{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:36:02Z","timestamp":1773246962397,"version":"3.50.1"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T00:00:00Z","timestamp":1672963200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T00:00:00Z","timestamp":1672963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100004326","name":"Bayer AG","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100004326","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>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      Explainable artificial intelligence (XAI) methods have shown increasing applicability in chemistry. In this context, visualization techniques can highlight regions of a molecule to reveal their influence over a predicted property. For this purpose, some XAI techniques calculate attribution scores associated with tokens of SMILES strings or with atoms of a molecule. While an association of a score with an atom can be directly visually represented on a molecule diagram, scores computed for SMILES non-atom tokens cannot. For instance, a substring\n                      <jats:italic>[N+]<\/jats:italic>\n                      contains 3 non-atom tokens, i.e., [,\n                      <jats:inline-formula>\n                        <jats:alternatives>\n                          <jats:tex-math>$$+$$<\/jats:tex-math>\n                          <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                            <mml:mo>+<\/mml:mo>\n                          <\/mml:math>\n                        <\/jats:alternatives>\n                      <\/jats:inline-formula>\n                      , and ], and their attributions, depending on the model, are not necessarily revealing an influence of the nitrogen atom over the predicted property; for that reason, it is not possible to represent the scores on a molecule diagram. Moreover, SMILES\u2019s notation is complex, foregrounding the need for techniques to facilitate the analysis of explanations associated with their tokens.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We propose XSMILES, an interactive visualization technique, to explore explainable artificial intelligence attributions scores and support the interpretation of SMILES. Users can input any type of score attributed to atom and non-atom tokens and visualize them on top of a 2D molecule diagram coordinated with a bar chart that represents a SMILES string. We demonstrate how attributions calculated for SMILES strings can be evaluated and better interpreted through interactivity with two use cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Data scientists can use XSMILES to understand their models\u2019 behavior and compare multiple modeling approaches. The tool provides a set of parameters to adapt the visualization to users\u2019 needs and it can be integrated into different platforms. We believe XSMILES can support data scientists to develop, improve, and communicate their models by making it easier to identify patterns and compare attributions through interactive exploratory visualization.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13321-022-00673-w","type":"journal-article","created":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T02:18:06Z","timestamp":1672971486000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["XSMILES: interactive visualization for molecules, SMILES and XAI attribution scores"],"prefix":"10.1186","volume":"15","author":[{"given":"Henry","family":"Heberle","sequence":"first","affiliation":[]},{"given":"Linlin","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Schmidt","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Wolf","sequence":"additional","affiliation":[]},{"given":"Julian","family":"Heinrich","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,6]]},"reference":[{"key":"673_CR1","doi-asserted-by":"publisher","unstructured":"Vamathevan J, Clark D, Czodrowski P, Dunham I, Ferran E, Lee G, Li B, Madabhushi A, Shah P, Spitzer M, Zhao S (2019) Applications of machine learning in drug discovery and development. Nat Rev Drug Discov 18(6):463\u2013477. https:\/\/doi.org\/10.1038\/s41573-019-0024-5. [cito:obtainsBackgroundFrom]","DOI":"10.1038\/s41573-019-0024-5"},{"key":"673_CR2","doi-asserted-by":"publisher","unstructured":"Elbadawi M, Gaisford S, Basit AW (2021) Advanced machine-learning techniques in drug discovery. Drug Discov Today 26(3):769\u2013777. https:\/\/doi.org\/10.1016\/j.drudis.2020.12.003. [cito:obtainsBackgroundFrom]","DOI":"10.1016\/j.drudis.2020.12.003"},{"key":"673_CR3","doi-asserted-by":"publisher","unstructured":"Polishchuk P (2017) Interpretation of quantitative structure\u2013activity relationship models: past, present, and future. J Chem Inf Model 57(11), 2618\u20132639. https:\/\/doi.org\/10.1021\/acs.jcim.7b00274. [cito:containsAssertionFrom]","DOI":"10.1021\/acs.jcim.7b00274"},{"key":"673_CR4","doi-asserted-by":"publisher","unstructured":"Rodr\u00edguez-P\u00e9rez R, Bajorath J (2020) Interpretation of compound activity predictions from complex machine learning models using local approximations and shapley values. J Comput-Aid Mol Des 63(16):8761\u20138777. https:\/\/doi.org\/10.1021\/acs.jmedchem.9b01101. [cito:containsAssertionFrom] [cito:usesMethodIn]","DOI":"10.1021\/acs.jmedchem.9b01101"},{"key":"673_CR5","doi-asserted-by":"publisher","unstructured":"Karpov P, Godin G, Tetko IV (2017) Transformer-CNN: Swiss knife for QSAR modeling and interpretation. J Cheminform 12(17): 1758\u20132946 (2020). https:\/\/doi.org\/10.1186\/s13321-020-00423-w. [cito:citesForInformation]","DOI":"10.1186\/s13321-020-00423-w"},{"key":"673_CR6","doi-asserted-by":"publisher","unstructured":"Jim\u00e9nez-Luna J, Grisoni F, Schneider G (2020) Drug discovery with explainable artificial intelligence. Nat Mach Intell 2(10):573\u2013584. https:\/\/doi.org\/10.1038\/s42256-020-00236-4. [cito:citesForInformation]","DOI":"10.1038\/s42256-020-00236-4"},{"key":"673_CR7","doi-asserted-by":"publisher","unstructured":"Jim\u00e9nez-Luna J, Skalic M, Weskamp N, Schneider G (2021) Coloring molecules with explainable artificial intelligence for preclinical relevance assessment. J Chem Inform Model 61(3):1083\u20131094. https:\/\/doi.org\/10.1021\/acs.jcim.0c01344. [cito:citesForInformation]","DOI":"10.1021\/acs.jcim.0c01344"},{"key":"673_CR8","doi-asserted-by":"publisher","unstructured":"Rasmussen MH, Christensen DS, Jensen JH (2022) Do machines dream of atoms? a quantitative molecular benchmark for explainable AI heatmaps (2022) https:\/\/doi.org\/10.26434\/chemrxiv-2022-gnq3w. This content is a preprint and has not been peer-reviewed. [cito:containsAssertionFrom] [cito:usesDataFrom] [cito:usesMethodIn]","DOI":"10.26434\/chemrxiv-2022-gnq3w"},{"key":"673_CR9","doi-asserted-by":"publisher","unstructured":"Zhao L, Montanari F, Heberle H, Schmidt S (2022) Modeling bioconcentration factors in fish with explainable deep learning. Artif Intell Life Sci 100047. https:\/\/doi.org\/10.1016\/j.ailsci.2022.100047","DOI":"10.1016\/j.ailsci.2022.100047"},{"key":"673_CR10","doi-asserted-by":"publisher","unstructured":"Humer C, Heberle H, Montanari F, Wolf T, Huber F, Henderson R, Heinrich J, Streit M (2022) ChemInformatics model explorer (CIME): exploratory analysis of chemical model explanations. J Cheminform 14(1): 1\u201314. https:\/\/doi.org\/10.1186\/s13321-022-00600-z. [cito:obtainsBackgroundFrom] [cito:AuthorSelfCitation] [cito:usesMethodIn]","DOI":"10.1186\/s13321-022-00600-z"},{"key":"673_CR11","doi-asserted-by":"publisher","unstructured":"Weininger D (1988) SMILES, a chemical language and information system. 1. introduction to methodology and encoding rules. Journal of chemical information and computer sciences 28(1), 31\u201336 . https:\/\/doi.org\/10.1021\/ci00057a005. [cito:usesMethodIn]","DOI":"10.1021\/ci00057a005"},{"key":"673_CR12","doi-asserted-by":"publisher","unstructured":"Lambard G, Gracheva E (2020) SMILES-x: autonomous molecular compounds characterization for small datasets without descriptors. Mach Learn Sci Technol 1(2):025004. https:\/\/doi.org\/10.1088\/2632-2153\/ab57f3. [cito:citesForInformation]","DOI":"10.1088\/2632-2153\/ab57f3"},{"key":"673_CR13","unstructured":"KNIME AG: KNIME. https:\/\/www.knime.com\/. Accessed 15 Jul 2022 [cito:usesMethodIn]"},{"key":"673_CR14","unstructured":"Brewer C, Harrower M, and The Pennsylvania State University: ColorBrewer 2.0\u2014Color Advice for Cartography. https:\/\/colorbrewer2.org\/. Accessed 15 Jul 2022 [cito:usesMethodIn]"},{"key":"673_CR15","unstructured":"Landrum G, et al (2022) RDKit MinimalLib. https:\/\/github.com\/rdkit\/rdkit\/tree\/master\/Code\/MinimalLib Accessed 15 Jul 2022 [cito:usesMethodIn]"},{"key":"673_CR16","unstructured":"Landrum G, et al (2022) RDKit: Open-Source Cheminformatics Software. https:\/\/rdkit.org\/ Accessed 15 Jul 2022 [cito:usesMethodIn]"},{"key":"673_CR17","unstructured":"Wied P (2022) Heatmap.js. https:\/\/github.com\/pa7\/heatmap.js Accessed 15 Jul 2022 [cito:usesMethodIn]"},{"key":"673_CR18","unstructured":"Facebook Open Source: React\u2014a JavaScript Library for Building User Interfaces. https:\/\/reactjs.org\/ Accessed 15 Jul 2022 [cito:usesMethodIn]"},{"key":"673_CR19","doi-asserted-by":"publisher","unstructured":"Winter R, Montanari F, No\u00e9 F, Clevert D-A (2019) Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations. Chem Sci. 10(6):1692\u20131701. https:\/\/doi.org\/10.1039\/c8sc04175j. [cito:usesMethodIn]","DOI":"10.1039\/c8sc04175j"},{"key":"673_CR20","doi-asserted-by":"publisher","unstructured":"Riniker S, Landrum GA (2013) Similarity maps - a visualization strategy for molecular fingerprints and machine-learning methods. J Cheminform 5(23):1\u20137. https:\/\/doi.org\/10.1186\/1758-2946-5-43.[cito:citesForInformation] [cito:usesMethodIn]","DOI":"10.1186\/1758-2946-5-43"},{"key":"673_CR21","unstructured":"Morgan Fingerprints. Accessed: 15\/06\/2022 [cito:citesForInformation]. https:\/\/rdkit.readthedocs.io\/en\/latest\/GettingStartedInPython.html#morgan-fingerprints-circular-fingerprints"},{"key":"673_CR22","unstructured":"Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 30. [cito:obtainsBackgroundFrom] [cito:usesMethodIn]"},{"key":"673_CR23","doi-asserted-by":"publisher","unstructured":"Rodr\u00edguez-P\u00e9rez R, Bajorath J (2019) Interpretation of compound activity predictions from complex machine learning models using local approximations and shapley values. J Med Chem 63(16):8761\u20138777. https:\/\/doi.org\/10.1021\/acs.jmedchem.9b01101 [cito:usesMethodIn]","DOI":"10.1021\/acs.jmedchem.9b01101"},{"key":"673_CR24","doi-asserted-by":"publisher","unstructured":"Dorogush AV, Ershov V, Gulin A (2018) Catboost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363.  https:\/\/doi.org\/10.48550\/arXiv.1810.11363. This content is a preprint and has not been peer-reviewed. [cito:usesMethodIn]","DOI":"10.48550\/arXiv.1810.11363"},{"key":"673_CR25","doi-asserted-by":"publisher","unstructured":"Krenn M, H\u00e4se F, Nigam A, Friederich P, Aspuru-Guzik A (2020) Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation. Mach Learn Sci Technol 1(4):045024. https:\/\/doi.org\/10.1088\/2632-2153\/aba947 [cito:citesForInformation]","DOI":"10.1088\/2632-2153\/aba947"},{"key":"673_CR26","doi-asserted-by":"publisher","unstructured":"Heller S, McNaught A, Stein S, Tchekhovskoi D, Pletnev I (2013) Inchi\u2014the worldwide chemical structure identifier standard. J Cheminform 5(1):1\u20139. https:\/\/doi.org\/10.1186\/1758-2946-5-7 [cito:citesForInformation]","DOI":"10.1186\/1758-2946-5-7"},{"key":"673_CR27","doi-asserted-by":"publisher","unstructured":"Probst D, Reymond J-L (2018) SmilesDrawer: Parsing and drawing SMILES-encoded molecular structures using client-side JavaScript. J Chem Inf Model 58(1):1\u20137. https:\/\/doi.org\/10.1021\/acs.jcim.7b00425 [cito:citesForInformation]","DOI":"10.1021\/acs.jcim.7b00425"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-022-00673-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-022-00673-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-022-00673-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T02:22:48Z","timestamp":1672971768000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-022-00673-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,6]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["673"],"URL":"https:\/\/doi.org\/10.1186\/s13321-022-00673-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2121152\/v1","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,6]]},"assertion":[{"value":"30 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2023","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 are employees of Bayer AG, a manufacturer of pharmaceuticals, agricultural, and consumer health chemicals.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2"}}