{"id":"https://openalex.org/W2992322589","doi":"https://doi.org/10.1126/sciadv.aau9630","title":"Semblance: An empirical similarity kernel on probability spaces","display_name":"Semblance: An empirical similarity kernel on probability spaces","publication_year":2019,"publication_date":"2019-12-05","ids":{"openalex":"https://openalex.org/W2992322589","doi":"https://doi.org/10.1126/sciadv.aau9630","mag":"2992322589","pmid":"https://pubmed.ncbi.nlm.nih.gov/31840051","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/6892634"},"language":"en","primary_location":{"id":"doi:10.1126/sciadv.aau9630","doi":"https://doi.org/10.1126/sciadv.aau9630","is_oa":true,"landing_page_url":"https://doi.org/10.1126/sciadv.aau9630","pdf_url":"https://advances.sciencemag.org/content/advances/5/12/eaau9630.full.pdf","source":{"id":"https://openalex.org/S2737427234","display_name":"Science Advances","issn_l":"2375-2548","issn":["2375-2548"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science Advances","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://advances.sciencemag.org/content/advances/5/12/eaau9630.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004155361","display_name":"Divyansh Agarwal","orcid":"https://orcid.org/0000-0003-0404-6877","observed_orcids":["https://orcid.org/0000-0003-0404-6877"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Divyansh Agarwal","raw_affiliation_strings":["Department of Statistics, The Wharton School, University of Pennsylvania, Philadelphia, PA 19104, USA","Genomics and Computational Biology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"],"raw_orcid":"https://orcid.org/0000-0003-0404-6877","affiliations":[{"raw_affiliation_string":"Department of Statistics, The Wharton School, University of Pennsylvania, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Genomics and Computational Biology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022335574","display_name":"Nancy Ruonan Zhang","orcid":"https://orcid.org/0000-0002-0880-5749","observed_orcids":["https://orcid.org/0000-0002-0880-5749"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nancy R. Zhang","raw_affiliation_strings":["Department of Statistics, The Wharton School, University of Pennsylvania, Philadelphia, PA 19104, USA","Genomics and Computational Biology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"],"raw_orcid":"https://orcid.org/0000-0002-0880-5749","affiliations":[{"raw_affiliation_string":"Department of Statistics, The Wharton School, University of Pennsylvania, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Genomics and Computational Biology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004155361","https://openalex.org/A5022335574"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":{"value":4500,"currency":"USD","value_usd":4500},"apc_paid":{"value":4500,"currency":"USD","value_usd":4500},"fwci":0.3912,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64870554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"5","issue":"12","first_page":"eaau9630","last_page":"eaau9630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13141","display_name":"Statistical Methods and Applications","score":0.4794999957084656,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13141","display_name":"Statistical Methods and Applications","score":0.4794999957084656,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.23499999940395355,"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/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.07850000262260437,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/pairwise-similarity","display_name":"pairwise similarity","score":0.5820000171661377},{"id":"https://openalex.org/keywords/probability-distributions","display_name":"probability distributions","score":0.6579999923706055},{"id":"https://openalex.org/keywords/mercer-kernels","display_name":"Mercer kernels","score":0.8429999947547913},{"id":"https://openalex.org/keywords/kernel-learning","display_name":"kernel learning","score":0.5569999814033508},{"id":"https://openalex.org/keywords/single-cell-transcriptomics","display_name":"single-cell transcriptomics","score":0.7889999747276306},{"id":"https://openalex.org/keywords/image-reconstruction","display_name":"image reconstruction","score":0.9990000128746033},{"id":"https://openalex.org/keywords/financial-forecasting","display_name":"financial forecasting","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7034871578216553},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6603982448577881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5424990057945251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40044617652893066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3492279648780823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3377246856689453},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12034255266189575},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D036262","descriptor_name":"Empirical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1126/sciadv.aau9630","doi":"https://doi.org/10.1126/sciadv.aau9630","is_oa":true,"landing_page_url":"https://doi.org/10.1126/sciadv.aau9630","pdf_url":"https://advances.sciencemag.org/content/advances/5/12/eaau9630.full.pdf","source":{"id":"https://openalex.org/S2737427234","display_name":"Science Advances","issn_l":"2375-2548","issn":["2375-2548"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science Advances","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:6892634","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6892634","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,"listed_in":[],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sci Adv","raw_type":"Text"},{"id":"pmid:31840051","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31840051","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,"listed_in":[],"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":"Science advances","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:1808.02061","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.02061","pdf_url":"https://arxiv.org/pdf/1808.02061","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1808.02061","doi":"https://doi.org/10.48550/arxiv.1808.02061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.02061","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1126/sciadv.aau9630","doi":"https://doi.org/10.1126/sciadv.aau9630","is_oa":true,"landing_page_url":"https://doi.org/10.1126/sciadv.aau9630","pdf_url":"https://advances.sciencemag.org/content/advances/5/12/eaau9630.full.pdf","source":{"id":"https://openalex.org/S2737427234","display_name":"Science Advances","issn_l":"2375-2548","issn":["2375-2548"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315823","host_organization_name":"American Association for the Advancement of Science","host_organization_lineage":["https://openalex.org/P4310315823"],"host_organization_lineage_names":["American Association for the Advancement of Science"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science Advances","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7683272344","display_name":"Single Cell Transcriptomic and Genetic Diversity by Single Molecule Long Read Sequencing","funder_award_id":"R01HG006137","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G8372697316","display_name":"Statistical Methods for Single-Cell Transcriptomics","funder_award_id":"R01GM125301","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320309070","display_name":"Brown University","ror":"https://ror.org/05gq02987"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2992322589.pdf","grobid_xml":"https://content.openalex.org/works/W2992322589.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W576428146","https://openalex.org/W1489867037","https://openalex.org/W1500878026","https://openalex.org/W1510073064","https://openalex.org/W1567012231","https://openalex.org/W1916565700","https://openalex.org/W1968172834","https://openalex.org/W1969353942","https://openalex.org/W1996388084","https://openalex.org/W2018173663","https://openalex.org/W2020984122","https://openalex.org/W2066014073","https://openalex.org/W2075234374","https://openalex.org/W2082573972","https://openalex.org/W2092638522","https://openalex.org/W2094304374","https://openalex.org/W2102212449","https://openalex.org/W2112723918","https://openalex.org/W2116538057","https://openalex.org/W2122617678","https://openalex.org/W2127435698","https://openalex.org/W2136362180","https://openalex.org/W2157963336","https://openalex.org/W2164765928","https://openalex.org/W2168029744","https://openalex.org/W2172073485","https://openalex.org/W2190545194","https://openalex.org/W2477264826","https://openalex.org/W2482297996","https://openalex.org/W2952027905","https://openalex.org/W2953251392"],"related_works":["https://openalex.org/W2887793632","https://openalex.org/W242872570","https://openalex.org/W2106131881","https://openalex.org/W2106928803","https://openalex.org/W2120084270","https://openalex.org/W2025822499","https://openalex.org/W2230888156","https://openalex.org/W2900029572","https://openalex.org/W2950727631","https://openalex.org/W7095783993"],"abstract_inverted_index":{"In":[0],"data":[1,35,93,119],"science,":[2],"determining":[3],"proximity":[4,82],"between":[5,34,63,83],"observations":[6],"is":[7,26,37,103],"critical":[8],"to":[9,31,58,77,97],"many":[10],"downstream":[11],"analyses":[12],"such":[13],"as":[14,95],"clustering,":[15],"classification,":[16],"and":[17,74,116,132,144],"prediction.":[18],"However,":[19],"when":[20],"the":[21,28,52,60,89,92,100],"data's":[22],"underlying":[23],"probability":[24],"distribution":[25,54],"unclear,":[27],"function":[29],"used":[30],"compute":[32],"similarity":[33,62],"points":[36],"often":[38],"arbitrarily":[39],"chosen.":[40],"Here,":[41],"we":[42],"present":[43],"a":[44,56,104],"novel":[45],"definition":[46],"of":[47,55,67,91],"proximity,":[48],"Semblance,":[49],"that":[50,86],"uses":[51],"empirical":[53],"feature":[57],"inform":[59],"pair-wise":[61],"observations.":[64],"The":[65],"advantage":[66],"Semblance":[68,102],"lies":[69],"in":[70,112,139],"its":[71,75,109,123],"distribution-free":[72],"formulation":[73],"ability":[76],"place":[78],"greater":[79],"emphasis":[80],"on":[81],"observation":[84],"pairs":[85],"fall":[87],"at":[88],"outskirts":[90],"distribution,":[94],"opposed":[96],"those":[98],"toward":[99],"center.":[101],"valid":[105],"Mercer":[106],"kernel,":[107],"allowing":[108],"principled":[110],"use":[111],"kernel-based":[113],"learning":[114],"algorithms,":[115],"for":[117],"any":[118],"modality.":[120],"We":[121],"demonstrate":[122],"consistently":[124],"improved":[125],"performance":[126],"against":[127],"conventional":[128],"methods":[129],"through":[130],"simulations":[131],"real":[133],"case":[134],"studies":[135],"from":[136],"diverse":[137],"applications":[138],"single-cell":[140],"transcriptomics,":[141],"image":[142],"reconstruction,":[143],"financial":[145],"forecasting.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2019-12-13T00:00:00"}