{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T23:45:39Z","timestamp":1783467939578,"version":"3.55.0"},"reference-count":65,"publisher":"American Chemical Society (ACS)","issue":"8","license":[{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005690","name":"Universit?t des Saarlandes","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005690","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Bundesministerium f?r Forschung, Technologie und Raumfahrt","award":["031L0306A"],"award-info":[{"award-number":["031L0306A"]}]},{"name":"Klaus Faber Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1021\/acs.jcim.6c00037","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T19:03:01Z","timestamp":1776279781000},"page":"4947-4961","source":"Crossref","is-referenced-by-count":1,"title":["Explainability Methods from Machine Learning Detect Important Drugs\u2019 Atoms in Drug-Target Interactions"],"prefix":"10.1021","volume":"66","author":[{"given":"Mrinal","family":"Mahindran","sequence":"first","affiliation":[{"name":"Center for Bioinformatics","place":["Saarbr\u00fccken, Germany"]},{"name":"Saarland University","place":["Saarbr\u00fccken, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics","place":["Saarbr\u00fccken, Germany"]},{"name":"Saarland University","place":["Saarbr\u00fccken, Germany"]},{"name":"Helmholtz Institute for Pharmaceutical Research Saarland (HIPS)","place":["Saarbr\u00fccken, Germany"]},{"name":"Helmholtz Centre for Infection Research (HZI)","place":["Saarbr\u00fccken, Germany"]},{"name":"International Max Planck Research School on Trustworthy Computing","place":["Saarbr\u00fccken, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vishak Madhwaraj","family":"Kadambalithaya","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics","place":["Saarbr\u00fccken, Germany"]},{"name":"Saarland University","place":["Saarbr\u00fccken, Germany"]},{"name":"Helmholtz Institute for Pharmaceutical Research Saarland (HIPS)","place":["Saarbr\u00fccken, Germany"]},{"name":"Helmholtz Centre for Infection Research (HZI)","place":["Saarbr\u00fccken, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9445-477X","authenticated-orcid":true,"given":"Olga V.","family":"Kalinina","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics","place":["Saarbr\u00fccken, Germany"]},{"name":"Saarland University","place":["Saarbr\u00fccken, Germany"]},{"name":"Helmholtz Institute for Pharmaceutical Research Saarland (HIPS)","place":["Saarbr\u00fccken, Germany"]},{"name":"Helmholtz Centre for Infection Research (HZI)","place":["Saarbr\u00fccken, Germany"]},{"name":"Medical Faculty","place":["Homburg, Germany"]},{"name":"Saarland University","place":["Homburg, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,4,15]]},"reference":[{"key":"ref1\/cit1","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2018.01.039"},{"key":"ref2\/cit2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00236-4"},{"key":"ref3\/cit3","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btn162"},{"key":"ref4\/cit4","doi-asserted-by":"publisher","DOI":"10.1021\/ci400709d"},{"key":"ref5\/cit5","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty593"},{"key":"ref6\/cit6","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz111"},{"key":"ref7\/cit7","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa544"},{"key":"ref8\/cit8","unstructured":"Gilmer, J.; Schoenholz, S. S.; Riley, P. F.; Vinyals, O.; Dahl, G. E. In\n                      Neural Message Passing for Quantum Chemistry\n                      , Proceedings of the 34th International Conference on Machine Learning (ICML), 2017; pp 1263\u20131272."},{"key":"ref9\/cit9","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00628"},{"key":"ref10\/cit10","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa921"},{"key":"ref11\/cit11","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2021.102327"},{"key":"ref12\/cit12","doi-asserted-by":"publisher","DOI":"10.1039\/D0RA02297G"},{"key":"ref13\/cit13","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty535"},{"key":"ref14\/cit14","doi-asserted-by":"crossref","unstructured":"Quan, Z.; Guo, Y.; Lin, X.; Wang, Z.J.; Zeng, X. In\n                      Graphcpi: Graph Neural Representation Learning for Compound-Protein Interaction\n                      , 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2019; pp 717\u2013722.","DOI":"10.1109\/BIBM47256.2019.8983267"},{"key":"ref15\/cit15","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2017.0387"},{"key":"ref16\/cit16","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref17\/cit17","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-016-9938-8"},{"key":"ref18\/cit18","unstructured":"Duvenaud, D. K.; Maclaurin, D.; Aguilera-Iparraguirre, J.; G\u00f3mez-Bombarelli, R.; Hirzel, T.; Aspuru-Guzik, A.; Adams, R. P. In\n                      Convolutional Networks on Graphs for Learning Molecular Fingerprints\n                      , Advances in Neural Information Processing Systems 28 (NIPS 2015), 2015; pp 2224\u20132232."},{"key":"ref19\/cit19","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"ref20\/cit20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08987-4"},{"key":"ref21\/cit21","doi-asserted-by":"crossref","unstructured":"Nguyen, A.; Yosinski, J.; Clune, J. In\n                      Deep Neural Networks Are Easily Fooled: High Confidence Predictions for Unrecognizable Images\n                      , Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015; pp 427\u2013436.","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref22\/cit22","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"ref23\/cit23","unstructured":"Murdoch, W. J.; Singh, C.; Kumbier, K.; Abbasi-Asl, R.; Yu, B. Interpretable Machine Learning: Definitions, Methods, and Applications. 2019, arXiv:1901.04592. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1901.04592."},{"key":"ref24\/cit24","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. T.; Singh, S.; Guestrin, C. In\n                      \u201cWhy Should I Trust You?\u201d Explaining the Predictions of Any Classifier\n                      , Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016; pp 1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"key":"ref25\/cit25","unstructured":"Baldassarre, F.; Azizpour, H. Explainability Techniques for Graph Convolutional Networks. 2019, arXiv:1905.13686. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1905.13686."},{"key":"ref26\/cit26","unstructured":"Ying, Z.; Bourgeois, D.; You, J.; Zitnik, M.; Leskovec, J. In\n                      Gnnexplainer: Generating Explanations for Graph Neural Networks\n                      , Advances in Neural Information Processing Systems 32, 2019."},{"key":"ref27\/cit27","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.6b00753"},{"key":"ref28\/cit28","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b01101"},{"key":"ref29\/cit29","doi-asserted-by":"publisher","DOI":"10.1039\/C8SC04228D"},{"key":"ref30\/cit30","unstructured":"Shang, C.; Liu, Q.; Chen, K.S.; Sun, J.; Lu, J.; Yi, J.; Bi, J. Edge Attention-Based Multi-Relational Graph Convolutional Networks. 2018, arXiv:1802.04944. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1802.04944."},{"key":"ref31\/cit31","doi-asserted-by":"publisher","DOI":"10.1039\/D5SC08461J"},{"key":"ref32\/cit32","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.70049"},{"key":"ref33\/cit33","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. T.; Singh, S.; Guestrin, C. In\n                      Anchors: High-Precision Model-Agnostic Explanations\n                      , Proceedings of the AAAI Conference on Artificial Intelligence, 2018.","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"ref34\/cit34","unstructured":"Feng, Q.; Huang, N.; Fan, J.; Xiao, L.; Wang, W.; Zhao, Q. In\n                      DEGREE: Decomposition Based Explanation for Graph Neural Networks\n                      , International Conference on Learning Representations (ICLR), 2022."},{"key":"ref35\/cit35","unstructured":"Yuan, H.; Yu, H.; Gui, S.; Ji, S. Explainability in Graph Neural Networks: A Taxonomic Survey. 2020, arXiv:2012.15445. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2012.15445."},{"key":"ref36\/cit36","unstructured":"Li, J.; Pang, M.; Dong, Y. Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks. 2025, arXiv:2502.04224. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2502.04224."},{"key":"ref37\/cit37","unstructured":"Yuan, H.; Yu, H.; Wang, J.; Li, K.; Ji, S. In\n                      On Explainability of Graph Neural Networks via Subgraph Explorations\n                      , International Conference on Machine Learning, 2021; pp 12241\u201312252."},{"key":"ref38\/cit38","unstructured":"Luo, D.; Cheng, W.; Xu, D.; Yu, W.; Zong, B.; Chen, H.; Zhang, X. In\n                      Parameterized Explainer for Graph Neural Network\n                      , Advances in Neural Information Processing Systems 33, 2020; pp 19620\u201319631."},{"key":"ref39\/cit39","unstructured":"Schwab, P.; Karlen, W. In\n                      Cxplain: Causal Explanations for Model Interpretation under Uncertainty\n                      , Advances in Neural Information Processing Systems 32, 2019."},{"key":"ref40\/cit40","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1510-8"},{"key":"ref41\/cit41","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106145"},{"key":"ref42\/cit42","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad355"},{"key":"ref43\/cit43","unstructured":"Veli\u010dkovi\u0107, P.; Cucurull, G.; Casanova, A.; Romero, A.; Li\u00f3, P.; Bengio, Y. Graph Attention Networks. 2018, arXiv:1710.10903. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1710.10903."},{"key":"ref44\/cit44","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa266"},{"key":"ref45\/cit45","doi-asserted-by":"publisher","DOI":"10.1039\/D1SC05180F"},{"key":"ref46\/cit46","unstructured":"Hechtlinger, Y. Interpretation of Prediction Models Using the Input Gradient. 2016, arXiv:1611.07634. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1611.07634."},{"key":"ref47\/cit47","unstructured":"Springenberg, J. T.; Dosovitskiy, A.; Brox, T.; Riedmiller, M. Striving for Simplicity: The All Convolutional Net. 2015, arXiv:1412.6806. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1412.6806."},{"key":"ref48\/cit48","unstructured":"Sundararajan, M.; Taly, A.; Yan, Q. In\n                      Axiomatic Attribution for Deep Networks\n                      , Proceedings of the 34th International Conference on Machine Learning (ICML), 2017; pp 3319\u20133328."},{"key":"ref49\/cit49","unstructured":"Lundberg, S. M.; Lee, S.I. In\n                      A Unified Approach to Interpreting Model Predictions\n                      , Advances in Neural Information Processing Systems, 2017."},{"key":"ref50\/cit50","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv302"},{"key":"ref51\/cit51","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.1990"},{"key":"ref52\/cit52","unstructured":"Landrum, G. RDKit: Open-Source Cheminformatics, 2006. http:\/\/www.rdkit.org (accessed Sept 15, 2025)."},{"key":"ref53\/cit53","doi-asserted-by":"publisher","DOI":"10.1016\/j.gde.2010.10.012"},{"key":"ref54\/cit54","doi-asserted-by":"publisher","DOI":"10.1038\/nrd.2017.178"},{"key":"ref55\/cit55","unstructured":"Fey, M.; Lenssen, J. E. In\n                      PyTorch Geometric: Deep Learning on Irregularly Structured Input Data\n                      , Proceedings of the International Conference on Learning Representations (ICLR) Workshop on Representation Learning on Graphs and Manifolds, 2019."},{"key":"ref56\/cit56","unstructured":"Brossard, R.; Frigo, O.; Dehaene, D. Graph Convolutions That Can Finally Model Local Structure. 2021, arXiv:2011.15069. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2011.15069."},{"key":"ref57\/cit57","unstructured":"Hamilton, W. L.; Ying, R.; Leskovec, J. Inductive Representation Learning on Large Graphs. 2018, arXiv:1706.02216. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1706.02216."},{"key":"ref58\/cit58","unstructured":"Yun, S.; Jeong, M.; Kim, R.; Kang, J.; Kim, H. J. Graph Transformer Networks. 2020, arXiv:1911.06455. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1911.06455."},{"key":"ref59\/cit59","unstructured":"Brockschmidt, M. GNN-FiLM: Graph Neural Networks with Feature-Wise Linear Modulation. 2020, arXiv:1906.12192. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1906.12192."},{"key":"ref60\/cit60","unstructured":"He, M.; Wei, Z.; Wen, J.R. Convolutional Neural Networks on Graphs with Chebyshev Approximation. 2024, arXiv:2202.03580. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2202.03580."},{"key":"ref61\/cit61","unstructured":"Kingma, D. P.; Ba, J. Adam: A Method for Stochastic Optimization. 2017, arXiv:1412.6980. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"ref62\/cit62","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa895"},{"key":"ref63\/cit63","unstructured":"Shrikumar, A.; Greenside, P.; Kundaje, A. In\n                      Learning Important Features through Propagating Activation Differences\n                      , International Conference on Machine Learning, 2017; pp 3145\u20133153."},{"key":"ref64\/cit64","unstructured":"Anani, A.; Lorenz, T.; Fritz, M.; Schiele, B. Pixel-Level Certified Explanations via Randomized Smoothing. 2025, arXiv:2506.15499. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2506.15499."},{"key":"ref65\/cit65","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv1072"}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00037","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T08:11:39Z","timestamp":1777277499000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/acs.jcim.6c00037"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,15]]},"references-count":65,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,4,27]]}},"alternative-id":["10.1021\/acs.jcim.6c00037"],"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c00037","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,15]]}}}