{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:54:35Z","timestamp":1759971275759,"version":"build-2065373602"},"reference-count":48,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["advanced.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Advanced Intelligent Systems"],"published-print":{"date-parts":[[2022,10]]},"abstract":"<jats:sec><jats:label\/><jats:p>\u201cAI &amp; Drug Discovery\u201d mode has significantly promoted drug development and achieved excellent performance, especially with the rapid development of deep learning, making remarkable contributions to protecting human physiological health. However, due to the \u201cblack\u2010box\u201d characteristic of the deep learning model, the decision route and predicted results in different research stages assisted by deep models are usually unexplainable, limiting their application in practice and more in\u2010depth research of drug discovery. Focusing on the drug molecules, an explainable fragment\u2010based molecular property attribution technique is proposed for analyzing the influence of particular molecule fragments on properties and the relationship between the molecular properties herein. Quantitative experiments on 42 benchmark property tasks demonstrate that 325 attribution fragments, which account for 90% of the overall attribution results obtained by the proposed method, have positive relevance to the corresponding property tasks. More impressively, most of the attribution results randomly selected are consistent with the existing mechanism explanations. The discovery mentioned above provides a reference standard for assisting researchers in developing more specific and practical drug molecule studies, such as synthesizing molecule with the targeted property using a fragment obtained from the attribution method. An interactive preprint version of the article can be found at: https:\/\/www.authorea.com\/doi\/full\/10.22541\/au.165279262.29589148.<\/jats:p><\/jats:sec>","DOI":"10.1002\/aisy.202200104","type":"journal-article","created":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T04:35:43Z","timestamp":1657341343000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Fragment\u2010Based Molecular Property Attribution"],"prefix":"10.1002","volume":"4","author":[{"given":"Lingxiang","family":"Jia","sequence":"first","affiliation":[{"name":"College of Computer Science Zhejiang University  Hangzhou 310027 China"}]},{"given":"Zunlei","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Computer Science Zhejiang University  Hangzhou 310027 China"}]},{"given":"Haotian","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences Zhejiang University  Hangzhou 310027 China"}]},{"given":"Jie","family":"Song","sequence":"additional","affiliation":[{"name":"College of Computer Science Zhejiang University  Hangzhou 310027 China"}]},{"given":"Zipeng","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Computer Science Zhejiang University  Hangzhou 310027 China"}]},{"given":"Shaolun","family":"Yao","sequence":"additional","affiliation":[{"name":"College of Computer Science Zhejiang University  Hangzhou 310027 China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2621-6048","authenticated-orcid":false,"given":"Mingli","family":"Song","sequence":"additional","affiliation":[{"name":"College of Computer Science Zhejiang University  Hangzhou 310027 China"}]}],"member":"311","published-online":{"date-parts":[[2022,7,9]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-385471-1.00030-1"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhealeco.2016.01.012"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03828-1"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.9b00576"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19266-y"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature25978"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemolab.2019.103853"},{"key":"e_1_2_9_9_1","unstructured":"I.Wallach M.Dzamba A.Heifets Preprint arXiv:1510.02855 v1 2015."},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty135"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/molecules24183383"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c00208"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbz152"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa205"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00459-7"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/make3040048"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.7b00244"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.1c00421"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1021\/jm00349a001"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b00917"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yrtph.2005.04.006"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1475"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1097\/ALN.0b013e318238bba6"},{"key":"e_1_2_9_24_1","first-page":"1","volume-title":"Progress in Medicinal Chemistry","author":"Smith G. F.","year":"2011"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1021\/acsomega.1c04017"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkab255"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci300245q"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1021\/tx200168d"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2017.06.174"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.15430\/JCP.2015.20.4.232"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1021\/tx025569n"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1124\/dmd.109.028860"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph15010025"},{"key":"e_1_2_9_35_1","unstructured":"T. N.Kipf M.Welling Preprint arXiv:1609.02907 v4 2017."},{"key":"e_1_2_9_36_1","first-page":"11","volume":"9","author":"Van der Maaten L.","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mayocp.2013.09.016"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djx206"},{"key":"e_1_2_9_39_1","unstructured":"W.Jin B.Regina J.Tommi in35th Int. Conf. Mach. Learn. Proceedings of Machine Learning Research (PMLR) Stockholm Sweden2018 pp.2323\u20132332."},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/molecules26165039"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1021\/jm401411z"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci970429i"},{"key":"e_1_2_9_43_1","first-page":"453","volume-title":"Encyclopedia of Physical Science and Technology","author":"Michl J.","year":"2003"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrestox.8b00046"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1021\/c160017a018"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470191699.ch3"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1021\/tx00044a007"},{"key":"e_1_2_9_48_1","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1016\/S0022-3565(25)39166-4","volume":"242","author":"Geneve J.","year":"1987","journal-title":"J. Pharmacol. Exp. Ther."},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1080\/10408440590935620"}],"container-title":["Advanced Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202200104","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/aisy.202200104","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202200104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T23:26:17Z","timestamp":1759879577000},"score":1,"resource":{"primary":{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/10.1002\/aisy.202200104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,9]]},"references-count":48,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["10.1002\/aisy.202200104"],"URL":"https:\/\/doi.org\/10.1002\/aisy.202200104","archive":["Portico"],"relation":{},"ISSN":["2640-4567","2640-4567"],"issn-type":[{"type":"print","value":"2640-4567"},{"type":"electronic","value":"2640-4567"}],"subject":[],"published":{"date-parts":[[2022,7,9]]},"assertion":[{"value":"2022-04-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2200104"}}