{"id":"https://openalex.org/W4294975370","doi":"https://doi.org/10.1109/embc48229.2022.9871730","title":"BaseFormer: Transformer based Base-Caller for Fast and Accurate Next Generation Sequencing","display_name":"BaseFormer: Transformer based Base-Caller for Fast and Accurate Next Generation Sequencing","publication_year":2022,"publication_date":"2022-07-11","ids":{"openalex":"https://openalex.org/W4294975370","doi":"https://doi.org/10.1109/embc48229.2022.9871730","pmid":"https://pubmed.ncbi.nlm.nih.gov/36085723"},"language":"en","primary_location":{"id":"doi:10.1109/embc48229.2022.9871730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc48229.2022.9871730","pdf_url":null,"source":{"id":"https://openalex.org/S4363607706","display_name":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100729846","display_name":"Shuwei Li","orcid":"https://orcid.org/0000-0001-7176-1964"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuwei Li","raw_affiliation_strings":["School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071087840","display_name":"Zhiru Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiru Guo","raw_affiliation_strings":["School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055425079","display_name":"Ao Shen","orcid":"https://orcid.org/0000-0003-4722-2367"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao Shen","raw_affiliation_strings":["School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061880857","display_name":"Zheqi Yu","orcid":"https://orcid.org/0000-0002-4152-4965"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheqi Yu","raw_affiliation_strings":["School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062269789","display_name":"Wei Mao","orcid":"https://orcid.org/0000-0003-2527-6778"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Mao","raw_affiliation_strings":["School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102638293","display_name":"Shaobo Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaobo Luo","raw_affiliation_strings":["School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034853402","display_name":"Hao Yu","orcid":"https://orcid.org/0000-0002-2674-4118"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yu","raw_affiliation_strings":["School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100729846"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":1.7649,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85601266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2022","issue":null,"first_page":"463","last_page":"466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9973999857902527,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9933000206947327,"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":0.6984546184539795},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6236323118209839},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5527825355529785},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5393009781837463},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4354846477508545},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42228615283966064},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38080212473869324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35184699296951294},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1687018871307373},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.1645798683166504},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12400203943252563},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12235444784164429},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11938929557800293},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08635780215263367},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08107611536979675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984546184539795},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6236323118209839},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5527825355529785},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5393009781837463},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4354846477508545},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42228615283966064},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38080212473869324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35184699296951294},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1687018871307373},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.1645798683166504},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12400203943252563},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12235444784164429},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11938929557800293},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08635780215263367},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08107611536979675},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004396","descriptor_name":"Coloring Agents","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004396","descriptor_name":"Coloring Agents","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004396","descriptor_name":"Coloring Agents","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006321","descriptor_name":"Heart","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006321","descriptor_name":"Heart","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006321","descriptor_name":"Heart","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008511","descriptor_name":"Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008511","descriptor_name":"Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008511","descriptor_name":"Medicine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc48229.2022.9871730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc48229.2022.9871730","pdf_url":null,"source":{"id":"https://openalex.org/S4363607706","display_name":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:36085723","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36085723","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":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1584274086","https://openalex.org/W1873332500","https://openalex.org/W2064675550","https://openalex.org/W2144940978","https://openalex.org/W2157331557","https://openalex.org/W2753974689","https://openalex.org/W2762638728","https://openalex.org/W2801006204","https://openalex.org/W2963462425","https://openalex.org/W2992656411","https://openalex.org/W4295177766","https://openalex.org/W4385245566","https://openalex.org/W6639175750","https://openalex.org/W6739901393","https://openalex.org/W6751134269"],"related_works":["https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W3037187668","https://openalex.org/W2760721665","https://openalex.org/W2112044895","https://openalex.org/W2375218795","https://openalex.org/W2393010557","https://openalex.org/W3037446006","https://openalex.org/W4287752972","https://openalex.org/W3037482713"],"abstract_inverted_index":{"Gene":[0],"sequencing":[1,15,23,74],"technology":[2],"is":[3,31],"a":[4,68],"tool":[5],"which":[6],"greatly":[7],"impacts":[8],"modern":[9],"biology":[10],"and":[11,54,61,108,111],"medicine.":[12],"The":[13,80],"next-generation":[14],"(NGS)":[16],"lies":[17],"at":[18,121],"the":[19,35,45,87,91,94],"heart":[20],"of":[21,38,99],"gene":[22,73],"for":[24],"its":[25],"massively":[26],"increasing":[27],"throughput,":[28],"but":[29],"it":[30],"difficult":[32],"to":[33,116],"analyze":[34],"large":[36],"quantities":[37],"fluorescent":[39,46],"images":[40],"with":[41,50,76,109],"high":[42],"accuracy":[43,60],"because":[44],"signals":[47],"are":[48,57,83],"weak":[49],"varying":[51],"noise":[52],"signals,":[53],"current":[55],"designs":[56],"limited":[58],"on":[59,86,118,124],"speed.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"proposed":[67],"novel":[69],"deep":[70],"learning":[71],"based":[72],"pipeline":[75],"semi-automatic":[77],"labelling":[78],"method.":[79],"obtained":[81],"results":[82],"promising,":[84],"especially":[85],"high-density":[88,125],"data,":[89],"as":[90],"BaseFormer":[92],"surpasses":[93],"traditional":[95],"methods":[96],"in":[97],"terms":[98],"cluster":[100],"quality":[101],"(Q30:":[102],"88":[103],"%),":[104],"throughput":[105],"(16.5%":[106],"better),":[107],"similar":[110],"low":[112],"error":[113],"rate":[114],"(down":[115],"0.137%":[117],"average,":[119],"best":[120],"0.068":[122],"%":[123],"data).":[126]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
