{"id":"https://openalex.org/W7204480085","doi":"https://doi.org/10.64898/2026.08.26.747074","title":"Multi-Peptide Prompting Enables In-Context Learning in Protein Language Models","display_name":"Multi-Peptide Prompting Enables In-Context Learning in Protein Language Models","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204480085","doi":"https://doi.org/10.64898/2026.08.26.747074"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.26.747074","doi":"https://doi.org/10.64898/2026.08.26.747074","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.26.747074","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/27/2026.08.26.747074.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/27/2026.08.26.747074.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094187329","display_name":"Joshua Almonte","orcid":"https://orcid.org/0000-0002-5267-2162","observed_orcids":["https://orcid.org/0000-0002-5267-2162"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Almonte","raw_affiliation_strings":["Chemical and Biomolecular Engineering, Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemical and Biomolecular Engineering, Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148462397","display_name":"Minh Triet Vu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minh Triet Vu","raw_affiliation_strings":["Chemistry and Chemical Biology, Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemistry and Chemical Biology, Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126422526","display_name":"Andrew Ahn","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Ahn","raw_affiliation_strings":["Chemistry and Chemical Biology, Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemistry and Chemical Biology, Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070853988","display_name":"Erik H. Thiede","orcid":"https://orcid.org/0000-0002-5666-1372","observed_orcids":["https://orcid.org/0000-0002-5666-1372"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Erik H. Thiede","raw_affiliation_strings":["Chemistry and Chemical Biology, Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemistry and Chemical Biology, Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070853988"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.8622999787330627,"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":0.8622999787330627,"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/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.09260000288486481,"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":0.021800000220537186,"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/protein-language-models","display_name":"protein language models","score":0.9929999709129333},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.9490000009536743},{"id":"https://openalex.org/keywords/peptide-discovery","display_name":"peptide discovery","score":0.703000009059906},{"id":"https://openalex.org/keywords/pattern-completion","display_name":"pattern completion","score":0.7620000243186951},{"id":"https://openalex.org/keywords/compositional-bias","display_name":"compositional bias","score":0.8240000009536743},{"id":"https://openalex.org/keywords/esm-2","display_name":"ESM-2","score":0.8489999771118164}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7078999876976013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6518999934196472},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5351999998092651},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4300000071525574},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C2988105877","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference system","level":5,"score":0.3154999911785126},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.26.747074","doi":"https://doi.org/10.64898/2026.08.26.747074","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.26.747074","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/27/2026.08.26.747074.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.08.26.747074","doi":"https://doi.org/10.64898/2026.08.26.747074","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.26.747074","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/27/2026.08.26.747074.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204480085.pdf","grobid_xml":"https://content.openalex.org/works/W7204480085.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1969051510","https://openalex.org/W1992450378","https://openalex.org/W2122779464","https://openalex.org/W3030163527","https://openalex.org/W3037620288","https://openalex.org/W3118363792","https://openalex.org/W4205095214","https://openalex.org/W4212959738","https://openalex.org/W4313483544","https://openalex.org/W4327550249","https://openalex.org/W4380551121","https://openalex.org/W4387906121","https://openalex.org/W4388024559","https://openalex.org/W4391930668","https://openalex.org/W4394966704","https://openalex.org/W4399497299","https://openalex.org/W4401966068","https://openalex.org/W4403444104","https://openalex.org/W4403824354","https://openalex.org/W4403924786","https://openalex.org/W4406199730","https://openalex.org/W4411644384","https://openalex.org/W4411865423","https://openalex.org/W4413117240","https://openalex.org/W4413440590","https://openalex.org/W6929558060"],"related_works":["https://openalex.org/W7130555421","https://openalex.org/W4396966015","https://openalex.org/W4401021891","https://openalex.org/W4416238756","https://openalex.org/W7139987738","https://openalex.org/W7202210351","https://openalex.org/W7143459218","https://openalex.org/W7202274444","https://openalex.org/W4309128937","https://openalex.org/W4388399759"],"abstract_inverted_index":{"A":[0],"bstract":[1],"We":[2,20,47,88],"show":[3],"that":[4,79,94],"single-sequence":[5,144],"PLMs":[6,80,145],"can":[7,81],"perform":[8],"in-context":[9,140,148],"peptide":[10,72,117,157],"learning":[11,118,149],"without":[12],"gradient":[13],"updates,":[14],"task-specific":[15],"retraining,":[16],"or":[17],"architectural":[18],"modification.":[19],"introduce":[21,90],"multi-peptide":[22],"example":[23],"prompts":[24],"(MPEPs),":[25],"in":[26,103,143],"which":[27],"demonstration":[28],"peptides":[29,42],"are":[30],"concatenated":[31],"with":[32,68,75,124],"glycine":[33],"spacers":[34],"and":[35,59,74,97,107,146],"used":[36],"as":[37,150],"context":[38],"for":[39,155],"scoring":[40],"query":[41],"by":[43],"their":[44],"prompted":[45,86],"probability.":[46],"evaluate":[48],"this":[49],"approach":[50],"across":[51],"multiple":[52],"tasks,":[53,65],"using":[54],"both":[55],"encoder-only":[56],"ESM-2":[57,129],"models":[58],"decoder-only":[60],"ProGen2":[61],"models.":[62],"Across":[63],"most":[64],"performance":[66],"improves":[67],"the":[69],"number":[70],"of":[71],"examples":[73],"model":[76],"scale,":[77],"indicating":[78],"extract":[82],"shared":[83],"properties":[84],"from":[85],"examples.":[87],"further":[89],"a":[91,151],"difference":[92],"score":[93],"contrasts":[95],"positive-example":[96],"negative-example":[98],"MPEPs,":[99],"reducing":[100],"compositional":[101],"biases":[102],"raw":[104],"PLM":[105],"probabilities":[106],"substantially":[108],"improving":[109],"classification.":[110,158],"Perhaps":[111],"surprisingly,":[112],"when":[113],"applied":[114],"to":[115],"few-shot":[116],"problems":[119],"MPEP-based":[120],"classification":[121],"is":[122],"competitive":[123],"classifiers":[125],"trained":[126],"on":[127],"frozen":[128],"embeddings,":[130],"despite":[131],"requiring":[132],"no":[133],"training.":[134],"These":[135],"results":[136],"reveal":[137],"an":[138],"unexpected":[139],"inference":[141],"capability":[142],"establish":[147],"potential":[152],"lightweight":[153],"strategy":[154],"low-data":[156]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-08-28T00:00:00"}