{"id":"https://openalex.org/W7225818592","doi":"https://doi.org/10.64898/2026.11.09.765394","title":"SIFT: Syncmer-Informed Selection of Haplotypes for T2T Imputation","display_name":"SIFT: Syncmer-Informed Selection of Haplotypes for T2T Imputation","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225818592","doi":"https://doi.org/10.64898/2026.11.09.765394"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.09.765394","doi":"https://doi.org/10.64898/2026.11.09.765394","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765394","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.11.09.765394","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107155529","display_name":"Eddie Ferro","orcid":"https://orcid.org/0009-0002-9738-0216","observed_orcids":["https://orcid.org/0009-0002-9738-0216"]},"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":"Eddie A Ferro","raw_affiliation_strings":["University of Florida;"],"raw_orcid":"https://orcid.org/0009-0002-9738-0216","affiliations":[{"raw_affiliation_string":"University of Florida;","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104649966","display_name":"Rahul Varki","orcid":"https://orcid.org/0009-0003-5721-9484","observed_orcids":["https://orcid.org/0009-0003-5721-9484"]},"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":"Rahul Varki","raw_affiliation_strings":["University of Florida;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida;","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004996054","display_name":"Mao-Jan Lin","orcid":"https://orcid.org/0000-0003-1860-7786","observed_orcids":["https://orcid.org/0000-0003-1860-7786"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mao-Jan Lin","raw_affiliation_strings":["Johns Hopkins University;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University;","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013172801","display_name":"Travis Gagie","orcid":"https://orcid.org/0000-0003-3689-327X","observed_orcids":["https://orcid.org/0000-0003-3689-327X"]},"institutions":[{"id":"https://openalex.org/I911713783","display_name":"Universidad Diego Portales","ror":"https://ror.org/03gtdcg60","country_code":"CL","type":"education","lineage":["https://openalex.org/I911713783"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Travis Gagie","raw_affiliation_strings":["Diego Portales University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Diego Portales University","institution_ids":["https://openalex.org/I911713783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009556658","display_name":"Ben Langmead","orcid":"https://orcid.org/0000-0003-2437-1976","observed_orcids":["https://orcid.org/0000-0003-2437-1976"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Langmead","raw_affiliation_strings":["Johns Hopkins University;"],"raw_orcid":"https://orcid.org/0000-0003-2437-1976","affiliations":[{"raw_affiliation_string":"Johns Hopkins University;","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059638281","display_name":"Christina Boucher","orcid":"https://orcid.org/0000-0001-5617-7495","observed_orcids":["https://orcid.org/0000-0001-5617-7495","https://orcid.org/0000-0001-9509-9725"]},"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":"Christina A Boucher","raw_affiliation_strings":["University of Florida;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida;","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107155529"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"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/T11269","display_name":"Algorithms and Data Compression","score":0.9541000127792358,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9541000127792358,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.04320000112056732,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.0006000000284984708,"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":[],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6802999973297119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6625000238418579},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.5873000025749207},{"id":"https://openalex.org/C197754878","wikidata":"https://www.wikidata.org/wiki/Q80711","display_name":"Haplotype","level":4,"score":0.5594000220298767},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.42730000615119934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.3612000048160553},{"id":"https://openalex.org/C156340839","wikidata":"https://www.wikidata.org/wiki/Q2704791","display_name":"Enumeration","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.3515999913215637},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.3122999966144562},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.09.765394","doi":"https://doi.org/10.64898/2026.11.09.765394","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765394","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.09.765394","doi":"https://doi.org/10.64898/2026.11.09.765394","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765394","pdf_url":null,"source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Genome":[0],"patching":[1,51],"improves":[2],"the":[3,95,125,138,146,184,192],"completeness":[4],"of":[5,83,110],"fragmented":[6],"assemblies":[7],"by":[8],"filling":[9],"unresolved":[10],"gaps":[11],"with":[12,52,73,171],"sequences":[13,115],"from":[14],"reference":[15,47,84,126,147,160,181],"genomes.":[16],"Pangenome":[17],"panels":[18,36,182],"provide":[19,68],"diverse":[20],"candidate":[21,159],"haplotypes":[22,48,161],"for":[23,45,49,162,178],"this":[24],"task,":[25],"but":[26],"identifying":[27],"suitable":[28],"references":[29],"efficiently":[30],"becomes":[31],"increasingly":[32],"challenging":[33],"as":[34],"these":[35],"grow.":[37],"We":[38,88],"present":[39],"SIFT,":[40],"a":[41,69,176],"compressed":[42,133,168],"indexing":[43,170],"method":[44],"selecting":[46],"genome":[50],"ImpuT2T.":[53],"SIFT":[54,123,187],"combines":[55],"closed-syncmer":[56],"parsing,":[57],"phrase-level":[58],"indexing,":[59],"and":[60,85,116,128,136,149,174],"pseudo-maximal":[61],"exact":[62],"match":[63],"(pseudo-MEM)":[64],"queries.":[65],"Closed":[66],"syncmers":[67,93],"context-independent":[70],"parsing":[71,82],"rule":[72],"bounded":[74],"distances":[75],"between":[76,145],"consecutive":[77],"selected":[78],"positions,":[79],"enabling":[80],"consistent":[81],"query":[86,150],"sequences.":[87],"demonstrate":[89],"that":[90,107],"two":[91,111],"closed":[92],"determine":[94],"distance":[96],"at":[97,183,195],"which":[98],"they":[99],"can":[100],"occur":[101],"consecutively":[102],"in":[103],"any":[104],"string,":[105],"so":[106],"equal":[108],"substrings":[109],"parses":[112],"represent":[113],"identical":[114],"no":[117],"gap":[118],"sequence":[119,169],"need":[120],"be":[121],"stored.":[122],"indexes":[124],"parse":[127,148],"its":[129],"reverse":[130],"using":[131],"run-length":[132],"suffix":[134],"arrays":[135],"adapts":[137],"Boyer-Moore-Li":[139],"search":[140],"procedure":[141],"to":[142,157],"identify":[143,158],"pseudo-MEMs":[144],"parse.":[151],"It":[152],"then":[153],"aggregates":[154],"matching":[155],"evidence":[156],"downstream":[163],"patching.":[164],"This":[165],"framework":[166],"connects":[167],"haplotype":[172],"selection":[173],"provides":[175],"basis":[177],"querying":[179],"large":[180],"phrase":[185],"level.":[186],"is":[188],"publicly":[189],"available":[190],"under":[191],"GNU":[193],"license":[194],"https://github.com/EddieFerro/SIFT.":[196]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
