{"id":"https://openalex.org/W7171570671","doi":"https://doi.org/10.1145/3807503.3819445","title":"ppLM-CO: Parameter-Efficient Codon Optimization with Frozen Pre-trained Protein Language Model and Guaranteed Translation Fidelity","display_name":"ppLM-CO: Parameter-Efficient Codon Optimization with Frozen Pre-trained Protein Language Model and Guaranteed Translation Fidelity","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7171570671","doi":"https://doi.org/10.1145/3807503.3819445"},"language":null,"primary_location":{"id":"doi:10.1145/3807503.3819445","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819445","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807503.3819445","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065353534","display_name":"Shashank Pathak","orcid":"https://orcid.org/0000-0002-7916-0191"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shashank Pathak","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada"],"raw_orcid":"https://orcid.org/0009-0004-3966-4960","affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089344475","display_name":"Guohui Lin","orcid":"https://orcid.org/0000-0003-4283-3396"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Guohui Lin","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada"],"raw_orcid":"https://orcid.org/0000-0003-4283-3396","affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6133999824523926},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.44839999079704285},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.29109999537467957},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.2761000096797943},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.2667999863624573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328999996185303},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6133999824523926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602999985218048},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3635999858379364},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35989999771118164},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2624000012874603}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3807503.3819445","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819445","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3807503.3819445","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819445","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1974887619","https://openalex.org/W2018590530","https://openalex.org/W2086561953","https://openalex.org/W2107804881","https://openalex.org/W2944311326","https://openalex.org/W3016851473","https://openalex.org/W3093282046","https://openalex.org/W3158470285","https://openalex.org/W3177500196","https://openalex.org/W3190542556","https://openalex.org/W3193427089","https://openalex.org/W4283269341","https://openalex.org/W4316339987","https://openalex.org/W4327550249","https://openalex.org/W4362601885","https://openalex.org/W4367681391","https://openalex.org/W4391943312","https://openalex.org/W4392564463","https://openalex.org/W4393276453","https://openalex.org/W4398763706","https://openalex.org/W4407399887","https://openalex.org/W4413190712","https://openalex.org/W4415740346"],"related_works":[],"abstract_inverted_index":{"Messenger":[0],"RNA":[1],"(mRNA)":[2],"therapeutics":[3],"require":[4],"coding":[5],"sequences":[6,181],"(CDSs)":[7],"that":[8,61,128,190],"preserve":[9,153],"protein":[10,36,66],"identity":[11],"while":[12,113],"optimizing":[13],"host-specific":[14],"translational":[15],"and":[16,47,75,102,109,165,178,208],"structural":[17],"properties.":[18],"Since":[19],"multiple":[20],"synonymous":[21,90,155,201],"codons":[22],"can":[23],"encode":[24],"the":[25,29],"same":[26],"amino":[27],"acid,":[28],"CDS":[30,160],"design":[31,161],"space":[32],"grows":[33],"combinatorially":[34],"with":[35,132,175,194,204],"length.":[37],"Existing":[38],"deep":[39],"learning":[40],"methods":[41],"often":[42],"train":[43],"large":[44],"task-specific":[45],"encoders":[46],"do":[48],"not":[49],"guarantee":[50],"translation":[51,94,206],"fidelity.":[52],"We":[53],"introduce":[54],"ppLM-CO,":[55],"a":[56,63,71,78,138,146],"parameter-efficient":[57,200],"codon":[58,143,202,210],"optimization":[59,203],"framework":[60],"reuses":[62],"frozen":[64,191],"pretrained":[65],"language":[67],"model":[68],"(ppLM)":[69],"as":[70],"contextual":[72],"amino-acid":[73],"encoder":[74],"trains":[76],"only":[77],"lightweight":[79],"linear":[80],"prediction":[81],"head.":[82],"A":[83],"biological":[84,196],"masking":[85],"mechanism":[86],"restricts":[87],"predictions":[88],"to":[89,124,145],"codons,":[91],"ensuring":[92],"100%":[93],"fidelity":[95,207],"by":[96,117],"construction.":[97],"Across":[98],"Human,":[99],"Chinese":[100],"Hamster,":[101],"Escherichia":[103],"coli,":[104],"ppLM-CO":[105,171],"achieves":[106],"strong":[107,176],"CAI/tAI":[108],"competitive":[110,174],"MFE":[111],"values":[112],"reducing":[114],"trainable":[115,135],"parameters":[116],"over":[118],"two":[119],"orders":[120],"of":[121,159],"magnitude":[122],"relative":[123],"CodonBERT.":[125],"Ablations":[126],"demonstrate":[127],"replacing":[129],"ppLM":[130,151],"embeddings":[131,152],"One-Hot,":[133],"Random,":[134],"embeddings,":[136],"or":[137],"frequency-based":[139],"lookup":[140],"baseline":[141],"collapses":[142],"selection":[144],"deterministic":[147],"zero-diversity":[148],"regime,":[149],"whereas":[150],"non-trivial":[154],"variation.":[156,211],"In":[157],"vaccine-application":[158],"for":[162],"SARS-CoV-2":[163],"spike":[164],"Varicella-zoster":[166],"virus":[167],"glycoprotein":[168],"(VZV-gE)":[169],"antigens,":[170],"generates":[172],"candidates":[173],"baselines":[177],"published":[179],"vaccine":[180],"on":[182],"standard":[183],"in-silico":[184],"proxy":[185],"metrics.":[186],"These":[187],"results":[188],"indicate":[189],"ppLMs,":[192],"combined":[193],"hard":[195],"constraints,":[197],"enable":[198],"scalable,":[199],"strict":[205],"structured":[209],"The":[212],"code":[213],"is":[214],"available":[215],"https://github.com/shashankcuber/Pretrained-PPLM-Codon-Optimization.":[216]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-29T00:00:00"}