{"id":"https://openalex.org/W4387567938","doi":"https://doi.org/10.1186/s13321-023-00765-1","title":"Bloom filters for molecules","display_name":"Bloom filters for molecules","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387567938","doi":"https://doi.org/10.1186/s13321-023-00765-1","pmid":"https://pubmed.ncbi.nlm.nih.gov/37828615"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-023-00765-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00765-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00765-1","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00765-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102827728","display_name":"Jorge Medina","orcid":"https://orcid.org/0000-0002-7865-0834"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jorge Medina","raw_affiliation_strings":["Department of Chemical Engineering, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103115676","display_name":"Andrew Dickson White","orcid":"https://orcid.org/0000-0002-6647-3965"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew D. White","raw_affiliation_strings":["Department of Chemical Engineering, University of Rochester, Rochester, NY, USA. andrew.white@rochester.edu","Department of Chemical Engineering, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, University of Rochester, Rochester, NY, USA. andrew.white@rochester.edu","institution_ids":[]},{"raw_affiliation_string":"Department of Chemical Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102827728"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.7526,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73191455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"15","issue":"1","first_page":"95","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10207","display_name":"Advanced biosensing and bioanalysis techniques","score":0.9930999875068665,"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/T10207","display_name":"Advanced biosensing and bioanalysis techniques","score":0.9930999875068665,"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":0.9811999797821045,"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":0.9671000242233276,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.9758107662200928},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7750027179718018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7466370463371277},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7194979190826416},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6980674266815186},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.6666216254234314},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48788881301879883},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4292936325073242},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4210158884525299},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38526737689971924},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33694419264793396},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2893970012664795},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1685386300086975},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.156418114900589},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10659962892532349},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07036155462265015}],"concepts":[{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.9758107662200928},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7750027179718018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466370463371277},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7194979190826416},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6980674266815186},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.6666216254234314},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48788881301879883},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4292936325073242},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4210158884525299},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38526737689971924},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33694419264793396},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2893970012664795},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1685386300086975},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.156418114900589},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10659962892532349},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07036155462265015},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1186/s13321-023-00765-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00765-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00765-1","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:37828615","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37828615","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 cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10571468","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10571468","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10571468/pdf/13321_2023_Article_765.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:1e8bcdcf40fe444e8fec45bf3d7237fe","is_oa":true,"landing_page_url":"https://doaj.org/article/1e8bcdcf40fe444e8fec45bf3d7237fe","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 15, Iss 1, Pp 1-6 (2023)","raw_type":"article"},{"id":"pmh:oai:osti.gov:2067674","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2067674","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:2472319","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2472319","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1186/s13321-023-00765-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-023-00765-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-023-00765-1","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G539732829","display_name":null,"funder_award_id":"DE-SC0023354","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320310246","display_name":"University of Rochester","ror":"https://ror.org/022kthw22"},{"id":"https://openalex.org/F4320310728","display_name":"Centre International de Recherche sur le Cancer","ror":"https://ror.org/00v452281"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387567938.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W19471559","https://openalex.org/W86504136","https://openalex.org/W1544599463","https://openalex.org/W1736726159","https://openalex.org/W1967373117","https://openalex.org/W1976892175","https://openalex.org/W1993284846","https://openalex.org/W2044834685","https://openalex.org/W2074633331","https://openalex.org/W2096541451","https://openalex.org/W2096864392","https://openalex.org/W2116435146","https://openalex.org/W2123845384","https://openalex.org/W2143635578","https://openalex.org/W2174991771","https://openalex.org/W2176758925","https://openalex.org/W2200017991","https://openalex.org/W2742124187","https://openalex.org/W2903195746","https://openalex.org/W2916086000","https://openalex.org/W3035302862","https://openalex.org/W3094640617","https://openalex.org/W3118695441","https://openalex.org/W4231078754","https://openalex.org/W4251602148","https://openalex.org/W4255371203","https://openalex.org/W4307468223","https://openalex.org/W4365597205","https://openalex.org/W4396723768"],"related_works":["https://openalex.org/W2227807207","https://openalex.org/W2370014100","https://openalex.org/W4287264924","https://openalex.org/W3137108924","https://openalex.org/W1852009617","https://openalex.org/W1979110442","https://openalex.org/W2042819006","https://openalex.org/W2170165007","https://openalex.org/W2156660460","https://openalex.org/W2362866566"],"abstract_inverted_index":{"Ultra-large":[0],"chemical":[1],"libraries":[2,16],"are":[3,52],"reaching":[4],"10s":[5],"to":[6,18,55,136],"100s":[7],"of":[8,10,58,65],"billions":[9,57],"molecules.":[11],"A":[12],"challenge":[13],"for":[14,34,123],"these":[15],"is":[17,25,39,128],"efficiently":[19],"check":[20,68],"if":[21,36,125],"a":[22,37,42,62,79,117,126,132],"proposed":[23],"molecule":[24,38,127],"present.":[26],"Here":[27],"we":[28],"propose":[29],"and":[30,67,85,107,120],"study":[31],"Bloom":[32,50,96],"filters":[33,51,97,122],"testing":[35],"present":[40],"in":[41,60,70],"set":[43],"using":[44,91],"either":[45],"string":[46,75],"or":[47,131],"fingerprint":[48],"representations.":[49],"small":[53,112],"enough":[54],"hold":[56],"molecules":[59],"just":[61],"few":[63],"GB":[64],"memory":[66,113],"membership":[69,109],"sub":[71],"milliseconds.":[72],"We":[73,115],"found":[74],"representations":[76],"can":[77],"have":[78],"false":[80],"positive":[81],"rate":[82],"below":[83],"1%":[84],"require":[86],"significantly":[87],"less":[88],"storage":[89],"than":[90],"fingerprints.":[92],"Canonical":[93],"SMILES":[94],"with":[95,98,111],"the":[99],"simple":[100],"FNV":[101],"(Fowler-Noll-Voll)":[102],"hashing":[103],"function":[104],"provide":[105,116],"fast":[106],"accurate":[108],"tests":[110],"requirements.":[114],"general":[118],"implementation":[119],"specific":[121],"detecting":[124],"purchasable,":[129],"patented,":[130],"natural":[133],"product":[134],"according":[135],"existing":[137],"databases":[138],"at":[139],"https://github.com/whitead/molbloom":[140],".":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
