{"id":"https://openalex.org/W4296907865","doi":"https://doi.org/10.1093/bib/bbac401","title":"SPRoBERTa: protein embedding learning with local fragment modeling","display_name":"SPRoBERTa: protein embedding learning with local fragment modeling","publication_year":2022,"publication_date":"2022-09-22","ids":{"openalex":"https://openalex.org/W4296907865","doi":"https://doi.org/10.1093/bib/bbac401","pmid":"https://pubmed.ncbi.nlm.nih.gov/36136367"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbac401","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac401","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5102750692","display_name":"Lijun Wu","orcid":"https://orcid.org/0000-0002-3530-590X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lijun Wu","raw_affiliation_strings":["Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074951383","display_name":"Chengcan Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengcan Yin","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University , 163 Xianlin Road, Qixia District, 210023, Nanjing, Jiangsu Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University , 163 Xianlin Road, Qixia District, 210023, Nanjing, Jiangsu Province, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028284977","display_name":"Jinhua Zhu","orcid":"https://orcid.org/0000-0003-2157-9077"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhua Zhu","raw_affiliation_strings":["CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China , No.96, JinZhai Road Baohe District, 230026, Hefei, Anhui Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of GIPAS, EEIS Department, University of Science and Technology of China , No.96, JinZhai Road Baohe District, 230026, Hefei, Anhui Province, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055397380","display_name":"Zhen Wu","orcid":"https://orcid.org/0000-0002-7678-103X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Wu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University , 163 Xianlin Road, Qixia District, 210023, Nanjing, Jiangsu Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University , 163 Xianlin Road, Qixia District, 210023, Nanjing, Jiangsu Province, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745388","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-6394-8531"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021772140","display_name":"Yingce Xia","orcid":"https://orcid.org/0000-0001-9823-9033"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingce Xia","raw_affiliation_strings":["Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088666942","display_name":"Shufang Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shufang Xie","raw_affiliation_strings":["Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, No. 5 Dan Ling Street , Haidian District, 100080, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5102750692"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":0.9528,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.73424591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"23","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994999766349792,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994999766349792,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7026801109313965},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6458383202552795},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.6261614561080933},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.605698823928833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344993472099304},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.46836721897125244},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.46188420057296753},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4404264986515045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4174022674560547},{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.41494932770729065},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.39987802505493164},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.3849930167198181},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19807219505310059},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13454169034957886},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13067534565925598},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.10075229406356812},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08275589346885681}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7026801109313965},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6458383202552795},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.6261614561080933},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.605698823928833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344993472099304},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.46836721897125244},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.46188420057296753},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4404264986515045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4174022674560547},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.41494932770729065},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.39987802505493164},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.3849930167198181},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19807219505310059},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13454169034957886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13067534565925598},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.10075229406356812},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08275589346885681},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","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":"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbac401","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac401","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36136367","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36136367","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":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2033339460","https://openalex.org/W2076048958","https://openalex.org/W2092672051","https://openalex.org/W2104972430","https://openalex.org/W2121879602","https://openalex.org/W2163584430","https://openalex.org/W2612690371","https://openalex.org/W2889498145","https://openalex.org/W2898402099","https://openalex.org/W2949867299","https://openalex.org/W2950374603","https://openalex.org/W2951433247","https://openalex.org/W2953008890","https://openalex.org/W2962784628","https://openalex.org/W2963026768","https://openalex.org/W2963250244","https://openalex.org/W2963979492","https://openalex.org/W2980789587","https://openalex.org/W2995514860","https://openalex.org/W2999481648","https://openalex.org/W3083386021","https://openalex.org/W3133458480","https://openalex.org/W3146944767","https://openalex.org/W3164046276","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3179485843","https://openalex.org/W3197123494","https://openalex.org/W4205773061","https://openalex.org/W4224939843","https://openalex.org/W4236965008","https://openalex.org/W4285651992","https://openalex.org/W6631190155","https://openalex.org/W6758485811","https://openalex.org/W6763868836","https://openalex.org/W6766673545","https://openalex.org/W6782527804","https://openalex.org/W6783944145","https://openalex.org/W6786632220","https://openalex.org/W6787297430","https://openalex.org/W6798272402","https://openalex.org/W6809747699","https://openalex.org/W6810961805"],"related_works":["https://openalex.org/W2593264178","https://openalex.org/W2470147982","https://openalex.org/W4311623193","https://openalex.org/W2043066834","https://openalex.org/W2185518315","https://openalex.org/W2181530468","https://openalex.org/W2039679484","https://openalex.org/W1504467230","https://openalex.org/W4385496101","https://openalex.org/W2129046747"],"abstract_inverted_index":{"Well":[0],"understanding":[1,12],"protein":[2,40,43,48,72,90,94,112,124,151,180],"function":[3,152],"and":[4,25,143,165,176,182],"structure":[5,133],"in":[6,10,71,162],"computational":[7],"biology":[8],"helps":[9],"the":[11,18,27,31,47,66,167],"of":[13,38],"human":[14],"beings.":[15],"To":[16],"face":[17],"limited":[19,57],"proteins":[20],"that":[21,156],"are":[22],"annotated":[23],"structurally":[24],"functionally,":[26],"scientific":[28],"community":[29],"embraces":[30],"self-supervised":[32],"pre-training":[33,81,106],"methods":[34],"from":[35],"large":[36],"amounts":[37],"unlabeled":[39],"sequences":[41],"for":[42,104,122,178],"embedding":[44],"learning.":[45],"However,":[46],"is":[49,108],"usually":[50],"represented":[51],"by":[52],"individual":[53],"amino":[54,127,135],"acids":[55],"with":[56,96],"vocabulary":[58],"size":[59],"(e.g.":[60,131,140],"20":[61],"type":[62],"proteins),":[63],"without":[64],"considering":[65],"strong":[67],"local":[68,97],"semantics":[69],"existing":[70],"sequences.":[73],"In":[74],"this":[75],"work,":[76],"we":[77],"propose":[78],"a":[79,101],"novel":[80,102],"modeling":[82],"approach":[83,158],"SPRoBERTa.":[84],"We":[85,170],"first":[86],"present":[87],"an":[88],"unsupervised":[89],"tokenizer":[91,181],"to":[92,110],"learn":[93,111],"representations":[95],"fragment":[98],"pattern.":[99],"Then,":[100],"framework":[103],"deep":[105],"model":[107],"introduced":[109],"embeddings.":[113],"After":[114],"pre-training,":[115],"our":[116,157,179],"method":[117],"can":[118],"be":[119],"easily":[120],"fine-tuned":[121],"different":[123],"tasks,":[125],"including":[126],"acid-level":[128],"prediction":[129,138,146],"task":[130,139,147],"secondary":[132],"prediction),":[134],"acid":[136],"pair-level":[137],"contact":[141],"prediction)":[142],"also":[144,171],"protein-level":[145],"(remote":[148],"homology":[149],"prediction,":[150],"prediction).":[153],"Experiments":[154],"show":[155],"achieves":[159],"significant":[160],"improvements":[161],"all":[163],"tasks":[164],"outperforms":[166],"previous":[168],"methods.":[169],"provide":[172],"detailed":[173],"ablation":[174],"studies":[175],"analysis":[177],"training":[183],"framework.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}