{"id":"https://openalex.org/W2807253167","doi":"https://doi.org/10.1101/338780","title":"GenotypeTensors: Efficient Neural Network Genotype Callers","display_name":"GenotypeTensors: Efficient Neural Network Genotype Callers","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2807253167","doi":"https://doi.org/10.1101/338780","mag":"2807253167"},"language":"en","primary_location":{"id":"doi:10.1101/338780","doi":"https://doi.org/10.1101/338780","is_oa":true,"landing_page_url":"https://doi.org/10.1101/338780","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2018/06/05/338780.full.pdf","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2018/06/05/338780.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Joshua Cohen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Cohen","raw_affiliation_strings":["The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America;Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America;Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]},{"raw_affiliation_string":"Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I4387153466"]},{"raw_affiliation_string":"The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015682032","display_name":"Manuele Simi","orcid":"https://orcid.org/0000-0001-6898-6249","observed_orcids":["https://orcid.org/0000-0001-6898-6249"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuele Simi","raw_affiliation_strings":["The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America;Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America;Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]},{"raw_affiliation_string":"Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I4387153466"]},{"raw_affiliation_string":"The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047846741","display_name":"Fabien Campagne","orcid":"https://orcid.org/0000-0001-6237-3564","observed_orcids":["https://orcid.org/0000-0001-6237-3564"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fabien Campagne","raw_affiliation_strings":["Department of Physiology and Biophysics, Weill Cornell Medical College, New York, NY, United States of America;Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America;Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","Department of Physiology and Biophysics, Weill Cornell Medical College, New York, NY, United States of America","Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physiology and Biophysics, Weill Cornell Medical College, New York, NY, United States of America;Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I4387153466"]},{"raw_affiliation_string":"The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America;Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]},{"raw_affiliation_string":"Department of Physiology and Biophysics, Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I4387153466"]},{"raw_affiliation_string":"Department of Physiology and Biophysics,Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I4387153466"]},{"raw_affiliation_string":"The HRH Prince Alwaleed Bin Talal Bin Abdulaziz Alsaud Institute for Computational Biomedicine, Weill Cornell Medical College, New York, NY, United States of America","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047846741"],"corresponding_institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.788100004196167,"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":0.788100004196167,"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":0.05389999970793724,"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":0.02759999968111515,"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/genotype-calling","display_name":"genotype calling","score":0.9700000286102295},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.8759999871253967},{"id":"https://openalex.org/keywords/indel-calling","display_name":"indel calling","score":0.6480000019073486},{"id":"https://openalex.org/keywords/limited-training-data","display_name":"limited training data","score":0.6480000019073486},{"id":"https://openalex.org/keywords/hg002","display_name":"HG002","score":0.8209999799728394},{"id":"https://openalex.org/keywords/dnanexus","display_name":"DNAnexus","score":0.5920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409462928771973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6750978827476501},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6688851118087769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.651268482208252},{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.5348417162895203},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.519737720489502},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.494721382856369},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.483636736869812},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4683156907558441},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.423404723405838},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34251868724823},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.23090195655822754},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08227214217185974},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/338780","doi":"https://doi.org/10.1101/338780","is_oa":true,"landing_page_url":"https://doi.org/10.1101/338780","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2018/06/05/338780.full.pdf","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/338780","doi":"https://doi.org/10.1101/338780","is_oa":true,"landing_page_url":"https://doi.org/10.1101/338780","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2018/06/05/338780.full.pdf","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2807253167.pdf","grobid_xml":"https://content.openalex.org/works/W2807253167.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2060965924","https://openalex.org/W2119180969","https://openalex.org/W2147733682","https://openalex.org/W2557283755","https://openalex.org/W2585257480","https://openalex.org/W2593768305","https://openalex.org/W2765407302","https://openalex.org/W2792376130","https://openalex.org/W2889664156","https://openalex.org/W2919717584","https://openalex.org/W2929354011","https://openalex.org/W2949987290","https://openalex.org/W2951529834"],"related_works":["https://openalex.org/W2033001683","https://openalex.org/W2046457574","https://openalex.org/W2167094946","https://openalex.org/W4387460329","https://openalex.org/W4382398022","https://openalex.org/W1949458596","https://openalex.org/W4285059642","https://openalex.org/W3144677376","https://openalex.org/W2168489430","https://openalex.org/W180869904"],"abstract_inverted_index":{"ABSTRACT":[0],"We":[1,37,97,115],"studied":[2],"the":[3,112,120],"problem":[4],"of":[5,40,43,50,71,85,95,122,149],"calling":[6,16],"genotypes":[7,17,172],"using":[8],"neural":[9,51],"networks.":[10],"A":[11,145],"machine":[12],"learning":[13],"approach":[14,23,45],"to":[15,24,67,118,161,167],"requires":[18],"a":[19,88],"training":[20,53,124,129,139],"set,":[21],"an":[22,107],"convert":[25],"genomic":[26],"sites":[27,133],"into":[28],"tensors":[29],"and":[30,34,46,58,93],"robust":[31],"model":[32,169],"development":[33],"evaluation":[35],"protocols.":[36],"discuss":[38],"each":[39],"these":[41,100],"components":[42],"our":[44],"compare":[47],"four":[48],"types":[49],"network":[52],"protocols,":[54],"two":[55,59],"fully":[56],"supervised":[57],"semi-supervised":[60],"approaches.":[61],"Semi-supervised":[62],"approaches":[63],"use":[64],"unlabeled":[65],"data":[66],"supplement":[68],"limited":[69],"quantities":[70],"labeled":[72],"data.":[73],"Random":[74],"hyper-parameter":[75],"searches":[76],"identified":[77],"highly":[78],"performing":[79],"models":[80,101,130],"that":[81],"reach":[82],"indel":[83],"F1":[84],"99.4%":[86],"on":[87,105],"chromosomes":[89],"20,":[90],"21,":[91],"22":[92],"X":[94],"NA12878/HG001.":[96],"further":[98],"validate":[99],"by":[102],"evaluating":[103],"performance":[104],"HG002,":[106],"independent":[108],"sample":[109],"used":[110],"in":[111],"PrecisionFDA":[113],"challenge.":[114],"apply":[116],"GenotypeTensors":[117,150],"evaluate":[119],"impact":[121],"(1)":[123],"with":[125,132,140,173],"small":[126],"datasets,":[127],"(2)":[128],"only":[131],"inside":[134],"confidence":[135],"regions,":[136],"or":[137,170],"(3)":[138],"improved":[141],"true":[142],"label":[143],"annotations.":[144],"PyTorch":[146],"open-source":[147],"implementation":[148],"is":[151],"available":[152],"at":[153],"https://github.com/CampagneLaboratory/GenotypeTensors":[154],".":[155],"DNANexus":[156],"cloud":[157],"applications":[158],"are":[159],"provided":[160],"help":[162],"process":[163],"new":[164],"datasets":[165],"both":[166],"train":[168],"call":[171],"trained":[174],"models.":[175]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}