{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:25:26Z","timestamp":1780421126643,"version":"3.54.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004022","name":"Jenny ja Antti Wihurin Rahasto","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004022","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004012","name":"Jane ja Aatos Erkon S\u00e4\u00e4ti\u00f6","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004012","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002341","name":"Research Council of Finland","doi-asserted-by":"crossref","award":["339421"],"award-info":[{"award-number":["339421"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002341","name":"Research Council of Finland","doi-asserted-by":"crossref","award":["345802"],"award-info":[{"award-number":["345802"]}],"id":[{"id":"10.13039\/501100002341","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:p>Accurate atom mapping, which establishes correspondences between atoms in reactants and products, is a crucial step in analyzing chemical reactions. In this paper, we present a novel end-to-end approach that formulates the atom mapping problem as a deep graph matching task. Our proposed model, AMNet (Atom Matching Network), utilizes molecular graph representations and employs various atom and bond features using graph neural networks to capture the intricate structural characteristics of molecules, ensuring precise atom correspondence predictions. Notably, AMNet incorporates the consideration of molecule symmetry, enhancing accuracy while simultaneously reducing computational complexity. The integration of the Weisfeiler-Lehman isomorphism test for symmetry identification refines the model\u2019s predictions. Furthermore, our model maps the entire atom set in a chemical reaction, offering a comprehensive approach beyond focusing solely on the main molecules in reactions. We evaluated AMNet\u2019s performance on a subset of USPTO reaction datasets, addressing various tasks, including assessing the impact of molecular symmetry identification, understanding the influence of feature selection on AMNet performance, and comparing its performance with the state-of-the-art method. The result reveals an average accuracy of 97.3% on mapped atoms, with 99.7% of reactions correctly mapped when the correct mapped atom is within the top 10 predicted atoms.<\/jats:p>\n                  <jats:p>\n                    <jats:bold>Scientific contribution<\/jats:bold>\n                  <\/jats:p>\n                  <jats:p>The paper introduces a novel end-to-end deep graph matching model for atom mapping, utilizing molecular graph representations to capture structural characteristics effectively. It enhances accuracy by integrating symmetry detection through the Weisfeiler-Lehman test, reducing the number of possible mappings and improving efficiency. Unlike previous methods, it maps the entire reaction, not just main components, providing a comprehensive view. Additionally, by integrating efficient graph matching techniques, it reduces computational complexity, making atom mapping more feasible.<\/jats:p>","DOI":"10.1186\/s13321-024-00841-0","type":"journal-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T11:01:53Z","timestamp":1713783713000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Learning symmetry-aware atom mapping in chemical reactions through deep graph matching"],"prefix":"10.1186","volume":"16","author":[{"given":"Maryam","family":"Astero","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juho","family":"Rousu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,22]]},"reference":[{"key":"841_CR1","unstructured":"Jin W, Coley C, Barzilay R, Jaakkola T (2017) Predicting organic reaction outcomes with weisfeiler-lehman network. Advances in neural information processing systems 30"},{"issue":"4","key":"841_CR2","doi-asserted-by":"publisher","first-page":"2087","DOI":"10.1021\/acs.joc.7b03021","volume":"83","author":"RK Acharyya","year":"2018","unstructured":"Acharyya RK, Rej RK, Nanda S (2018) Exploration of ring rearrangement metathesis reaction: a general and flexible approach for the rapid construction [5, n]-fused bicyclic systems en route to linear triquinanes. J Org Chem 83(4):2087\u20132103","journal-title":"J Org Chem"},{"issue":"23","key":"841_CR3","doi-asserted-by":"publisher","first-page":"3135","DOI":"10.1093\/bioinformatics\/btp549","volume":"25","author":"M Leber","year":"2009","unstructured":"Leber M, Egelhofer V, Schomburg I, Schomburg D (2009) Automatic assignment of reaction operators to enzymatic reactions. Bioinformatics 25(23):3135\u20133142","journal-title":"Bioinformatics"},{"key":"841_CR4","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1021\/acs.accounts.8b00087","volume":"51","author":"CW Coley","year":"2018","unstructured":"Coley CW, Green WH, Jensen KF (2018) Machine learning in computer-aided synthesis planning. Acc Chem Res 51:1281\u20131289","journal-title":"Acc Chem Res"},{"issue":"14","key":"841_CR5","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1093\/bioinformatics\/btu150","volume":"30","author":"M Latendresse","year":"2014","unstructured":"Latendresse M, Krummenacker M, Karp PD (2014) Optimal metabolic route search based on atom mappings. Bioinformatics 30(14):2043\u20132050","journal-title":"Bioinformatics"},{"issue":"9","key":"841_CR6","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.1093\/bioinformatics\/btaa036","volume":"36","author":"X Cheng","year":"2020","unstructured":"Cheng X, Sun D, Zhang D, Tian Y, Ding S, Cai P, Hu Q-N (2020) Rxnblast: molecular scaffold and reactive chemical environment feature extractor for biochemical reactions. Bioinformatics 36(9):2946\u20132947","journal-title":"Bioinformatics"},{"key":"841_CR7","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1023\/A:1021271615909","volume":"16","author":"JW Raymond","year":"2002","unstructured":"Raymond JW, Willett P (2002) Maximum common subgraph isomorphism algorithms for the matching of chemical structures. J Comput Aided Mol Design 16:521\u2013533","journal-title":"J Comput Aided Mol Design"},{"key":"841_CR8","first-page":"144","volume":"14","author":"M Hattori","year":"2003","unstructured":"Hattori M, Okuno Y, Goto S, Kanehisa M (2003) Heuristics for chemical compound matching. Genom Inf 14:144\u2013153","journal-title":"Genom Inf"},{"issue":"1","key":"841_CR9","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1002\/wcms.5","volume":"1","author":"H-C Ehrlich","year":"2011","unstructured":"Ehrlich H-C, Rarey M (2011) Maximum common subgraph isomorphism algorithms and their applications in molecular science: a review. Wiley Interdisciplinary Rev Comput Mol Sci 1(1):68\u201379","journal-title":"Wiley Interdisciplinary Rev Comput Mol Sci"},{"issue":"3","key":"841_CR10","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1021\/ci60015a009","volume":"18","author":"MF Lynch","year":"1978","unstructured":"Lynch MF, Willett P (1978) The automatic detection of chemical reaction sites. J Chem Inf Comput Sci 18(3):154\u2013159","journal-title":"J Chem Inf Comput Sci"},{"issue":"1","key":"841_CR11","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1089\/cmb.2009.0216","volume":"18","author":"M Heinonen","year":"2011","unstructured":"Heinonen M, Lappalainen S, Mielik\u00e4inen T, Rousu J (2011) Computing atom mappings for biochemical reactions without subgraph isomorphism. J Comput Biol 18(1):43\u201358","journal-title":"J Comput Biol"},{"issue":"11","key":"841_CR12","doi-asserted-by":"publisher","first-page":"2970","DOI":"10.1021\/ci3002217","volume":"52","author":"M Latendresse","year":"2012","unstructured":"Latendresse M, Malerich JP, Travers M, Karp PD (2012) Accurate atom-mapping computation for biochemical reactions. J Chem Inf Modeling 52(11):2970\u20132982","journal-title":"J Chem Inf Modeling"},{"key":"841_CR13","doi-asserted-by":"crossref","unstructured":"Akutsu T (2003) Efficient extraction of mapping rules of atoms from enzymatic reaction data. In: Proceedings of the seventh annual international conference on Research in computational molecular biology, pp 1\u20138","DOI":"10.1145\/640075.640076"},{"issue":"7","key":"841_CR14","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1002\/anie.198004953","volume":"19","author":"C Jochum","year":"1980","unstructured":"Jochum C, Gasteiger J, Ugi I (1980) The principle of minimum chemical distance (pmcd). Angewandte Chem Int Edition English 19(7):495\u2013505","journal-title":"Angewandte Chem Int Edition English"},{"key":"841_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13015-014-0023-3","volume":"9","author":"M Mann","year":"2014","unstructured":"Mann M, Nahar F, Schnorr N, Backofen R, Stadler PF, Flamm C (2014) Atom mapping with constraint programming. Algorithms Mol Biol 9:1\u201312","journal-title":"Algorithms Mol Biol"},{"issue":"1","key":"841_CR16","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.1038\/s41467-019-09440-2","volume":"10","author":"W Jaworski","year":"2019","unstructured":"Jaworski W, Szymku\u0107 S, Mikulak-Klucznik B, Piecuch K, Klucznik T, Ka\u017amierowski M, Rydzewski J, Gambin A, Grzybowski BA (2019) Automatic mapping of atoms across both simple and complex chemical reactions. Nat Commun 10(1):1434","journal-title":"Nat Commun"},{"issue":"11","key":"841_CR17","doi-asserted-by":"publisher","first-page":"2812","DOI":"10.1021\/ci400326p","volume":"53","author":"D Fooshee","year":"2013","unstructured":"Fooshee D, Andronico A, Baldi P (2013) Reactionmap: an efficient atom-mapping algorithm for chemical reactions. J Chem Inf Modeling 53(11):2812\u20132819","journal-title":"J Chem Inf Modeling"},{"issue":"13","key":"841_CR18","doi-asserted-by":"publisher","first-page":"2065","DOI":"10.1093\/bioinformatics\/btw096","volume":"32","author":"SA Rahman","year":"2016","unstructured":"Rahman SA, Torrance G, Baldacci L, Mart\u00ednez Cuesta S, Fenninger F, Gopal N, Choudhary S, May JW, Holliday GL, Steinbeck C et al (2016) Reaction decoder tool (rdt): extracting features from chemical reactions. Bioinformatics 32(13):2065\u20132066","journal-title":"Bioinformatics"},{"issue":"4","key":"841_CR19","doi-asserted-by":"publisher","first-page":"2100138","DOI":"10.1002\/minf.202100138","volume":"41","author":"A Lin","year":"2022","unstructured":"Lin A, Dyubankova N, Madzhidov TI, Nugmanov RI, Verhoeven J, Gimadiev TR, Afonina VA, Ibragimova Z, Rakhimbekova A, Sidorov P et al (2022) Atom-to-atom mapping: a benchmarking study of popular mapping algorithms and consensus strategies. Mol Inf 41(4):2100138","journal-title":"Mol Inf"},{"issue":"15","key":"841_CR20","doi-asserted-by":"publisher","first-page":"eabe4166","DOI":"10.1126\/sciadv.abe4166","volume":"7","author":"P Schwaller","year":"2021","unstructured":"Schwaller P, Hoover B, Reymond J-L, Strobelt H, Laino T (2021) Extraction of organic chemistry grammar from unsupervised learning of chemical reactions. Sci Adv 7(15):eabe4166","journal-title":"Sci Adv"},{"key":"841_CR21","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Advances in neural information processing systems 30"},{"key":"841_CR22","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"issue":"14","key":"841_CR23","doi-asserted-by":"publisher","first-page":"3307","DOI":"10.1021\/acs.jcim.2c00344","volume":"62","author":"R Nugmanov","year":"2022","unstructured":"Nugmanov R, Dyubankova N, Gedich A, Wegner JK (2022) Bidirectional graphormer for reactivity understanding: neural network trained to reaction atom-to-atom mapping task. J Chem Inf Modeling 62(14):3307\u20133315","journal-title":"J Chem Inf Modeling"},{"key":"841_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-017-0223-1","volume":"9","author":"GA Preciat Gonzalez","year":"2017","unstructured":"Preciat Gonzalez GA, El Assal LR, Noronha A, Thiele I, Haraldsd\u00f3ttir HS, Fleming RM (2017) Comparative evaluation of atom mapping algorithms for balanced metabolic reactions: application to recon 3d. J Cheminf 9:1\u201315","journal-title":"J Cheminf"},{"issue":"03","key":"841_CR25","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1142\/S0218001404003228","volume":"18","author":"D Conte","year":"2004","unstructured":"Conte D, Foggia P, Sansone C, Vento M (2004) Thirty years of graph matching in pattern recognition. Int J Pattern Recogn Arti Intell 18(03):265\u2013298","journal-title":"Int J Pattern Recogn Arti Intell"},{"key":"841_CR26","unstructured":"Fey M, Lenssen JE, Morris C, Masci J, Kriege NM (2020) Deep graph matching consensus. arXiv preprint arXiv:2001.09621"},{"key":"841_CR27","unstructured":"Grohe M, Rattan G, Woeginger GJ (2018) Graph similarity and approximate isomorphism. arXiv preprint arXiv:1802.08509"},{"key":"841_CR28","unstructured":"Li Y, Gu C, Dullien T, Vinyals O, Kohli P (2019) Graph matching networks for learning the similarity of graph structured objects. In: International conference on machine learning. PMLR, pp 3835\u20133845"},{"key":"841_CR29","doi-asserted-by":"crossref","unstructured":"Cho M, Alahari K, Ponce J (2013) Learning graphs to match. In: Proceedings of the IEEE International Conference on Computer Vision, pp 25\u201332","DOI":"10.1109\/ICCV.2013.11"},{"issue":"4","key":"841_CR30","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/34.491619","volume":"18","author":"S Gold","year":"1996","unstructured":"Gold S, Rangarajan A (1996) A graduated assignment algorithm for graph matching. IEEE Trans Pattern Anal Mach Intell 18(4):377\u2013388","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"841_CR31","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1109\/TPAMI.2009.28","volume":"31","author":"TS Caetano","year":"2009","unstructured":"Caetano TS, McAuley JJ, Cheng L, Le QV, Smola AJ (2009) Learning graph matching. IEEE Trans Pattern Anal Mach Intell 31(6):1048\u20131058","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"841_CR32","unstructured":"Bruna J, Zaremba W, Szlam A, LeCun Y (2013) Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203"},{"key":"841_CR33","unstructured":"Bai Y, Ding H, Sun Y, Wang W (2018) Convolutional set matching for graph similarity. arXiv preprint arXiv:1810.10866"},{"key":"841_CR34","doi-asserted-by":"crossref","unstructured":"Bai Y, Ding H, Bian S, Chen T, Sun Y, Wang W (2019) Simgnn: A neural network approach to fast graph similarity computation. In: Proceedings of the twelfth ACM international conference on web search and data mining, pp 384\u2013392","DOI":"10.1145\/3289600.3290967"},{"key":"841_CR35","doi-asserted-by":"crossref","unstructured":"Zanfir A, Sminchisescu C (2018) Deep learning of graph matching. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2684\u20132693","DOI":"10.1109\/CVPR.2018.00284"},{"key":"841_CR36","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1109\/TPAMI.2009.28","volume":"31","author":"TS Caetano","year":"2009","unstructured":"Caetano TS, McAuley JJ, Cheng L, Le QV, Smola AJ (2009) Learning graph matching. IEEE Trans Pattern Anal Mach Intell 31:1048\u20131058","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"841_CR37","first-page":"12","volume":"2","author":"B Weisfeiler","year":"1968","unstructured":"Weisfeiler B, Leman A (1968) The reduction of a graph to canonical form and the algebra which appears therein. Series 2(9):12\u201316","journal-title":"Series"},{"key":"841_CR38","unstructured":"Xu K, Hu W, Leskovec J, Jegelka S (2018) How powerful are graph neural networks?. arXiv preprint arXiv:1810.00826"},{"key":"841_CR39","unstructured":"Lowe DM (2012) Extraction of chemical structures and reactions from the literature. PhD thesis, University of Cambridge"},{"key":"841_CR40","unstructured":"Fey M, Lenssen JE (2019) Fast graph representation learning with pytorch geometric. arXiv preprint arXiv:1903.02428"},{"key":"841_CR41","unstructured":"Xu K, Li C, Tian Y, Sonobe T, Kawarabayashi K-i, Jegelka S (2018) Representation learning on graphs with jumping knowledge networks. In: International conference on machine learning, PMLR, pp 5453\u20135462"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-024-00841-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-024-00841-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-024-00841-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T11:05:06Z","timestamp":1713783906000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-024-00841-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,22]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["841"],"URL":"https:\/\/doi.org\/10.1186\/s13321-024-00841-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3865935\/v1","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,22]]},"assertion":[{"value":"15 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 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":"46"}}