{"id":"https://openalex.org/W4313526969","doi":"https://doi.org/10.1109/bibm55620.2022.9995293","title":"Haplotype-phasing of long-read HiFi data to enhance structural variant detection through a Skip-Gram model","display_name":"Haplotype-phasing of long-read HiFi data to enhance structural variant detection through a Skip-Gram model","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4313526969","doi":"https://doi.org/10.1109/bibm55620.2022.9995293"},"language":"en","primary_location":{"id":"doi:10.1109/bibm55620.2022.9995293","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm55620.2022.9995293","pdf_url":null,"source":{"id":"https://openalex.org/S4363607730","display_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5089336048","display_name":"Can Luo","orcid":"https://orcid.org/0000-0002-7311-5963"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Can Luo","raw_affiliation_strings":["Vanderbilt University,Biomedical Engineering,Nashville,USA","Biomedical Engineering, Vanderbilt University, Nashville, USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Biomedical Engineering,Nashville,USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Biomedical Engineering, Vanderbilt University, Nashville, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000980569","display_name":"Parth Datar","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parth A. Datar","raw_affiliation_strings":["Computer Science Vanderbilt University,Nashville,USA","Computer Science Vanderbilt University, Nashville, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Vanderbilt University,Nashville,USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Computer Science Vanderbilt University, Nashville, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068921286","display_name":"Yichen Henry Liu","orcid":"https://orcid.org/0009-0006-8320-9636"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yichen Henry Liu","raw_affiliation_strings":["Computer Science Vanderbilt University,Nashville,USA","Computer Science Vanderbilt University, Nashville, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Vanderbilt University,Nashville,USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Computer Science Vanderbilt University, Nashville, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065917738","display_name":"Xin Zhou","orcid":"https://orcid.org/0000-0003-4015-4787"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Zhou","raw_affiliation_strings":["Computer Science Vanderbilt University,Nashville,USA","Computer Science Vanderbilt University, Nashville, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Vanderbilt University,Nashville,USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Computer Science Vanderbilt University, Nashville, USA","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089336048"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44541139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2326","last_page":"2333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994999766349792,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994999766349792,"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/T11764","display_name":"Evolution and Genetic Dynamics","score":0.994700014591217,"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":0.991599977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7019739151000977},{"id":"https://openalex.org/keywords/haplotype","display_name":"Haplotype","score":0.6991503238677979},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.60515958070755},{"id":"https://openalex.org/keywords/phaser","display_name":"Phaser","score":0.5546379685401917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3810279369354248},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.28205615282058716},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.23390743136405945},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09288334846496582},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09121504426002502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019739151000977},{"id":"https://openalex.org/C197754878","wikidata":"https://www.wikidata.org/wiki/Q80711","display_name":"Haplotype","level":4,"score":0.6991503238677979},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.60515958070755},{"id":"https://openalex.org/C135393689","wikidata":"https://www.wikidata.org/wiki/Q1551588","display_name":"Phaser","level":2,"score":0.5546379685401917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3810279369354248},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.28205615282058716},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.23390743136405945},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09288334846496582},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09121504426002502},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm55620.2022.9995293","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm55620.2022.9995293","pdf_url":null,"source":{"id":"https://openalex.org/S4363607730","display_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309151","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1971321176","https://openalex.org/W1973067702","https://openalex.org/W2012016911","https://openalex.org/W2104549677","https://openalex.org/W2124715997","https://openalex.org/W2147733682","https://openalex.org/W2211504288","https://openalex.org/W2493916176","https://openalex.org/W2563351168","https://openalex.org/W2779975541","https://openalex.org/W2809646241","https://openalex.org/W2950121474","https://openalex.org/W2963626623","https://openalex.org/W2979942779","https://openalex.org/W3046401484","https://openalex.org/W3047598142","https://openalex.org/W3116571403","https://openalex.org/W3128198169","https://openalex.org/W3159882286","https://openalex.org/W3189231637","https://openalex.org/W4229641819","https://openalex.org/W4294170691","https://openalex.org/W4313250582","https://openalex.org/W6682691769","https://openalex.org/W6731031554"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2163341755","https://openalex.org/W3146762847","https://openalex.org/W2398263405","https://openalex.org/W2146741998","https://openalex.org/W2056886854","https://openalex.org/W2025446304","https://openalex.org/W2166354960","https://openalex.org/W2466266952"],"abstract_inverted_index":{"Haplotype-resolved":[0],"assembly":[1,71],"is":[2,127],"the":[3,12,82,117,128],"optimal":[4],"approach":[5],"to":[6,59,75,132],"characterize":[7],"structural":[8],"variants":[9],"(SVs)":[10],"in":[11],"human":[13],"genome.":[14],"Current":[15],"long-read":[16],"technologies,":[17],"such":[18],"as":[19],"high-fidelity":[20],"(HiFi)":[21],"reads":[22,63],"provide":[23],"both":[24],"low":[25],"sequencing":[26],"error":[27],"and":[28,84,88,109,116,126],"long-range":[29],"information":[30],"which":[31,47],"enable":[32],"phased,":[33],"diploid":[34,42],"assembly.":[35,67],"Here":[36],"we":[37,95],"introduce":[38],"embSV,":[39],"a":[40,51],"haplotype-phasing-assisted":[41],"assembly-based":[43],"SV":[44,93],"detection":[45],"tool,":[46],"takes":[48],"advantage":[49],"of":[50,86],"word-embedding":[52],"model":[53],"inspired":[54],"by":[55],"natural":[56],"language":[57],"processing":[58],"faithfully":[60],"partition":[61],"HiFi":[62],"for":[64],"local":[65],"haplotype-specific":[66],"The":[68],"genome-wide":[69],"haplotype-resolved":[70],"then":[72],"allows":[73],"us":[74],"comprehensively":[76],"detect":[77],"SVs.":[78],"To":[79],"thoroughly":[80],"test":[81],"performance":[83],"robustness":[85],"embSV":[87,122],"compare":[89],"it":[90],"with":[91],"existing":[92,124],"callers,":[94],"have":[96],"run":[97],"several":[98],"benchmarking":[99],"experiments.":[100],"Tuning":[101],"different":[102],"parameters":[103],"that":[104,121],"can":[105],"affect":[106],"breakpoint":[107],"shift":[108],"alternate":[110],"sequence":[111],"similarity":[112],"between":[113],"called":[114],"SVs":[115],"gold":[118],"standard":[119],"reveals":[120],"outperforms":[123],"tools":[125],"most":[129],"robust":[130],"tool":[131],"parameter":[133],"change.":[134]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}