{"id":"https://openalex.org/W7214710174","doi":"https://doi.org/10.48550/arxiv.2609.34654","title":"A General Harness for Protein Foundation Model Fitness Prediction","display_name":"A General Harness for Protein Foundation Model Fitness Prediction","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214710174","doi":"https://doi.org/10.48550/arxiv.2609.34654"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34654","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34654","pdf_url":"https://arxiv.org/pdf/2609.34654","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.34654","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153514755","display_name":"Yang Tan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Yang","raw_affiliation_strings":["Shanghai Innovation Institute","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153519253","display_name":"Qijia Tian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian, Qijia","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020223845","display_name":"Gangyu Sun","orcid":"https://orcid.org/0000-0002-7333-1260","observed_orcids":["https://orcid.org/0000-0002-7333-1260"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Gangyu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090728932","display_name":"Bozitao Zhong","orcid":"https://orcid.org/0000-0001-9363-6099","observed_orcids":["https://orcid.org/0000-0001-9363-6099","https://orcid.org/0000-0002-3897-9766"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong, Bozitao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153407052","display_name":"Mingchen Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Mingchen","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153428603","display_name":"Yuanxi Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Yuanxi","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124967630","display_name":"Nanqing Dong","orcid":"https://orcid.org/0000-0001-5014-1993","observed_orcids":["https://orcid.org/0000-0001-5014-1993"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong, Nanqing","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory * Equal contribution","Shanghai Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory * Equal contribution","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153415865","display_name":"Liang Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong, Liang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory * Equal contribution","Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory * Equal contribution","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.5570999979972839,"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":0.5570999979972839,"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":0.2754000127315521,"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/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.032099999487400055,"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":0.9340000152587891},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.8029999732971191},{"id":"https://openalex.org/keywords/model-uncertainty","display_name":"model uncertainty","score":0.6420000195503235},{"id":"https://openalex.org/keywords/solvent-exposure","display_name":"solvent exposure","score":0.9589999914169312},{"id":"https://openalex.org/keywords/protein-engineering","display_name":"protein engineering","score":0.6499999761581421},{"id":"https://openalex.org/keywords/sequence-function-relationships","display_name":"sequence-function relationships","score":0.6869999766349792},{"id":"https://openalex.org/keywords/immune-evasion","display_name":"immune evasion","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6510999798774719},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5972999930381775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5424000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5288000106811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5152999758720398},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.4174000024795532},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.4146000146865845},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C159744936","wikidata":"https://www.wikidata.org/wiki/Q1126730","display_name":"Spearman's rank correlation coefficient","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.32190001010894775},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C101601086","wikidata":"https://www.wikidata.org/wiki/Q3753228","display_name":"Rank correlation","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2619999945163727}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34654","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34654","pdf_url":"https://arxiv.org/pdf/2609.34654","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.34654","doi":"https://doi.org/10.48550/arxiv.2609.34654","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34654","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.34654","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34654","pdf_url":"https://arxiv.org/pdf/2609.34654","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214710174.pdf","grobid_xml":"https://content.openalex.org/works/W7214710174.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1836313771","https://openalex.org/W1969012077","https://openalex.org/W2890223884","https://openalex.org/W2973042438","https://openalex.org/W2987965949","https://openalex.org/W4225395139","https://openalex.org/W4280491725","https://openalex.org/W4283646162","https://openalex.org/W4309306331","https://openalex.org/W4312019047","https://openalex.org/W4320497972","https://openalex.org/W4380853304","https://openalex.org/W4388024559","https://openalex.org/W4388539873","https://openalex.org/W4389174567","https://openalex.org/W4390394037","https://openalex.org/W4391956897","https://openalex.org/W4396750450","https://openalex.org/W4399998351","https://openalex.org/W4400279796","https://openalex.org/W4400651824","https://openalex.org/W4400680285","https://openalex.org/W4400819708","https://openalex.org/W4400906358","https://openalex.org/W4402132679","https://openalex.org/W4404294209","https://openalex.org/W4404824543","https://openalex.org/W4404942814","https://openalex.org/W4406167408","https://openalex.org/W4408789657","https://openalex.org/W4409668938","https://openalex.org/W4410130203","https://openalex.org/W4410511604","https://openalex.org/W4410811941","https://openalex.org/W4412887084","https://openalex.org/W4413670702","https://openalex.org/W4415113534","https://openalex.org/W4416850754","https://openalex.org/W7128163174","https://openalex.org/W7131279937","https://openalex.org/W7134847968","https://openalex.org/W7139973710","https://openalex.org/W7162507345","https://openalex.org/W7213419991"],"related_works":["https://openalex.org/W4404633904","https://openalex.org/W4412426792","https://openalex.org/W7222529950","https://openalex.org/W4415318270","https://openalex.org/W4389472984","https://openalex.org/W7204889878","https://openalex.org/W4313291879","https://openalex.org/W7134954688","https://openalex.org/W4394854346","https://openalex.org/W7220849258"],"abstract_inverted_index":{"Accurate":[0],"fitness":[1,47],"prediction":[2],"is":[3,168],"central":[4],"to":[5,89,150,171],"protein":[6,17],"engineering":[7],"and":[8,52,97,104,110,118,157,160,179],"understanding":[9],"sequence-function":[10],"relationships.":[11],"With":[12],"advances":[13],"in":[14,174],"deep":[15],"learning,":[16],"foundation":[18],"models":[19,34],"(PFMs)":[20],"have":[21],"become":[22],"widely":[23],"used":[24],"for":[25],"this":[26],"task.":[27],"Recent":[28],"analyses,":[29],"however,":[30],"show":[31],"that":[32],"these":[33,58],"share":[35],"preferences":[36],"reflecting":[37],"their":[38],"training":[39],"corpora,":[40],"while":[41],"unreliable":[42],"inputs":[43],"can":[44,55],"further":[45],"distort":[46],"predictions.":[48],"Family-specific":[49],"evolutionary":[50],"evidence":[51,87],"structural":[53,102],"context":[54],"help":[56],"address":[57],"limitations":[59],"by":[60,135],"providing":[61],"complementary":[62],"constraints":[63],"on":[64,101,131,137],"model":[65,80,90],"scores,":[66],"motivating":[67],"VenusREM-Harness":[68],"(VRH),":[69],"a":[70,183],"general,":[71],"model-agnostic,":[72],"training-free":[73],"Retrieval-Enhanced":[74],"Mutation":[75],"harness.":[76],"It":[77],"fuses":[78],"frozen":[79],"scores":[81],"with":[82,139,165,182],"multiple":[83],"sequence":[84],"alignment":[85],"(MSA)":[86],"according":[88],"uncertainty,":[91],"then":[92],"applies":[93],"gated":[94],"background":[95],"correction":[96],"score":[98],"shrinkage":[99],"based":[100],"confidence":[103],"solvent":[105],"exposure.":[106],"Across":[107],"1,211":[108],"assays":[109],"3.1":[111],"million":[112],"measured":[113],"variants":[114],"from":[115],"ProteinGym,":[116],"VenusMutHub,":[117],"the":[119,169,191],"newly":[120],"curated":[121],"viral":[122],"benchmark":[123],"VenusViroHub,":[124],"all":[125,132,175],"71":[126],"configurations":[127],"improve":[128],"Spearman":[129,186],"correlation":[130],"3":[133],"benchmarks":[134],"0.073":[136],"average,":[138],"broad":[140],"gains":[141,149,156],"across":[142],"5":[143],"metrics.":[144],"Extended":[145],"analyses":[146],"relate":[147],"retrieval":[148],"model-MSA":[151],"preference":[152],"differences,":[153],"assess":[154],"domain-level":[155],"immune-escape":[158],"cases,":[159],"quantify":[161],"computational":[162],"speedups.":[163],"Built":[164],"VRH,":[166],"VenusREM2":[167],"first":[170],"rank":[172],"highest":[173],"function,":[176],"taxon,":[177],"MSA-depth,":[178],"mutation-depth":[180],"categories,":[181],"ProteinGym":[184],"Average":[185],"of":[187],"0.556,":[188],"0.038":[189],"above":[190],"prior":[192],"best.":[193]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}