GROQ-seq Function Measurements for TEV Protease ML Libraries

Fuente: Zenodo
Guardado en:
Detalles Bibliográficos
Autores principales: Spinner, Aviv, Notin, Pascal, Berry, Sam, Cortade, Dana, Sisson, Zach, Ikonomova, Svetlana P., Ross, David, Marks, Debbie
Formato: Recurso digital
Publicado: Zenodo 2026
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866902274078408704
author Spinner, Aviv
Notin, Pascal
Berry, Sam
Cortade, Dana
Sisson, Zach
Ikonomova, Svetlana P.
Ross, David
Marks, Debbie
author_facet Spinner, Aviv
Notin, Pascal
Berry, Sam
Cortade, Dana
Sisson, Zach
Ikonomova, Svetlana P.
Ross, David
Marks, Debbie
contents <p>This dataset contains GROQ-seq functional measurements of an ML-designed TEV protease variant library generated by seven generative protein-design models — PSSM, Potts/EVCouplings, EVE, ESM2, Tranception, ESM-IF1, and ProteinMPNN — under a unified Gibbs-sampling framework, alongside an error-prone PCR (epPCR) baseline. Variants are organized into three section libraries (residues 1–78, 79–157, 158–236) and a fully combinatorial library, each filtered for a complete catalytic triad and ≤10 mutations from wild type. Fitness is measured via the same split-DHFR system as the TEV protease pilot across 24 experimental conditions independently varying TEV expression, split-DHFR expression, and trimethoprim selection.</p> <p>This run of the assay was performed at the Living Measurements Systems Foundry (LMSF) at the National Institute of Standards and Technology, alongside the TEV protease pilot. Part of a broader effort to benchmark generative protein-design models against experimental enzyme function — providing a standardized evaluation framework for sequence-, language-, and structure-based approaches and informing model selection for protein engineering.      </p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19926162
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle GROQ-seq Function Measurements for TEV Protease ML Libraries
Spinner, Aviv
Notin, Pascal
Berry, Sam
Cortade, Dana
Sisson, Zach
Ikonomova, Svetlana P.
Ross, David
Marks, Debbie
<p>This dataset contains GROQ-seq functional measurements of an ML-designed TEV protease variant library generated by seven generative protein-design models — PSSM, Potts/EVCouplings, EVE, ESM2, Tranception, ESM-IF1, and ProteinMPNN — under a unified Gibbs-sampling framework, alongside an error-prone PCR (epPCR) baseline. Variants are organized into three section libraries (residues 1–78, 79–157, 158–236) and a fully combinatorial library, each filtered for a complete catalytic triad and ≤10 mutations from wild type. Fitness is measured via the same split-DHFR system as the TEV protease pilot across 24 experimental conditions independently varying TEV expression, split-DHFR expression, and trimethoprim selection.</p> <p>This run of the assay was performed at the Living Measurements Systems Foundry (LMSF) at the National Institute of Standards and Technology, alongside the TEV protease pilot. Part of a broader effort to benchmark generative protein-design models against experimental enzyme function — providing a standardized evaluation framework for sequence-, language-, and structure-based approaches and informing model selection for protein engineering.      </p>
title GROQ-seq Function Measurements for TEV Protease ML Libraries
url https://doi.org/10.5281/zenodo.19926162