{"id":"https://openalex.org/W4410767619","doi":"https://doi.org/10.1021/acs.jcim.5c00627","title":"BitBIRCH Clustering Refinement Strategies","display_name":"BitBIRCH Clustering Refinement Strategies","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W4410767619","doi":"https://doi.org/10.1021/acs.jcim.5c00627","pmid":"https://pubmed.ncbi.nlm.nih.gov/40425525"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c00627","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00627","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/A5113205000","display_name":"Kenneth L\u00f3pez P\u00e9rez","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth L\u00f3pez P\u00e9rez","raw_affiliation_strings":["Department of Chemistry and Quantum Theory Project","University of Florida"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Quantum Theory Project","institution_ids":[]},{"raw_affiliation_string":"University of Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031028280","display_name":"Kate Huddleston","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kate Huddleston","raw_affiliation_strings":["Department of Chemistry and Quantum Theory Project","University of Florida"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Quantum Theory Project","institution_ids":[]},{"raw_affiliation_string":"University of Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106576125","display_name":"Vicky Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vicky Jung","raw_affiliation_strings":["Department of Chemistry and Quantum Theory Project","University of Florida"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Quantum Theory Project","institution_ids":[]},{"raw_affiliation_string":"University of Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039322037","display_name":"Ram\u00f3n Alain Miranda\u2010Quintana","orcid":"https://orcid.org/0000-0003-2121-4449"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ram\u00f3n Alain Miranda-Quintana","raw_affiliation_strings":["Department of Chemistry and Quantum Theory Project","University of Florida"],"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Quantum Theory Project","institution_ids":[]},{"raw_affiliation_string":"University of Florida","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039322037"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":5.7199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95474347,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"65","issue":"11","first_page":"5280","last_page":"5288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10885","display_name":"Gene expression and cancer classification","score":0.9732000231742859,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6280390024185181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4039266109466553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25558966398239136}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6280390024185181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4039266109466553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25558966398239136}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c00627","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00627","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:40425525","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40425525","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W144237460","https://openalex.org/W1605923270","https://openalex.org/W1984994707","https://openalex.org/W1992419399","https://openalex.org/W2000376564","https://openalex.org/W2026265322","https://openalex.org/W2042007894","https://openalex.org/W2046344452","https://openalex.org/W2060531713","https://openalex.org/W2151697120","https://openalex.org/W2156077095","https://openalex.org/W2167212630","https://openalex.org/W2395375510","https://openalex.org/W2412446857","https://openalex.org/W2469049024","https://openalex.org/W2741196387","https://openalex.org/W2784878841","https://openalex.org/W4223988818","https://openalex.org/W4307722378","https://openalex.org/W4310225030","https://openalex.org/W4377012858","https://openalex.org/W4388455891","https://openalex.org/W4388569233","https://openalex.org/W4396712309","https://openalex.org/W4405056329","https://openalex.org/W4408405256"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Chemical":[0],"libraries":[1],"are":[2,10],"becoming":[3],"not":[4],"only":[5],"increasingly":[6],"bigger,":[7],"but":[8],"they":[9],"doing":[11],"so":[12],"at":[13],"an":[14],"accelerated":[15],"pace.":[16],"Keeping":[17],"up":[18,61],"with":[19,46,81],"this":[20,44,74,89,127],"explosion":[21],"in":[22,43],"chemical":[23],"data":[24],"demands":[25],"more":[26,34],"than":[27],"just":[28],"hardware":[29],"upgrades;":[30],"we":[31,69,92],"need":[32],"dramatically":[33,118],"efficient":[35],"algorithms":[36],"as":[37,150,152],"well.":[38],"We":[39,138],"have":[40],"been":[41],"working":[42],"direction,":[45],"the":[47,50,62,85,101,109,114,120,123,132,135,147,156],"introduction":[48],"of":[49,64,79,122,134],"instant":[51],"similarity":[52,58],"(iSIM)":[53],"framework,":[54],"which":[55],"uses":[56],"<i>n</i>-ary":[57],"to":[59,72,76,98],"speed":[60],"processing":[63],"very":[65],"large":[66],"sets.":[67],"Recently,":[68],"showed":[70],"how":[71],"use":[73],"technique":[75],"cluster":[77],"billions":[78],"molecules":[80],"unprecedented":[82],"efficiency":[83,133],"through":[84],"BitBIRCH":[86,102,159],"algorithm.":[87],"In":[88],"Application":[90],"Note,":[91],"present":[93,140],"a":[94],"package":[95],"fully":[96],"dedicated":[97],"expanding":[99],"on":[100],"method,":[103],"including":[104],"multiple":[105],"options":[106],"that":[107,144],"give":[108],"user":[110],"appreciable":[111],"control":[112],"over":[113],"tree":[115],"structure,":[116],"while":[117],"improving":[119],"quality":[121],"final":[124],"partitions.":[125],"Remarkably,":[126],"is":[128,160],"achieved":[129],"without":[130],"compromising":[131],"original":[136],"method.":[137],"also":[139],"new":[141,157],"postprocessing":[142],"tools":[143],"help":[145],"dissect":[146],"clustering":[148],"information,":[149],"well":[151],"ample":[153],"examples":[154],"showcasing":[155],"functionalities.":[158],"publicly":[161],"available":[162],"at:":[163],"https://github.com/mqcomplab/bitbirch.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
