{"id":"https://openalex.org/W4366082790","doi":"https://doi.org/10.1371/journal.pcbi.1011047","title":"Sequence similarity governs generalizability of de novo deep learning models for RNA secondary structure prediction","display_name":"Sequence similarity governs generalizability of de novo deep learning models for RNA secondary structure prediction","publication_year":2023,"publication_date":"2023-04-17","ids":{"openalex":"https://openalex.org/W4366082790","doi":"https://doi.org/10.1371/journal.pcbi.1011047","pmid":"https://pubmed.ncbi.nlm.nih.gov/37068100"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1011047","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1011047","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011047&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011047&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057146487","display_name":"Xiangyun Qiu","orcid":"https://orcid.org/0000-0002-2600-5032"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiangyun Qiu","raw_affiliation_strings":["Department of Physics, George Washington University, Washington DC, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics, George Washington University, Washington DC, United States of America","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5057146487"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":2.2268,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.88649402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"19","issue":"4","first_page":"e1011047","last_page":"e1011047"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":1.0,"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":1.0,"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":0.9983000159263611,"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/T11482","display_name":"RNA modifications and cancer","score":0.9958000183105469,"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/generalizability-theory","display_name":"Generalizability theory","score":0.9701513648033142},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6790132522583008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.655524492263794},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6409701704978943},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5888750553131104},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5831073522567749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5623466968536377},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.48865774273872375},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4259013533592224},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.35391414165496826},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.318713515996933},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20932018756866455},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20060187578201294},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09376254677772522}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.9701513648033142},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6790132522583008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.655524492263794},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6409701704978943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5888750553131104},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5831073522567749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5623466968536377},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.48865774273872375},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4259013533592224},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.35391414165496826},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.318713515996933},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20932018756866455},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20060187578201294},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09376254677772522},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1371/journal.pcbi.1011047","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1011047","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011047&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:37068100","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37068100","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10138783","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10138783","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10138783/pdf/pcbi.1011047.pdf","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":"PLoS Comput Biol","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:364c8faf44544d89af094872f505a862","is_oa":true,"landing_page_url":"https://doaj.org/article/364c8faf44544d89af094872f505a862","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 19, Iss 4, p e1011047 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1011047","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1011047","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1011047&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308380","display_name":"Yale University","ror":"https://ror.org/03v76x132"},{"id":"https://openalex.org/F4320309515","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366082790.pdf","grobid_xml":"https://content.openalex.org/works/W4366082790.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W166206240","https://openalex.org/W1981576666","https://openalex.org/W1984867418","https://openalex.org/W1987592711","https://openalex.org/W2003993220","https://openalex.org/W2018216725","https://openalex.org/W2020546070","https://openalex.org/W2025763720","https://openalex.org/W2026181790","https://openalex.org/W2027141824","https://openalex.org/W2031352989","https://openalex.org/W2038598202","https://openalex.org/W2068205741","https://openalex.org/W2071883352","https://openalex.org/W2086561953","https://openalex.org/W2097924797","https://openalex.org/W2098571862","https://openalex.org/W2102017611","https://openalex.org/W2106478835","https://openalex.org/W2109638684","https://openalex.org/W2121918723","https://openalex.org/W2133839648","https://openalex.org/W2138007734","https://openalex.org/W2141157874","https://openalex.org/W2142038007","https://openalex.org/W2142678478","https://openalex.org/W2145149786","https://openalex.org/W2155858493","https://openalex.org/W2159548583","https://openalex.org/W2170747616","https://openalex.org/W2268094462","https://openalex.org/W2342878844","https://openalex.org/W2414122243","https://openalex.org/W2536860838","https://openalex.org/W2596417560","https://openalex.org/W2725568163","https://openalex.org/W2759571676","https://openalex.org/W2808896479","https://openalex.org/W2866340037","https://openalex.org/W2896457183","https://openalex.org/W2910705748","https://openalex.org/W2919479895","https://openalex.org/W2933083636","https://openalex.org/W2945901478","https://openalex.org/W2951298881","https://openalex.org/W2954102902","https://openalex.org/W2954432347","https://openalex.org/W2983889514","https://openalex.org/W2990528340","https://openalex.org/W2998238598","https://openalex.org/W3001271520","https://openalex.org/W3005909538","https://openalex.org/W3014154699","https://openalex.org/W3037359378","https://openalex.org/W3047090055","https://openalex.org/W3087202564","https://openalex.org/W3111119989","https://openalex.org/W3126773939","https://openalex.org/W3161531818","https://openalex.org/W3163993681","https://openalex.org/W3177828909","https://openalex.org/W3212533323","https://openalex.org/W4205788935","https://openalex.org/W4210378368","https://openalex.org/W4283447041","https://openalex.org/W4285013647","https://openalex.org/W4311276451"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W410723623","https://openalex.org/W2413243053","https://openalex.org/W2015341305","https://openalex.org/W4225593417","https://openalex.org/W2035068594","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W3160494304","https://openalex.org/W1549477351"],"abstract_inverted_index":{"Making":[0],"no":[1,62],"use":[2],"of":[3,36,43,48,51,161],"physical":[4],"laws":[5],"or":[6],"co-evolutionary":[7],"information,":[8],"de":[9,52,172],"novo":[10,53,173],"deep":[11],"learning":[12,117],"(DL)":[13],"models":[14,73,133,175],"for":[15,170,181],"RNA":[16],"secondary":[17],"structure":[18,148],"prediction":[19],"have":[20],"achieved":[21],"far":[22],"superior":[23],"performances":[24],"than":[25],"traditional":[26],"algorithms.":[27],"However,":[28,86],"their":[29],"statistical":[30,162],"underpinning":[31],"raises":[32],"the":[33,44,90,94,102,159],"crucial":[34],"question":[35],"generalizability.":[37],"We":[38,139],"present":[39],"a":[40,49,57,167],"quantitative":[41,156],"study":[42],"performance":[45,91,124],"and":[46,61,69,78,96,115,125,137,147,178],"generalizability":[47,126,143],"series":[50],"DL":[54,114,174],"models,":[55],"with":[56,134],"minimal":[58],"two-module":[59],"architecture":[60],"post-processing,":[63],"under":[64],"varied":[65],"similarities":[66],"between":[67,93,123],"seen":[68,95],"unseen":[70,97],"sequences.":[71],"Our":[72],"demonstrate":[74],"excellent":[75],"expressive":[76],"capacities":[77],"outperform":[79],"existing":[80],"methods":[81],"on":[82,145],"common":[83],"benchmark":[84],"datasets.":[85],"model":[87],"generalizability,":[88],"i.e.,":[89],"gap":[92],"sets,":[98],"degrades":[99],"rapidly":[100],"as":[101],"sequence":[103,146],"similarity":[104],"decreases.":[105],"The":[106],"same":[107],"trends":[108],"are":[109,184],"observed":[110],"from":[111],"several":[112],"recent":[113],"machine":[116],"models.":[118],"And":[119],"an":[120],"inverse":[121],"correlation":[122],"is":[127],"revealed":[128],"collectively":[129],"across":[130],"all":[131],"learning-based":[132],"wide-ranging":[135],"architectures":[136],"sizes.":[138],"further":[140],"quantitate":[141],"how":[142],"depends":[144],"identity":[149],"scores":[150],"via":[151],"pairwise":[152],"alignment,":[153],"providing":[154],"unique":[155],"insights":[157],"into":[158],"limitations":[160],"learning.":[163],"Generalizability":[164],"thus":[165],"poses":[166],"major":[168],"hurdle":[169],"deploying":[171],"in":[176],"practice":[177],"various":[179],"pathways":[180],"future":[182],"advances":[183],"discussed.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}