{"id":"https://openalex.org/W7166521728","doi":"https://doi.org/10.1186/s13321-026-01245-y","title":"Count your bits: fingerprint benchmarking to assess broad chemical space representation","display_name":"Count your bits: fingerprint benchmarking to assess broad chemical space representation","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7166521728","doi":"https://doi.org/10.1186/s13321-026-01245-y","pmid":"https://pubmed.ncbi.nlm.nih.gov/42374557"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-026-01245-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01245-y","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-026-01245-y.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/s13321-026-01245-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068532928","display_name":"Florian Huber","orcid":"https://orcid.org/0000-0002-3535-9406"},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Florian Huber","raw_affiliation_strings":["Centre for Digitalisation and Digitality, D\u00fcsseldorf University of Applied Sciences, D\u00fcsseldorf, Germany. florian.huber@hs-duesseldorf.de"],"raw_orcid":"https://orcid.org/0000-0002-3535-9406","affiliations":[{"raw_affiliation_string":"Centre for Digitalisation and Digitality, D\u00fcsseldorf University of Applied Sciences, D\u00fcsseldorf, Germany. florian.huber@hs-duesseldorf.de","institution_ids":["https://openalex.org/I44260953"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872015","display_name":"Judith Pollmann","orcid":"https://orcid.org/0009-0004-3784-0019"},"institutions":[{"id":"https://openalex.org/I44260953","display_name":"Heinrich Heine University D\u00fcsseldorf","ror":"https://ror.org/024z2rq82","country_code":"DE","type":"education","lineage":["https://openalex.org/I44260953"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julian Pollmann","raw_affiliation_strings":["Centre for Digitalisation and Digitality, D\u00fcsseldorf University of Applied Sciences, D\u00fcsseldorf, Germany"],"raw_orcid":"https://orcid.org/0009-0004-3784-0019","affiliations":[{"raw_affiliation_string":"Centre for Digitalisation and Digitality, D\u00fcsseldorf University of Applied Sciences, D\u00fcsseldorf, Germany","institution_ids":["https://openalex.org/I44260953"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5068532928"],"corresponding_institution_ids":["https://openalex.org/I44260953"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67105431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.6565999984741211,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.6565999984741211,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.22669999301433563,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.021800000220537186,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8715999722480774},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.578499972820282},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.5658000111579895},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5658000111579895},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5364999771118164},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.52920001745224},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.49950000643730164}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8715999722480774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674999833106995},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5658000111579895},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.52920001745224},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46619999408721924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4180999994277954},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4056999981403351},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36980000138282776},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C168406668","wikidata":"https://www.wikidata.org/wiki/Q178022","display_name":"Fingerprint recognition","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-026-01245-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01245-y","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-026-01245-y.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:42374557","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42374557","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:doaj.org/article:9b8a74f96cb64c53a2437169fdc3daad","is_oa":false,"landing_page_url":"https://doaj.org/article/9b8a74f96cb64c53a2437169fdc3daad","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 18, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13317254","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13317254/","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"}],"best_oa_location":{"id":"doi:10.1186/s13321-026-01245-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01245-y","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-026-01245-y.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":[{"id":"https://openalex.org/G5796700125","display_name":"Communityzentriertes opensource Framework f\u00fcr die Analyse von gro\u00dfen TandemMassenspektrometriedaten","funder_award_id":"528775510","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166521728.pdf","grobid_xml":"https://content.openalex.org/works/W7166521728.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1974880836","https://openalex.org/W1982870104","https://openalex.org/W1983478747","https://openalex.org/W1988037271","https://openalex.org/W1988909822","https://openalex.org/W1992156271","https://openalex.org/W1993492933","https://openalex.org/W2006575776","https://openalex.org/W2008381136","https://openalex.org/W2016979469","https://openalex.org/W2021748110","https://openalex.org/W2064440950","https://openalex.org/W2064576005","https://openalex.org/W2094493457","https://openalex.org/W2096725584","https://openalex.org/W2107081909","https://openalex.org/W2119512897","https://openalex.org/W2125253492","https://openalex.org/W2140972311","https://openalex.org/W2151697120","https://openalex.org/W2160114756","https://openalex.org/W2179948434","https://openalex.org/W2200017991","https://openalex.org/W2245493112","https://openalex.org/W2472085920","https://openalex.org/W2548357532","https://openalex.org/W2622236128","https://openalex.org/W2786672974","https://openalex.org/W2901476322","https://openalex.org/W2901942917","https://openalex.org/W2994270865","https://openalex.org/W3003257820","https://openalex.org/W3014988774","https://openalex.org/W3035302862","https://openalex.org/W3108604517","https://openalex.org/W3116865743","https://openalex.org/W3206426065","https://openalex.org/W3206742358","https://openalex.org/W3209680996","https://openalex.org/W4213070269","https://openalex.org/W4280636794","https://openalex.org/W4281688302","https://openalex.org/W4285794641","https://openalex.org/W4289524482","https://openalex.org/W4293199734","https://openalex.org/W4295312788","https://openalex.org/W4295988913","https://openalex.org/W4296162381","https://openalex.org/W4297179162","https://openalex.org/W4310780836","https://openalex.org/W4320857994","https://openalex.org/W4379184641","https://openalex.org/W4383216745","https://openalex.org/W4385637657","https://openalex.org/W4388455891","https://openalex.org/W4393152099","https://openalex.org/W4396854777","https://openalex.org/W4402082179","https://openalex.org/W4403665140","https://openalex.org/W4404346391","https://openalex.org/W4404511389","https://openalex.org/W4406201162","https://openalex.org/W4407409549","https://openalex.org/W4407590529","https://openalex.org/W4408017019","https://openalex.org/W7128303164"],"related_works":[],"abstract_inverted_index":{"Quantifying":[0],"molecular":[1,208],"similarity":[2,41,199],"is":[3,67],"a":[4,70,129,203],"cornerstone":[5],"of":[6,23,30,33,39,75,190],"cheminformatics,":[7],"underpinning":[8],"applications":[9],"from":[10],"virtual":[11],"screening":[12],"and":[13,20,53,72,93,107,124,135,142,163,175,193,229,254,259,265,282],"nearest-neighbor":[14],"search":[15],"to":[16,68,128,277],"chemical":[17],"space":[18],"visualization":[19],"the":[21,36,46,181,272],"evaluation":[22,112],"machine-learning":[24],"predictions.":[25],"Yet,":[26],"despite":[27],"widespread":[28],"use":[29],"Tanimoto":[31],"comparisons":[32],"2D":[34],"fingerprints,":[35,155,248],"practical":[37],"behavior":[38,223],"these":[40,102,279],"measures":[42],"depends":[43],"strongly":[44,150],"on":[45,168,232],"fingerprint":[47,77,126,280,289],"type,":[48],"representation":[49,98],"(binary":[50],"vs.":[51],"count),":[52],"whether":[54],"fingerprints":[55,103,195,209],"are":[56],"folded":[57],"into":[58],"fixed-length":[59],"vectors.":[60],"In":[61],"this":[62],"work,":[63],"our":[64],"main":[65],"goal":[66],"provide":[69],"broad":[71],"systematic":[73],"comparison":[74],"common":[76,241],"types,":[78],"including":[79],"dictionary-based,":[80],"circular":[81],"(Morgan/FCFP),":[82],"path-based":[83],"(RDKit),":[84],"topological-distance-based":[85],"(Atom":[86],"Pair),":[87],"hybrid":[88],"distance-encoded":[89],"(MAP4),":[90],"torsion,":[91],"LINGO,":[92],"Avalon,":[94],"together":[95,196],"with":[96,197,267],"several":[97],"variants.":[99],"We":[100,270],"benchmark":[101],"across":[104],"multiple":[105],"large":[106],"heterogeneous":[108,169,234],"datasets":[109],"using":[110],"complementary":[111],"tasks":[113],"that":[114,210,240,255],"probe":[115],"specificity,":[116],"score":[117,222],"distributions,":[118],"compound-size":[119,225],"dependence,":[120],"top-k":[121],"ranking":[122,227],"agreement,":[123,228],"compare":[125],"similarities":[127,152],"graph-based":[130],"reference.":[131],"Across":[132],"benchmarks,":[133],"count":[134,256],"often":[136,164],"log-count":[137],"variants":[138,158,261,281],"generally":[139],"improve":[140,263],"specificity":[141,219,264],"structural":[143],"alignment,":[144],"while":[145],"folding-induced":[146],"bit":[147],"collisions":[148],"can":[149,249],"distort":[151],"for":[153,161,166,207,246,287],"high-occupancy":[154,247],"making":[156],"unfolded":[157,260],"particularly":[159],"important":[160],"RDKit":[162],"necessary":[165],"MAP4":[167],"datasets.":[170,236],"To":[171],"support":[172],"reproducible":[173],"benchmarking":[174,205,286],"future":[176,288],"extensions,":[177],"we":[178],"also":[179],"introduce":[180,202,250],"open-source":[182,273],"Python":[183,274],"library":[184,275],"chemap,":[185],"which":[186],"provides":[187],"unified":[188],"computation":[189],"folded,":[191],"unfolded,":[192],"frequency-folded":[194],"optimized":[198],"calculations.Scientific":[200],"contributionWe":[201],"multi-criteria":[204],"framework":[206],"goes":[211],"beyond":[212],"classical":[213],"virtual-screening":[214],"retrieval":[215],"tests":[216],"by":[217],"evaluating":[218],"(fingerprint":[220],"duplicates),":[221],"(including":[224],"dependence),":[226],"neighborhood":[230],"structure":[231],"large,":[233],"small-molecule":[235],"Our":[237],"results":[238],"reveal":[239],"default":[242],"settings,":[243],"especially":[244],"folding":[245],"severe":[251],"bit-collision":[252],"artifacts,":[253],"(often":[257],"log-count)":[258],"substantially":[262],"agreement":[266],"structure-based":[268],"references.":[269],"release":[271],"chemap":[276],"standardize":[278],"enable":[283],"reproducible,":[284],"extensible":[285],"development.":[290]},"counts_by_year":[],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2026-06-30T00:00:00"}