{"id":"https://openalex.org/W4289694730","doi":"https://doi.org/10.1080/10618600.2022.2156522","title":"Probabilistic $K$-mean with local alignment for clustering and motif discovery in functional data","display_name":"Probabilistic $K$-mean with local alignment for clustering and motif discovery in functional data","publication_year":2018,"publication_date":"2018-08-14","ids":{"openalex":"https://openalex.org/W4289694730","doi":"https://doi.org/10.1080/10618600.2022.2156522"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:1808.04773","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.04773","pdf_url":"https://arxiv.org/pdf/1808.04773","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.04773","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065603929","display_name":"Marzia A. Cremona","orcid":"https://orcid.org/0000-0001-8899-7316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cremona, Marzia A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015561999","display_name":"Francesca Chiaromonte","orcid":"https://orcid.org/0000-0001-5605-9886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chiaromonte, Francesca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9965000152587891,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9965000152587891,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9894000291824341,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9835000038146973,"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":0.8075043559074402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.613871693611145},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5893095135688782},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4972861111164093},{"id":"https://openalex.org/keywords/functional-data-analysis","display_name":"Functional data analysis","score":0.43856891989707947},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4204276204109192},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3764321804046631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3680165708065033},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22232085466384888},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08226945996284485}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8075043559074402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.613871693611145},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5893095135688782},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4972861111164093},{"id":"https://openalex.org/C51820054","wikidata":"https://www.wikidata.org/wiki/Q5508814","display_name":"Functional data analysis","level":2,"score":0.43856891989707947},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4204276204109192},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3764321804046631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3680165708065033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22232085466384888},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08226945996284485},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:1808.04773","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.04773","pdf_url":"https://arxiv.org/pdf/1808.04773","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1808.04773","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.04773","pdf_url":"https://arxiv.org/pdf/1808.04773","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2299080873","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254","https://openalex.org/W1926736923"],"abstract_inverted_index":{"We":[0,98],"develop":[1],"a":[2],"new":[3],"method":[4,38,104],"to":[5,31,66,127,139],"locally":[6],"cluster":[7],"curves":[8,24,134],"and":[9,21,47,61,85,110,135],"discover":[10],"functional":[11,42,119],"motifs,":[12],"i.e.~typical":[13],"``shapes''":[14],"that":[15],"may":[16],"recur":[17],"several":[18],"times":[19],"along":[20],"across":[22],"the":[23,55,89,100],"capturing":[25],"important":[26],"local":[27],"characteristics.":[28],"In":[29],"order":[30],"identify":[32],"these":[33],"shared":[34],"curve":[35],"portions,":[36],"our":[37,103],"leverages":[39],"ideas":[40],"from":[41],"data":[43,125,137],"analysis":[44],"(joint":[45],"clustering":[46,63,116],"alignment":[48,53],"of":[49,57,96,102],"curves),":[50],"bioinformatics":[51],"(local":[52],"through":[54],"extension":[56],"high":[58],"similarity":[59],"seeds)":[60],"fuzzy":[62],"(curves":[64],"belonging":[65],"more":[67,74],"than":[68,75],"one":[69,76],"cluster,":[70],"if":[71],"they":[72],"contain":[73],"typical":[77],"``shape'').":[78],"It":[79],"can":[80],"employ":[81],"various":[82],"dissimilarity":[83],"measures":[84],"incorporate":[86],"derivatives":[87],"in":[88],"discovery":[90],"process,":[91],"thus":[92],"exploiting":[93],"complex":[94],"facets":[95],"shapes.":[97],"demonstrate":[99],"performance":[101],"with":[105],"an":[106],"extensive":[107],"simulation":[108],"study,":[109],"show":[111],"how":[112],"it":[113],"generalizes":[114],"other":[115],"methods":[117],"for":[118],"data.":[120],"Finally,":[121],"we":[122],"provide":[123],"real":[124],"applications":[126],"Berkeley":[128],"growth":[129],"data,":[130],"Italian":[131],"Covid-19":[132],"death":[133],"``Omics''":[136],"related":[138],"mutagenesis.":[140]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2023-01-04T00:00:00"}