{"id":"https://openalex.org/W2540970325","doi":"https://doi.org/10.1186/s13321-016-0173-z","title":"Filtered circular fingerprints improve either prediction or runtime performance while retaining interpretability","display_name":"Filtered circular fingerprints improve either prediction or runtime performance while retaining interpretability","publication_year":2016,"publication_date":"2016-10-31","ids":{"openalex":"https://openalex.org/W2540970325","doi":"https://doi.org/10.1186/s13321-016-0173-z","mag":"2540970325","pmid":"https://pubmed.ncbi.nlm.nih.gov/27853484"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-016-0173-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0173-z","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-016-0173-z","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/s13321-016-0173-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065697003","display_name":"Martin G\u00fctlein","orcid":"https://orcid.org/0000-0003-2939-2469"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin G\u00fctlein","raw_affiliation_strings":["Chair of Data Mining, Institute of Computer Science, Johannes Gutenberg - Universit\u00e4t Mainz, Staudingerweg 9, 55128 Mainz, Germany","Chair of Data Mining, Institute of Computer Science, Johannes Gutenberg - Universit\u00e4t Mainz, Staudingerweg 9, 55128, Mainz, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2939-2469","affiliations":[{"raw_affiliation_string":"Chair of Data Mining, Institute of Computer Science, Johannes Gutenberg - Universit\u00e4t Mainz, Staudingerweg 9, 55128 Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Chair of Data Mining, Institute of Computer Science, Johannes Gutenberg - Universit\u00e4t Mainz, Staudingerweg 9, 55128, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102744434","display_name":"Stefan Kr\u00e4mer","orcid":"https://orcid.org/0000-0003-0136-2540"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Kramer","raw_affiliation_strings":["Chair of Data Mining, Institute of Computer Science, Johannes Gutenberg - Universit\u00e4t Mainz, Staudingerweg 9, 55128 Mainz, Germany","Chair of Data Mining, Institute of Computer Science, Johannes Gutenberg - Universit\u00e4t Mainz, Staudingerweg 9, 55128, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Data Mining, Institute of Computer Science, Johannes Gutenberg - Universit\u00e4t Mainz, Staudingerweg 9, 55128 Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Chair of Data Mining, Institute of Computer Science, Johannes Gutenberg - Universit\u00e4t Mainz, Staudingerweg 9, 55128, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065697003"],"corresponding_institution_ids":["https://openalex.org/I197323543"],"apc_list":{"value":2390,"currency":"USD","value_usd":2390},"apc_paid":{"value":1898,"currency":"EUR","value_usd":2046},"fwci":1.6415,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.86143179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"8","issue":"1","first_page":"60","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.567799985408783,"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":0.567799985408783,"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":0.250900000333786,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.03020000085234642,"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/interpretability","display_name":"Interpretability","score":0.928202748298645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7111680507659912},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.6403082013130188},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5943801999092102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5341823101043701},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.513486921787262},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5060374140739441},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47299250960350037}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.928202748298645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111680507659912},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.6403082013130188},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5943801999092102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5341823101043701},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.513486921787262},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5060374140739441},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47299250960350037},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13321-016-0173-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0173-z","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-016-0173-z","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:27853484","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27853484","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:5088672","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5088672","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/s13321-016-0173-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-016-0173-z","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-016-0173-z","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":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2540970325.pdf","grobid_xml":"https://content.openalex.org/works/W2540970325.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W178169250","https://openalex.org/W1512098439","https://openalex.org/W1523762189","https://openalex.org/W1540105270","https://openalex.org/W1964513093","https://openalex.org/W1967482463","https://openalex.org/W1976526581","https://openalex.org/W1977340881","https://openalex.org/W1978253274","https://openalex.org/W1981411466","https://openalex.org/W1988037271","https://openalex.org/W1992476311","https://openalex.org/W2015907087","https://openalex.org/W2021574925","https://openalex.org/W2033757486","https://openalex.org/W2039749139","https://openalex.org/W2040813073","https://openalex.org/W2042007894","https://openalex.org/W2042110087","https://openalex.org/W2044834685","https://openalex.org/W2045673749","https://openalex.org/W2055878543","https://openalex.org/W2055955780","https://openalex.org/W2062875420","https://openalex.org/W2089589794","https://openalex.org/W2100523380","https://openalex.org/W2102319243","https://openalex.org/W2108150886","https://openalex.org/W2112912103","https://openalex.org/W2116133514","https://openalex.org/W2119512897","https://openalex.org/W2120199131","https://openalex.org/W2122513050","https://openalex.org/W2125781388","https://openalex.org/W2127019019","https://openalex.org/W2127760066","https://openalex.org/W2133990480","https://openalex.org/W2139666427","https://openalex.org/W2142602210","https://openalex.org/W2147499591","https://openalex.org/W2148797284","https://openalex.org/W2149914376","https://openalex.org/W2152932486","https://openalex.org/W2160785561","https://openalex.org/W2162652393","https://openalex.org/W2166474856","https://openalex.org/W2169678694","https://openalex.org/W2218645992","https://openalex.org/W2911964244","https://openalex.org/W4246413330"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4312407344","https://openalex.org/W4384115502","https://openalex.org/W4226258012","https://openalex.org/W4383681494","https://openalex.org/W4288103012"],"abstract_inverted_index":{"BACKGROUND:":[0],"Even":[1],"though":[2],"circular":[3,43,99,224],"fingerprints":[4,55,122,137,171,204,225],"have":[5,103],"been":[6,104],"first":[7],"introduced":[8],"more":[9,145,268],"than":[10,278],"50":[11],"years":[12],"ago,":[13],"they":[14],"are":[15,46,80,143,205],"still":[16],"widely":[17],"used":[18,82],"for":[19,83,172,189,271,275,286],"building":[20,231],"highly":[21,211],"predictive,":[22],"state-of-the-art":[23],"(Q)SAR":[24,84,96,163,173,273],"models.":[25,164,233],"Historically,":[26],"these":[27],"structural":[28,66,194,207,217],"fragments":[29,45,101],"were":[30],"designed":[31],"to":[32,38,49,63,94,118,133,220,243],"search":[33],"large":[34],"molecular":[35],"databases.":[36],"Hence,":[37],"derive":[39],"a":[40,144,240,267],"compact":[41,146],"representation,":[42],"fingerprint":[44,100,253],"often":[47,81],"folded":[48,74,113,119,229],"comparatively":[50],"short":[51],"bit-strings.":[52],"However,":[53,219],"folding":[54],"introduces":[56],"bit":[57],"collisions,":[58],"and":[59,68,127,130,142,147,214],"therefore":[60],"adds":[61],"noise":[62],"the":[64,139,154,167,197,245,260,279],"encoded":[65],"information":[67],"removes":[69],"its":[70],"interpretability.":[71],"Both":[72],"representations,":[73],"as":[75,77],"well":[76],"unprocessed":[78,134],"fingerprints,":[79,120,135],"modeling.":[85],"RESULTS:":[86],"We":[87,165],"show":[88,236],"that":[89,102,186,209,237,259],"it":[90],"can":[91],"be":[92,228],"preferable":[93],"build":[95],"models":[97,213,274],"with":[98,251],"filtered":[105,121,136,170],"by":[106,175,191],"supervised":[107],"feature":[108,150],"selection,":[109],"instead":[110],"of":[111,169],"applying":[112],"or":[114,283],"all":[115,252],"fragments.":[116,254],"Compared":[117,132],"significantly":[123],"increase":[124],"predictive":[125,162,212],"performance":[126],"remain":[128],"unambiguous":[129],"interpretable.":[131],"reduce":[138,244],"computational":[140,247],"effort":[141,248],"less":[148],"redundant":[149],"representation.":[151],"Depending":[152],"on":[153],"selected":[155],"learning":[156],"algorithm":[157],"filtering":[158,238],"yields":[159],"about":[160],"equally":[161],"demonstrate":[166],"suitability":[168],"modeling":[174],"presenting":[176],"our":[177,256],"freely":[178],"available":[179],"web":[180],"service":[181],"Collision-free":[182],"Filtered":[183],"Circular":[184,203],"Fingerprints":[185],"provides":[187],"rationales":[188],"predictions":[190],"highlighting":[192],"important":[193],"features":[195,208],"in":[196],"query":[198],"compound":[199],"(see":[200],"http://coffer.informatik.uni-mainz.de).":[201],"CONCLUSIONS:":[202],"potent":[206],"yield":[210],"encode":[215],"interpretable":[216],"information.":[218],"not":[221,227],"lose":[222],"interpretability,":[223],"should":[226],"when":[230,249],"prediction":[232],"Our":[234],"experiments":[235,257],"is":[239,266],"suitable":[241],"option":[242],"high":[246],"working":[250],"Additionally,":[255],"suggest":[258],"area":[261,280],"under":[262,281],"precision":[263],"recall":[264],"curve":[265],"sensible":[269],"statistic":[270],"validating":[272],"virtual":[276],"screening":[277],"ROC":[282],"other":[284],"measures":[285],"early":[287],"recognition.":[288]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}