{"id":"https://openalex.org/W7118186657","doi":"https://doi.org/10.3389/fbinf.2025.1694924","title":"A Transformers-based framework for refinement of genetic variants","display_name":"A Transformers-based framework for refinement of genetic variants","publication_year":2026,"publication_date":"2026-01-05","ids":{"openalex":"https://openalex.org/W7118186657","doi":"https://doi.org/10.3389/fbinf.2025.1694924","pmid":"https://pubmed.ncbi.nlm.nih.gov/41561439"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2025.1694924","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1694924","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1694924/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1694924/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051919101","display_name":"Omar Abdelwahab","orcid":"https://orcid.org/0000-0001-6783-5799"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Omar Abdelwahab","raw_affiliation_strings":["Centre de recherche et d'innovation sur les v\u00e9g\u00e9taux (CRIV), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","D\u00e9partement de Phytologie, Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","Institut de Biologie Int\u00e9grative et des Syst\u00e8mes (IBIS), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","Institut intelligence et donn\u00e9es (IID), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Centre de recherche et d'innovation sur les v\u00e9g\u00e9taux (CRIV), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","institution_ids":["https://openalex.org/I43406934"]},{"raw_affiliation_string":"D\u00e9partement de Phytologie, Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","institution_ids":["https://openalex.org/I43406934"]},{"raw_affiliation_string":"Institut de Biologie Int\u00e9grative et des Syst\u00e8mes (IBIS), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","institution_ids":["https://openalex.org/I43406934"]},{"raw_affiliation_string":"Institut intelligence et donn\u00e9es (IID), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","institution_ids":["https://openalex.org/I43406934"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017614266","display_name":"Davoud Torkamaneh","orcid":"https://orcid.org/0000-0002-9782-5695"},"institutions":[{"id":"https://openalex.org/I43406934","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03","country_code":"CA","type":"education","lineage":["https://openalex.org/I43406934"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Davoud Torkamaneh","raw_affiliation_strings":["Centre de recherche et d'innovation sur les v\u00e9g\u00e9taux (CRIV), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","D\u00e9partement de Phytologie, Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","Institut de Biologie Int\u00e9grative et des Syst\u00e8mes (IBIS), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","Institut intelligence et donn\u00e9es (IID), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Centre de recherche et d'innovation sur les v\u00e9g\u00e9taux (CRIV), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","institution_ids":["https://openalex.org/I43406934"]},{"raw_affiliation_string":"D\u00e9partement de Phytologie, Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","institution_ids":["https://openalex.org/I43406934"]},{"raw_affiliation_string":"Institut de Biologie Int\u00e9grative et des Syst\u00e8mes (IBIS), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","institution_ids":["https://openalex.org/I43406934"]},{"raw_affiliation_string":"Institut intelligence et donn\u00e9es (IID), Universit\u00e9 Laval, Qu\u00e9bec, QC, Canada","institution_ids":["https://openalex.org/I43406934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017614266"],"corresponding_institution_ids":["https://openalex.org/I43406934"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02956552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"1694924","last_page":"1694924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.8686000108718872,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.8686000108718872,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.07079999893903732,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.007600000128149986,"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/heuristic","display_name":"Heuristic","score":0.6248999834060669},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47839999198913574},{"id":"https://openalex.org/keywords/blueprint","display_name":"Blueprint","score":0.478300005197525},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.3785000145435333},{"id":"https://openalex.org/keywords/genetic-variants","display_name":"Genetic variants","score":0.37779998779296875},{"id":"https://openalex.org/keywords/precision-medicine","display_name":"Precision medicine","score":0.3402000069618225},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3328999876976013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556999921798706},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4966999888420105},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47839999198913574},{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4754999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C2993967602","wikidata":"https://www.wikidata.org/wiki/Q5532932","display_name":"Genetic variants","level":4,"score":0.37779998779296875},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fbinf.2025.1694924","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1694924","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1694924/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41561439","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41561439","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,"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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:51285e588aec405ab171b80171b208fe","is_oa":true,"landing_page_url":"https://doaj.org/article/51285e588aec405ab171b80171b208fe","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 5 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12813134","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12813134/","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2025.1694924","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1694924","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2025.1694924/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310137","display_name":"Universit\u00e9 Laval","ror":"https://ror.org/04sjchr03"},{"id":"https://openalex.org/F4320310787","display_name":"Genome Canada","ror":"https://ror.org/029s29983"},{"id":"https://openalex.org/F4320314025","display_name":"G\u00e9nome Qu\u00e9bec","ror":null},{"id":"https://openalex.org/F4320314217","display_name":"Grain Farmers of Ontario","ror":"https://ror.org/023tfyg79"},{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"},{"id":"https://openalex.org/F4320330224","display_name":"Canadian Field Crop Research Alliance","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7118186657.pdf","grobid_xml":"https://content.openalex.org/works/W7118186657.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W66588809","https://openalex.org/W1912982817","https://openalex.org/W1919257374","https://openalex.org/W1988301066","https://openalex.org/W1999790144","https://openalex.org/W2011301426","https://openalex.org/W2012254260","https://openalex.org/W2021341670","https://openalex.org/W2059185913","https://openalex.org/W2103441770","https://openalex.org/W2107432340","https://openalex.org/W2108234281","https://openalex.org/W2112005039","https://openalex.org/W2119180969","https://openalex.org/W2142721632","https://openalex.org/W2158698691","https://openalex.org/W2170551349","https://openalex.org/W2189510244","https://openalex.org/W2244501064","https://openalex.org/W2327315544","https://openalex.org/W2532996183","https://openalex.org/W2555298751","https://openalex.org/W2597490071","https://openalex.org/W2765185461","https://openalex.org/W2889664156","https://openalex.org/W2898882839","https://openalex.org/W2951331911","https://openalex.org/W2952870794","https://openalex.org/W2980282514","https://openalex.org/W2999309192","https://openalex.org/W3131055609","https://openalex.org/W4226151130","https://openalex.org/W4254687493","https://openalex.org/W4283819568","https://openalex.org/W4294214983","https://openalex.org/W4399678281"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"variant":[1,46,89,98,161,183,218],"calling":[2,47,162],"refinement":[3,79,90,171,219],"is":[4,32,243],"crucial":[5],"for":[6,27,42,76,87,217,227],"distinguishing":[7],"true":[8],"genetic":[9,88],"variants":[10,120],"from":[11,121],"technical":[12],"artifacts":[13],"in":[14,54,67,220],"high-throughput":[15],"sequencing":[16],"data.":[17,44],"While":[18],"heuristic":[19,35,167],"filtering":[20,36,145,240],"and":[21,34,100,114,132,202,239],"manual":[22,30],"review":[23,31],"are":[24],"common":[25],"approaches":[26],"refining":[28],"variants,":[29],"time-consuming,":[33],"often":[37,49],"lacks":[38],"optimal":[39],"solutions,":[40],"especially":[41,53],"low-coverage":[43],"Traditional":[45],"methods":[48],"struggle":[50],"with":[51,108],"accuracy,":[52],"regions":[55],"of":[56,136,172,215,235],"low":[57],"read":[58],"coverage,":[59],"leading":[60],"to":[61,94,231],"false-positive":[62],"or":[63],"false-negative":[64],"calls.":[65],"Advances":[66],"artificial":[68],"intelligence,":[69],"particularly":[70],"deep":[71],"learning,":[72],"offer":[73],"promising":[74],"solutions":[75],"automating":[77],"this":[78,197],"process.":[80],"Here,":[81],"we":[82,210],"present":[83],"a":[84,133,192,200,207,225,232],"Transformers-based":[85],"framework":[86,128,204],"that":[91],"leverages":[92],"self-attention":[93],"model":[95],"dependencies":[96],"among":[97],"features":[99],"directly":[101],"processes":[102],"VCF":[103],"files,":[104],"enabling":[105],"seamless":[106],"integration":[107],"standard":[109],"pipelines":[110],"such":[111,185],"as":[112,186,191,199],"BCFTools":[113],"GATK4.":[115],"Trained":[116],"on":[117],"2":[118],"million":[119],"the":[122,127,139,153,177,212],"GIAB":[123],"(v4.2.1)":[124],"sample":[125],"HG003,":[126],"achieved":[129,179],"89.26%":[130],"accuracy":[131,146,178],"ROC":[134],"AUC":[135],"0.88.":[137],"Across":[138],"tested":[140],"samples,":[141],"VariantTransformer":[142,164],"improved":[143],"baseline":[144],"by":[147,180],"4%-10%,":[148],"demonstrating":[149],"consistent":[150],"gains":[151],"over":[152],"default":[154],"caller":[155,174],"filters.":[156],"When":[157],"integrated":[158],"into":[159],"conventional":[160],"pipelines,":[163],"outperformed":[165],"traditional":[166],"filters":[168],"and,":[169],"through":[170],"existing":[173],"outputs,":[175],"approached":[176],"state-of-the-art":[181],"AI-based":[182],"callers":[184],"DeepVariant,":[187],"despite":[188],"not":[189],"operating":[190],"standalone":[193],"caller.":[194],"By":[195],"positioning":[196],"work":[198],"flexible":[201],"generalizable":[203],"rather":[205],"than":[206],"single-use":[208],"model,":[209],"highlight":[211],"underexplored":[213],"potential":[214],"Transformers":[216],"genomics.":[221],"This":[222],"study":[223],"contributes":[224],"blueprint":[226],"adapting":[228],"Transformer":[229],"architectures":[230],"wide":[233],"range":[234],"genomic":[236],"quality":[237],"control":[238],"tasks.":[241],"Code":[242],"available":[244],"at:":[245],"https://github.com/Omar-Abd-Elwahab/VariantTransformer.":[246]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-01-05T00:00:00"}
