{"id":"https://openalex.org/W2076942392","doi":"https://doi.org/10.1021/ci6002152","title":"Lingos, Finite State Machines, and Fast Similarity Searching","display_name":"Lingos, Finite State Machines, and Fast Similarity Searching","publication_year":2006,"publication_date":"2006-09-01","ids":{"openalex":"https://openalex.org/W2076942392","doi":"https://doi.org/10.1021/ci6002152","mag":"2076942392","pmid":"https://pubmed.ncbi.nlm.nih.gov/16995721"},"language":"en","primary_location":{"id":"doi:10.1021/ci6002152","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci6002152","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"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 Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5113625729","display_name":"Jennifer Grant","orcid":null},"institutions":[{"id":"https://openalex.org/I105036370","display_name":"AstraZeneca (United Kingdom)","ror":"https://ror.org/04r9x1a08","country_code":"GB","type":"company","lineage":["https://openalex.org/I105036370"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"J. Andrew Grant","raw_affiliation_strings":["AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England","institution_ids":["https://openalex.org/I105036370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079470556","display_name":"James A. Haigh","orcid":null},"institutions":[{"id":"https://openalex.org/I105036370","display_name":"AstraZeneca (United Kingdom)","ror":"https://ror.org/04r9x1a08","country_code":"GB","type":"company","lineage":["https://openalex.org/I105036370"]},{"id":"https://openalex.org/I4210139427","display_name":"Rancho Research Institute","ror":"https://ror.org/04s7a0g31","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210139427"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"James A. Haigh","raw_affiliation_strings":["AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England","Department of Chemistry, The University of Sheffield, Sheffield S3 7HF, England","OpenEye Scientific Software Inc., 3600 Cerrillos Road, Suite 1107, Santa Fe, New Mexico 87507"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England","institution_ids":["https://openalex.org/I105036370"]},{"raw_affiliation_string":"Department of Chemistry, The University of Sheffield, Sheffield S3 7HF, England","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"OpenEye Scientific Software Inc., 3600 Cerrillos Road, Suite 1107, Santa Fe, New Mexico 87507","institution_ids":["https://openalex.org/I4210139427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056614766","display_name":"Barry T. Pickup","orcid":"https://orcid.org/0000-0002-2728-5486"},"institutions":[{"id":"https://openalex.org/I105036370","display_name":"AstraZeneca (United Kingdom)","ror":"https://ror.org/04r9x1a08","country_code":"GB","type":"company","lineage":["https://openalex.org/I105036370"]},{"id":"https://openalex.org/I4210139427","display_name":"Rancho Research Institute","ror":"https://ror.org/04s7a0g31","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210139427"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Barry T. Pickup","raw_affiliation_strings":["AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England","Department of Chemistry, The University of Sheffield, Sheffield S3 7HF, England","OpenEye Scientific Software Inc., 3600 Cerrillos Road, Suite 1107, Santa Fe, New Mexico 87507"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England","institution_ids":["https://openalex.org/I105036370"]},{"raw_affiliation_string":"Department of Chemistry, The University of Sheffield, Sheffield S3 7HF, England","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"OpenEye Scientific Software Inc., 3600 Cerrillos Road, Suite 1107, Santa Fe, New Mexico 87507","institution_ids":["https://openalex.org/I4210139427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102879646","display_name":"Anthony Nicholls","orcid":"https://orcid.org/0000-0001-8488-9641"},"institutions":[{"id":"https://openalex.org/I105036370","display_name":"AstraZeneca (United Kingdom)","ror":"https://ror.org/04r9x1a08","country_code":"GB","type":"company","lineage":["https://openalex.org/I105036370"]},{"id":"https://openalex.org/I4210139427","display_name":"Rancho Research Institute","ror":"https://ror.org/04s7a0g31","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210139427"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Anthony Nicholls","raw_affiliation_strings":["AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England","Department of Chemistry, The University of Sheffield, Sheffield S3 7HF, England","OpenEye Scientific Software Inc., 3600 Cerrillos Road, Suite 1107, Santa Fe, New Mexico 87507"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England","institution_ids":["https://openalex.org/I105036370"]},{"raw_affiliation_string":"Department of Chemistry, The University of Sheffield, Sheffield S3 7HF, England","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"OpenEye Scientific Software Inc., 3600 Cerrillos Road, Suite 1107, Santa Fe, New Mexico 87507","institution_ids":["https://openalex.org/I4210139427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064515321","display_name":"Roger A. Sayle","orcid":"https://orcid.org/0000-0003-0188-471X"},"institutions":[{"id":"https://openalex.org/I105036370","display_name":"AstraZeneca (United Kingdom)","ror":"https://ror.org/04r9x1a08","country_code":"GB","type":"company","lineage":["https://openalex.org/I105036370"]},{"id":"https://openalex.org/I4210139427","display_name":"Rancho Research Institute","ror":"https://ror.org/04s7a0g31","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210139427"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Roger A. Sayle","raw_affiliation_strings":["AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England","Department of Chemistry, The University of Sheffield, Sheffield S3 7HF, England","OpenEye Scientific Software Inc., 3600 Cerrillos Road, Suite 1107, Santa Fe, New Mexico 87507"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca Pharmaceuticals, Mereside, Macclesfield, Cheshire SK10 4TF, England","institution_ids":["https://openalex.org/I105036370"]},{"raw_affiliation_string":"Department of Chemistry, The University of Sheffield, Sheffield S3 7HF, England","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"OpenEye Scientific Software Inc., 3600 Cerrillos Road, Suite 1107, Santa Fe, New Mexico 87507","institution_ids":["https://openalex.org/I4210139427"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9946,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.91076895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"46","issue":"5","first_page":"1912","last_page":"1918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9980999827384949,"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":0.9980999827384949,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9976000189781189,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9902999997138977,"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/similarity","display_name":"Similarity (geometry)","score":0.7954339385032654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6684654951095581},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6418548226356506},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.6394621133804321},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6171942949295044},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.6168224811553955},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5773347616195679},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.518135666847229},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4607888162136078},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45883694291114807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4519009292125702},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4097248911857605},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34847474098205566},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20147067308425903},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05688256025314331}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7954339385032654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6684654951095581},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6418548226356506},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.6394621133804321},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6171942949295044},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.6168224811553955},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5773347616195679},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.518135666847229},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4607888162136078},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45883694291114807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4519009292125702},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4097248911857605},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34847474098205566},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20147067308425903},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05688256025314331},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020342","descriptor_name":"Finite Element Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020342","descriptor_name":"Finite Element Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020342","descriptor_name":"Finite Element Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci6002152","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci6002152","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"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 Modeling","raw_type":"journal-article"},{"id":"pmid:16995721","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16995721","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1975147762","https://openalex.org/W1978184203","https://openalex.org/W1980069772","https://openalex.org/W1997455636","https://openalex.org/W2008381136","https://openalex.org/W2010604075","https://openalex.org/W2021083597","https://openalex.org/W2029213117","https://openalex.org/W2038702914","https://openalex.org/W2052943632","https://openalex.org/W2056177030","https://openalex.org/W2071717945","https://openalex.org/W2096729078","https://openalex.org/W2119126379","https://openalex.org/W2125253492","https://openalex.org/W2137262074","https://openalex.org/W2171963266","https://openalex.org/W2752061190","https://openalex.org/W2752885492","https://openalex.org/W4210951666","https://openalex.org/W4245602869"],"related_works":["https://openalex.org/W2324047026","https://openalex.org/W2339806289","https://openalex.org/W4281261571","https://openalex.org/W3008853525","https://openalex.org/W2535494882","https://openalex.org/W1972035260","https://openalex.org/W2368132270","https://openalex.org/W2173185020","https://openalex.org/W2946784807","https://openalex.org/W4387185219"],"abstract_inverted_index":{"We":[0],"apply":[1],"a":[2,31,55,60],"recently":[3],"published":[4],"method":[5,64],"of":[6,19,23,45,54],"text-based":[7],"molecular":[8],"similarity":[9,66],"searching":[10],"(LINGO)":[11],"to":[12,49,52],"standard":[13],"data":[14],"sets":[15],"for":[16,65],"the":[17,21,24],"purpose":[18],"quantifying":[20],"accuracy":[22,44],"approach.":[25],"Our":[26],"implementation":[27],"is":[28,47],"based":[29],"on":[30],"pattern-matching":[32],"finite":[33],"state":[34],"machine":[35],"(FSM)":[36],"which":[37],"results":[38],"in":[39],"fast":[40],"search":[41],"times.":[42],"The":[43],"LINGO":[46],"demonstrated":[48],"be":[50],"comparable":[51],"that":[53],"path-based":[56],"fingerprint":[57],"and":[58],"offers":[59],"simple":[61],"yet":[62],"effective":[63],"searching.":[67]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}
