{"id":"https://openalex.org/W3196311544","doi":"https://doi.org/10.1109/tcbb.2021.3109557","title":"GapPredict \u2013 A Language Model for Resolving Gaps in Draft Genome Assemblies","display_name":"GapPredict \u2013 A Language Model for Resolving Gaps in Draft Genome Assemblies","publication_year":2021,"publication_date":"2021-09-03","ids":{"openalex":"https://openalex.org/W3196311544","doi":"https://doi.org/10.1109/tcbb.2021.3109557","mag":"3196311544","pmid":"https://pubmed.ncbi.nlm.nih.gov/34478378"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2021.3109557","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3109557","pdf_url":"https://ieeexplore.ieee.org/ielx7/8857/9642421/09528958.pdf","source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/8857/9642421/09528958.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104667513","display_name":"Eric Chen","orcid":"https://orcid.org/0000-0003-3604-9925"},"institutions":[{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Eric Chen","raw_affiliation_strings":["Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076845048","display_name":"Justin Chu","orcid":"https://orcid.org/0000-0003-0549-4997"},"institutions":[{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Justin Chu","raw_affiliation_strings":["Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044901337","display_name":"Jessica Zhang","orcid":"https://orcid.org/0009-0009-7940-2048"},"institutions":[{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jessica Zhang","raw_affiliation_strings":["Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102829017","display_name":"Ren\u00e9 L. Warren","orcid":"https://orcid.org/0000-0002-9890-2293"},"institutions":[{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rene L. Warren","raw_affiliation_strings":["Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017539699","display_name":"\u0130nan\u00e7 Birol","orcid":"https://orcid.org/0000-0003-0950-7839"},"institutions":[{"id":"https://openalex.org/I4210133112","display_name":"Canada's Michael Smith Genome Sciences Centre","ror":"https://ror.org/0333j0897","country_code":"CA","type":"other","lineage":["https://openalex.org/I4210133112"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Inanc Birol","raw_affiliation_strings":["Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Canada's Michael Smith Genome Sciences Centre, BC Cancer, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I4210133112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104667513"],"corresponding_institution_ids":["https://openalex.org/I4210133112"],"apc_list":null,"apc_paid":null,"fwci":0.4879,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.62289054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"18","issue":"6","first_page":"2802","last_page":"2808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.98580002784729,"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/genome","display_name":"Genome","score":0.7008438110351562},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.6586242318153381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5837213397026062},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5364482998847961},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5321915149688721},{"id":"https://openalex.org/keywords/scaffold","display_name":"Scaffold","score":0.517233669757843},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4969830811023712},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4844219982624054},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46808797121047974},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.45736536383628845},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.45142167806625366},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.41187000274658203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34133589267730713},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32756704092025757},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2896290421485901},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.28267186880111694},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.26483285427093506},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2250766158103943},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21239537000656128},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.16161346435546875},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12737995386123657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10966488718986511}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7008438110351562},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.6586242318153381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5837213397026062},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5364482998847961},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5321915149688721},{"id":"https://openalex.org/C89429830","wikidata":"https://www.wikidata.org/wiki/Q735710","display_name":"Scaffold","level":2,"score":0.517233669757843},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4969830811023712},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4844219982624054},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46808797121047974},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.45736536383628845},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.45142167806625366},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.41187000274658203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34133589267730713},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32756704092025757},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2896290421485901},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.28267186880111694},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.26483285427093506},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2250766158103943},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21239537000656128},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.16161346435546875},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12737995386123657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10966488718986511},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011381","descriptor_name":"Programming Languages","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/tcbb.2021.3109557","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3109557","pdf_url":"https://ieeexplore.ieee.org/ielx7/8857/9642421/09528958.pdf","source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34478378","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34478378","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8772386","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8772386","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Comput Biol Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1109/tcbb.2021.3109557","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3109557","pdf_url":"https://ieeexplore.ieee.org/ielx7/8857/9642421/09528958.pdf","source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G4568173531","display_name":null,"funder_award_id":"2R01HG007182-04A1","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6277516419","display_name":null,"funder_award_id":"R01HG007182","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3196311544.pdf","grobid_xml":"https://content.openalex.org/works/W3196311544.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1255676896","https://openalex.org/W1522301498","https://openalex.org/W1767772592","https://openalex.org/W1793987388","https://openalex.org/W1828163288","https://openalex.org/W1994568187","https://openalex.org/W2021630037","https://openalex.org/W2046192291","https://openalex.org/W2051039710","https://openalex.org/W2054211501","https://openalex.org/W2064675550","https://openalex.org/W2102619694","https://openalex.org/W2105067980","https://openalex.org/W2107772251","https://openalex.org/W2108234281","https://openalex.org/W2118020555","https://openalex.org/W2120902911","https://openalex.org/W2130942839","https://openalex.org/W2132546867","https://openalex.org/W2156226201","https://openalex.org/W2156798505","https://openalex.org/W2198606573","https://openalex.org/W2336509392","https://openalex.org/W2589379462","https://openalex.org/W2790102940","https://openalex.org/W2949791539","https://openalex.org/W2953384591","https://openalex.org/W3022783334","https://openalex.org/W3041800561","https://openalex.org/W4299518610","https://openalex.org/W4394666350","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6674561012","https://openalex.org/W6679436768","https://openalex.org/W6682132143","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W4210830088","https://openalex.org/W2484133401","https://openalex.org/W2115501618","https://openalex.org/W3011183076","https://openalex.org/W2079322808","https://openalex.org/W2216477337","https://openalex.org/W2794893153","https://openalex.org/W2721624558","https://openalex.org/W2767590279","https://openalex.org/W3090794301"],"abstract_inverted_index":{"Short-read":[0],"DNA":[1],"sequencing":[2],"instruments":[3],"can":[4,109],"yield":[5],"over":[6],"10<sup>12</sup>":[7],"bases":[8,16],"per":[9],"run,":[10],"typically":[11],"composed":[12],"of":[13,46,77,80,112,134],"reads":[14,34],"150":[15],"long.":[17],"Despite":[18],"this":[19],"high":[20,124],"throughput,":[21],"de":[22],"novo":[23],"assembly":[24,50],"algorithms":[25],"have":[26],"difficulty":[27],"reconstructing":[28],"contiguous":[29],"genome":[30,143],"sequences":[31,57,63],"using":[32,58],"short":[33,48],"due":[35],"to":[36,88,126,138],"both":[37],"repetitive":[38],"and":[39,104],"difficult-to-sequence":[40],"regions":[41],"in":[42,64,92,142],"these":[43,65],"genomes.":[44],"Some":[45],"the":[47,99,107,113,121,127,131,139],"read":[49],"challenges":[51],"are":[52],"mitigated":[53],"by":[54,120],"scaffolding":[55],"assembled":[56],"paired-end":[59],"reads.":[60],"However,":[61],"unresolved":[62,90],"scaffolds":[66],"appear":[67],"as":[68],"\"gaps\".":[69],"Here,":[70],"we":[71],"introduce":[72],"GapPredict":[73,97],"-":[74],"An":[75],"implementation":[76],"a":[78,84],"proof":[79],"concept":[81],"that":[82,106,116],"uses":[83],"character-level":[85],"language":[86],"model":[87],"predict":[89],"nucleotides":[91],"scaffold":[93],"gaps.":[94],"We":[95],"benchmarked":[96],"against":[98],"state-of-the-art":[100],"gap-filling":[101,140],"tool":[102],"Sealer,":[103],"observed":[105],"former":[108],"fill":[110],"65.6%":[111],"sampled":[114],"gaps":[115],"were":[117],"left":[118],"unfilled":[119],"latter":[122],"with":[123],"similarity":[125],"reference":[128],"genome,":[129],"demonstrating":[130],"practical":[132],"utility":[133],"deep":[135],"learning":[136],"approaches":[137],"problem":[141],"assembly.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}