{"id":"https://openalex.org/W4405427523","doi":"https://doi.org/10.1145/3698587.3701385","title":"Peptide Sequencing Via Protein Language Models","display_name":"Peptide Sequencing Via Protein Language Models","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4405427523","doi":"https://doi.org/10.1145/3698587.3701385"},"language":"en","primary_location":{"id":"doi:10.1145/3698587.3701385","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698587.3701385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5109782540","display_name":"Thuong Le Hoai Pham","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thuong Le Hoai Pham","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0009-0001-1149-7927","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023922327","display_name":"Jillur Rahman Saurav","orcid":"https://orcid.org/0000-0001-7451-9962"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jillur Rahman Saurav","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0000-0001-7451-9962","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107218427","display_name":"Aisosa A. Omere","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aisosa A. Omere","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0009-0007-8080-340X","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107218428","display_name":"Calvin J. Heyl","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calvin J. Heyl","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0009-0003-5247-9359","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087719124","display_name":"Mohammad Sadegh Nasr","orcid":"https://orcid.org/0000-0001-9675-5640"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Sadegh Nasr","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0000-0001-9675-5640","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059734870","display_name":"Cerisa R. Reynolds","orcid":"https://orcid.org/0009-0008-2791-6445"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cody Tyler Reynolds","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0009-0008-2791-6445","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092160845","display_name":"Jai Prakash Veerla","orcid":"https://orcid.org/0009-0000-5023-0769"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jai Prakash Yadav Veerla","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0009-0000-5023-0769","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022943841","display_name":"Helen H. Shang","orcid":"https://orcid.org/0000-0002-4684-6859"},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Helen H. Shang","raw_affiliation_strings":["UCLA Health, Los Angeles, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-4684-6859","affiliations":[{"raw_affiliation_string":"UCLA Health, Los Angeles, California, USA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043869958","display_name":"Justyn Jaworski","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justyn Jaworski","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0000-0001-9214-3671","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035177917","display_name":"Alison Ravenscraft","orcid":"https://orcid.org/0000-0003-4974-4804"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alison Ravenscraft","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0000-0003-4974-4804","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047735891","display_name":"Joseph A. Buonomo","orcid":"https://orcid.org/0000-0002-9618-0215"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Anthony Buonomo","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0000-0002-9618-0215","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013180076","display_name":"Jacob M. Luber","orcid":"https://orcid.org/0000-0001-5268-5732"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob M. Luber","raw_affiliation_strings":["University of Texas at Arlington, Texas USA"],"raw_orcid":"https://orcid.org/0000-0001-5268-5732","affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Texas USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2041,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58266154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9976000189781189,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9976000189781189,"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":0.995199978351593,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9940000176429749,"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":0.6143171787261963},{"id":"https://openalex.org/keywords/peptide","display_name":"Peptide","score":0.47450846433639526},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.41834762692451477},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.26606443524360657},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16336840391159058},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.1447426974773407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6143171787261963},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.47450846433639526},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41834762692451477},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.26606443524360657},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16336840391159058},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.1447426974773407}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3698587.3701385","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3698587.3701385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1505191356","https://openalex.org/W1897236478","https://openalex.org/W1977032270","https://openalex.org/W1981978551","https://openalex.org/W2073371472","https://openalex.org/W2082825869","https://openalex.org/W2102245393","https://openalex.org/W2115540209","https://openalex.org/W2140673705","https://openalex.org/W2149605074","https://openalex.org/W2153735280","https://openalex.org/W2314049493","https://openalex.org/W2322616200","https://openalex.org/W2325516935","https://openalex.org/W2490087886","https://openalex.org/W2593943479","https://openalex.org/W2607135274","https://openalex.org/W2810642653","https://openalex.org/W2884597274","https://openalex.org/W2896321622","https://openalex.org/W2898259619","https://openalex.org/W2937482900","https://openalex.org/W2970444068","https://openalex.org/W2979867545","https://openalex.org/W3000435127","https://openalex.org/W3002071299","https://openalex.org/W3087184316","https://openalex.org/W3088983575","https://openalex.org/W3095548690","https://openalex.org/W3154094799","https://openalex.org/W3166142427","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W4210889601","https://openalex.org/W4211115069","https://openalex.org/W4225274782","https://openalex.org/W4226058407","https://openalex.org/W4285293171","https://openalex.org/W4317721671","https://openalex.org/W4320578140","https://openalex.org/W4387123633","https://openalex.org/W4391836523","https://openalex.org/W4394594668","https://openalex.org/W4399304345","https://openalex.org/W4400350094","https://openalex.org/W6783352278","https://openalex.org/W6959643953"],"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/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,91],"introduce":[1],"a":[2,12,18,96,102,172,190],"protein":[3,26,45,78,177,196],"language":[4],"model":[5,152],"for":[6,101,156,175],"determining":[7],"the":[8,81,114,145,194],"complete":[9,115,195],"sequence":[10,41,178,197],"of":[11,17,21,113,148,164,193],"peptide":[13],"based":[14,37],"on":[15,29,118],"measurement":[16],"limited":[19,199],"set":[20],"amino":[22,54,69,133],"acids.":[23],"To":[24],"date,":[25],"sequencing":[27,46,64,89],"relies":[28],"mass":[30],"spectrometry,":[31],"with":[32,168],"some":[33],"novel":[34],"Edman":[35],"degradation":[36],"platforms":[38],"able":[39],"to":[40,75,128],"non-native":[42],"peptides.":[43],"Current":[44],"techniques":[47],"face":[48],"limitations":[49],"in":[50,77,183],"accurately":[51],"identifying":[52],"all":[53],"acids,":[55],"hindering":[56],"comprehensive":[57],"proteome":[58],"analysis.":[59],"Our":[60],"method":[61],"simulates":[62],"partial":[63],"data":[65],"by":[66,188],"selectively":[67],"masking":[68,86],"acids":[70,134],"that":[71],"are":[72,136],"experimentally":[73],"difficult":[74],"identify":[76],"sequences":[79],"from":[80,198],"UniRef":[82],"database.":[83],"This":[84,162],"targeted":[85],"mimics":[87],"real-world":[88],"limitations.":[90],"then":[92],"modify":[93],"and":[94,142,185],"finetune":[95],"ProtBERT":[97],"derived":[98],"transformer-based":[99],"model,":[100],"new":[103],"downstream":[104],"task":[105],"predicting":[106],"these":[107],"masked":[108],"residues,":[109],"providing":[110,189],"an":[111],"approximation":[112],"sequence.":[116],"Evaluating":[117],"three":[119],"bacterial":[120],"Escherichia":[121],"species,":[122],"we":[123],"achieve":[124],"per-amino-acid":[125],"accuracy":[126],"up":[127],"90.5%":[129],"when":[130],"only":[131],"four":[132],"([KCYM])":[135],"known.":[137],"Structural":[138],"assessment":[139],"using":[140],"AlphaFold2":[141],"TM-score":[143],"validates":[144],"biological":[146],"relevance":[147],"our":[149],"predictions.":[150],"The":[151],"also":[153],"demonstrates":[154],"potential":[155],"evolutionary":[157],"analysis":[158],"through":[159],"cross-species":[160],"performance.":[161],"integration":[163],"simulated":[165],"experimental":[166,200],"constraints":[167],"computational":[169],"predictions":[170],"offers":[171],"promising":[173],"avenue":[174],"enhancing":[176],"analysis,":[179],"potentially":[180],"accelerating":[181],"advancements":[182],"proteomics":[184],"structural":[186],"biology":[187],"probabilistic":[191],"reconstruction":[192],"data.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}