{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T16:27:17Z","timestamp":1774974437829,"version":"3.50.1"},"reference-count":98,"publisher":"American Chemical Society (ACS)","issue":"14","license":[{"start":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T00:00:00Z","timestamp":1688515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000165","name":"Division of Chemistry","doi-asserted-by":"publisher","award":["CHE-2144153"],"award-info":[{"award-number":["CHE-2144153"]}],"id":[{"id":"10.13039\/100000165","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Schmidt Futures","award":["G-22-64475"],"award-info":[{"award-number":["G-22-64475"]}]},{"name":"Machine Learning for Pharmaceutical Discovery and Synthesis consortium"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2023,7,24]]},"DOI":"10.1021\/acs.jcim.3c00607","type":"journal-article","created":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T14:47:25Z","timestamp":1688568445000},"page":"4253-4265","source":"Crossref","is-referenced-by-count":33,"title":["Data Sharing in Chemistry: Lessons Learned and a Case for Mandating Structured Reaction Data"],"prefix":"10.1021","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6170-6088","authenticated-orcid":true,"given":"Roc\u00edo","family":"Mercado","sequence":"first","affiliation":[{"name":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States"},{"name":"Department of Computer Science and Engineering, Chalmers University of Technology, 412 96 Gothenburg, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4579-4388","authenticated-orcid":true,"given":"Steven M.","family":"Kearnes","sequence":"additional","affiliation":[{"name":"Relay Therapeutics, Cambridge, Massachusetts 02142-1213, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8271-8723","authenticated-orcid":true,"given":"Connor W.","family":"Coley","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States"},{"name":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States"}]}],"member":"316","published-online":{"date-parts":[[2023,7,5]]},"reference":[{"key":"ref1\/cit1","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.7b00064"},{"key":"ref2\/cit2","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.9b00576"},{"key":"ref3\/cit3","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b01919"},{"key":"ref4\/cit4","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3ffb"},{"key":"ref5\/cit5","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c01065"},{"key":"ref6\/cit6","doi-asserted-by":"publisher","DOI":"10.1038\/nature25978"},{"key":"ref7\/cit7","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00472-1"},{"key":"ref8\/cit8","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax1566"},{"key":"ref9\/cit9","doi-asserted-by":"publisher","DOI":"10.1039\/C9SC05704H"},{"key":"ref10\/cit10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19266-y"},{"key":"ref11\/cit11","doi-asserted-by":"crossref","unstructured":"Xie, S.; Yan, R.; Han, P.; Xia, Y.; Wu, L.; Guo, C.; Yang, B.; Qin, T. Retrograph: Retrosynthetic planning with graph search. In  Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022; pp 2120\u20132129.","DOI":"10.1145\/3534678.3539446"},{"key":"ref12\/cit12","unstructured":"Chen, B.; Li, C.; Dai, H.; Song, L. Retro*: learning retrosynthetic planning with neural guided A* search. In  Proceedings of the 37th International Conference on Machine Learning, 2020; Vol. 119, pp 1608\u20131616."},{"key":"ref13\/cit13","unstructured":"Kim, J.; Ahn, S.; Lee, H.; Shin, J. Self-improved retrosynthetic planning. In  Proceedings of the 38th International Conference on Machine Learning, 2021; Vol. 139, pp 5486\u20135495."},{"key":"ref14\/cit14","doi-asserted-by":"publisher","DOI":"10.1039\/D1SC06932B"},{"key":"ref15\/cit15","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.8b00357"},{"key":"ref16\/cit16","doi-asserted-by":"publisher","DOI":"10.1002\/minf.202100294"},{"key":"ref17\/cit17","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c01234"},{"key":"ref18\/cit18","doi-asserted-by":"publisher","DOI":"10.1021\/acs.accounts.8b00087"},{"key":"ref19\/cit19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1288-y"},{"key":"ref20\/cit20","doi-asserted-by":"publisher","DOI":"10.1002\/anie.202008366"},{"key":"ref21\/cit21","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c01140"},{"key":"ref22\/cit22","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.1c09820"},{"key":"ref23\/cit23","unstructured":"Lowe, D. M. Extraction of chemical structures and reactions from the literature. Ph.D. Thesis, University of Cambridge, 2012."},{"key":"ref24\/cit24","unstructured":"Mayfield, J.; Lowe, D.; Sayle, R. Pistachio, version 2022-10-03 (2022Q3). Available at https:\/\/www.nextmovesoftware.com\/pistachio.html (accessed 2022-04-10)."},{"key":"ref25\/cit25","unstructured":"Elsevier Reaxys: An expert-curated chemistry database. Available\nat https:\/\/www.elsevier.com\/solutions\/reaxys (accessed 2022-12-19)."},{"key":"ref26\/cit26","unstructured":"American Chemical Society.  CAS Data. Available at https:\/\/www.cas.org\/cas-data (accessed 2022-12-21)."},{"key":"ref27\/cit27","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar5169"},{"key":"ref28\/cit28","doi-asserted-by":"publisher","DOI":"10.1126\/science.aap9112"},{"key":"ref29\/cit29","doi-asserted-by":"publisher","DOI":"10.1126\/science.1259203"},{"key":"ref30\/cit30","unstructured":"cOAlition S. Plan S: Making full and immediate Open Access a reality. Available at https:\/\/www.coalition-s.org\/ (accessed 2022-12-21)."},{"key":"ref31\/cit31","unstructured":"The White House OSTP Issues Guidance to Make Federally Funded Research Freely\nAvailable Without Delay. Available at https:\/\/www.whitehouse.gov\/ostp\/news-updates\/2022\/08\/25\/ostp-issues-guidance-to-make-federally-funded-research-freely-available-without-delay\/ (accessed 2023-01-20)."},{"key":"ref32\/cit32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2022.05.019"},{"key":"ref33\/cit33","unstructured":"Cambridge Structural\nDatabase.  CSD Publication Year\nStatistics: 1 January 2022. Available at https:\/\/www.ccdc.cam.ac.uk\/media\/Documentation\/9DA399C5-90F8-478E-9C41-EAFD1868ED31\/9da399c590f8478e9c41eafd1868ed31.pdf (accessed 2023-02-28)."},{"key":"ref34\/cit34","unstructured":"Protein Data Bank.  Deposition Statistics. Available at https:\/\/www.wwpdb.org\/stats\/deposition (accessed 2023-03-01)."},{"key":"ref35\/cit35","unstructured":"NIH National Human Genome Research\nInstitute.  NIH Creates Nationwide\nNetwork of Molecular Libraries Screening Centers To Accelerate Study\nof Human Biology and Disease. Available at https:\/\/www.genome.gov\/15014443\/2005-release-nih-nationwide-network-of-molecular-libraries-screening-centers (accessed 2023-03-01)."},{"key":"ref36\/cit36","unstructured":"Big Chemical\nEncyclopedia, NIH Molecular Libraries Roadmap Initiative.\nAvailable at https:\/\/chempedia.info\/info\/nih_molecular_libraries_roadmap_initiative\/ (accessed 2023-03-01)."},{"key":"ref37\/cit37","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-9-401"},{"key":"ref38\/cit38","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkp456"},{"key":"ref39\/cit39","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr1132"},{"key":"ref40\/cit40","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkw1118"},{"key":"ref41\/cit41","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1033"},{"key":"ref42\/cit42","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa971"},{"key":"ref43\/cit43","unstructured":"NIH\nNational Library of Medicine.  PubChem\nData Counts. Available\nat https:\/\/pubchem.ncbi.nlm.nih.gov\/docs\/statistics (accessed 2022-12-25)."},{"key":"ref44\/cit44","unstructured":"ChEMBL Interface\nDocumentation, Downloads. Available at https:\/\/chembl.gitbook.io\/chembl-interface-documentation\/downloads (accessed 2022-12-25)."},{"key":"ref45\/cit45","unstructured":"The Cambridge\nCrystallographic Data Centre (CCDC), Our History. Available\nat https:\/\/www.ccdc.cam.ac.uk\/theccdcprofile\/history\/ (accessed 2022-05-25)."},{"key":"ref46\/cit46","unstructured":"The Cambridge Crystallographic\nData Centre (CCDC).  Opening lecture by Dr Olga Kennard\nOBE FRS. Available at https:\/\/www.youtube.com\/watch?v=HkR7_uxvU8Q (accessed 2022-06-30)."},{"key":"ref47\/cit47","unstructured":"CCDC.  CCDC Research. Available at https:\/\/www.ccdc.cam.ac.uk\/researchandconsultancy\/ccdcresearch\/ccdcresearchers\/ (accessed 2022-12-23)."},{"key":"ref48\/cit48","unstructured":"CCDC.  New Year, New Data Resolutions! Available at https:\/\/www.ccdc.cam.ac.uk\/Community\/blog\/data-resolutions\/ (accessed 2022-12-23)."},{"key":"ref49\/cit49","unstructured":"Retraction Watch.  Crystallography database flags nearly 1000 structures linked\nto a paper mill. Available at https:\/\/retractionwatch.com\/2022\/07\/26\/crystallography-database-flags-nearly-1000-structures-linked-to-a-paper-mill\/ (accessed 2022-12-19)."},{"key":"ref50\/cit50","unstructured":"CCDC Retractions in the Cambridge Structural Database. Available at https:\/\/www.ccdc.cam.ac.uk\/support-and-resources\/support\/case\/?caseid=819cfd76-c25d-40a2-ac9b-b4cf20d775a7 (accessed 12\u201319\u20132022)."},{"key":"ref51\/cit51","unstructured":"The Cambridge\nCrystallographic Data Centre (CCDC).  A million thanks. Available at https:\/\/www.ccdc.cam.ac.uk\/Community\/blog\/A-million-thanks\/ (accessed 2022-06-25)."},{"key":"ref52\/cit52","unstructured":"ACS Publications.  Requirements for Depositing X-Ray\nCrystallographic Data. Available at https:\/\/pubsapp.acs.org\/paragonplus\/submission\/acs_cif_authguide.pdf (accessed 2023-03-04)."},{"key":"ref53\/cit53","unstructured":"The Cambridge Crystallographic\nData Centre (CCDC).  Big data leads\nthe way for structural chemistry. Available at https:\/\/www.ccdc.cam.ac.uk\/News\/List\/the-cambridge-structural-database-reaches-one-million\/ (accessed 2022-06-25)."},{"key":"ref54\/cit54","doi-asserted-by":"publisher","DOI":"10.1021\/ci00002a004"},{"key":"ref55\/cit55","first-page":"e14","volume":"75","author":"Ward S.","year":"2019","journal-title":"Acta Cryst."},{"key":"ref56\/cit56","doi-asserted-by":"publisher","DOI":"10.1107\/S0108768109046448"},{"issue":"4","key":"ref57\/cit57","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1080\/0889311X.2018.1508209","volume":"24","author":"Schwalbe C. H.","year":"2018","journal-title":"Crystallogr. Rev."},{"key":"ref58\/cit58","doi-asserted-by":"publisher","DOI":"10.1107\/S0108768111024608"},{"key":"ref59\/cit59","unstructured":"RCSB PDB.  PDB History. Available at https:\/\/www.rcsb.org\/pages\/about-us\/history (accessed 2022-07-12)."},{"key":"ref60\/cit60","unstructured":"Cold Spring Harbor Laboratory.  Structure and Function of Proteins at the\nThree-Dimensional Level. Available at http:\/\/library.cshl.edu\/symposia\/1971\/index.html (accessed 2022-05-12)."},{"key":"ref61\/cit61","unstructured":"PDB Community\nFocus: Michael G. Rossmann. In  RCSB PDB Newsletter, 2006. Available at https:\/\/cdn.rcsb.org\/rcsb-pdb\/general_information\/news_publications\/newsletters\/2006q2\/community.html (accessed 2022-05-12)."},{"key":"ref62\/cit62","doi-asserted-by":"publisher","DOI":"10.1002\/pro.5560060724"},{"key":"ref63\/cit63","unstructured":"RCSB\nPDB.  Number of Released PDB Structures\nper Year. Available\nat https:\/\/www.rcsb.org\/stats\/all-released-structures (accessed 2022-05-13)."},{"key":"ref64\/cit64","doi-asserted-by":"publisher","DOI":"10.1107\/S0108767389007695"},{"key":"ref65\/cit65","doi-asserted-by":"publisher","DOI":"10.1038\/27971"},{"key":"ref66\/cit66","unstructured":"National Library of Medicine PubChem. Available at https:\/\/pubchem.ncbi.nlm.nih.gov\/ (accessed 2022-05-23)."},{"key":"ref67\/cit67","unstructured":"National Institutes of Health\n(NIH).  Molecular Libraries High Throughput\nScreening Centers: Request For Information (RFI); 2003. Available at https:\/\/grants.nih.gov\/grants\/guide\/notice-files\/NOT-RM-04-001.html (accessed 2022-05-25)."},{"key":"ref68\/cit68","unstructured":"National Library of Medicine.  PubChem Data Sources; 2022. Available at https:\/\/pubchem.ncbi.nlm.nih.gov\/sources\/ (accessed 2022-07-12)."},{"key":"ref69\/cit69","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkm895"},{"key":"ref70\/cit70","unstructured":"PubChem.  PubChemRDF. Available at https:\/\/pubchemdocs.ncbi.nlm.nih.gov\/rdf (accessed 2022-07-10)."},{"key":"ref71\/cit71","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-015-0084-4"},{"key":"ref72\/cit72","unstructured":"ChEBI The online chemical dictionary for small\nmolecules, ChEBI\nOntology. Available at https:\/\/www.ebi.ac.uk\/training\/online\/courses\/chebi-the-online-chemical-dictionary-for-small-molecules\/chebi-ontology\/ (accessed 2023-03-07)."},{"key":"ref73\/cit73","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0025513"},{"key":"ref74\/cit74","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkw1075"},{"key":"ref75\/cit75","unstructured":"Office\nof Scholarly Communication,\nUniversity of California.  American\nChemical Society Expresses Opposition to NIH\u2019s PubChem; 2005. Available at https:\/\/osc.universityofcalifornia.edu\/2005\/05\/american-chemical-society-calls-on-congress-to-shut-down-nihs-pubchem\/#note1 (accessed 2022-05-25)."},{"key":"ref76\/cit76","unstructured":"EMBL\u2019s European Bioinformatics\nInstitute.  Unleashing the potential\nof big data in biology. Available at https:\/\/www.ebi.ac.uk\/ (accessed 2022-07-07)."},{"key":"ref77\/cit77","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-009-9260-9"},{"key":"ref78\/cit78","unstructured":"ChEMBL Interface\nDocumentation. Acknowledgments. Available\nat https:\/\/chembl.gitbook.io\/chembl-interface-documentation\/acknowledgments (accessed 2022-07-07)."},{"key":"ref79\/cit79","unstructured":"Chemical Biology\nServices, Members. Available at https:\/\/www.ebi.ac.uk\/about\/teams\/chemical-biology-services\/members\/ (accessed 2023-03-08)."},{"key":"ref80\/cit80","unstructured":"ChEMBL Interface\nDocumentation, New Web Interface. Available\nat https:\/\/chembl.gitbook.io\/chembl-interface-documentation\/ (accessed 2023-03-08)."},{"key":"ref81\/cit81","doi-asserted-by":"publisher","DOI":"10.1021\/ac00054a716"},{"key":"ref82\/cit82","doi-asserted-by":"publisher","DOI":"10.1351\/pac197229040625"},{"key":"ref83\/cit83","doi-asserted-by":"publisher","DOI":"10.1351\/pac197645030217"},{"key":"ref84\/cit84","doi-asserted-by":"publisher","DOI":"10.1021\/jo971176v"},{"key":"ref85\/cit85","doi-asserted-by":"publisher","DOI":"10.1021\/om100106e"},{"key":"ref86\/cit86","unstructured":"ACS Publications.  NMR Guidelines for ACS Journals. Available at https:\/\/pubsapp.acs.org\/paragonplus\/submission\/acs_nmr_guidelines.pdf (accessed 2023-03-04)."},{"key":"ref87\/cit87","doi-asserted-by":"publisher","DOI":"10.1351\/pac200173111795"},{"key":"ref88\/cit88","doi-asserted-by":"publisher","DOI":"10.1351\/pac200880010059"},{"key":"ref89\/cit89","doi-asserted-by":"publisher","DOI":"10.1039\/C6NP00022C"},{"key":"ref90\/cit90","doi-asserted-by":"publisher","DOI":"10.1021\/acs.joc.0c00248"},{"key":"ref91\/cit91","doi-asserted-by":"publisher","DOI":"10.1021\/acs.joc.0c00800"},{"key":"ref92\/cit92","doi-asserted-by":"publisher","DOI":"10.1002\/mrc.4263"},{"key":"ref93\/cit93","unstructured":"Lowe, D. Patent Reaction Extraction. Available at https:\/\/github.com\/dan2097\/patent-reaction-extraction (accessed 2023-03-04)."},{"key":"ref94\/cit94","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c00284"},{"key":"ref95\/cit95","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c01017"},{"key":"ref96\/cit96","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-017-0221-3"},{"key":"ref97\/cit97","doi-asserted-by":"publisher","DOI":"10.1002\/9783527825042.ch13"},{"key":"ref98\/cit98","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-022-00402-1"}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.3c00607","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.3c00607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T08:10:40Z","timestamp":1690186240000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/acs.jcim.3c00607"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,5]]},"references-count":98,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2023,7,24]]}},"alternative-id":["10.1021\/acs.jcim.3c00607"],"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.3c00607","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,5]]}}}