{"id":{"repo_id":"washington","oai_identifier":"oai:digital.lib.washington.edu:1773/55120"},"canonical_url":"https://search.dev.ndltd.org/etd/washington/oai:digital.lib.washington.edu:1773/55120","repository":{"repo_id":"washington","name":"University of Washington","base_url":"https://digital.lib.washington.edu/server/oai/request"},"display":{"title":"Protein Design at Library Scale","abstract":"Recent advances in de novo protein design have made it increasingly feasibleto create proteins with novel functions, driven by rapid progress in both com- putational modeling and high-throughput experimentation. Modern tools can explore vast sequence-structure spaces and evaluate biomolecular interactions, while experimental assays can now screen billions of variants in parallel. Yet, a key limitation remains: our current predictive models still struggle to capture the complex physical and dynamical factors that underlie enzyme function. My the- sis addresses this gap by developing an integrated experimental–computational framework for enzyme design that couples large-scale protein library construc- tion with data-driven model development. I design and test extensive libraries of enzyme variants to both optimize catalytic activity and generate training data for next-generation predictors of protein function. Ultimately, this approach ad- vances our ability to connect sequence, structure, and function.","abstract_html":"Recent advances in de novo protein design have made it increasingly feasibleto create proteins with novel functions, driven by rapid progress in both com- putational modeling and high-throughput experimentation. Modern tools can explore vast sequence-structure spaces and evaluate biomolecular interactions, while experimental assays can now screen billions of variants in parallel. Yet, a key limitation remains: our current predictive models still struggle to capture the complex physical and dynamical factors that underlie enzyme function. My the- sis addresses this gap by developing an integrated experimental–computational framework for enzyme design that couples large-scale protein library construc- tion with data-driven model development. I design and test extensive libraries of enzyme variants to both optimize catalytic activity and generate training data for next-generation predictors of protein function. Ultimately, this approach ad- vances our ability to connect sequence, structure, and function.","abstract_has_math":false,"creators":["Gershon, Jacob"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Baker, David"],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-02-05","date_published":"2026-02-05","updated_at":"2026-07-24T05:58:12Z","subjects":["ai4science","protein","protein design","protein engineering","protein modeling","protein optimization","Biochemistry","Computer science"],"languages":["en_US"],"rights":["none"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1773/55120","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Baker, David"]},{"key":"dc:creator","label":"Author","values":["Gershon, Jacob"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-02-05T19:30:05Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-02-05T19:30:05Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-02-05"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["ai4science","protein","protein design","protein engineering","protein modeling","protein optimization","Biochemistry","Computer science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["none"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["Gershon_washington_0250E_29052.pdf"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1773/55120"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph.D.)--University of Washington, 2025"]},{"key":"dc:description.abstract","label":"Abstract","values":["Recent advances in de novo protein design have made it increasingly feasibleto create proteins with novel functions, driven by rapid progress in both com- putational modeling and high-throughput experimentation. Modern tools can explore vast sequence-structure spaces and evaluate biomolecular interactions, while experimental assays can now screen billions of variants in parallel. Yet, a key limitation remains: our current predictive models still struggle to capture the complex physical and dynamical factors that underlie enzyme function. My the- sis addresses this gap by developing an integrated experimental–computational framework for enzyme design that couples large-scale protein library construc- tion with data-driven model development. I design and test extensive libraries of enzyme variants to both optimize catalytic activity and generate training data for next-generation predictors of protein function. Ultimately, this approach ad- vances our ability to connect sequence, structure, and function."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Protein Design at Library Scale"]}]}],"canonical_facts":{"dc:contributor.advisor":["Baker, David"],"dc:creator":["Gershon, Jacob"],"dc:date.accessioned":["2026-02-05T19:30:05Z"],"dc:date.available":["2026-02-05T19:30:05Z"],"dc:date.issued":["2026-02-05"],"dc:description":["Thesis (Ph.D.)--University of Washington, 2025"],"dc:description.abstract":["Recent advances in de novo protein design have made it increasingly feasibleto create proteins with novel functions, driven by rapid progress in both com- putational modeling and high-throughput experimentation. Modern tools can explore vast sequence-structure spaces and evaluate biomolecular interactions, while experimental assays can now screen billions of variants in parallel. Yet, a key limitation remains: our current predictive models still struggle to capture the complex physical and dynamical factors that underlie enzyme function. My the- sis addresses this gap by developing an integrated experimental–computational framework for enzyme design that couples large-scale protein library construc- tion with data-driven model development. I design and test extensive libraries of enzyme variants to both optimize catalytic activity and generate training data for next-generation predictors of protein function. Ultimately, this approach ad- vances our ability to connect sequence, structure, and function."],"dc:format.mimetype":["application/pdf"],"dc:identifier.other":["Gershon_washington_0250E_29052.pdf"],"dc:identifier.uri":["https://hdl.handle.net/1773/55120"],"dc:language.iso":["en_US"],"dc:rights":["none"],"dc:subject":["ai4science","protein","protein design","protein engineering","protein modeling","protein optimization","Biochemistry","Computer science"],"dc:title":["Protein Design at Library Scale"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T05:58:12Z"}