{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T17:28:52Z","timestamp":1781803732901,"version":"3.54.5"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T00:00:00Z","timestamp":1637712000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T00:00:00Z","timestamp":1637712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Comput Aided Mol Des"],"published-print":{"date-parts":[[2022,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We here present a streamlined, explainable graph convolutional neural network (gCNN) architecture for small molecule activity prediction. We first conduct a hyperparameter optimization across nearly 800 protein targets that produces a simplified gCNN QSAR architecture, and we observe that such a model can yield performance improvements over both standard gCNN and RF methods on difficult-to-classify test sets. Additionally, we discuss how reductions in convolutional layer dimensions potentially speak to the \u201canatomical\u201d needs of gCNNs with respect to radial coarse graining of molecular substructure. We augment this simplified architecture with saliency map technology that highlights molecular substructures relevant to activity, and we perform saliency analysis on nearly 100 data-rich protein targets. We show that resultant substructural clusters are useful visualization tools for understanding substructure-activity relationships. We go on to highlight connections between our models\u2019 saliency predictions and observations made in the medicinal chemistry literature, focusing on four case studies of past lead finding and lead optimization campaigns.<\/jats:p>","DOI":"10.1007\/s10822-021-00421-6","type":"journal-article","created":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T05:02:37Z","timestamp":1637730157000},"page":"391-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Simplified, interpretable graph convolutional neural networks for small molecule activity prediction"],"prefix":"10.1007","volume":"36","author":[{"given":"Jeffrey K.","family":"Weber","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph A.","family":"Morrone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sugato","family":"Bagchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan D. Estrada","family":"Pabon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seung-gu","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leili","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7339-0201","authenticated-orcid":false,"given":"Wendy D.","family":"Cornell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,11,24]]},"reference":[{"key":"421_CR1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1021\/jm00135a001","volume":"24","author":"Y Martin","year":"1981","unstructured":"Martin Y (1981) A practitioner\u2019s perspective of the role of quantitative structure-activity analysis in medicinal chemistry. J Med Chem 24:229\u2013237","journal-title":"J Med Chem"},{"key":"421_CR2","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1021\/ci500666m","volume":"55","author":"RP Sheridan","year":"2015","unstructured":"Sheridan RP, McMasters DR, Voigt JH, Wildey MJ (2015) ECounterscreening: using QSAR predictions to prioritize testing for off-target activities and setting the balance between benefit and risk. J Chem Inf Model 55:231\u2013238. https:\/\/doi.org\/10.1021\/ci500666m","journal-title":"J Chem Inf Model"},{"key":"421_CR3","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00375","author":"EJ Martin","year":"2019","unstructured":"Martin EJ, Polyakov VR, Zhu X-W et al (2019) All-assay-Max2 pQSAR: Activity predictions as accurate as four-concentration IC 50 s for 8558 novartis assays. J Chem Inf Model. https:\/\/doi.org\/10.1021\/acs.jcim.9b00375","journal-title":"J Chem Inf Model"},{"key":"421_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.01.021","author":"JM Stokes","year":"2020","unstructured":"Stokes JM, Yang K, Swanson K et al (2020) A deep learning approach to antibiotic discovery. Cell. https:\/\/doi.org\/10.1016\/j.cell.2020.01.021","journal-title":"Cell"},{"key":"421_CR5","doi-asserted-by":"publisher","DOI":"10.1080\/13543776.2018.1475560","author":"AK Halder","year":"2018","unstructured":"Halder AK, Moura AS, Cordeiro MNDS (2018) QSAR modelling: a therapeutic patent review 2010-present. Expert Opin Ther Pat. https:\/\/doi.org\/10.1080\/13543776.2018.1475560","journal-title":"Expert Opin Ther Pat"},{"key":"421_CR6","doi-asserted-by":"publisher","first-page":"3525","DOI":"10.1039\/D0CS00098A","volume":"49","author":"EN Muratov","year":"2020","unstructured":"Muratov EN, Bajorath J, Sheridan RP et al (2020) QSAR without borders. Chem Soc Rev 49:3525\u20133564","journal-title":"Chem Soc Rev"},{"key":"421_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-011-9449-6","author":"Y Martin","year":"2011","unstructured":"Martin Y, Stouch T (2011) In tribute to Corwin Hansch, father of QSAR. J Comput Aided Mol Des. https:\/\/doi.org\/10.1007\/s10822-011-9449-6","journal-title":"J Comput Aided Mol Des"},{"key":"421_CR8","doi-asserted-by":"publisher","DOI":"10.1021\/ci034160g","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. https:\/\/doi.org\/10.1021\/ci034160g","journal-title":"J Chem Inf Comput Sci"},{"key":"421_CR9","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":"421_CR10","unstructured":"PubChem substructure fingerprint description. ftp:\/\/ftp.ncbi.nlm.nih.gov\/pubchem\/specifications\/pubchem_fingerprints.pdf"},{"key":"421_CR11","first-page":"199","volume":"9","author":"RC Glem","year":"2006","unstructured":"Glem RC, Bender A, Arnby CH et al (2006) Circular fingerprints: flexible molecular descriptors with applications from physical chem. IDrugs 9:199\u2013204","journal-title":"IDrugs"},{"key":"421_CR12","unstructured":"Duvenaud D, Maclaurin D, Aguilera-Iparraguirre J, et al (2015) Convolutional networks on graphs for learning molecular fingerprints. In: Advances in neural information processing systems"},{"key":"421_CR13","doi-asserted-by":"publisher","DOI":"10.1002\/minf.201300180","author":"L Li","year":"2014","unstructured":"Li L, Hu J, Ho Y-S (2014) Global performance and trend of QSAR\/QSPR research: a bibliometric analysis. Mol Inf. https:\/\/doi.org\/10.1002\/minf.201300180","journal-title":"Mol Inf"},{"key":"421_CR14","doi-asserted-by":"publisher","DOI":"10.3390\/ijms21155576","author":"P Willett","year":"2020","unstructured":"Willett P (2020) The literature of chemoinformatics: 1978\u20132018. Int J Mol Sci. https:\/\/doi.org\/10.3390\/ijms21155576","journal-title":"Int J Mol Sci"},{"key":"421_CR15","doi-asserted-by":"publisher","DOI":"10.1021\/ci200081k","author":"AB Yongye","year":"2011","unstructured":"Yongye AB, Byler K, Santos R et al (2011) Consensus models of activity landscapes with multiple chemical, conformer, and property representations. J Chem Inf Model. https:\/\/doi.org\/10.1021\/ci200081k","journal-title":"J Chem Inf Model"},{"key":"421_CR16","doi-asserted-by":"publisher","DOI":"10.1021\/ci200615h","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. https:\/\/doi.org\/10.1021\/ci200615h","journal-title":"J Chem Inf Model"},{"key":"421_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-016-9938-8","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. https:\/\/doi.org\/10.1007\/s10822-016-9938-8","journal-title":"J Comput Aided Mol Des"},{"key":"421_CR18","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.6b00367","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. https:\/\/doi.org\/10.1021\/acscentsci.6b00367","journal-title":"ACS Cent Sci"},{"key":"421_CR19","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1021\/acs.jcim.6b00601","volume":"57","author":"CW Coley","year":"2017","unstructured":"Coley CW, Barzilay R, Green WH et al (2017) Convolutional embedding of attributed molecular graphs for physical property prediction. J Chem Inf Model 57:1757\u20131772. https:\/\/doi.org\/10.1021\/acs.jcim.6b00601","journal-title":"J Chem Inf Model"},{"key":"421_CR20","doi-asserted-by":"publisher","DOI":"10.1039\/c7sc02664a","author":"Z Wu","year":"2018","unstructured":"Wu Z, Ramsundar B, Feinberg EN et al (2018) MoleculeNet: a benchmark for molecular machine learning. Chem Sci. https:\/\/doi.org\/10.1039\/c7sc02664a","journal-title":"Chem Sci"},{"key":"421_CR21","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00927","author":"JA Morrone","year":"2020","unstructured":"Morrone JA, Weber JK, Huynh T et al (2020) Combining docking pose rank and structure with deep learning improves protein\u2212ligand binding mode prediction over a baseline docking approach. J Chem Inf Model. https:\/\/doi.org\/10.1021\/acs.jcim.9b00927","journal-title":"J Chem Inf Model"},{"key":"421_CR22","doi-asserted-by":"publisher","first-page":"1324","DOI":"10.1021\/acs.jcim.8b00825","volume":"59","author":"RP Sheridan","year":"2019","unstructured":"Sheridan RP (2019) Interpretation of QSAR models by coloring atoms according to changes in predicted activity: how robust is it? J Chem Inf Model 59:1324\u20131337. https:\/\/doi.org\/10.1021\/acs.jcim.8b00825","journal-title":"J Chem Inf Model"},{"key":"421_CR23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-10663-6","author":"T Xie","year":"2019","unstructured":"Xie T, France-Lanord A, Wang Y et al (2019) Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials. Nat Commun. https:\/\/doi.org\/10.1038\/s41467-019-10663-6","journal-title":"Nat Commun"},{"key":"421_CR24","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":"421_CR25","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-0414-z","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. https:\/\/doi.org\/10.1186\/s13321-020-0414-z","journal-title":"J Cheminform"},{"key":"421_CR26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012460413855","author":"T Kadir","year":"2001","unstructured":"Kadir T, Brady M (2001) Saliency, scale and image description. Int J Comput Vis. https:\/\/doi.org\/10.1023\/A:1012460413855","journal-title":"Int J Comput Vis"},{"key":"421_CR27","doi-asserted-by":"crossref","unstructured":"Pope PE, Kolouri S, Rostami M, et al (2019) Explainability methods for graph convolutional neural networks. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2019.01103"},{"key":"421_CR28","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2544-0","author":"S Dey","year":"2018","unstructured":"Dey S, Luo H, Fokoue A et al (2018) Predicting adverse drug reactions through interpretable deep learning framework. BMC Bioinform. https:\/\/doi.org\/10.1186\/s12859-018-2544-0","journal-title":"BMC Bioinform"},{"key":"421_CR29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.97.062412","author":"CX Hern\u00e1ndez","year":"2018","unstructured":"Hern\u00e1ndez CX, Wayment-Steele HK, Sultan MM et al (2018) Variational encoding of complex dynamics. Phys Rev E. https:\/\/doi.org\/10.1103\/PhysRevE.97.062412","journal-title":"Phys Rev E"},{"key":"421_CR30","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-018-0325-4","author":"N Bosc","year":"2019","unstructured":"Bosc N, Atkinson F, Felix E et al (2019) Large scale comparison of QSAR and conformal prediction methods and their applications in drug discovery. J Cheminform. https:\/\/doi.org\/10.1186\/s13321-018-0325-4","journal-title":"J Cheminform"},{"key":"421_CR31","doi-asserted-by":"publisher","DOI":"10.1021\/ci400084k","author":"RP Sheridan","year":"2013","unstructured":"Sheridan RP (2013) Time-split cross-validation as a method for estimating the goodness of prospective prediction. J Chem Inf Model. https:\/\/doi.org\/10.1021\/ci400084k","journal-title":"J Chem Inf Model"},{"key":"421_CR32","unstructured":"Abadi M, Agarwal A, Barham P, et al (2016) TensorFlow: large-scale machine learning on heterogeneous distributed systems"},{"key":"421_CR33","unstructured":"Landrum G (2021) RDKit: open-source cheminformatics software. https:\/\/www.rdkit.org\/"},{"key":"421_CR34","doi-asserted-by":"publisher","first-page":"1912","DOI":"10.1021\/ci049782w","volume":"44","author":"RP Sheridan","year":"2004","unstructured":"Sheridan RP, Feuston BP, Maiorov VN, Kearsley SK (2004) Similarity to molecules in the training set is a good discriminator for prediction accuracy in QSAR. J Chem Inf Comput Sci 44:1912\u20131928. https:\/\/doi.org\/10.1021\/ci049782w","journal-title":"J Chem Inf Comput Sci"},{"key":"421_CR35","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1016\/j.bmcl.2011.10.049","volume":"22","author":"L Alcaraz","year":"2012","unstructured":"Alcaraz L, Bailey A, Cadogan E et al (2012) From libraries to candidate: the discovery of new ultra long-acting dibasic \u03b2 2-adrenoceptor agonists. Bioorg Med Chem Lett 22:689\u2013695. https:\/\/doi.org\/10.1016\/j.bmcl.2011.10.049","journal-title":"Bioorg Med Chem Lett"},{"key":"421_CR36","doi-asserted-by":"publisher","DOI":"10.1021\/jm960871c","author":"LJ MacPherson","year":"1997","unstructured":"MacPherson LJ, Bayburt EK, Capparelli MP et al (1997) Discovery of CGS 27023A, a non-peptidic, potent, and orally active stromelysin inhibitor that blocks cartilage degradation in rabbits. J Med Chem. https:\/\/doi.org\/10.1021\/jm960871c","journal-title":"J Med Chem"},{"key":"421_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.bmcl.2011.03.099","author":"TE Barta","year":"2011","unstructured":"Barta TE, Becker DP, Bedell LJ et al (2011) MMP-13 selective \u03b1-sulfone hydroxamates: A survey of P1\u2032 heterocyclic amide isosteres. Bioorg Med Chem Lett. https:\/\/doi.org\/10.1016\/j.bmcl.2011.03.099","journal-title":"Bioorg Med Chem Lett"},{"key":"421_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmech.2011.03.033","author":"E Nuti","year":"2011","unstructured":"Nuti E, Casalini F, Santamaria S et al (2011) Synthesis and biological evaluation in U87MG glioma cells of (ethynylthiophene)sulfonamido-based hydroxamates as matrix metalloproteinase inhibitors. Eur J Med Chem. https:\/\/doi.org\/10.1016\/j.ejmech.2011.03.033","journal-title":"Eur J Med Chem"},{"key":"421_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.bmcl.2003.10.023","author":"PL Beaulieu","year":"2004","unstructured":"Beaulieu PL, B\u00f6s M, Bousquet Y et al (2004) Non-nucleoside inhibitors of the hepatitis C virus NS5B polymerase: discovery and preliminary SAR of benzimidazole derivatives. Bioorg Med Chem Lett. https:\/\/doi.org\/10.1016\/j.bmcl.2003.10.023","journal-title":"Bioorg Med Chem Lett"},{"key":"421_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.bmcl.2006.01.032","author":"T Ishida","year":"2006","unstructured":"Ishida T, Suzuki T, Hirashima S et al (2006) Benzimidazole inhibitors of hepatitis C virus NS5B polymerase: identification of 2-[(4-diarylmethoxy)phenyl]-benzimidazole. Bioorg Med Chem Lett. https:\/\/doi.org\/10.1016\/j.bmcl.2006.01.032","journal-title":"Bioorg Med Chem Lett"},{"key":"421_CR41","doi-asserted-by":"publisher","DOI":"10.1128\/JVI.75.18.8615-8623.2001","author":"CT Ranjith-Kumar","year":"2001","unstructured":"Ranjith-Kumar CT, Gajewski J, Gutshall L et al (2001) Terminal nucleotidyl transferase activity of recombinant Flaviviridae RNA-dependent RNA polymerases: implication for viral RNA synthesis. J Virol. https:\/\/doi.org\/10.1128\/JVI.75.18.8615-8623.2001","journal-title":"J Virol"},{"key":"421_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.bmc.2011.06.079","author":"D Das","year":"2011","unstructured":"Das D, Hong J, Chen S-H et al (2011) Recent advances in drug discovery of benzothiadiazine and related analogs as HCV NS5B polymerase inhibitors. Bioorg Med Chem. https:\/\/doi.org\/10.1016\/j.bmc.2011.06.079","journal-title":"Bioorg Med Chem"},{"key":"421_CR43","doi-asserted-by":"publisher","DOI":"10.1021\/jm050855s","author":"R Tedesco","year":"2006","unstructured":"Tedesco R, Shaw AN, Bambal R et al (2006) 3-(1,1-Dioxo-2 H -(1,2,4)-benzothiadiazin-3-yl)-4-hydroxy-2(1 H )-quinolinones, potent inhibitors of hepatitis C virus RNA-dependent RNA polymerase. J Med Chem. https:\/\/doi.org\/10.1021\/jm050855s","journal-title":"J Med Chem"},{"key":"421_CR44","doi-asserted-by":"publisher","DOI":"10.3390\/v2102169","author":"MH Powdrill","year":"2010","unstructured":"Powdrill MH, Bernatchez JA, G\u00f6tte M (2010) Inhibitors of the hepatitis C virus RNA-dependent RNA polymerase NS5B. Viruses. https:\/\/doi.org\/10.3390\/v2102169","journal-title":"Viruses"},{"key":"421_CR45","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00451","author":"S Maramai","year":"2016","unstructured":"Maramai S, Gemma S, Brogi S et al (2016) Dopamine D3 receptor antagonists as potential therapeutics for the treatment of neurological diseases. Front Neurosci. https:\/\/doi.org\/10.3389\/fnins.2016.00451","journal-title":"Front Neurosci"},{"key":"421_CR46","doi-asserted-by":"publisher","DOI":"10.1021\/jm401895u","author":"M Ko\u0142aczkowski","year":"2014","unstructured":"Ko\u0142aczkowski M, Marcinkowska M, Bucki A et al (2014) Novel arylsulfonamide derivatives with 5-HT6\/5-HT7 receptor antagonism targeting behavioral and psychological symptoms of dementia. J Med Chem. https:\/\/doi.org\/10.1021\/jm401895u","journal-title":"J Med Chem"},{"key":"421_CR47","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.6b01578","author":"A de Simone","year":"2017","unstructured":"de Simone A, Russo D, Ruda GF et al (2017) Design, synthesis, structure-activity relationship studies, and three-dimensional quantitative structure-activity relationship (3D-QSAR) modeling of a series of O-biphenyl carbamates as dual modulators of dopamine D3 receptor and fatty acid amide hydrolase. J Med Chem. https:\/\/doi.org\/10.1021\/acs.jmedchem.6b01578","journal-title":"J Med Chem"},{"key":"421_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.bmcl.2014.12.023","author":"X Peng","year":"2015","unstructured":"Peng X, Wang Q, Mishra Y et al (2015) Synthesis, pharmacological evaluation and molecular modeling studies of triazole containing dopamine D3 receptor ligands. Bioorg Med Chem Lett. https:\/\/doi.org\/10.1016\/j.bmcl.2014.12.023","journal-title":"Bioorg Med Chem Lett"},{"key":"421_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.bmc.2016.02.031","author":"F Micheli","year":"2016","unstructured":"Micheli F, Bernardelli A, Bianchi F et al (2016) 1,2,4-Triazolyl octahydropyrrolo[2,3-b]pyrroles: a new series of potent and selective dopamine D3 receptor antagonists. Bioorg Med Chem. https:\/\/doi.org\/10.1016\/j.bmc.2016.02.031","journal-title":"Bioorg Med Chem"},{"key":"421_CR50","unstructured":"Dhurandhar A, Chen P-Y, Luss R, et al Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives"},{"key":"421_CR51","doi-asserted-by":"publisher","first-page":"11624","DOI":"10.1073\/pnas.1820657116","volume":"116","author":"K McCloskey","year":"2019","unstructured":"McCloskey K, Taly A, Monti F et al (2019) Using attribution to decode binding mechanism in neural network models for chemistry. Proc Natl Acad Sci U S A 116:11624\u201311629. https:\/\/doi.org\/10.1073\/pnas.1820657116","journal-title":"Proc Natl Acad Sci U S A"},{"key":"421_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42005-020-0338-y","volume":"3","author":"S Kajita","year":"2020","unstructured":"Kajita S, Kinjo T, Nishi T (2020) Autonomous molecular design by Monte-Carlo tree search and rapid evaluations using molecular dynamics simulations. Commun Phys 3:1\u201311. https:\/\/doi.org\/10.1038\/s42005-020-0338-y","journal-title":"Commun Phys"},{"key":"421_CR53","doi-asserted-by":"publisher","first-page":"3567","DOI":"10.1039\/c8sc05372c","volume":"10","author":"JH Jensen","year":"2019","unstructured":"Jensen JH (2019) A graph-based genetic algorithm and generative model\/Monte Carlo tree search for the exploration of chemical space. Chem Sci 10:3567\u20133572. https:\/\/doi.org\/10.1039\/c8sc05372c","journal-title":"Chem Sci"}],"container-title":["Journal of Computer-Aided Molecular Design"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-021-00421-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10822-021-00421-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-021-00421-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T08:09:25Z","timestamp":1658822965000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10822-021-00421-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,24]]},"references-count":53,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["421"],"URL":"https:\/\/doi.org\/10.1007\/s10822-021-00421-6","relation":{},"ISSN":["0920-654X","1573-4951"],"issn-type":[{"value":"0920-654X","type":"print"},{"value":"1573-4951","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,24]]},"assertion":[{"value":"9 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}