{"id":"https://openalex.org/W7220849258","doi":"https://doi.org/10.64898/2026.10.06.756934","title":"Generalizing Protein Fitness Prediction Across Distribution Shifts via Structural and Co-evolutionary Priors","display_name":"Generalizing Protein Fitness Prediction Across Distribution Shifts via Structural and Co-evolutionary Priors","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220849258","doi":"https://doi.org/10.64898/2026.10.06.756934"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.06.756934","doi":"https://doi.org/10.64898/2026.10.06.756934","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.06.756934","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/07/2026.10.06.756934.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"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/2026/10/07/2026.10.06.756934.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119153010","display_name":"Nopsinth Vithayapalert","orcid":"https://orcid.org/0009-0009-0757-0886","observed_orcids":["https://orcid.org/0009-0009-0757-0886"]},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nopsinth Vithayapalert","raw_affiliation_strings":["Department of Biomedical Engineering Eindhoven University of Technology"],"raw_orcid":"https://orcid.org/0009-0009-0757-0886","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079103855","display_name":"Maytus Piriyajitakonkij","orcid":"https://orcid.org/0000-0002-7610-8953","observed_orcids":["https://orcid.org/0000-0002-7610-8953"]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maytus Piriyajitakonkij","raw_affiliation_strings":["Department of Computer Science University of Manchester"],"raw_orcid":"https://orcid.org/0000-0002-7610-8953","affiliations":[{"raw_affiliation_string":"Department of Computer Science University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078946433","display_name":"Francesca Grisoni","orcid":"https://orcid.org/0000-0001-8552-6615","observed_orcids":["https://orcid.org/0000-0001-8552-6615"]},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Francesca Grisoni","raw_affiliation_strings":["Department of Biomedical Engineering Eindhoven University of Technology"],"raw_orcid":"https://orcid.org/0000-0001-8552-6615","affiliations":[{"raw_affiliation_string":"Department of Biomedical Engineering Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078946433"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9125999808311462,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9125999808311462,"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":0.06340000033378601,"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":0.003700000001117587,"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-fitness-prediction","display_name":"protein fitness prediction","score":1.0},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.9150000214576721},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.847000002861023},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.8700000047683716},{"id":"https://openalex.org/keywords/structural-priors","display_name":"structural priors","score":0.8140000104904175},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.828000009059906},{"id":"https://openalex.org/keywords/protein-design","display_name":"protein design","score":0.5090000033378601},{"id":"https://openalex.org/keywords/protein-engineering","display_name":"protein engineering","score":0.453000009059906}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7272999882698059},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7210999727249146},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5981000065803528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.529699981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48989999294281006},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.4553000032901764},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4442000091075897},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.3815999925136566},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3246000111103058},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C176066374","wikidata":"https://www.wikidata.org/wiki/Q629118","display_name":"Fitness function","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.26579999923706055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.06.756934","doi":"https://doi.org/10.64898/2026.10.06.756934","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.06.756934","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/07/2026.10.06.756934.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.06.756934","doi":"https://doi.org/10.64898/2026.10.06.756934","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.06.756934","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/07/2026.10.06.756934.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6022517900","display_name":"ChemWISE \u2013 Next-generation chemistry-augmented AI paradigms for drug discovery","funder_award_id":"VI.Vidi.233.164","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220849258.pdf","grobid_xml":"https://content.openalex.org/works/W7220849258.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W7222529950","https://openalex.org/W4415318270","https://openalex.org/W7131365204","https://openalex.org/W4415067411","https://openalex.org/W4403141065","https://openalex.org/W4394854346","https://openalex.org/W7214165525","https://openalex.org/W4380136229","https://openalex.org/W3197005806","https://openalex.org/W4399272586"],"abstract_inverted_index":{"Abstract":[0],"Protein":[1],"fitness":[2,86,122,213],"prediction":[3,114],"is":[4,31],"essential":[5],"for":[6,85,187,197,224],"protein":[7,46,51,69,163,189,225],"engineering.":[8,70],"Recent":[9],"fitness-landscape":[10],"benchmarks":[11],"such":[12,61],"as":[13,218],"FLIP2":[14,132],"have":[15],"shown":[16],"that":[17,76,215],"methods":[18],"performing":[19],"well":[20],"under":[21,60],"conventional":[22],"train\u2013test":[23],"splits":[24],"can":[25,216],"fail":[26],"when":[27],"the":[28,128,144,157,202,208],"test":[29],"set":[30],"shifted":[32],"out":[33],"of":[34,137,146,210],"distribution":[35,62,138,192],"(OOD),":[36],"including":[37],"mutations":[38],"at":[39],"unseen":[40,45],"positions":[41],"and":[42,82,104,110,191],"variants":[43],"from":[44,96],"backbones.":[47],"In":[48],"particular,":[49],"current":[50],"language":[52],"models":[53],"(pLMs)":[54],"often":[55],"suffer":[56],"substantial":[57],"performance":[58,159],"degradation":[59],"shifts,":[63,193],"limiting":[64],"their":[65],"practical":[66,195],"use":[67,111],"in":[68,149],"We":[71,140],"therefore":[72],"develop":[73],"a":[74,112,177],"framework":[75,125,151],"augments":[77],"sequence":[78,103,107],"representations":[79,120,199],"with":[80,93],"structural":[81],"co-evolutionary":[83],"information":[84],"prediction.":[87],"Specifically,":[88],"we":[89,181],"pair":[90],"structure-aware":[91],"pLMs":[92],"features":[94,167],"pooled":[95],"an":[97],"AlphaFold-style":[98],"trunk":[99,166],"applied":[100],"to":[101,116,121,152,170,201],"each":[102,147],"its":[105],"multiple":[106],"alignment":[108],"(MSA),":[109],"lightweight":[113],"probe":[115],"map":[117],"these":[118],"frozen":[119],"scores.":[123],"Our":[124],"consistently":[126],"outperforms":[127],"best":[129,179],"previously":[130],"reported":[131],"scores":[133],"across":[134],"several":[135],"types":[136],"shift.":[139],"then":[141],"systematically":[142],"study":[143],"contribution":[145],"component":[148],"our":[150],"generalization.":[153],"Structural":[154],"priors":[155],"yield":[156],"largest":[158],"gains":[160],"on":[161],"held-out":[162,171],"backbones,":[164],"whereas":[165],"improve":[168],"generalization":[169,203],"mutation":[172],"positions.":[173],"Rather":[174],"than":[175],"proposing":[176],"single":[178],"method,":[180],"characterize":[182],"which":[183],"modalities":[184],"are":[185],"effective":[186,219],"different":[188],"families":[190],"providing":[194],"guidance":[196],"choosing":[198],"according":[200],"regime.":[204],"These":[205],"findings":[206],"support":[207],"development":[209],"more":[211],"generalizable":[212],"predictors":[214],"serve":[217],"reward":[220],"functions":[221],"or":[222],"oracles":[223],"design":[226],"toward":[227],"desired":[228],"functions.":[229]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-08T00:00:00"}