{"id":"https://openalex.org/W4403789015","doi":"https://doi.org/10.48550/arxiv.2409.16333","title":"Predicting Distance matrix with large language models","display_name":"Predicting Distance matrix with large language models","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4403789015","doi":"https://doi.org/10.48550/arxiv.2409.16333"},"language":"en","primary_location":{"id":"pmh:oai:RePEc:arx:papers:2409.16333","doi":null,"is_oa":false,"landing_page_url":"http://arxiv.org/pdf/2409.16333","pdf_url":"http://arxiv.org/pdf/2409.16333","source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"preprint"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.16333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101605461","display_name":"Jiaxing Yang","orcid":"https://orcid.org/0000-0003-4914-485X","observed_orcids":["https://orcid.org/0000-0003-4914-485X","https://orcid.org/0009-0003-7537-3362"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang, Jiaxing","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory Shanghai , Shanghai 201100 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory Shanghai , Shanghai 201100 , China","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101605461"],"corresponding_institution_ids":["https://openalex.org/I4391012619"],"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":0.9922000169754028,"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":0.9922000169754028,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.002300000051036477,"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":0.000699999975040555,"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/rna-structure-prediction","display_name":"RNA structure prediction","score":0.8050000071525574},{"id":"https://openalex.org/keywords/distance-maps","display_name":"distance maps","score":0.7289999723434448},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7910000085830688},{"id":"https://openalex.org/keywords/rna-language-models","display_name":"RNA language models","score":0.8740000128746033},{"id":"https://openalex.org/keywords/primary-sequence","display_name":"primary sequence","score":0.6729999780654907},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.4880000054836273},{"id":"https://openalex.org/keywords/rna-tertiary-structure","display_name":"RNA tertiary structure","score":0.7480000257492065}],"concepts":[{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.5506262183189392},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.500927209854126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4924801290035248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3227754831314087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21324193477630615},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:RePEc:arx:papers:2409.16333","doi":null,"is_oa":false,"landing_page_url":"http://arxiv.org/pdf/2409.16333","pdf_url":"http://arxiv.org/pdf/2409.16333","source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"preprint"},{"id":"pmh:oai:arXiv.org:2409.16333","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16333","pdf_url":"https://arxiv.org/pdf/2409.16333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.16333","doi":"https://doi.org/10.48550/arxiv.2409.16333","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.16333","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.16333","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16333","pdf_url":"https://arxiv.org/pdf/2409.16333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403789015.pdf","grobid_xml":"https://content.openalex.org/works/W4403789015.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W1573368088","https://openalex.org/W1517651240","https://openalex.org/W2065260367"],"abstract_inverted_index":{"Structural":[0],"prediction":[1,49,88],"has":[2,20],"long":[3],"been":[4,91],"considered":[5],"critical":[6],"in":[7,16,30,43],"RNA":[8,47,59,85,99,176,183],"research,":[9],"especially":[10],"following":[11],"the":[12,25,173],"success":[13],"of":[14,118,135],"AlphaFold2":[15],"protein":[17,44],"studies,":[18],"which":[19],"drawn":[21],"significant":[22,52],"attention":[23],"to":[24,55],"field.":[26],"While":[27],"recent":[28],"advances":[29],"machine":[31],"learning":[32],"and":[33,75,80,144],"data":[34,56,61],"accumulation":[35],"have":[36,90],"effectively":[37],"addressed":[38],"many":[39],"biological":[40],"tasks,":[41],"particularly":[42],"related":[45],"research.":[46],"structure":[48,87],"remains":[50,109],"a":[51,115,128,151,180,188],"challenge":[53],"due":[54],"limitations.":[57],"Obtaining":[58],"structural":[60,100,136,156],"is":[62,95,145],"difficult":[63],"because":[64],"traditional":[65],"methods":[66,89],"such":[67,105],"as":[68,106],"nuclear":[69],"magnetic":[70],"resonance":[71],"spectroscopy,":[72],"Xray":[73],"crystallography,":[74],"electron":[76],"microscopy":[77],"are":[78],"expensive":[79],"time":[81],"consuming.":[82],"Although":[83],"several":[84],"3D":[86,130,142],"proposed,":[92],"their":[93],"accuracy":[94],"still":[96],"limited.":[97],"Predicting":[98],"information":[101,137],"at":[102],"another":[103],"level,":[104],"distance":[107],"maps,":[108],"highly":[110],"valuable.":[111],"Distance":[112],"maps":[113],"provide":[114],"simplified":[116],"representation":[117],"spatial":[119],"constraints":[120],"between":[121,175],"nucleotides,":[122],"capturing":[123],"essential":[124],"relationships":[125],"without":[126],"requiring":[127],"full":[129],"model.":[131],"This":[132],"intermediate":[133],"level":[134],"can":[138,170],"guide":[139],"more":[140],"accurate":[141],"modeling":[143],"computationally":[146],"less":[147],"intensive,":[148],"making":[149],"it":[150],"useful":[152],"tool":[153],"for":[154],"improving":[155],"predictions.":[157],"In":[158],"this":[159],"work,":[160],"we":[161,169],"demonstrate":[162],"that":[163],"using":[164],"only":[165],"primary":[166],"sequence":[167],"information,":[168],"accurately":[171],"infer":[172],"distances":[174],"bases":[177],"by":[178],"utilizing":[179],"large":[181],"pretrained":[182],"language":[184],"model":[185],"coupled":[186],"with":[187],"well":[189],"trained":[190],"downstream":[191],"transformer.":[192]},"counts_by_year":[],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2025-10-10T00:00:00"}