{"id":"https://openalex.org/W4387171262","doi":"https://doi.org/10.3233/faia230492","title":"GENEMASK: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning","display_name":"GENEMASK: Fast Pretraining of Gene Sequences to Enable Few-Shot Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387171262","doi":"https://doi.org/10.3233/faia230492"},"language":"en","primary_location":{"id":"doi:10.3233/faia230492","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230492","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230492","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230492","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010730449","display_name":"Soumyadeep Roy","orcid":"https://orcid.org/0000-0001-7269-2163"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Soumyadeep Roy","raw_affiliation_strings":["Indian Institute of Technology Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066650027","display_name":"Jonas Wallat","orcid":"https://orcid.org/0000-0003-1239-2067"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Wallat","raw_affiliation_strings":["L3S Research Center, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006341541","display_name":"Sowmya S. Sundaram","orcid":"https://orcid.org/0000-0002-0086-7582"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sowmya S. Sundaram","raw_affiliation_strings":["L3S Research Center, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074427964","display_name":"Wolfgang Nejdl","orcid":"https://orcid.org/0000-0003-3374-2193"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Nejdl","raw_affiliation_strings":["L3S Research Center, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073812421","display_name":"Niloy Ganguly","orcid":"https://orcid.org/0000-0002-3967-186X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Niloy Ganguly","raw_affiliation_strings":["Indian Institute of Technology Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010730449"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":2.3526,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89718076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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":0.9977999925613403,"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":0.9977999925613403,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9923999905586243,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9897000193595886,"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/computer-science","display_name":"Computer science","score":0.7027860879898071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5920844078063965},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.5203894376754761},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4751315414905548},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45194271206855774},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.44722333550453186},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.44096454977989197},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.15919393301010132},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09552350640296936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027860879898071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5920844078063965},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.5203894376754761},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4751315414905548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45194271206855774},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.44722333550453186},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.44096454977989197},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.15919393301010132},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09552350640296936},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230492","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230492","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230492","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230492","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230492","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230492","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G367552324","display_name":"Internationales Leibniz Zukunftslabor K\u00fcnstliche Intelligenz","funder_award_id":"01DD20003","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320325536","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387171262.pdf"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1570757418","https://openalex.org/W1816313093","https://openalex.org/W2036131961","https://openalex.org/W2050712820","https://openalex.org/W2076154138","https://openalex.org/W2122732537","https://openalex.org/W2147380886","https://openalex.org/W2154866190","https://openalex.org/W2259938310","https://openalex.org/W2343416635","https://openalex.org/W2523060838","https://openalex.org/W2568988948","https://openalex.org/W2582377823","https://openalex.org/W2606984267","https://openalex.org/W2617242334","https://openalex.org/W2725988230","https://openalex.org/W2785490704","https://openalex.org/W2790244616","https://openalex.org/W2896457183","https://openalex.org/W2932524182","https://openalex.org/W2938830017","https://openalex.org/W2962177523","https://openalex.org/W2962753370","https://openalex.org/W2962784628","https://openalex.org/W2963959597","https://openalex.org/W2996771978","https://openalex.org/W3002104146","https://openalex.org/W3011411500","https://openalex.org/W3034199299","https://openalex.org/W3045733172","https://openalex.org/W3081391674","https://openalex.org/W3087291937","https://openalex.org/W3090048242","https://openalex.org/W3147114346","https://openalex.org/W3153427360","https://openalex.org/W3172642864","https://openalex.org/W3179640609","https://openalex.org/W3196356630","https://openalex.org/W3197120431","https://openalex.org/W3201819732","https://openalex.org/W3207661553","https://openalex.org/W4211244284","https://openalex.org/W4280594315","https://openalex.org/W4282825107","https://openalex.org/W4287646293","https://openalex.org/W4287704453","https://openalex.org/W4307205411","https://openalex.org/W4320813769","https://openalex.org/W4385567255","https://openalex.org/W4385572490","https://openalex.org/W6678235093"],"related_works":["https://openalex.org/W1892467659","https://openalex.org/W1529400504","https://openalex.org/W1989705153","https://openalex.org/W2998403542","https://openalex.org/W2808586768","https://openalex.org/W2789919619","https://openalex.org/W2496228846","https://openalex.org/W2293457016","https://openalex.org/W2359001871","https://openalex.org/W2584532118"],"abstract_inverted_index":{"Large-scale":[0],"language":[1],"models":[2,134,139],"such":[3],"as":[4,85],"DNABert":[5,161],"and":[6,14,43,54,88,126,141,189,208],"LOGO":[7],"aim":[8],"to":[9,47,105,155],"learn":[10],"optimal":[11],"gene":[12,74,83,146],"representations":[13],"are":[15,128,210],"trained":[16,164,206],"on":[17],"the":[18,91,94,98,111,117,137,159,170,175,197],"entire":[19],"Human":[20],"Reference":[21],"Genome.":[22],"However,":[23],"standard":[24],"tokenization":[25],"schemes":[26],"involve":[27],"a":[28,65,82,182],"simple":[29],"sliding":[30],"window":[31],"of":[32,50,73,113,169,172,174,199],"tokens":[33,188],"like":[34,124],"k-mers":[35],"that":[36,109],"do":[37],"not":[38],"leverage":[39],"any":[40],"gene-based":[41],"semantics":[42,115],"thus":[44],"may":[45,195],"lead":[46],"(trivial)":[48],"masking":[49,67],"easily":[51],"predictable":[52],"sequences,":[53,75],"subsequently":[55],"inefficient":[56],"Masked":[57],"Language":[58],"Modeling":[59],"(MLM)":[60],"training.":[61],"Therefore,":[62],"we":[63,77],"propose":[64],"novel":[66],"algorithm,":[68],"GENEMASK,":[69],"for":[70,165],"MLM":[71],"training":[72],"where":[76],"randomly":[78],"identify":[79],"positions":[80],"in":[81,110,116,131,150],"sequence":[84,147,192],"mask":[86,95],"centers":[87],"locally":[89],"select":[90],"span":[92],"around":[93],"center":[96],"with":[97],"highest":[99],"Normalized":[100],"Pointwise":[101],"Mutual":[102],"Information":[103],"(NPMI)":[104],"mask.":[106],"We":[107,179],"observe":[108,181],"absence":[112],"human-understandable":[114],"genomics":[118],"domain":[119],"(in":[120],"contrast,":[121],"semantic":[122],"units":[123],"words":[125],"phrases":[127],"inherently":[129],"available":[130,213],"NLP),":[132],"GENEMASK-based":[133,160],"substantially":[135],"outperform":[136],"SOTA":[138,177],"(DNABert":[140],"LOGO)":[142],"over":[143],"four":[144],"benchmark":[145],"classification":[148],"datasets":[149,209],"five":[151],"few-shot":[152],"settings":[153],"(10":[154],"1000-shot).":[156],"More":[157],"significantly,":[158],"model":[162],"is":[163],"less":[166],"than":[167],"one-tenth":[168],"number":[171],"epochs":[173],"original":[176],"model.":[178],"also":[180],"strong":[183],"correlation":[184],"between":[185],"top-ranked":[186],"PMI":[187],"conserved":[190],"DNA":[191],"motifs,":[193],"which":[194],"indicate":[196],"incorporation":[198],"latent":[200],"genomic":[201],"information.":[202],"The":[203],"codes":[204],"(including":[205],"models)":[207],"made":[211],"publicly":[212],"at":[214],"https://github.com/roysoumya/GeneMask.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}