{"id":"https://openalex.org/W2094580724","doi":"https://doi.org/10.1021/ci600384z","title":"Similarity by Compression","display_name":"Similarity by Compression","publication_year":2006,"publication_date":"2006-12-09","ids":{"openalex":"https://openalex.org/W2094580724","doi":"https://doi.org/10.1021/ci600384z","mag":"2094580724","pmid":"https://pubmed.ncbi.nlm.nih.gov/17238245"},"language":"en","primary_location":{"id":"doi:10.1021/ci600384z","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci600384z","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/A5051322573","display_name":"James L. Melville","orcid":null},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James L. Melville","raw_affiliation_strings":["School of Chemistry, University of Nottingham, University Park, Nottingham NG7 2RD, United Kingdom","School of Chemistry, University of Nottingham , University Park, Nottingham, NG7 2RD, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Chemistry, University of Nottingham, University Park, Nottingham NG7 2RD, United Kingdom","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"School of Chemistry, University of Nottingham , University Park, Nottingham, NG7 2RD, United Kingdom","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090149448","display_name":"Jenna F. Riley","orcid":null},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jenna F. Riley","raw_affiliation_strings":["School of Chemistry, University of Nottingham, University Park, Nottingham NG7 2RD, United Kingdom","School of Chemistry, University of Nottingham , University Park, Nottingham, NG7 2RD, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Chemistry, University of Nottingham, University Park, Nottingham NG7 2RD, United Kingdom","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"School of Chemistry, University of Nottingham , University Park, Nottingham, NG7 2RD, United Kingdom","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051687648","display_name":"Jonathan D. Hirst","orcid":"https://orcid.org/0000-0002-2726-0983"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jonathan D. Hirst","raw_affiliation_strings":["School of Chemistry, University of Nottingham, University Park, Nottingham NG7 2RD, United Kingdom","School of Chemistry, University of Nottingham , University Park, Nottingham, NG7 2RD, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Chemistry, University of Nottingham, University Park, Nottingham NG7 2RD, United Kingdom","institution_ids":["https://openalex.org/I142263535"]},{"raw_affiliation_string":"School of Chemistry, University of Nottingham , University Park, Nottingham, NG7 2RD, United Kingdom","institution_ids":["https://openalex.org/I142263535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051687648"],"corresponding_institution_ids":["https://openalex.org/I142263535"],"apc_list":null,"apc_paid":null,"fwci":0.9982,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.77102467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"47","issue":"1","first_page":"25","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.998199999332428,"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":0.998199999332428,"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":0.9907000064849854,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9851999878883362,"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/computer-science","display_name":"Computer science","score":0.7572735548019409},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6794267892837524},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5581275224685669},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5468104481697083},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5344497561454773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5333879590034485},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5221619606018066},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.5152902603149414},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.48158740997314453},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4312202036380768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40117335319519043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3743416368961334},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09632498025894165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572735548019409},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6794267892837524},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5581275224685669},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5468104481697083},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5344497561454773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5333879590034485},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5221619606018066},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.5152902603149414},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.48158740997314453},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4312202036380768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40117335319519043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3743416368961334},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09632498025894165},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009930","descriptor_name":"Organic Chemicals","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci600384z","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci600384z","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:17238245","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17238245","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":[{"id":"https://openalex.org/G7825761375","display_name":null,"funder_award_id":"GR/S75765/01","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320319997","display_name":"Nuffield Foundation","ror":"https://ror.org/0281jqk77"},{"id":"https://openalex.org/F4320320324","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1538011504","https://openalex.org/W1595350250","https://openalex.org/W1605923270","https://openalex.org/W1969462276","https://openalex.org/W1975147762","https://openalex.org/W1980069772","https://openalex.org/W1992095612","https://openalex.org/W2000541041","https://openalex.org/W2005219245","https://openalex.org/W2006814566","https://openalex.org/W2008381136","https://openalex.org/W2010604075","https://openalex.org/W2014276094","https://openalex.org/W2017739727","https://openalex.org/W2029213117","https://openalex.org/W2038702914","https://openalex.org/W2048283878","https://openalex.org/W2049241863","https://openalex.org/W2062556965","https://openalex.org/W2062930223","https://openalex.org/W2071717945","https://openalex.org/W2076942392","https://openalex.org/W2088930249","https://openalex.org/W2093737637","https://openalex.org/W2096729078","https://openalex.org/W2097413543","https://openalex.org/W2105098383","https://openalex.org/W2112912103","https://openalex.org/W2128859735","https://openalex.org/W2131003320","https://openalex.org/W2136010267","https://openalex.org/W2138407645","https://openalex.org/W2139666427","https://openalex.org/W2151554142","https://openalex.org/W2159822007","https://openalex.org/W2160114756","https://openalex.org/W2161488606","https://openalex.org/W2161628678","https://openalex.org/W2177508090","https://openalex.org/W2203775767","https://openalex.org/W2320034101","https://openalex.org/W4230960895"],"related_works":["https://openalex.org/W1512321724","https://openalex.org/W4231317009","https://openalex.org/W2367696392","https://openalex.org/W4383723869","https://openalex.org/W4293703255","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W2271907651","https://openalex.org/W3007688875","https://openalex.org/W4384298135"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,16,78],"simple":[3],"and":[4,24,82],"effective":[5],"method":[6,35],"for":[7],"similarity":[8,63,68,90],"searching":[9,64,69],"in":[10],"virtual":[11],"high-throughput":[12],"screening,":[13],"requiring":[14],"only":[15],"string-based":[17],"representation":[18,81],"of":[19,43,52],"the":[20,37,44,50,73],"molecules":[21],"(e.g.,":[22],"SMILES)":[23],"standard":[25,67],"compression":[26,39],"software,":[27],"available":[28,92],"on":[29,49],"all":[30],"modern":[31],"desktop":[32],"computers.":[33],"This":[34],"utilizes":[36],"normalized":[38,45],"distance,":[40,47],"an":[41],"approximation":[42],"information":[46],"based":[48],"concept":[51],"Kolmogorov":[53],"complexity.":[54],"On":[55],"representative":[56],"data":[57,83],"sets,":[58],"we":[59],"demonstrate":[60],"that":[61],"compression-based":[62,89],"can":[65],"outperform":[66],"protocols,":[70],"exemplified":[71],"by":[72],"Tanimoto":[74],"coefficient":[75],"combined":[76],"with":[77],"binary":[79],"fingerprint":[80],"fusion.":[84],"Software":[85],"to":[86],"carry":[87],"out":[88],"is":[91],"from":[93],"our":[94],"Web":[95],"site":[96],"at":[97],"http://comp.chem.nottingham.ac.uk/download/zippity.":[98]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-17T06:14:20.161405","created_date":"2025-10-10T00:00:00"}
