{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:11:42Z","timestamp":1779333102487,"version":"3.51.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T00:00:00Z","timestamp":1589241600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T00:00:00Z","timestamp":1589241600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001863","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001863","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Deep learning is developing as an important technology to perform various tasks in cheminformatics. In particular, graph convolutional neural networks (GCNs) have been reported to perform well in many types of prediction tasks related to molecules. Although GCN exhibits considerable potential in various applications, appropriate utilization of this resource for obtaining reasonable and reliable prediction results requires thorough understanding of GCN and programming. To leverage the power of GCN to benefit various users from chemists to cheminformaticians, an open-source GCN tool, kGCN, is introduced. To support the users with various levels of programming skills, kGCN includes three interfaces: a graphical user interface (GUI) employing KNIME for users with limited programming skills such as chemists, as well as command-line and Python library interfaces for users with advanced programming skills such as cheminformaticians. To support the three steps required for building a prediction model, i.e., pre-processing, model tuning, and interpretation of results, kGCN includes functions of typical pre-processing, Bayesian optimization for automatic model tuning, and visualization of the atomic contribution to prediction for interpretation of results. kGCN supports three types of approaches, single-task, multi-task, and multi-modal predictions. The prediction of compound-protein interaction for four matrixmetalloproteases, MMP-3, -9, -12 and -13, in the inhibition assays is performed as a representative case study using kGCN. Additionally, kGCN provides the visualization of atomic contributions to the prediction. Such visualization is useful for the validation of the prediction models and the design of molecules based on the prediction model, realizing \u201cexplainable AI\u201d for understanding the factors affecting AI prediction. kGCN is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/clinfo\">https:\/\/github.com\/clinfo<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1186\/s13321-020-00435-6","type":"journal-article","created":{"date-parts":[[2020,5,12]],"date-time":"2020-05-12T03:03:07Z","timestamp":1589252587000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":96,"title":["kGCN: a graph-based deep learning framework for chemical structures"],"prefix":"10.1186","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1095-8864","authenticated-orcid":false,"given":"Ryosuke","family":"Kojima","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoichi","family":"Ishida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masateru","family":"Ohta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroaki","family":"Iwata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teruki","family":"Honma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasushi","family":"Okuno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,5,12]]},"reference":[{"issue":"1","key":"435_CR1","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(1):3\u201314. https:\/\/doi.org\/10.1002\/minf.201501008","journal-title":"Mol Inform"},{"issue":"16","key":"435_CR2","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1002\/jcc.24764","volume":"38","author":"GB Goh","year":"2017","unstructured":"Goh GB, Hodas NO, Vishnu A (2017) Deep learning for computational chemistry. J Comput Chem 38(16):1291\u20131307","journal-title":"J Comput Chem"},{"issue":"4","key":"435_CR3","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1039\/C9ME00039A","volume":"4","author":"DC Elton","year":"2019","unstructured":"Elton DC, Boukouvalas Z, Fuge MD, Chung PW (2019) Deep learning for molecular design - a review of the state of the art. Mol Syst Design Eng 4(4):828\u2013849","journal-title":"Mol Syst Design Eng"},{"issue":"10","key":"435_CR4","doi-asserted-by":"publisher","first-page":"4131","DOI":"10.1021\/acs.jcim.9b00628","volume":"59","author":"W Torng","year":"2019","unstructured":"Torng W, Altman RB (2019) Graph convolutional neural networks for predicting drug-target interactions. J Chem Inform Model 59(10):4131\u20134149","journal-title":"J Chem Inform Model"},{"issue":"2","key":"435_CR5","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, Dahl GE, Svetnik V (2015) Deep neural nets as a method for quantitative structure-activity relationships. J Chem Inform Model 55(2):263\u2013274","journal-title":"J Chem Inform Model"},{"issue":"11","key":"435_CR6","doi-asserted-by":"publisher","first-page":"4893","DOI":"10.1021\/acs.jcim.9b00460","volume":"59","author":"S Schneckener","year":"2019","unstructured":"Schneckener S, Grimbs S, Hey J, Menz S, Osmers M, Schaper S, Hillisch A, G\u00f6ller AH (2019) Prediction of oral bioavailability in rats: transferring insights from in vitro correlations to (deep) machine learning models using in silico model outputs and chemical structure parameters. J Chem Inform Model 59(11):4893\u20134905","journal-title":"J Chem Inform Model"},{"issue":"11","key":"435_CR7","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/2366316.2366334","volume":"55","author":"JK Wegner","year":"2012","unstructured":"Wegner JK, Sterling A, Guha R, Bender A, Faulon J-L, Hastings J, O\u2019Boyle N, Overington J, Van Vlijmen H, Willighagen E (2012) Cheminformatics. Commun ACM 55(11):65\u201375","journal-title":"Commun ACM"},{"issue":"8","key":"435_CR8","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, Pande V, Riley P (2016) Molecular graph convolutions: moving beyond fingerprints. J Comput Aided Mol Des 30(8):595\u2013608","journal-title":"J Comput Aided Mol Des"},{"key":"435_CR9","unstructured":"Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE (2017) Neural message passing for quantum chemistry. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp 1263\u20131272"},{"key":"435_CR10","first-page":"2224","volume":"28","author":"DK Duvenaud","year":"2015","unstructured":"Duvenaud DK, Maclaurin D, Iparraguirre J, Bombarell R, Hirzel T, Aspuru-Guzik A, Adams RP (2015) Convolutional networks on graphs for learning molecular fingerprints. Adv Neural Inform Process Syst 28:2224\u20132232","journal-title":"Adv Neural Inform Process Syst"},{"key":"435_CR11","unstructured":"Jin W, Coley CW, Barzilay R, Jaakkola T (2017) Predicting organic reaction outcomes with weisfeiler-lehman network. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp 2604\u20132613"},{"issue":"1","key":"435_CR12","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1145\/1656274.1656280","volume":"11","author":"MR Berthold","year":"2009","unstructured":"Berthold MR, Cebron N, Dill F, Gabriel TR, Kotter T, Meinl T, Ohl P, Thiel K, Wiswedel B (2009) Knime - the konstanz information miner: version 20 and beyond. ACM SIGKDD Explorat Newslett 11(1):26\u201331","journal-title":"ACM SIGKDD Explorat Newslett"},{"key":"435_CR13","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep Learning. MIT Press"},{"issue":"1\u20132","key":"435_CR14","doi-asserted-by":"publisher","first-page":"1600045","DOI":"10.1002\/minf.201600045","volume":"36","author":"M Hamanaka","year":"2017","unstructured":"Hamanaka M, Taneishi K, Iwata H, Ye J, Pei J, Hou J, Okuno Y (2017) Cgbvs-dnn: prediction of compound-protein interactions based on deep learning. Mol Inform 36(1\u20132):1600045","journal-title":"Mol Inform"},{"key":"435_CR15","doi-asserted-by":"publisher","unstructured":"Nguyen TT, Nguyen T, Le DH, Quinn H, Venkatesh S (2020) Predicting drug\u2013target binding affinity with graph neural networks. bioRxiv. https:\/\/doi.org\/10.1101\/684662. https:\/\/www.biorxiv.org\/content\/early\/2020\/01\/22\/684662.full.pdf","DOI":"10.1101\/684662"},{"issue":"2","key":"435_CR16","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1093\/bioinformatics\/bty535","volume":"35","author":"M Tsubaki","year":"2019","unstructured":"Tsubaki M, Tomii K, Sese J (2019) Compound-protein interaction prediction with end-to-end learning of neural networks for graphs and sequences. Bioinformatics 35(2):309\u2013318","journal-title":"Bioinformatics"},{"issue":"8","key":"435_CR17","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.1021\/acs.jcim.7b00146","volume":"57","author":"B Ramsundar","year":"2017","unstructured":"Ramsundar B, Liu B, Wu Z, Verras A, Tudor M, Sheridan RP, Pande V (2017) Is multitask deep learning practical for pharma? J Chem Inform Model 57(8):2068\u20132076","journal-title":"J Chem Inform Model"},{"key":"435_CR18","unstructured":"Sanyal S, Balachandran J, Yadati N, Kumar A, Rajagopalan P, Sanyal S, Talukdar P (2018) MT-CGCNN: Integrating crystal graph convolutional neural network with multitask learning for material property prediction. arXiv preprint arXiv:1811.05660"},{"issue":"14","key":"435_CR19","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.3390\/ijms20143389","volume":"20","author":"K Liu","year":"2019","unstructured":"Liu K, Sun X, Jia L, Ma J, Xing H, Wu J, Gao H, Sun Y, Boulnois F, Fan J (2019) Chemi-net: a molecular graph convolutional network for accurate drug property prediction. Int J Mol Sci 20(14):3389","journal-title":"Int J Mol Sci"},{"key":"435_CR20","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das Vedantam AR, Parikh D, Batra D (2017) Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"435_CR21","unstructured":"Smilkov D, Thorat N, Kim B, Viegas F, Wattenberg M (2017) Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825"},{"key":"435_CR22","unstructured":"Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning, vol 70, pp 3319\u20133328. JMLR.org"},{"key":"435_CR23","unstructured":"Snoek J, Larochelle H, Adams RP (2012) Practical bayesian optimization of machine learning algorithms. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, vol 2, pp 2951\u20132959"},{"key":"435_CR24","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, et al. (2016) Tensorflow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation, pp 265\u2013283"},{"key":"435_CR25","unstructured":"Ramsundar B, Eastman P, Walters P, Pande V (2019) Deep learning for the life sciences. O\u2019Reilly Media inc.,"},{"key":"435_CR26","unstructured":"pfnet research: chainer-chemistry. https:\/\/github.com\/pfnet-research\/chainer-chemistry"},{"key":"435_CR27","unstructured":"Popova M Openchem: deep learning toolkit for computational chemistry and drug design. https:\/\/github.com\/Mariewelt\/OpenChem"},{"key":"435_CR28","unstructured":"Tokui S, Oono K, Hido S, Clayton J Chainer (2015) A next-generation open source framework for deep learning. In: Proceedings of Workshop on Machine Learning Systems (LearningSys) in the Twenty-ninth Annual Conference on Neural Information Processing Systems (NIPS), vol 5, pp 1\u20136"},{"key":"435_CR29","unstructured":"Landrum G (2018) RDKit: open-source cheminformatics. http:\/\/www.rdkit.org (Accessed August 21 2019)"},{"key":"435_CR30","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations"},{"key":"435_CR31","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1021\/acscentsci.6b00367","volume":"3","author":"H Altae-Tran","year":"2017","unstructured":"Altae-Tran H, Ramsundar B, Pappu AS, Pande V (2017) Low data drug discovery with one-shot learning. ACS Cent Sci 3:283\u2013293","journal-title":"ACS Cent Sci"},{"key":"435_CR32","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint. arXiv:1502.03167"},{"issue":"1","key":"435_CR33","doi-asserted-by":"publisher","first-page":"44","DOI":"10.3390\/molecules25010044","volume":"25","author":"F Montanari","year":"2020","unstructured":"Montanari F, Kuhnke L, Laak A Ter, Clevert D-A (2020) Modeling physico-chemical admet endpoints with multitask graph convolutional networks. Molecules 25(1):44","journal-title":"Molecules"},{"key":"435_CR34","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Zheng X (2015) TensorFlow: large-scale machine learning on heterogeneous systems. https:\/\/www.tensorflow.org\/ (Accessed 21 August 2019)"},{"key":"435_CR35","unstructured":"Chollet F, et al (2015) Keras. https:\/\/github.com\/fchollet\/keras"},{"issue":"12","key":"435_CR36","doi-asserted-by":"publisher","first-page":"5026","DOI":"10.1021\/acs.jcim.9b00538","volume":"59","author":"S Ishida","year":"2019","unstructured":"Ishida S, Terayama K, Kojima R, Takasu K, Okuno Y (2019) Prediction and interpretable visualization of retrosynthetic reactions using graph convolutional networks. J Chem Inform Model 59(12):5026\u20135033","journal-title":"J Chem Inform Model"},{"key":"435_CR37","unstructured":"The GPyOpt authors: GPyOpt (2016) A bayesian optimization framework in Python. http:\/\/github.com\/SheffieldML\/GPyOpt"},{"issue":"7270","key":"435_CR38","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, Laggner C, Abbas AI, Hufeisen SJ, Jensen NH, Kuijer MB, Matos RC, Tran TB et al (2009) Predicting new molecular targets for known drugs. Nature 462(7270):175\u2013181","journal-title":"Nature"},{"issue":"1","key":"435_CR39","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.drudis.2019.07.013","volume":"25","author":"A Gimeno","year":"2020","unstructured":"Gimeno A, Beltr\u00e1n-Deb\u00f3n R, Mulero M, Pujadas G, Garcia-Vallv\u00e9 S (2020) Understanding the variability of the S1\u2019 pocket to improve matrix metalloproteinase inhibitor selectivity profiles. Drug Discov Today 25(1):38\u201357","journal-title":"Drug Discov Today"},{"issue":"5","key":"435_CR40","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 Informat Model 50(5):742\u2013754","journal-title":"J Chem Informat Model"},{"issue":"2","key":"435_CR41","first-page":"237","volume":"56","author":"A Mauri","year":"2006","unstructured":"Mauri A, Consonni V, Pavan M, Todeschini R (2006) Dragon software: an easy approach to molecular descriptor calculations. MATCH Commun Math Comput Chem 56(2):237\u2013248","journal-title":"MATCH Commun Math Comput Chem"},{"issue":"6","key":"435_CR42","first-page":"1057","volume":"18","author":"P Zhang","year":"2016","unstructured":"Zhang P, Tao L, Zeng X, Qin C, Chen S, Zhu F, Li Z, Jiang Y, Chen W, Chen Y-Z (2016) A protein network descriptor server and its use in studying protein, disease, metabolic and drug targeted networks. Brief Bioinform 18(6):1057\u20131070","journal-title":"Brief Bioinform"},{"issue":"5","key":"435_CR43","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.1016\/j.bmcl.2005.01.024","volume":"15","author":"A Rossello","year":"2005","unstructured":"Rossello A, Nuti E, Carelli P, Orlandini E, Macchia M, Nencetti S, Zandomeneghi M, Balzano F, Barretta GU, Albini A, Benelli R, Cercignani G, Murphy G, Balsamo A (2005) Ni-propoxy-n-biphenylsulfonylaminobutylhydroxamic acids as potent and selective inhibitors of mmp-2 and mt1-mmp. Bioorg Med Chem Lett 15(5):1321\u20131326","journal-title":"Bioorg Med Chem Lett"},{"issue":"3","key":"435_CR44","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.jsb.2013.03.015","volume":"182","author":"C Antoni","year":"2013","unstructured":"Antoni C, Vera L, Devel L, Catalani MP, Czarny B, Cassar-Lajeunesse E, Nuti E, Rossello A, Dive V, Stura EA (2013) Crystallization of bi-functional ligand protein complexes. J Struct Biol 182(3):246\u2013254","journal-title":"J Struct Biol"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-020-00435-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-020-00435-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-020-00435-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T20:07:02Z","timestamp":1620763622000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-020-00435-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,12]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["435"],"URL":"https:\/\/doi.org\/10.1186\/s13321-020-00435-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.2.23904\/v1","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv.11859684.v1","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,12]]},"assertion":[{"value":"17 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"32"}}