{"id":"https://openalex.org/W7225328012","doi":"https://doi.org/10.21203/rs.3.rs-11489874/v1","title":"RNAflash: Fast and Sensitive Structure-aware RNA Homology Detection and Alignment","display_name":"RNAflash: Fast and Sensitive Structure-aware RNA Homology Detection and Alignment","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225328012","doi":"https://doi.org/10.21203/rs.3.rs-11489874/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11489874/v1","doi":"https://doi.org/10.21203/rs.3.rs-11489874/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11489874/v1","pdf_url":"https://www.researchsquare.com/article/rs-11489874/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11489874/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091365447","display_name":"Xiaoyong Pan","orcid":"https://orcid.org/0000-0001-5010-464X","observed_orcids":["https://orcid.org/0000-0001-5010-464X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyong Pan","raw_affiliation_strings":["Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0001-5010-464X","affiliations":[{"raw_affiliation_string":"Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443096","display_name":"Bing Chen","orcid":"https://orcid.org/0000-0002-1012-2007","observed_orcids":["https://orcid.org/0000-0002-1012-2007"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingtong Chen","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000956717","display_name":"Shengfan Wang","orcid":"https://orcid.org/0000-0003-4441-7820","observed_orcids":["https://orcid.org/0000-0003-4441-7820"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengfan Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144004989","display_name":"Weimin Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025903051","display_name":"Yiming Xue","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Xue","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076024045","display_name":"Hong\u2010Bin Shen","orcid":"https://orcid.org/0000-0002-4029-3325","observed_orcids":["https://orcid.org/0000-0002-4029-3325"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong-Bin Shen","raw_affiliation_strings":["Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0002-4029-3325","affiliations":[{"raw_affiliation_string":"Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.8901000022888184,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.8901000022888184,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0957999974489212,"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/T11269","display_name":"Algorithms and Data Compression","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rna-alignment","display_name":"RNA alignment","score":0.656000018119812},{"id":"https://openalex.org/keywords/rna-language-models","display_name":"RNA language models","score":0.7519999742507935},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.6069999933242798},{"id":"https://openalex.org/keywords/cross-encoder-reranking","display_name":"cross-encoder reranking","score":0.9440000057220459},{"id":"https://openalex.org/keywords/rna-secondary-structure","display_name":"RNA secondary structure","score":0.6790000200271606},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.800000011920929},{"id":"https://openalex.org/keywords/rfam","display_name":"Rfam","score":0.7559999823570251},{"id":"https://openalex.org/keywords/infernal","display_name":"infernal","score":0.6520000100135803},{"id":"https://openalex.org/keywords/rna-structure-prediction","display_name":"RNA structure prediction","score":0.6830000281333923}],"concepts":[{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.7592999935150146},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6503000259399414},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.5677000284194946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.503000020980835},{"id":"https://openalex.org/C126142528","wikidata":"https://www.wikidata.org/wiki/Q3771876","display_name":"Nucleic acid structure","level":4,"score":0.49309998750686646},{"id":"https://openalex.org/C85468374","wikidata":"https://www.wikidata.org/wiki/Q6589957","display_name":"Nucleic acid secondary structure","level":4,"score":0.38940000534057617},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.38100001215934753},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.35679998993873596},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C512185932","wikidata":"https://www.wikidata.org/wiki/Q28745","display_name":"Nucleotide","level":3,"score":0.3492000102996826},{"id":"https://openalex.org/C194993378","wikidata":"https://www.wikidata.org/wiki/Q427087","display_name":"Non-coding RNA","level":4,"score":0.34200000762939453},{"id":"https://openalex.org/C2779315201","wikidata":"https://www.wikidata.org/wiki/Q414601","display_name":"Sequence homology","level":4,"score":0.3384000062942505},{"id":"https://openalex.org/C169627665","wikidata":"https://www.wikidata.org/wiki/Q5767913","display_name":"Homology modeling","level":3,"score":0.32589998841285706},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C21786251","wikidata":"https://www.wikidata.org/wiki/Q14886350","display_name":"RNA editing","level":4,"score":0.31619998812675476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.2957000136375427},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C3017666073","wikidata":"https://www.wikidata.org/wiki/Q1764062","display_name":"Base sequence","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C84148353","wikidata":"https://www.wikidata.org/wiki/Q863908","display_name":"Nucleic acid sequence","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.25279998779296875},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11489874/v1","doi":"https://doi.org/10.21203/rs.3.rs-11489874/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11489874/v1","pdf_url":"https://www.researchsquare.com/article/rs-11489874/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11489874/v1","doi":"https://doi.org/10.21203/rs.3.rs-11489874/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11489874/v1","pdf_url":"https://www.researchsquare.com/article/rs-11489874/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1273304962","display_name":null,"funder_award_id":"62573293","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1333001686","display_name":null,"funder_award_id":"(24510714300","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G1630822546","display_name":null,"funder_award_id":"62473257","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7216433570","display_name":null,"funder_award_id":"24ZR1435300","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225328012.pdf","grobid_xml":"https://content.openalex.org/works/W7225328012.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416951812","https://openalex.org/W4303475038","https://openalex.org/W1950410402","https://openalex.org/W4311276451","https://openalex.org/W7172098307","https://openalex.org/W2126883736","https://openalex.org/W4409962073","https://openalex.org/W2159522654","https://openalex.org/W1557536303","https://openalex.org/W2161534813"],"abstract_inverted_index":{"Abstract":[0],"RNA":[1,9,28,48,64,86,170,187],"homology":[2,171],"search":[3,126,150,172],"plays":[4],"a":[5,13,23,51],"crucial":[6],"role":[7],"in":[8],"structure":[10,188],"prediction,":[11],"facing":[12],"trade-off":[14],"between":[15],"sensitivity":[16],"and":[17,35,60,93,116,121,127,135,141,160,173,178],"speed.":[18],"Here":[19],"we":[20],"present":[21],"RNAflash,":[22],"two-stage":[24],"framework":[25],"that":[26,166],"combines":[27],"language":[29],"model-based":[30],"retrieval":[31,38],"with":[32,113],"structure-informed":[33],"reranking":[34],"alignment.":[36],"A":[37],"bi-encoder":[39],"RNAflash-R":[40],"trained":[41,68],"through":[42],"contrastive":[43],"learning":[44],"first":[45],"retrieves":[46],"candidate":[47],"sequences":[49],"from":[50],"large":[52],"pre-encoded":[53],"database.":[54],"Then,":[55],"its":[56],"cross-encoder":[57],"RNAflash-A":[58],"reranks":[59],"aligns":[61],"the":[62],"retrieved":[63,85],"candidates":[65],"via":[66],"jointly":[67],"prediction":[69],"heads,":[70],"using":[71],"predicted":[72],"secondary":[73],"structures":[74],"to":[75,97],"refine":[76],"nucleotide":[77],"correspondence":[78],"scores.":[79],"Across":[80],"held-out":[81],"Rfam":[82],"families,":[83],"RNAflash":[84,107,167],"homologs":[87],"more":[88,176],"sensitively":[89],"than":[90,119,132,139,158],"sequence-based":[91,120],"methods,":[92],"produced":[94],"alignments":[95,111],"comparable":[96],"those":[98],"of":[99,105,183],"structure-based":[100],"methods.":[101],"In":[102],"large-scale":[103],"searches":[104],"RNAcentral,":[106],"generated":[108],"multiple":[109],"sequence":[110],"(MSAs)":[112],"stronger":[114],"coupling":[115],"covariation":[117],"signals":[118],"Infernal":[122,140],"pipelines,":[123],"while":[124,154],"performing":[125],"MSA":[128,174],"construction":[129,175],"3.7-fold":[130],"faster":[131,138],"non-iterative":[133,161],"Riboseek":[134],"over":[136],"100-fold":[137],"RNAcmap.":[142],"The":[143,163],"lightweight":[144],"variant":[145],"RNAflash-L":[146],"achieves":[147],"sub-second":[148],"average":[149],"times":[151],"per":[152],"query":[153],"producing":[155],"higher-quality":[156],"MSAs":[157,184],"nhmmer":[159],"Riboseek.":[162],"results":[164],"show":[165],"makes":[168],"sensitive":[169],"scalable,":[177],"provides":[179],"an":[180],"efficient":[181],"source":[182],"for":[185],"downstream":[186],"prediction.":[189]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-06T00:00:00"}