{"id":"https://openalex.org/W4385667255","doi":"https://doi.org/10.1021/acs.jcim.3c00817","title":"AggBERT: Best in Class Prediction of Hexapeptide Amyloidogenesis with a Semi-Supervised ProtBERT Model","display_name":"AggBERT: Best in Class Prediction of Hexapeptide Amyloidogenesis with a Semi-Supervised ProtBERT Model","publication_year":2023,"publication_date":"2023-08-08","ids":{"openalex":"https://openalex.org/W4385667255","doi":"https://doi.org/10.1021/acs.jcim.3c00817","pmid":"https://pubmed.ncbi.nlm.nih.gov/37552230","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10777593"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c00817","doi":"https://doi.org/10.1021/acs.jcim.3c00817","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00817","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10777593/pdf/nihms-1950881.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023612814","display_name":"Ryann M. Perez","orcid":"https://orcid.org/0000-0003-2233-8910","observed_orcids":["https://orcid.org/0000-0003-2233-8910"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryann Perez","raw_affiliation_strings":["Department of Chemistry, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103125499","display_name":"Xinning Li","orcid":"https://orcid.org/0000-0003-0177-9696","observed_orcids":["https://orcid.org/0000-0003-0177-9696"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinning Li","raw_affiliation_strings":["Department of Chemistry, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072512563","display_name":"Sam G. Giannakoulias","orcid":"https://orcid.org/0000-0003-1830-6369","observed_orcids":["https://orcid.org/0000-0003-1830-6369"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sam Giannakoulias","raw_affiliation_strings":["Department of Chemistry, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States"],"raw_orcid":"https://orcid.org/0000-0003-1830-6369","affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028662408","display_name":"E. James Petersson","orcid":"https://orcid.org/0000-0003-3854-9210","observed_orcids":["https://orcid.org/0000-0003-3854-9210"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"E. James Petersson","raw_affiliation_strings":["Department of Chemistry, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States"],"raw_orcid":"https://orcid.org/0000-0003-3854-9210","affiliations":[{"raw_affiliation_string":"Department of Chemistry, University of Pennsylvania, Philadelphia, Pennsylvania 19104, United States","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5028662408","https://openalex.org/A5072512563"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":{"value":5000,"currency":"USD","value_usd":5000},"apc_paid":null,"fwci":1.3598,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.79328121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"63","issue":"18","first_page":"5727","last_page":"5733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4465000033378601,"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":0.4465000033378601,"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":0.350600004196167,"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/T10086","display_name":"Alzheimer's disease research and treatments","score":0.08630000054836273,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protbert","display_name":"ProtBERT","score":0.8790000081062317},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8309999704360962},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.8289999961853027},{"id":"https://openalex.org/keywords/protein-folding","display_name":"protein folding","score":0.550000011920929},{"id":"https://openalex.org/keywords/sequence-based-prediction","display_name":"sequence-based prediction","score":0.6729999780654907}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.668376088142395},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.5609151124954224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5450823307037354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5188913941383362},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.5094252228736877},{"id":"https://openalex.org/C204328495","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein folding","level":2,"score":0.49850940704345703},{"id":"https://openalex.org/C2994168385","wikidata":"https://www.wikidata.org/wiki/Q6740853","display_name":"Amyloid fibril","level":4,"score":0.4925266206264496},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4184054136276245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41595935821533203},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.41506367921829224},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3976025879383087},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2770756483078003},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.23015984892845154},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18019410967826843},{"id":"https://openalex.org/C3019447875","wikidata":"https://www.wikidata.org/wiki/Q417667","display_name":"Amyloid \u03b2","level":3,"score":0.17908582091331482},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.12492892146110535},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.09874019026756287},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09844481945037842},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","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":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","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":"D000682","descriptor_name":"Amyloid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010455","descriptor_name":"Peptides","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.3c00817","doi":"https://doi.org/10.1021/acs.jcim.3c00817","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c00817","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:37552230","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37552230","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,"listed_in":[],"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":"Journal of chemical information and modeling","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10777593","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10777593","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10777593/pdf/nihms-1950881.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,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10777593","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10777593","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10777593/pdf/nihms-1950881.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,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3072816452","display_name":null,"funder_award_id":"DGE-184529 8","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G335821698","display_name":"Graduate Research Fellowship Program(GRFP)","funder_award_id":"1845298","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3777820544","display_name":null,"funder_award_id":"DGE\u20101845298","funder_id":"https://openalex.org/F4320337368","funder_display_name":"Division of Graduate Education"},{"id":"https://openalex.org/G5317449886","display_name":"Studying Aggregation in Neurodegenerative Disease Using Synthetic Proteins","funder_award_id":"R01NS103873","funder_id":"https://openalex.org/F4320337359","funder_display_name":"National Institute of Neurological Disorders and Stroke"},{"id":"https://openalex.org/G9000289404","display_name":null,"funder_award_id":"NS103873","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G9000874752","display_name":"Predoctoral Training at the Chemistry-Biology Interface","funder_award_id":"T32GM133398","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337359","display_name":"National Institute of Neurological Disorders and Stroke","ror":"https://ror.org/01s5ya894"},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385667255.pdf","grobid_xml":"https://content.openalex.org/works/W4385667255.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1972798923","https://openalex.org/W1986299453","https://openalex.org/W2005907096","https://openalex.org/W2011301426","https://openalex.org/W2026120904","https://openalex.org/W2043614254","https://openalex.org/W2044074081","https://openalex.org/W2047468814","https://openalex.org/W2051224630","https://openalex.org/W2065303540","https://openalex.org/W2076048958","https://openalex.org/W2080831965","https://openalex.org/W2087661061","https://openalex.org/W2125493700","https://openalex.org/W2133425057","https://openalex.org/W2134439639","https://openalex.org/W2140389961","https://openalex.org/W2150593711","https://openalex.org/W2165186407","https://openalex.org/W2271840356","https://openalex.org/W2474664766","https://openalex.org/W2527672088","https://openalex.org/W2604209550","https://openalex.org/W2752738101","https://openalex.org/W2765546463","https://openalex.org/W2884001105","https://openalex.org/W2902652978","https://openalex.org/W2972174635","https://openalex.org/W2979826702","https://openalex.org/W3012384638","https://openalex.org/W3027366962","https://openalex.org/W3039766211","https://openalex.org/W3081982682","https://openalex.org/W3084020241","https://openalex.org/W3177500196","https://openalex.org/W3183799089","https://openalex.org/W3199779932","https://openalex.org/W4200602311","https://openalex.org/W4210282678","https://openalex.org/W4210374324","https://openalex.org/W4306757331"],"related_works":["https://openalex.org/W2041850751","https://openalex.org/W4412937861","https://openalex.org/W4414596548","https://openalex.org/W4416777085","https://openalex.org/W7220836053","https://openalex.org/W4388621595","https://openalex.org/W4404393708","https://openalex.org/W7221093107","https://openalex.org/W4410115151","https://openalex.org/W2787580408"],"abstract_inverted_index":{"The":[0],"prediction":[1,88],"of":[2,12,49,85,101,111],"peptide":[3,58],"amyloidogenesis":[4,59],"is":[5],"a":[6,50],"challenging":[7],"problem":[8],"in":[9,29,108],"the":[10,20,47,73,81,98,109],"field":[11],"protein":[13,31,38],"folding.":[14],"Large":[15],"language":[16,77,106],"models,":[17],"such":[18,35],"as":[19,26,36],"ProtBERT":[21,54],"model,":[22],"have":[23],"recently":[24],"emerged":[25],"powerful":[27],"tools":[28],"analyzing":[30],"sequences":[32,61],"for":[33,75],"applications,":[34],"predicting":[37],"structure":[39],"and":[40,52,83,104,114],"function.":[41],"In":[42],"this":[43],"article,":[44],"we":[45,66],"describe":[46],"use":[48],"semisupervised":[51],"fine-tuned":[53],"model":[55],"to":[56,79],"predict":[57],"from":[60],"alone.":[62],"Our":[63],"approach,":[64],"which":[65],"call":[67],"AggBERT,":[68],"achieved":[69],"state-of-the-art":[70],"performance,":[71],"demonstrating":[72],"potential":[74,100],"large":[76,105],"models":[78,107],"improve":[80],"accuracy":[82],"speed":[84],"amyloid":[86],"fibril":[87],"over":[89],"simple":[90],"heuristics":[91],"or":[92],"structure-based":[93],"approaches.":[94],"This":[95],"work":[96],"highlights":[97],"transformative":[99],"machine":[102],"learning":[103],"fields":[110],"chemical":[112],"biology":[113],"biomedicine.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-08-09T00:00:00"}