{"id":"https://openalex.org/W7164890260","doi":"https://doi.org/10.1093/bioinformatics/btag402","title":"NanoSimFormer: an end-to-end transformer-based nanopore signal simulator with basecaller guidance","display_name":"NanoSimFormer: an end-to-end transformer-based nanopore signal simulator with basecaller guidance","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7164890260","doi":"https://doi.org/10.1093/bioinformatics/btag402","pmid":"https://pubmed.ncbi.nlm.nih.gov/42302398"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag402","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag402","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021288733","display_name":"Shaohui Xie","orcid":"https://orcid.org/0009-0007-5611-8066"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Xie","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University , Shenzhen,","National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University , Shenzhen,","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen,","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138734566","display_name":"Lulu Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lulu Ding","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen,","School of Artificial Intelligence, Shenzhen University , Shenzhen,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen,","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University , Shenzhen,","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136381741","display_name":"L Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Liu","raw_affiliation_strings":["Guangzhou Institute of Technology, Xidian University , Guangzhou,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou Institute of Technology, Xidian University , Guangzhou,","institution_ids":["https://openalex.org/I149594827","https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123345214","display_name":"Yew Soon Ong","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yew Soon Ong","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University ,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393871","display_name":"Jianqiang Li","orcid":"https://orcid.org/0000-0002-2208-962X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Li","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen,","School of Artificial Intelligence, Shenzhen University , Shenzhen,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen,","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University , Shenzhen,","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052762681","display_name":"Zexuan Zhu","orcid":"https://orcid.org/0000-0001-8479-6904"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zexuan Zhu","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen,","School of Artificial Intelligence, Shenzhen University , Shenzhen,"],"raw_orcid":"https://orcid.org/0000-0001-8479-6904","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing, Shenzhen University , Shenzhen,","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"School of Artificial Intelligence, Shenzhen University , Shenzhen,","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052762681"],"corresponding_institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388","https://openalex.org/I4210099586"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72407768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11582","display_name":"Nanopore and Nanochannel Transport Studies","score":0.5188000202178955,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11582","display_name":"Nanopore and Nanochannel Transport Studies","score":0.5188000202178955,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3970000147819519,"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":0.018699999898672104,"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/nanopore-sequencing","display_name":"Nanopore sequencing","score":0.843500018119812},{"id":"https://openalex.org/keywords/nanopore","display_name":"Nanopore","score":0.7716000080108643},{"id":"https://openalex.org/keywords/minion","display_name":"Minion","score":0.6661999821662903},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6396999955177307},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4505999982357025},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.41449999809265137},{"id":"https://openalex.org/keywords/false-positives-and-false-negatives","display_name":"False positives and false negatives","score":0.41350001096725464}],"concepts":[{"id":"https://openalex.org/C126513998","wikidata":"https://www.wikidata.org/wiki/Q8973627","display_name":"Nanopore sequencing","level":4,"score":0.843500018119812},{"id":"https://openalex.org/C141795571","wikidata":"https://www.wikidata.org/wiki/Q580942","display_name":"Nanopore","level":2,"score":0.7716000080108643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239999771118164},{"id":"https://openalex.org/C2779927696","wikidata":"https://www.wikidata.org/wiki/Q6865654","display_name":"Minion","level":5,"score":0.6661999821662903},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.41350001096725464},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38940000534057617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C119054055","wikidata":"https://www.wikidata.org/wiki/Q1576681","display_name":"Indel","level":5,"score":0.366100013256073},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32850000262260437},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.31200000643730164},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3091000020503998},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.25290000438690186}],"mesh":[{"descriptor_ui":"D000081414","descriptor_name":"Nanopore Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D000081414","descriptor_name":"Nanopore Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058608","descriptor_name":"Nanopores","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058608","descriptor_name":"Nanopores","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btag402","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag402","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:42302398","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42302398","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13312124","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13312124/","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag402","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag402","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5433012282","display_name":null,"funder_award_id":"2022YFF1202104","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6276227692","display_name":null,"funder_award_id":"62471310","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7832799632","display_name":null,"funder_award_id":"32401256","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G949662064","display_name":null,"funder_award_id":"62571401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2107092366","https://openalex.org/W2107772251","https://openalex.org/W2346680365","https://openalex.org/W2467325308","https://openalex.org/W2503273054","https://openalex.org/W2591367881","https://openalex.org/W2607669908","https://openalex.org/W2789843538","https://openalex.org/W2929062889","https://openalex.org/W2950266744","https://openalex.org/W2950609999","https://openalex.org/W2950827710","https://openalex.org/W2952870794","https://openalex.org/W2999719567","https://openalex.org/W3033216646","https://openalex.org/W3096927760","https://openalex.org/W3112356228","https://openalex.org/W3208186059","https://openalex.org/W4205338875","https://openalex.org/W4313250582","https://openalex.org/W4313430580","https://openalex.org/W4317553434","https://openalex.org/W4388979610","https://openalex.org/W4390500910","https://openalex.org/W4392519792","https://openalex.org/W4394772107","https://openalex.org/W4396541611","https://openalex.org/W4404047801","https://openalex.org/W4405728194","https://openalex.org/W4407931608","https://openalex.org/W4408249282","https://openalex.org/W4408387392","https://openalex.org/W4409647413","https://openalex.org/W4411279316","https://openalex.org/W4413612292","https://openalex.org/W4415103556","https://openalex.org/W4415294368","https://openalex.org/W4416823254","https://openalex.org/W4417188046","https://openalex.org/W7116678162","https://openalex.org/W7134044543"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"High-fidelity":[1],"simulation":[2],"of":[3,14,31,119],"nanopore":[4,16,32,75],"sequencing":[5],"signals":[6,50],"is":[7,182],"critical":[8],"for":[9,89,123],"rigorous":[10],"benchmarking":[11],"and":[12,55,85,96,121,126,143,166,175],"validation":[13],"the":[15,28,113],"signal":[17,22,64],"processing":[18],"pipeline.":[19],"However,":[20],"existing":[21],"simulators":[23],"often":[24],"fail":[25],"to":[26,45,72],"capture":[27],"non-linear":[29],"dynamics":[30],"current":[33],"signals,":[34],"relying":[35],"on":[36,185],"static":[37],"pore":[38],"models":[39],"or":[40],"lacking":[41],"optimization":[42],"objectives":[43],"tied":[44],"basecalling,":[46],"resulting":[47],"in":[48,141,173],"synthetic":[49],"with":[51,132,156,170],"low":[52],"basecalling":[53,81],"accuracy":[54,82],"fidelity.":[56],"RESULTS:":[57],"We":[58],"introduce":[59],"NanoSimFormer,":[60],"an":[61],"end-to-end":[62],"Transformer-based":[63],"simulator":[65],"that":[66],"integrates":[67],"basecaller":[68],"guidance":[69],"during":[70],"training":[71],"generate":[73],"high-fidelity":[74],"signals.":[76],"NanoSimFormer":[77,135,181],"achieves":[78],"a":[79],"median":[80],"exceeding":[83],"99%":[84],"Q-scores":[86],"above":[87],"22.8":[88],"Oxford":[90],"Nanopore":[91],"Technologies'":[92],"latest":[93],"DNA":[94],"R10.4.1":[95],"direct":[97],"RNA":[98],"sequencing,":[99],"closely":[100],"mirroring":[101],"real":[102],"experimental":[103,108,171],"baselines.":[104],"It":[105],"faithfully":[106],"recapitulates":[107],"variant":[109],"calling":[110],"performance":[111],"across":[112],"five":[114],"human":[115],"samples,":[116],"achieving":[117],"F1-scores":[118],"0.9953-0.9973":[120],"0.7862-0.8612":[122],"single-nucleotide":[124],"polymorphisms":[125],"small":[127],"indels":[128],"detections,":[129],"respectively.":[130],"Compared":[131],"previous":[133],"simulators,":[134],"also":[136],"substantially":[137],"reduces":[138],"false":[139],"positives":[140],"homopolymer":[142],"short":[144],"tandem":[145],"repeat":[146],"regions.":[147],"NanoSimFormer-derived":[148],"reads":[149],"enable":[150],"high-quality":[151],"de":[152],"novo":[153],"bacterial":[154],"assembly":[155],"consensus":[157],"error":[158],"rates":[159],"below":[160],"one":[161],"mismatch":[162],"per":[163],"100":[164],"kbp":[165],"maintain":[167],"high":[168],"correlations":[169],"abundance":[172],"metagenomic":[174],"transcriptomic":[176],"datasets.":[177],"AVAILABILITY":[178],"AND":[179],"IMPLEMENTATION:":[180],"freely":[183],"available":[184],"GitHub":[186],"at:":[187],"https://github.com/BioinfoSZU/NanoSimFormer.":[188]},"counts_by_year":[],"updated_date":"2026-06-30T06:16:30.551410","created_date":"2026-06-17T00:00:00"}
