{"id":"https://openalex.org/W2119148238","doi":"https://doi.org/10.1109/icdm.2002.1183885","title":"Mining molecular fragments: finding relevant substructures of molecules","display_name":"Mining molecular fragments: finding relevant substructures of molecules","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2119148238","doi":"https://doi.org/10.1109/icdm.2002.1183885","mag":"2119148238"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2002.1183885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://kops.uni-konstanz.de/server/api/core/bitstreams/551c66b2-a4ed-4623-8933-e4d708ce83b8/content","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109526047","display_name":"Christian Borgelt","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138551","display_name":"University Hospital Magdeburg","ror":"https://ror.org/03m04df46","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210138551"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"C. Borgelt","raw_affiliation_strings":["School of Computer Science, University of Magdeburg, Magdeburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I4210138551"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035270195","display_name":"Michael R. Berthold","orcid":"https://orcid.org/0000-0001-9095-3283"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M.R. Berthold","raw_affiliation_strings":["Data Analysis Research Laboratory, Tripos, Inc., San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Analysis Research Laboratory, Tripos, Inc., San Francisco, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":53.5669,"has_fulltext":true,"cited_by_count":439,"citation_normalized_percentile":{"value":0.99974987,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.993399977684021,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.993399977684021,"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"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9926999807357788,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6476747989654541},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6441354751586914},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5897419452667236},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5598576664924622},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.501708984375},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.48237863183021545},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4715709090232849},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46420225501060486},{"id":"https://openalex.org/keywords/search-tree","display_name":"Search tree","score":0.4636451303958893},{"id":"https://openalex.org/keywords/brute-force","display_name":"Brute force","score":0.44449037313461304},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.4366297721862793},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.3983170986175537},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36184537410736084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2807869613170624},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.24019959568977356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21410542726516724},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.17083534598350525},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.126794695854187},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10878631472587585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6476747989654541},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6441354751586914},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5897419452667236},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5598576664924622},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.501708984375},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.48237863183021545},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4715709090232849},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46420225501060486},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.4636451303958893},{"id":"https://openalex.org/C2986801135","wikidata":"https://www.wikidata.org/wiki/Q1209494","display_name":"Brute force","level":2,"score":0.44449037313461304},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.4366297721862793},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3983170986175537},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36184537410736084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2807869613170624},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.24019959568977356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21410542726516724},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.17083534598350525},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.126794695854187},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10878631472587585},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icdm.2002.1183885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2002.1183885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:kops.uni-konstanz.de:123456789/5589","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bsz:352-opus-65705","pdf_url":"https://kops.uni-konstanz.de/server/api/core/bitstreams/551c66b2-a4ed-4623-8933-e4d708ce83b8/content","source":{"id":"https://openalex.org/S4306401487","display_name":"KOPS (University of Konstanz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189712700","host_organization_name":"University of Konstanz","host_organization_lineage":["https://openalex.org/I189712700"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.. IEEE Comput. Soc, 2002, S. 51-58. ISBN 0-7695-1754-4. Verf\u00fcgbar unter: doi: 10.1109/ICDM.2002.1183885","raw_type":"doc-type:conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.565.6565","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.565.6565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.inf.uni-konstanz.de/bioml2/publications/Papers2002/BoBe02_mofa_icdm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.857.2683","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.857.2683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://kops.uni-konstanz.de/bitstream/handle/123456789/5589/Mining_Molecular_Fragments.pdf%3Bjsessionid%3DDD342FD21FD02D6A9DFC58E77DDA050A?sequence%3D1","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.87.8513","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.87.8513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.inf.uni-konstanz.de/bioml/research/mofa/papers/icdm_02.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:kops.uni-konstanz.de:123456789/5589","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bsz:352-opus-65705","pdf_url":"https://kops.uni-konstanz.de/server/api/core/bitstreams/551c66b2-a4ed-4623-8933-e4d708ce83b8/content","source":{"id":"https://openalex.org/S4306401487","display_name":"KOPS (University of Konstanz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189712700","host_organization_name":"University of Konstanz","host_organization_lineage":["https://openalex.org/I189712700"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2002 IEEE International Conference on Data Mining, 2002. Proceedings.. IEEE Comput. Soc, 2002, S. 51-58. ISBN 0-7695-1754-4. Verf\u00fcgbar unter: doi: 10.1109/ICDM.2002.1183885","raw_type":"doc-type:conferenceObject"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2119148238.pdf","grobid_xml":"https://content.openalex.org/works/W2119148238.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W8319953","https://openalex.org/W1483679765","https://openalex.org/W1507626491","https://openalex.org/W1574456717","https://openalex.org/W1976683819","https://openalex.org/W1985104873","https://openalex.org/W2077440882","https://openalex.org/W2098688598","https://openalex.org/W2101649019","https://openalex.org/W2166559705","https://openalex.org/W6600318201","https://openalex.org/W6628973722","https://openalex.org/W6684726440"],"related_works":["https://openalex.org/W4205121176","https://openalex.org/W2789480285","https://openalex.org/W1976673004","https://openalex.org/W1971267722","https://openalex.org/W2402589461","https://openalex.org/W3094979732","https://openalex.org/W2037710955","https://openalex.org/W2885402535","https://openalex.org/W183780713","https://openalex.org/W2049361636"],"abstract_inverted_index":{"We":[0,83],"present":[1],"an":[2],"algorithm":[3,89],"to":[4,14],"find":[5],"fragments":[6,38],"in":[7,23,42,46,65,100],"a":[8,24,32,55],"set":[9],"of":[10,19,29,58,87,94,97],"molecules":[11,45],"that":[12],"help":[13],"discriminate":[15],"between":[16],"different":[17],"classes":[18],"for":[20,73],"instance,":[21],"activity":[22],"drug":[25],"discovery":[26,93],"context.":[27],"Instead":[28],"carrying":[30],"out":[31],"brute-force":[33],"search,":[34],"our":[35,88],"method":[36],"generates":[37],"by":[39,69,79,90],"embedding":[40],"them":[41],"all":[43],"appropriate":[44],"parallel":[47],"and":[48,61,78],"prunes":[49],"the":[50,59,71,85,92,101],"search":[51,68],"tree":[52],"based":[53],"on":[54],"local":[56],"order":[57],"atoms":[60],"bonds,":[62],"which":[63],"results":[64],"substantially":[66],"faster":[67],"eliminating":[70],"need":[72],"frequent,":[74],"computationally":[75],"expensive":[76],"reembeddings":[77],"suppressing":[80],"redundant":[81],"search.":[82],"prove":[84],"usefulness":[86],"demonstrating":[91],"activity-related":[95],"groups":[96],"chemical":[98],"compounds":[99],"well-known":[102],"National":[103],"Cancer":[104],"Institute's":[105],"HIV-screening":[106],"dataset.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":28},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":30}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}