{"id":"https://openalex.org/W2952213121","doi":"https://doi.org/10.1021/ci960151e","title":"Clustering of Large Databases of Compounds: Using the MDL \u201cKeys\u201d as Structural Descriptors","display_name":"Clustering of Large Databases of Compounds: Using the MDL \u201cKeys\u201d as Structural Descriptors","publication_year":1997,"publication_date":"1997-05-01","ids":{"openalex":"https://openalex.org/W2952213121","doi":"https://doi.org/10.1021/ci960151e","mag":"2952213121"},"language":"en","primary_location":{"id":"doi:10.1021/ci960151e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci960151e","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Computer Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001521927","display_name":"Malcolm J. McGregor","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Malcolm J. McGregor","raw_affiliation_strings":["Procept, Inc., 840 Memorial Drive, Cambridge, Massachusetts 02139"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Procept, Inc., 840 Memorial Drive, Cambridge, Massachusetts 02139","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089806964","display_name":"Peter V. Pallai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter V. Pallai","raw_affiliation_strings":["Procept, Inc., 840 Memorial Drive, Cambridge, Massachusetts 02139"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Procept, Inc., 840 Memorial Drive, Cambridge, Massachusetts 02139","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5001521927"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.7671,"has_fulltext":false,"cited_by_count":184,"citation_normalized_percentile":{"value":0.99221593,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"37","issue":"3","first_page":"443","last_page":"448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8983529806137085},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5916357040405273},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5530520081520081},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5386661291122437},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4827529788017273},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.44877752661705017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44758597016334534},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09879818558692932}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8983529806137085},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5916357040405273},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5530520081520081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5386661291122437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4827529788017273},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.44877752661705017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44758597016334534},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09879818558692932},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1021/ci960151e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci960151e","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Computer Sciences","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1963790256","https://openalex.org/W2005685204","https://openalex.org/W2021083597","https://openalex.org/W2022116853","https://openalex.org/W2060531713","https://openalex.org/W2069530087","https://openalex.org/W2171378053","https://openalex.org/W2177902895"],"related_works":["https://openalex.org/W2489956408","https://openalex.org/W2095614499","https://openalex.org/W2037989911","https://openalex.org/W349256592","https://openalex.org/W2086694237","https://openalex.org/W4213307346","https://openalex.org/W2068210614","https://openalex.org/W2130372067","https://openalex.org/W32469337","https://openalex.org/W4288056018"],"abstract_inverted_index":{"An":[0],"analysis":[1],"of":[2,10,17,38,49],"chemical":[3],"structures":[4],"from":[5],"several":[6],"commercially":[7],"available":[8],"libraries":[9],"compounds":[11,19],"is":[12,42],"presented":[13],"with":[14],"a":[15],"view":[16],"acquiring":[18],"for":[20],"screening.":[21],"The":[22,36],"Jarvis\u2212Patrick":[23],"clustering":[24,51,56],"method":[25],"has":[26],"been":[27],"applied,":[28],"using":[29],"the":[30,39,50],"MDL":[31,40],"\u201ckeys\u201d":[32],"as":[33],"structural":[34],"descriptors.":[35],"nature":[37],"keys":[41],"examined":[43],"in":[44],"this":[45],"context,":[46],"some":[47],"features":[48],"algorithm":[52],"are":[53,58],"discussed,":[54],"and":[55],"statistics":[57],"presented.":[59]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":12}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
