{"id":"https://openalex.org/W2905012389","doi":"https://doi.org/10.1186/s13321-018-0321-8","title":"A probabilistic molecular fingerprint for big data settings","display_name":"A probabilistic molecular fingerprint for big data settings","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2905012389","doi":"https://doi.org/10.1186/s13321-018-0321-8","mag":"2905012389","pmid":"https://pubmed.ncbi.nlm.nih.gov/30564943"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-018-0321-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0321-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-018-0321-8.pdf","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://link.springer.com/content/pdf/10.1186/s13321-018-0321-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046410250","display_name":"Daniel Probst","orcid":"https://orcid.org/0000-0003-1737-4407"},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Daniel Probst","raw_affiliation_strings":["Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Berne, Freiestrasse 3, 3012, Bern, Switzerland. daniel.probst@dcb.unibe.ch","Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Berne, Freiestrasse 3, 3012, Bern, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-1737-4407","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Berne, Freiestrasse 3, 3012, Bern, Switzerland. daniel.probst@dcb.unibe.ch","institution_ids":["https://openalex.org/I118564535"]},{"raw_affiliation_string":"Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Berne, Freiestrasse 3, 3012, Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040848839","display_name":"Jean\u2010Louis Reymond","orcid":"https://orcid.org/0000-0003-2724-2942"},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jean-Louis Reymond","raw_affiliation_strings":["Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Berne, Freiestrasse 3, 3012, Bern, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Berne, Freiestrasse 3, 3012, Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046410250"],"corresponding_institution_ids":["https://openalex.org/I118564535"],"apc_list":{"value":2390,"currency":"USD","value_usd":2390},"apc_paid":{"value":2390,"currency":"USD","value_usd":2390},"fwci":7.4828,"has_fulltext":true,"cited_by_count":203,"citation_normalized_percentile":{"value":0.97783422,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"10","issue":"1","first_page":"66","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.978600025177002,"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":0.978600025177002,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.004800000227987766,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11476","display_name":"Graph theory and applications","score":0.00279999990016222,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.8612319827079773},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7785582542419434},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.6936014890670776},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5708932876586914},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5615898370742798},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.549119770526886},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5474543571472168},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5320972204208374},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.48620906472206116},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4688457250595093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38514000177383423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35829079151153564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.287792444229126},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.26032888889312744}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.8612319827079773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785582542419434},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.6936014890670776},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5708932876586914},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5615898370742798},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.549119770526886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5474543571472168},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5320972204208374},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.48620906472206116},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4688457250595093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38514000177383423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35829079151153564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.287792444229126},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.26032888889312744},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1186/s13321-018-0321-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0321-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-018-0321-8.pdf","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:30564943","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30564943","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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:6755601","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6755601","pdf_url":null,"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:doi:10.7892/boris.122955","is_oa":false,"landing_page_url":"https://boris-portal.unibe.ch/handle/20.500.12422/61862","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"JournalArticle"},{"id":"pmh:oai:boris.unibe.ch:122955","is_oa":true,"landing_page_url":"https://boris.unibe.ch/122955/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401086","display_name":"Bern Open Repository and Information System (University of Bern)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118564535","host_organization_name":"University of Bern","host_organization_lineage":["https://openalex.org/I118564535"],"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":"Probst, Daniel; Reymond, Jean-Louis (2018). A probabilistic molecular fingerprint for big data settings. Journal of cheminformatics, 10(1) BioMed Central 10.1186/s13321-018-0321-8 <http://dx.doi.org/10.1186/s13321-018-0321-8>","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:e72c25bd86ea402fb768fe5e81650870","is_oa":false,"landing_page_url":"https://doaj.org/article/e72c25bd86ea402fb768fe5e81650870","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 10, Iss 1, Pp 1-12 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-018-0321-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-018-0321-8","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-018-0321-8.pdf","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2905012389.pdf","grobid_xml":"https://content.openalex.org/works/W2905012389.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W188370263","https://openalex.org/W621207742","https://openalex.org/W1496508106","https://openalex.org/W1541459201","https://openalex.org/W1609518033","https://openalex.org/W1964513093","https://openalex.org/W1966613725","https://openalex.org/W1988037271","https://openalex.org/W1991800036","https://openalex.org/W2001424887","https://openalex.org/W2008999889","https://openalex.org/W2016979469","https://openalex.org/W2026869383","https://openalex.org/W2044834685","https://openalex.org/W2066636486","https://openalex.org/W2076459491","https://openalex.org/W2078396547","https://openalex.org/W2085816609","https://openalex.org/W2092493635","https://openalex.org/W2114687365","https://openalex.org/W2114704115","https://openalex.org/W2119512897","https://openalex.org/W2127553917","https://openalex.org/W2127760066","https://openalex.org/W2132069633","https://openalex.org/W2141036837","https://openalex.org/W2146292423","https://openalex.org/W2147717514","https://openalex.org/W2148781362","https://openalex.org/W2151697120","https://openalex.org/W2153693853","https://openalex.org/W2164523872","https://openalex.org/W2165558283","https://openalex.org/W2169678694","https://openalex.org/W2176516200","https://openalex.org/W2176720124","https://openalex.org/W2327481811","https://openalex.org/W2558999090","https://openalex.org/W2574633002","https://openalex.org/W2767891136","https://openalex.org/W2952138792","https://openalex.org/W4237307902","https://openalex.org/W4237383663","https://openalex.org/W6748602471"],"related_works":["https://openalex.org/W2148008870","https://openalex.org/W2381195555","https://openalex.org/W4246757943","https://openalex.org/W2368606575","https://openalex.org/W3094967175","https://openalex.org/W2144265691","https://openalex.org/W2166822184","https://openalex.org/W3096071782","https://openalex.org/W2902799860","https://openalex.org/W4289129280"],"abstract_inverted_index":{"BACKGROUND:":[0],"Among":[1],"the":[2,71,95,107,119,137,155,159,231,245],"various":[3],"molecular":[4,218],"fingerprints":[5,194],"available":[6,256],"to":[7,16,46,65,70,86,147,158],"describe":[8,132],"small":[9],"organic":[10],"molecules,":[11],"extended":[12,96],"connectivity":[13,97],"fingerprint,":[14,81,84,219],"up":[15,85,146],"four":[17],"bonds":[18,88,152],"(ECFP4)":[19],"performs":[20],"best":[21],"in":[22,50,55,101,114,165,195,205],"benchmarking":[23,115,166],"drug":[24],"analog":[25,167,227],"recovery":[26,168,201],"studies":[27,116],"as":[28,60,182,187],"it":[29],"encodes":[30,91],"substructures":[31,93,142],"with":[32],"a":[33,79,102,133,148,216],"high":[34,41],"level":[35],"of":[36,73,99,109,121,139,150,197,234,247],"detail.":[37],"Unfortunately,":[38],"ECFP4":[39,51,164,193,225],"requires":[40],"dimensional":[42],"representations":[43],"(\u2265":[44],"1024D)":[45],"perform":[47,66,181],"well,":[48],"resulting":[49,160],"nearest":[52,111,127,177],"neighbor":[53,112,128,178],"searches":[54,113,228],"very":[56,67,206],"large":[57,248],"databases":[58],"such":[59],"GDB,":[61],"PubChem":[62],"or":[63],"ZINC":[64],"slowly":[68],"due":[69],"curse":[72],"dimensionality.":[74],"RESULTS:":[75],"Herein":[76],"we":[77],"report":[78],"new":[80,217],"called":[82],"MinHash":[83,156],"six":[87,151],"(MHFP6),":[89],"which":[90,223],"detailed":[92],"using":[94],"principle":[98],"ECFP":[100],"fundamentally":[103],"different":[104],"manner,":[105],"increasing":[106],"performance":[108],"exact":[110],"and":[117,153,199,208],"enabling":[118],"application":[120,233],"locality":[122,172,235],"sensitive":[123,173,236],"hashing":[124,237],"(LSH)":[125],"approximate":[126,176],"search":[129,179],"algorithms.":[130,238],"To":[131],"molecule,":[134],"MHFP6":[135,162,186,214,254],"extracts":[136],"SMILES":[138],"all":[140],"circular":[141,221],"around":[143],"each":[144],"atom":[145],"diameter":[149],"applies":[154],"method":[157],"set.":[161],"outperforms":[163,224],"studies.":[169],"By":[170],"leveraging":[171],"hashing,":[174],"LSH":[175],"methods":[180,189],"well":[183,242],"on":[184,191,257],"unfolded":[185],"comparable":[188],"do":[190],"folded":[192],"terms":[196],"speed":[198],"relative":[200],"rate,":[202],"while":[203,229],"operating":[204],"sparse":[207],"high-dimensional":[209],"binary":[210],"chemical":[211],"space.":[212],"CONCLUSION:":[213],"is":[215,255],"encoding":[220],"substructures,":[222],"for":[226,244,253],"allowing":[230],"direct":[232],"It":[239],"should":[240],"be":[241],"suited":[243],"analysis":[246],"databases.":[249],"The":[250],"source":[251],"code":[252],"GitHub":[258],"(":[259],"https://github.com/reymond-group/mhfp":[260],").":[261]},"counts_by_year":[{"year":2026,"cited_by_count":20},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":46},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}