{"id":"https://openalex.org/W7127040434","doi":"https://doi.org/10.64898/2026.02.01.703093","title":"An AI-Native Biofoundry for Autonomous Enzyme Engineering: Integrating Active Learning with Automated Experimentation","display_name":"An AI-Native Biofoundry for Autonomous Enzyme Engineering: Integrating Active Learning with Automated Experimentation","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7127040434","doi":"https://doi.org/10.64898/2026.02.01.703093"},"language":null,"primary_location":{"id":"doi:10.64898/2026.02.01.703093","doi":"https://doi.org/10.64898/2026.02.01.703093","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.02.01.703093","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/01/2026.02.01.703093.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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/01/2026.02.01.703093.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124714473","display_name":"Chuwen Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387156387","display_name":"MGI","ror":"https://ror.org/02yrqby68","country_code":null,"type":"company","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387156387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuwen Zhang","raw_affiliation_strings":["MGI Tech, Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MGI Tech, Shenzhen 518083, China","institution_ids":["https://openalex.org/I4387156387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124705958","display_name":"Lixiang Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387156387","display_name":"MGI","ror":"https://ror.org/02yrqby68","country_code":null,"type":"company","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387156387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixiang Yang","raw_affiliation_strings":["MGI Tech, Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MGI Tech, Shenzhen 518083, China","institution_ids":["https://openalex.org/I4387156387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124695751","display_name":"Yanjia Qin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387156387","display_name":"MGI","ror":"https://ror.org/02yrqby68","country_code":null,"type":"company","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387156387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjia Qin","raw_affiliation_strings":["MGI Tech, Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MGI Tech, Shenzhen 518083, China","institution_ids":["https://openalex.org/I4387156387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015067111","display_name":"Danjing Li","orcid":"https://orcid.org/0009-0006-7335-4039","observed_orcids":["https://orcid.org/0009-0006-7335-4039"]},"institutions":[{"id":"https://openalex.org/I4387156387","display_name":"MGI","ror":"https://ror.org/02yrqby68","country_code":null,"type":"company","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387156387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danjing Li","raw_affiliation_strings":["MGI Tech, Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MGI Tech, Shenzhen 518083, China","institution_ids":["https://openalex.org/I4387156387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124713883","display_name":"Shimao Dong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387156387","display_name":"MGI","ror":"https://ror.org/02yrqby68","country_code":null,"type":"company","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387156387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimao Dong","raw_affiliation_strings":["MGI Tech, Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MGI Tech, Shenzhen 518083, China","institution_ids":["https://openalex.org/I4387156387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124745481","display_name":"Meng Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387156387","display_name":"MGI","ror":"https://ror.org/02yrqby68","country_code":null,"type":"company","lineage":["https://openalex.org/I100135526","https://openalex.org/I4387156387"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng Yang","raw_affiliation_strings":["MGI Tech, Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MGI Tech, Shenzhen 518083, China","institution_ids":["https://openalex.org/I4387156387"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5124745481"],"corresponding_institution_ids":["https://openalex.org/I4387156387"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.7904999852180481,"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/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.7904999852180481,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.09910000115633011,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.018400000408291817,"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/enzyme-engineering","display_name":"enzyme engineering","score":0.7879999876022339},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.703000009059906},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.5540000200271606},{"id":"https://openalex.org/keywords/automated-experimentation","display_name":"automated experimentation","score":0.5899999737739563},{"id":"https://openalex.org/keywords/laboratory-automation","display_name":"laboratory automation","score":0.6079999804496765},{"id":"https://openalex.org/keywords/model-context-protocol","display_name":"Model Context Protocol","score":0.718999981880188},{"id":"https://openalex.org/keywords/edge-cloud-computing","display_name":"edge-cloud computing","score":0.7319999933242798},{"id":"https://openalex.org/keywords/esm-2","display_name":"ESM-2","score":0.8519999980926514},{"id":"https://openalex.org/keywords/b-family-dna-polymerases","display_name":"family B DNA polymerase","score":0.7509999871253967},{"id":"https://openalex.org/keywords/design-build-test-learn-cycle","display_name":"design-build-test-learn cycle","score":0.722000002861023},{"id":"https://openalex.org/keywords/rugged-fitness-landscapes","display_name":"rugged fitness landscapes","score":0.6639999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6344000101089478},{"id":"https://openalex.org/C191908910","wikidata":"https://www.wikidata.org/wiki/Q862838","display_name":"Synthetic biology","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.42399999499320984},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.02.01.703093","doi":"https://doi.org/10.64898/2026.02.01.703093","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.02.01.703093","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/01/2026.02.01.703093.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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.02.01.703093","doi":"https://doi.org/10.64898/2026.02.01.703093","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.02.01.703093","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/02/01/2026.02.01.703093.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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Industry, innovation and infrastructure","score":0.60999995470047,"id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127040434.pdf","grobid_xml":"https://content.openalex.org/works/W7127040434.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1556398360","https://openalex.org/W1954202239","https://openalex.org/W1971439989","https://openalex.org/W1973950074","https://openalex.org/W1984180361","https://openalex.org/W1993336267","https://openalex.org/W2066690664","https://openalex.org/W2095719702","https://openalex.org/W2118265845","https://openalex.org/W2144483773","https://openalex.org/W2147993766","https://openalex.org/W2170747616","https://openalex.org/W2313116527","https://openalex.org/W2555332535","https://openalex.org/W2622780413","https://openalex.org/W2751743037","https://openalex.org/W2767044445","https://openalex.org/W2938803199","https://openalex.org/W2950629258","https://openalex.org/W2963907999","https://openalex.org/W2980789587","https://openalex.org/W2989052455","https://openalex.org/W3042021489","https://openalex.org/W3119780302","https://openalex.org/W3177828909","https://openalex.org/W3194729882","https://openalex.org/W4206087583","https://openalex.org/W4280594636","https://openalex.org/W4288066876","https://openalex.org/W4308616064","https://openalex.org/W4318071656","https://openalex.org/W4327550249","https://openalex.org/W4387826128","https://openalex.org/W4389991792","https://openalex.org/W4390754450","https://openalex.org/W4411887054"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"The":[1,68],"engineering":[2],"of":[3,11,139,160,175,207,219],"enzymes":[4],"with":[5,180],"novel":[6],"functions":[7],"is":[8],"a":[9,64,136,147,155,172,181,190,212],"cornerstone":[10],"synthetic":[12],"biology":[13],"but":[14,209],"remains":[15],"bottlenecked":[16],"by":[17,76,205],"the":[18,43,82,89,106,158,169,217],"fragmentation":[19],"between":[20,92],"computational":[21],"design":[22],"and":[23,81,96,124,177],"physical":[24],"execution.":[25,99],"While":[26],"\u201cself-driving\u201d":[27],"laboratories":[28],"promise":[29],"to":[30,45,104,145,189],"resolve":[31],"this,":[32],"existing":[33],"systems":[34],"often":[35],"rely":[36],"on":[37],"rigid,":[38],"device-specific":[39],"scripts":[40],"that":[41,58,196],"lack":[42],"flexibility":[44],"handle":[46],"complex,":[47],"evolving":[48],"scientific":[49,94,221],"tasks.":[50],"Here,":[51],"we":[52,141],"report":[53],"an":[54,71],"AI-native":[55,197],"autonomous":[56,167],"biofoundry":[57],"fundamentally":[59],"redefines":[60],"laboratory":[61],"automation":[62],"through":[63],"\u201ccloud-edge":[65],"synergistic\u201d":[66],"architecture.":[67],"platform":[69,144,170],"features":[70],"Agent-Native":[72],"control":[73],"system":[74,129],"powered":[75],"Large":[77],"Language":[78],"Models":[79],"(LLMs)":[80],"Model":[83],"Context":[84],"Protocol":[85],"(MCP),":[86],"which":[87],"bridges":[88],"semantic":[90],"gap":[91],"abstract":[93],"intent":[95],"heterogeneous":[97],"hardware":[98],"This":[100,193],"architecture":[101],"enables":[102],"non-experts":[103],"orchestrate":[105],"entire":[107],"Design-Build-Test-Learn":[108],"(DBTL)":[109],"cycle":[110],"via":[111],"natural":[112],"language.":[113],"By":[114],"integrating":[115],"deep":[116],"phylogenetic":[117],"mining,":[118],"zero-shot":[119],"protein":[120],"language":[121],"models":[122],"(ESM-2),":[123],"supervised":[125],"active":[126],"learning,":[127],"our":[128],"efficiently":[130],"navigates":[131],"rugged":[132],"fitness":[133],"landscapes.":[134],"As":[135],"rigorous":[137],"proof":[138],"concept,":[140],"applied":[142],"this":[143],"evolve":[146],"Family":[148],"B":[149],"DNA":[150],"polymerase":[151],"for":[152,216],"CoolMPS":[153],"sequencing,":[154],"task":[156],"requiring":[157],"incorporation":[159],"non-natural":[161],"3\u2019-blocked":[162],"nucleotides.":[163],"In":[164],"just":[165],"three":[166],"rounds,":[168],"achieved":[171],"hit":[173],"rate":[174,187],">66%":[176],"identified":[178],"variants":[179],"37%":[182],"reduction":[183],"in":[184],"sequencing":[185],"error":[186],"compared":[188],"commercial":[191],"reference.":[192],"work":[194],"demonstrates":[195],"infrastructures":[198],"can":[199],"not":[200],"only":[201],"accelerate":[202],"trait":[203],"evolution":[204],"orders":[206],"magnitude":[208],"also":[210],"provide":[211],"scalable,":[213],"brand-agnostic":[214],"paradigm":[215],"future":[218],"automated":[220],"discovery.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-02-03T00:00:00"}