20136","journal-title":"BMC Bioinformatics"},{"key":"799_CR84","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1038\/nbt1358","volume":"26","author":"MW Karaman","year":"2008","unstructured":"Karaman MW, Herrgard S, Treiber DK et al (2008) A quantitative analysis of kinase inhibitor selectivity. Nat Biotechnol 26:127\u2013132. https:\/\/doi.org\/10.1038\/nbt1358","journal-title":"Nat Biotechnol"},{"key":"799_CR85","doi-asserted-by":"publisher","first-page":"5773","DOI":"10.1021\/jm070562u","volume":"50","author":"PP Graczyk","year":"2007","unstructured":"Graczyk PP (2007) Gini coefficient: a new way to express selectivity of kinase inhibitors against a family of kinases. J Med Chem 50:5773\u20135779. https:\/\/doi.org\/10.1021\/jm070562u","journal-title":"J Med Chem"},{"key":"799_CR86","doi-asserted-by":"publisher","first-page":"1468","DOI":"10.1136\/bmj.320.7247.1468","volume":"320","author":"JM Bland","year":"2000","unstructured":"Bland JM (2000) Statistics notes: the odds ratio. BMJ 320:1468\u20131468. https:\/\/doi.org\/10.1136\/bmj.320.7247.1468","journal-title":"BMJ"},{"key":"799_CR87","doi-asserted-by":"publisher","first-page":"1793","DOI":"10.1021\/acs.jmedchem.6b01413","volume":"60","author":"X Liang","year":"2017","unstructured":"Liang X, Lv F, Wang B et al (2017) Discovery of 2-((3-Acrylamido-4-methylphenyl)amino)-N-(2-methyl-5-(3,4,5-trimethoxybenzamido)phenyl)-4-(methylamino)pyrimidine-5-carboxamide (CHMFL-BMX-078) as a highly potent and selective type II irreversible bone marrow kinase in the X chromosome (BMX) kinase inhibitor. J Med Chem 60:1793\u20131816. https:\/\/doi.org\/10.1021\/acs.jmedchem.6b01413","journal-title":"J Med Chem"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00799-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-023-00799-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00799-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T17:03:39Z","timestamp":1706634219000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-023-00799-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,30]]},"references-count":87,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["799"],"URL":"https:\/\/doi.org\/10.1186\/s13321-023-00799-5","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,30]]},"assertion":[{"value":"30 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"13"}}