{"id":"https://openalex.org/W7162252282","doi":"https://doi.org/10.3390/a19060426","title":"A Clustering Approach for Rare Variant Classification by Effect Direction and Magnitude","display_name":"A Clustering Approach for Rare Variant Classification by Effect Direction and Magnitude","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162252282","doi":"https://doi.org/10.3390/a19060426"},"language":"en","primary_location":{"id":"doi:10.3390/a19060426","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19060426","pdf_url":"https://www.mdpi.com/1999-4893/19/6/426/pdf?version=1779626335","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/19/6/426/pdf?version=1779626335","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020770791","display_name":"Xianbang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianbang Sun","raw_affiliation_strings":["Department of Biostatistics, Boston University School of Public Health, Boston, MA 02118, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Boston University School of Public Health, Boston, MA 02118, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031005167","display_name":"X Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xue Liu","raw_affiliation_strings":["Department of Biostatistics, Boston University School of Public Health, Boston, MA 02118, USA"],"raw_orcid":"https://orcid.org/0000-0002-4196-3597","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Boston University School of Public Health, Boston, MA 02118, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136875069","display_name":"Yumeng Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yumeng Cao","raw_affiliation_strings":["Department of Biostatistics, Boston University School of Public Health, Boston, MA 02118, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Boston University School of Public Health, Boston, MA 02118, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136880296","display_name":"Chunyu Liu","orcid":"https://orcid.org/0000-0002-9160-0153"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunyu Liu","raw_affiliation_strings":["Department of Biostatistics, Boston University School of Public Health, Boston, MA 02118, USA"],"raw_orcid":"https://orcid.org/0000-0002-9160-0153","affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Boston University School of Public Health, Boston, MA 02118, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031005167"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57994228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"6","first_page":"426","last_page":"426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.8898000121116638,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.8898000121116638,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.09920000284910202,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.002899999963119626,"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":0.6840000152587891},{"id":"https://openalex.org/keywords/linkage-disequilibrium","display_name":"Linkage disequilibrium","score":0.6247000098228455},{"id":"https://openalex.org/keywords/genetic-association","display_name":"Genetic association","score":0.5070000290870667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5058000087738037},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.499099999666214},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.444599986076355},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.39800000190734863},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.392300009727478},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.37470000982284546},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3619999885559082}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6840000152587891},{"id":"https://openalex.org/C35605836","wikidata":"https://www.wikidata.org/wiki/Q2064311","display_name":"Linkage disequilibrium","level":5,"score":0.6247000098228455},{"id":"https://openalex.org/C186413461","wikidata":"https://www.wikidata.org/wiki/Q744727","display_name":"Genetic association","level":5,"score":0.5070000290870667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.45210000872612},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3952000141143799},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C40696583","wikidata":"https://www.wikidata.org/wiki/Q989120","display_name":"Type I and type II errors","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C157410074","wikidata":"https://www.wikidata.org/wiki/Q6869145","display_name":"Minor allele frequency","level":5,"score":0.35519999265670776},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.34360000491142273},{"id":"https://openalex.org/C81941488","wikidata":"https://www.wikidata.org/wiki/Q853421","display_name":"Quantitative trait locus","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C36382193","wikidata":"https://www.wikidata.org/wiki/Q7068966","display_name":"Null model","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.3239000141620636},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.29249998927116394},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C37463918","wikidata":"https://www.wikidata.org/wiki/Q387981","display_name":"Allele frequency","level":4,"score":0.2759000062942505},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25940001010894775}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a19060426","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19060426","pdf_url":"https://www.mdpi.com/1999-4893/19/6/426/pdf?version=1779626335","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7e942df69efc4347bbc83dcd56f7ce5e","is_oa":false,"landing_page_url":"https://doaj.org/article/7e942df69efc4347bbc83dcd56f7ce5e","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":"Algorithms, Vol 19, Iss 6, p 426 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a19060426","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19060426","pdf_url":"https://www.mdpi.com/1999-4893/19/6/426/pdf?version=1779626335","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1647374451","display_name":null,"funder_award_id":"R01HL15569","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"},{"id":"https://openalex.org/G2177652278","display_name":null,"funder_award_id":"R21HL144877","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"},{"id":"https://openalex.org/G2190227717","display_name":null,"funder_award_id":"R01HL15569","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G3769226514","display_name":null,"funder_award_id":"R01AG059727","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"},{"id":"https://openalex.org/G3914897939","display_name":null,"funder_award_id":"R21HL144877","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G4105637369","display_name":null,"funder_award_id":"R01AA028263","funder_id":"https://openalex.org/F4320337330","funder_display_name":"National Institute on Alcohol Abuse and Alcoholism"},{"id":"https://openalex.org/G5394812262","display_name":null,"funder_award_id":"R01AA028263","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G5778120067","display_name":null,"funder_award_id":"R01AG059727","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"}],"funders":[{"id":"https://openalex.org/F4320337330","display_name":"National Institute on Alcohol Abuse and Alcoholism","ror":"https://ror.org/02jzrsm59"},{"id":"https://openalex.org/F4320337337","display_name":"National Institute on Aging","ror":"https://ror.org/049v75w11"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7162252282.pdf","grobid_xml":"https://content.openalex.org/works/W7162252282.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1986818660","https://openalex.org/W2049633694","https://openalex.org/W2058148991","https://openalex.org/W2063655230","https://openalex.org/W2100909778","https://openalex.org/W2104549677","https://openalex.org/W2114901030","https://openalex.org/W2150593711","https://openalex.org/W2163953557","https://openalex.org/W2488678869","https://openalex.org/W2518986366","https://openalex.org/W2572331255","https://openalex.org/W2595081468","https://openalex.org/W2609272369","https://openalex.org/W2725988230","https://openalex.org/W2794716113","https://openalex.org/W2802368873","https://openalex.org/W2951393041","https://openalex.org/W3085430416","https://openalex.org/W3109183357","https://openalex.org/W4235169531","https://openalex.org/W4400378164","https://openalex.org/W4402827573","https://openalex.org/W4403098894","https://openalex.org/W4405310666","https://openalex.org/W4415126802","https://openalex.org/W4416402482"],"related_works":[],"abstract_inverted_index":{"Several":[0],"gene-based":[1],"tests,":[2],"such":[3],"as":[4],"the":[5,97,140,183,214],"sequence":[6],"kernel":[7],"association":[8,178],"test,":[9],"have":[10],"been":[11],"developed":[12],"to":[13,66,84,163],"assess":[14],"associations":[15],"between":[16],"rare":[17,53,164,205,218],"single":[18],"nucleotide":[19],"variants":[20,34,37,54,74,165,206],"(SNVs)":[21],"and":[22,57,80,88,106,120,151,156,180,191,210],"disease":[23],"traits.":[24],"However,":[25],"these":[26],"aggregate":[27],"methods":[28],"do":[29],"not":[30],"distinguish":[31],"potentially":[32],"causal":[33],"from":[35,70,174],"null":[36,56],"within":[38,207],"associated":[39,169,208],"regions.":[40],"To":[41],"address":[42],"this":[43],"limitation,":[44],"we":[45],"propose":[46],"gvClust,":[47],"a":[48,61,175,200],"clustering":[49,155],"approach":[50],"that":[51,197],"classifies":[52],"into":[55,78],"signal":[58],"groups":[59],"using":[60,96],"Gaussian":[62],"mixture":[63],"model":[64],"applied":[65,161],"variant-level":[67],"summary":[68],"statistics":[69],"multiple-variant":[71],"models.":[72],"Signal":[73],"are":[75],"further":[76],"partitioned":[77],"risk":[79],"protective":[81,192],"subgroups":[82],"according":[83],"their":[85],"effect":[86,116],"direction":[87],"magnitude.":[89],"We":[90,159],"evaluated":[91],"gvClust":[92,127,162,186,198],"in":[93,138,166],"simulation":[94],"studies":[95],"adjusted":[98],"Rand":[99],"index":[100],"(ARI),":[101],"mean":[102],"squared":[103],"error":[104],"(MSE),":[105],"accuracy":[107,137],"of":[108,142,217],"cluster":[109],"number":[110,141],"selection":[111],"under":[112],"different":[113],"sample":[114,133,149],"sizes,":[115,150],"configurations,":[117],"outcome":[118],"types,":[119],"linkage":[121],"disequilibrium":[122],"(LD)":[123],"structures.":[124],"In":[125,182],"simulations,":[126],"showed":[128],"improved":[129],"performance":[130],"with":[131,170],"increasing":[132],"size,":[134],"achieved":[135],"high":[136],"determining":[139],"clusters":[143],"for":[144,203],"continuous":[145],"traits":[146,173],"at":[147],"large":[148,176],"outperformed":[152],"both":[153],"k-means":[154],"initialization-only":[157],"clustering.":[158],"then":[160],"six":[167],"genes":[168],"blood":[171],"pressure":[172],"genome-wide":[177],"study":[179],"meta-analysis.":[181],"real-data":[184],"application,":[185],"identified":[187],"distinct":[188],"null,":[189],"risk,":[190],"clusters.":[193],"These":[194],"results":[195],"suggest":[196],"provides":[199],"practical":[201],"framework":[202],"classifying":[204],"regions":[209],"may":[211],"help":[212],"improve":[213],"biological":[215],"interpretation":[216],"variant":[219],"signals.":[220]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-05-25T00:00:00"}