EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

Evaluating zero‐shot prediction of monomeric protein design success by AlphaFold , ESMFold , and ProteinMPNN

Mario Garcia iD, Sugyan M Dixit, Gabriel J Rocklin

Protein Science · 2026-02 · 35 (2)

DOI: 10.1002/pro.70453 ↗

At a glance

Journal article in Protein Science, published online on 2026-01-20. Written by Mario Garcia and 2 co-authors. Institution: Department of Pharmacology & Center for Synthetic Biology, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA. Major MEDLINE topics: Proteins, Protein Engineering. Cited 22 times so far (Crossref); 37 references. The full text is freely available (open access, CC BY 4.0). Funded by: NIGMS NIH HHS, National Institutes of Health (NIH) Director's New Innovator Award, Northwestern Molecular Biophysics Training Program.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

De novo protein design has enabled the creation of proteins with diverse functionalities that are not found in nature. Despite recent advances, experimental success rates remain inconsistent and context‐dependent, posing a bottleneck for broader applications of de novo design. To overcome this, structure and sequence prediction models have been applied to assess design quality prior to experimental testing to save time and resources. In this study, we examined the extent to which AlphaFold, Protein MPNN, and ESMFold can discriminate between experimentally successful and unsuccessful designs. We first curated a benchmark dataset of 614 experimentally characterized de novo designed monomers from 11 different design studies between 2012 and 2021. All predictive models demonstrated moderate ability to discriminate experimental successes (expressed, soluble, monomeric, and fold with the correct secondary structure) from failures. Still, many failed designs have better confidence metrics than successful designs, and confidence metrics were topology‐dependent. Among all computational models evaluated, ESMFold average predicted local‐distance difference test (pLDDT) yielded the best individual performance at distinguishing between successful and unsuccessful designs. A logistic regression model combining all confidence metrics provided only modest improvement over ESMFold pLDDT alone. Overall, these results show that these models can serve as an initial filtering strategy prior to experimental validation; however, their utility at accurately predicting experimentally successful designs remains limited without task‐specific training.

Subjects

MeSH terms (MEDLINE)

ProteinsProtein EngineeringModels, MolecularPrediction AlgorithmsProtein FoldingAlgorithmsProtein Structure, SecondaryComputational Biology

Author keywords

de novo protein designprotein biophysicssequence predictionstructure prediction

Substances

Proteins

Authors and institutions

  • Department of Pharmacology & Center for Synthetic Biology, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA.
  • Robert H. Lurie Comprehensive Cancer Center, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA.

ORCID profiles: Mario Garcia

Funding

  • NIGMS NIH HHS
  • National Institutes of Health (NIH) Director's New Innovator Award
  • Northwestern Molecular Biophysics Training Program

Cite

APA

Garcia, M., Dixit, S. M., & Rocklin, G. J. (2026). Evaluating zero‐shot prediction of monomeric protein design success by AlphaFold , ESMFold , and ProteinMPNN. Protein Science, 35(2). https://doi.org/10.1002/pro.70453

Vancouver

Garcia M, Dixit SM, Rocklin GJ. Evaluating zero‐shot prediction of monomeric protein design success by AlphaFold , ESMFold , and ProteinMPNN. Protein Science. 2026;35(2). doi:10.1002/pro.70453

BibTeX
@article{Garcia2026,
  author = {Garcia, Mario and Dixit, Sugyan M and Rocklin, Gabriel J},
  title = {Evaluating zero‐shot prediction of monomeric protein design success by AlphaFold , ESMFold , and ProteinMPNN},
  journal = {Protein Science},
  year = {2026},
  volume = {35},
  number = {2},
  doi = {10.1002/pro.70453}
}
Start for free →