{"id":"https://openalex.org/W4416728353","doi":"https://doi.org/10.1101/2025.11.23.689994","title":"General-Purpose Large Language Models, such as DeepSeek V3.2, Have Evolved Protein Design Capabilities","display_name":"General-Purpose Large Language Models, such as DeepSeek V3.2, Have Evolved Protein Design Capabilities","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4416728353","doi":"https://doi.org/10.1101/2025.11.23.689994"},"language":"en","primary_location":{"id":"doi:10.1101/2025.11.23.689994","doi":"https://doi.org/10.1101/2025.11.23.689994","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.11.23.689994","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/11/24/2025.11.23.689994.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/2025/11/24/2025.11.23.689994.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiawei Li","orcid":"https://orcid.org/0009-0004-3205-7041","observed_orcids":["https://orcid.org/0009-0004-3205-7041"]},"institutions":[{"id":"https://openalex.org/I4210136047","display_name":"Weifang University of Science and Technology","ror":"https://ror.org/04ha2bb10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136047"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Li","raw_affiliation_strings":["Weifang University of Science and Technology"],"raw_orcid":"https://orcid.org/0009-0004-3205-7041","affiliations":[{"raw_affiliation_string":"Weifang University of Science and Technology","institution_ids":["https://openalex.org/I4210136047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103034530","display_name":"Xinxiu Dong","orcid":"https://orcid.org/0000-0002-7898-5327","observed_orcids":["https://orcid.org/0000-0002-7898-5327"]},"institutions":[{"id":"https://openalex.org/I4210136047","display_name":"Weifang University of Science and Technology","ror":"https://ror.org/04ha2bb10","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136047"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinxiu Dong","raw_affiliation_strings":["Weifang University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weifang University of Science and Technology","institution_ids":["https://openalex.org/I4210136047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103034530"],"corresponding_institution_ids":["https://openalex.org/I4210136047"],"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":0.9765999913215637,"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":0.9765999913215637,"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":0.01489999983459711,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-design","display_name":"protein design","score":0.8130000233650208},{"id":"https://openalex.org/keywords/deepseek-v3-2","display_name":"DeepSeek-V3.2","score":0.953000009059906},{"id":"https://openalex.org/keywords/four-helix-bundle","display_name":"four-helix bundle","score":0.8100000023841858},{"id":"https://openalex.org/keywords/protein-solubility","display_name":"protein solubility","score":0.8460000157356262},{"id":"https://openalex.org/keywords/protein-engineering","display_name":"protein engineering","score":0.36399999260902405}],"concepts":[{"id":"https://openalex.org/C152769699","wikidata":"https://www.wikidata.org/wiki/Q410814","display_name":"Protein design","level":3,"score":0.6593000292778015},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6398000121116638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5353999733924866},{"id":"https://openalex.org/C2778134712","wikidata":"https://www.wikidata.org/wiki/Q1047307","display_name":"Bundle","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.4652000069618225},{"id":"https://openalex.org/C147816474","wikidata":"https://www.wikidata.org/wiki/Q169525","display_name":"Protein engineering","level":3,"score":0.42579999566078186},{"id":"https://openalex.org/C203087120","wikidata":"https://www.wikidata.org/wiki/Q372229","display_name":"Helix bundle","level":3,"score":0.39640000462532043},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.35569998621940613},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.35519999265670776},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34549999237060547},{"id":"https://openalex.org/C2778530040","wikidata":"https://www.wikidata.org/wiki/Q1937315","display_name":"Helix (gastropod)","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C204328495","wikidata":"https://www.wikidata.org/wiki/Q847556","display_name":"Protein folding","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.28049999475479126},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2644999921321869}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/2025.11.23.689994","doi":"https://doi.org/10.1101/2025.11.23.689994","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.11.23.689994","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/11/24/2025.11.23.689994.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:10.1101/2025.11.23.689994","doi":"https://doi.org/10.1101/2025.11.23.689994","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.11.23.689994","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/11/24/2025.11.23.689994.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416728353.pdf","grobid_xml":"https://content.openalex.org/works/W4416728353.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2011301426","https://openalex.org/W2103083136","https://openalex.org/W2114850508","https://openalex.org/W2992752586","https://openalex.org/W3177828909","https://openalex.org/W4281790889","https://openalex.org/W4296032638","https://openalex.org/W4296502374","https://openalex.org/W4383957026","https://openalex.org/W4396721167","https://openalex.org/W4399361756","https://openalex.org/W4399746375","https://openalex.org/W4410140539","https://openalex.org/W4414281281","https://openalex.org/W7223152200"],"related_works":["https://openalex.org/W4406259721","https://openalex.org/W7203571009","https://openalex.org/W4406548156","https://openalex.org/W4319071809","https://openalex.org/W4416975519","https://openalex.org/W4400978157","https://openalex.org/W4312197262","https://openalex.org/W6887326600","https://openalex.org/W4388581010","https://openalex.org/W4409882638"],"abstract_inverted_index":{"Abstract":[0],"General-Purpose":[1],"Large":[2],"Language":[3],"Models":[4],"(GLLMs),":[5],"although":[6],"primarily":[7],"developed":[8],"for":[9,163],"natural":[10],"language":[11],"processing,":[12],"are":[13],"increasingly":[14],"demonstrating":[15],"emergent":[16],"capabilities":[17],"in":[18,34],"specialized":[19],"scientific":[20],"domains.":[21],"In":[22],"this":[23],"study,":[24],"we":[25],"explored":[26],"the":[27,61,89],"potential":[28],"of":[29,54,114],"GLLMs,specifically":[30],"DeepSeek":[31,133],"V3.2":[32,134],"Exp":[33],"reasoning":[35],"mode":[36],"to":[37,59,71,140],"perform":[38],"practical":[39],"protein":[40,73,143,164],"engineering":[41],"tasks":[42],"without":[43],"domain-specific":[44],"biological":[45],"training.":[46],"Two":[47],"representative":[48,103],"design":[49,70],"problems":[50],"were":[51],"addressed:":[52],"Generation":[53],"amino":[55],"acid":[56],"sequences":[57],"predicted":[58,111],"adopt":[60],"canonical":[62],"4-":[63,83],"helix":[64,84],"bundle":[65,85],"topology,":[66],"and":[67,116,165],"targeted":[68],"mutation":[69,153],"improve":[72],"solubility":[74],"while":[75],"preserving":[76],"core":[77],"structural":[78,119],"integrity.":[79],"Across":[80],"49":[81],"generated":[82],"candidates,":[86],"40":[87],"adopted":[88],"desired":[90],"geometry,":[91],"with":[92,108,155],"36":[93],"achieving":[94],"pLDDT":[95],"scores":[96],"above":[97],"70.":[98],"Solubility":[99],"optimization":[100],"on":[101],"50":[102],"proteins":[104],"yielded":[105],"46":[106],"mutants":[107],"an":[109,160],"average":[110],"score":[112],"increase":[113],"0.178,":[115],"29":[117],"maintained":[118],"deviations":[120],"below":[121],"3":[122],"\u00c5":[123],"RMSD.":[124],"These":[125],"results":[126],"indicate":[127],"that":[128,150],"general-purpose":[129],"LLMs":[130],"such":[131],"as":[132],"can":[135],"integrate":[136],"sequence\u2013structure\u2013property":[137],"relationships":[138],"sufficiently":[139],"produce":[141],"viable":[142],"designs.":[144],"We":[145],"propose":[146],"a":[147],"hybrid":[148],"workflow":[149],"couples":[151],"GLLM-based":[152],"generation":[154],"established":[156],"computational":[157],"validation,":[158],"offering":[159],"accessible":[161],"route":[162],"peptide":[166],"engineering.":[167]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2025-11-25T00:00:00"}