{"id":"https://openalex.org/W7224760869","doi":"https://doi.org/10.64898/2026.10.26.762056","title":"ProtoPure: Literature Mining and Analysis of Protein Purification Protocols at Proteome Scale","display_name":"ProtoPure: Literature Mining and Analysis of Protein Purification Protocols at Proteome Scale","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224760869","doi":"https://doi.org/10.64898/2026.10.26.762056"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.26.762056","doi":"https://doi.org/10.64898/2026.10.26.762056","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.26.762056","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.26.762056.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/2026/10/30/2026.10.26.762056.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097371969","display_name":"Ricardo Almada\u2010Monter","orcid":"https://orcid.org/0009-0007-7201-3125","observed_orcids":["https://orcid.org/0009-0007-7201-3125"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricardo Almada Monter","raw_affiliation_strings":["University of California San Diego;"],"raw_orcid":"https://orcid.org/0009-0007-7201-3125","affiliations":[{"raw_affiliation_string":"University of California San Diego;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020473625","display_name":"Jose Martinez-Lomeli","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I8961855","display_name":"Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/01tmp8f25","country_code":"MX","type":"education","lineage":["https://openalex.org/I8961855"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jose Martinez-Lomeli","raw_affiliation_strings":["Departamento de Matematicas, Facultad de Ciencias, UNAM, Ciudad Universitaria, Circuito 11 Exterior, Cd. de Mexico, C.P., 04510, Mexico;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Matematicas, Facultad de Ciencias, UNAM, Ciudad Universitaria, Circuito 11 Exterior, Cd. de Mexico, C.P., 04510, Mexico;","institution_ids":["https://openalex.org/I8961855"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028642344","display_name":"Erika Garay","orcid":"https://orcid.org/0000-0001-6898-2256","observed_orcids":["https://orcid.org/0000-0001-6898-2256"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erika Garay","raw_affiliation_strings":["Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, California 92093, United States;"],"raw_orcid":"https://orcid.org/0000-0001-6898-2256","affiliations":[{"raw_affiliation_string":"Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, California 92093, United States;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160202127","display_name":"Joaquin Trevilla Santa Ana","orcid":"https://orcid.org/0009-0009-1103-9043","observed_orcids":["https://orcid.org/0009-0009-1103-9043"]},"institutions":[{"id":"https://openalex.org/I4210118730","display_name":"Instituto Tecnol\u00f3gico de Tijuana","ror":"https://ror.org/03dga7879","country_code":"MX","type":"education","lineage":["https://openalex.org/I4210118730"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Joaquin Trevilla Santa Ana","raw_affiliation_strings":["Instituto Tecnologico de Tijuana, Tijuana, Baja California, MX;"],"raw_orcid":"https://orcid.org/0009-0009-1103-9043","affiliations":[{"raw_affiliation_string":"Instituto Tecnologico de Tijuana, Tijuana, Baja California, MX;","institution_ids":["https://openalex.org/I4210118730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072872088","display_name":"Andy Spencer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amanda Spencer","raw_affiliation_strings":["Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego,  La Jolla, California 92093, United States;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego,  La Jolla, California 92093, United States;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006150272","display_name":"Adriana Siordia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adriana Siordia","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of California San Diego, La Jolla,  California 92093, United States;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of California San Diego, La Jolla,  California 92093, United States;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116127767","display_name":"Param Chordiya","orcid":"https://orcid.org/0009-0009-6839-0782","observed_orcids":["https://orcid.org/0009-0009-6839-0782"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Param Chordiya","raw_affiliation_strings":["Department of Electrical & Computer Engineering, University of California San Diego, La Jolla, California 92093, United States;"],"raw_orcid":"https://orcid.org/0009-0009-6839-0782","affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, University of California San Diego, La Jolla, California 92093, United States;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160228749","display_name":"Sofia Luna Armijo","orcid":"https://orcid.org/0009-0002-6207-039X","observed_orcids":["https://orcid.org/0009-0002-6207-039X"]},"institutions":[{"id":"https://openalex.org/I173664879","display_name":"Universidad Aut\u00f3noma de Baja California","ror":"https://ror.org/05xwcq167","country_code":"MX","type":"education","lineage":["https://openalex.org/I173664879"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Sofia Luna Armijo","raw_affiliation_strings":["Universidad Autonoma de Baja California, Tijuana, Baja California, Mexico;"],"raw_orcid":"https://orcid.org/0009-0002-6207-039X","affiliations":[{"raw_affiliation_string":"Universidad Autonoma de Baja California, Tijuana, Baja California, Mexico;","institution_ids":["https://openalex.org/I173664879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112571180","display_name":"Joel Maya Herrera","orcid":"https://orcid.org/0009-0004-8644-5867","observed_orcids":["https://orcid.org/0009-0004-8644-5867"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Javier Espinoza Herrera","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of California San Diego, La Jolla, California 92093, United States;"],"raw_orcid":"https://orcid.org/0009-0004-8644-5867","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of California San Diego, La Jolla, California 92093, United States;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114742501","display_name":"Nathaniel Roethler","orcid":"https://orcid.org/0009-0001-0143-2791","observed_orcids":["https://orcid.org/0009-0001-0143-2791"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel Roethler","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of California San Diego, La Jolla, California 92093, United States;"],"raw_orcid":"https://orcid.org/0009-0001-0143-2791","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of California San Diego, La Jolla, California 92093, United States;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114742503","display_name":"Sarah Marta Veskim\u00e4gi","orcid":"https://orcid.org/0009-0002-4254-3188","observed_orcids":["https://orcid.org/0009-0002-4254-3188"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Marta Veskimagi","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of California San Diego, La Jolla, California 92093, United States;"],"raw_orcid":"https://orcid.org/0009-0002-4254-3188","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of California San Diego, La Jolla, California 92093, United States;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160169136","display_name":"Akshay Uppal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akshay Uppal","raw_affiliation_strings":["Halicioglu School of Data Science and Computing, University of California San Diego, La Jolla, California, 92093, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Halicioglu School of Data Science and Computing, University of California San Diego, La Jolla, California, 92093, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027640052","display_name":"Melina Shamshoum","orcid":"https://orcid.org/0009-0006-8148-7878","observed_orcids":["https://orcid.org/0009-0006-8148-7878"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Melina Shamshoum","raw_affiliation_strings":["Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, California 92093, United States;"],"raw_orcid":"https://orcid.org/0009-0006-8148-7878","affiliations":[{"raw_affiliation_string":"Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, California 92093, United States;","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019436022","display_name":"Adri\u00e1n Jinich","orcid":"https://orcid.org/0000-0001-8616-9250","observed_orcids":["https://orcid.org/0000-0001-8616-9250"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adrian Jinich","raw_affiliation_strings":["University of California San Diego;"],"raw_orcid":"https://orcid.org/0000-0001-8616-9250","affiliations":[{"raw_affiliation_string":"University of California San Diego;","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019436022"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"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/T11124","display_name":"Protein purification and stability","score":0.698199987411499,"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/T11124","display_name":"Protein purification and stability","score":0.698199987411499,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.05939999967813492,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.050700001418590546,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/literature-mining","display_name":"literature mining","score":0.9549999833106995},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8539999723434448},{"id":"https://openalex.org/keywords/protein-expression-systems","display_name":"protein expression systems","score":0.4320000112056732},{"id":"https://openalex.org/keywords/escherichia-coli-bl21-de3","display_name":"Escherichia coli BL21(DE3)","score":0.8610000014305115},{"id":"https://openalex.org/keywords/recombinant-protein-expression","display_name":"recombinant protein expression","score":0.9010000228881836},{"id":"https://openalex.org/keywords/protein-families","display_name":"protein families","score":0.5559999942779541},{"id":"https://openalex.org/keywords/protein-engineering","display_name":"protein engineering","score":0.46299999952316284},{"id":"https://openalex.org/keywords/elution-conditions","display_name":"elution conditions","score":0.5130000114440918},{"id":"https://openalex.org/keywords/buffer-composition","display_name":"buffer composition","score":0.7990000247955322}],"concepts":[{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.7563999891281128},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6491000056266785},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5724999904632568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5608000159263611},{"id":"https://openalex.org/C8985478","wikidata":"https://www.wikidata.org/wiki/Q903485","display_name":"Protein purification","level":2,"score":0.5421000123023987},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3937000036239624},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C6856738","wikidata":"https://www.wikidata.org/wiki/Q331672","display_name":"Protein expression","level":3,"score":0.3747999966144562},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37470000982284546},{"id":"https://openalex.org/C147816474","wikidata":"https://www.wikidata.org/wiki/Q169525","display_name":"Protein engineering","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C183696295","wikidata":"https://www.wikidata.org/wiki/Q2487696","display_name":"Biochemical engineering","level":1,"score":0.34040001034736633},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.3176000118255615},{"id":"https://openalex.org/C80311884","wikidata":"https://www.wikidata.org/wiki/Q7268939","display_name":"Quantitative proteomics","level":4,"score":0.30820000171661377},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C2780430158","wikidata":"https://www.wikidata.org/wiki/Q7685902","display_name":"Target protein","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C73826308","wikidata":"https://www.wikidata.org/wiki/Q684907","display_name":"Elution","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.26.762056","doi":"https://doi.org/10.64898/2026.10.26.762056","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.26.762056","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.26.762056.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:10.64898/2026.10.26.762056","doi":"https://doi.org/10.64898/2026.10.26.762056","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.26.762056","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/30/2026.10.26.762056.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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306082","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332603","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224760869.pdf","grobid_xml":"https://content.openalex.org/works/W7224760869.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2911489562","https://openalex.org/W2936695845","https://openalex.org/W3046375318","https://openalex.org/W3164540570","https://openalex.org/W3186744718","https://openalex.org/W3211951295","https://openalex.org/W4319323476","https://openalex.org/W4385027818","https://openalex.org/W4385572894","https://openalex.org/W4385574224","https://openalex.org/W4387994739","https://openalex.org/W4389519254","https://openalex.org/W4391836235","https://openalex.org/W4392186815","https://openalex.org/W4396723768","https://openalex.org/W4396977542","https://openalex.org/W4398161652","https://openalex.org/W4403230932","https://openalex.org/W4405616956","https://openalex.org/W4406260039","https://openalex.org/W4406634509","https://openalex.org/W4407406911","https://openalex.org/W4407779049","https://openalex.org/W4408345962","https://openalex.org/W4410875995","https://openalex.org/W4411622822","https://openalex.org/W4415400619","https://openalex.org/W4417530433","https://openalex.org/W7119499507","https://openalex.org/W7120088840","https://openalex.org/W7125490172","https://openalex.org/W7133239970","https://openalex.org/W7138303952"],"related_works":["https://openalex.org/W4407779049","https://openalex.org/W4362515160","https://openalex.org/W2404912504","https://openalex.org/W7223159358","https://openalex.org/W1833476499","https://openalex.org/W6941430714","https://openalex.org/W2509757482","https://openalex.org/W2098513388","https://openalex.org/W7214700973","https://openalex.org/W305067754"],"abstract_inverted_index":{"Protein":[0],"purification":[1,26,101,136,168,177,199,247],"is":[2],"a":[3,44,49,63,75,144,172,190,212,253],"fundamental":[4],"step":[5],"for":[6,66,82,105],"analyzing":[7],"individual":[8],"proteins":[9,67,151],"and":[10,13,34,84,96,112,125,132,170,225,234],"protein":[11,25,91,94,135,223],"complexes":[12],"identifying":[14,99],"interactions":[15],"with":[16,68,219,261],"other":[17],"proteins,":[18],"DNA,":[19],"or":[20,155],"RNA.":[21],"A":[22],"variety":[23],"of":[24,62,89,109,134,150,167,175,203,215,228],"strategies":[27,200],"exist":[28],"to":[29,197],"address":[30,116],"desired":[31],"scale,":[32],"throughput,":[33],"downstream":[35,246],"applications.":[36],"However,":[37],"selecting":[38],"an":[39,122],"effective":[40,100],"experimental":[41,187],"procedure":[42],"remains":[43,103],"largely":[45],"empirical":[46],"process":[47],"that":[48,127,256],"quick":[50],"literature":[51,140],"review":[52],"can":[53],"help":[54],"guide.":[55],"Researchers":[56],"typically":[57],"survey":[58],"on":[59,74,164],"the":[60,87,129,165],"order":[61],"dozen":[64],"publications":[65],"similar":[69],"biochemical":[70,264],"properties,":[71],"assessing":[72],"conditions":[73,102,137],"case-by-case":[76],"basis,":[77],"leaving":[78],"no":[79],"systematic":[80],"framework":[81],"comparison":[83],"decision-making":[85],"at":[86,141],"scale":[88],"entire":[90],"families.":[92],"As":[93],"engineering":[95],"design":[97],"evolve,":[98],"critical":[104],"obtaining":[106],"sufficient":[107],"quantities":[108],"properly":[110],"folded":[111],"functional":[113],"proteins.":[114,204],"To":[115],"this":[117],"gap,":[118],"we":[119],"developed":[120],"ProtoPure,":[121],"LLM-based":[123],"workflow":[124,254],"database":[126],"automates":[128],"extraction,":[130],"standardization":[131],"analysis":[133],"from":[138],"peer-reviewed":[139],"scale.":[142],"Given":[143],"user-defined":[145],"UniProt":[146],"table-enabling":[147],"flexible":[148,263],"selection":[149],"by":[152,242],"family,":[153],"organism,":[154],"proteome.":[156],"ProtoPure":[157,193],"retrieves":[158],"associated":[159],"publications,":[160],"classifies":[161],"them":[162],"based":[163],"presence":[166],"protocols,":[169],"extracts":[171],"standardized":[173,258],"set":[174,214],"12":[176],"parameters":[178,248],"(e.g.,":[179],"buffer":[180],"composition,":[181],"elution":[182],"conditions).":[183],"By":[184],"transforming":[185],"dispersed":[186],"descriptions":[188],"into":[189],"structured":[191],"resource,":[192],"makes":[194],"it":[195],"possible":[196],"compare":[198],"across":[201],"thousands":[202],"The":[205],"resulting":[206],"dataset":[207],"revealed":[208],"quantitative":[209],"convergence":[210],"toward":[211],"limited":[213],"recombinant":[216],"expression":[217,229,259],"practices,":[218],"BL21(DE3)-based":[220],"systems":[221],"dominating":[222],"production":[224],"recurrent":[226],"combinations":[227],"host,":[230],"inducer,":[231],"growth":[232],"medium,":[233],"plasmid":[235],"occurring":[236],"substantially":[237],"more":[238,262],"frequently":[239],"than":[240],"expected":[241],"chance.":[243],"In":[244],"contrast,":[245],"exhibited":[249],"greater":[250],"diversity,":[251],"revealing":[252],"architecture":[255],"combines":[257],"infrastructure":[260],"components.":[265]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-31T00:00:00"}
