EUVIMEDOpdag EUVIMED
Crossref

DeepUSPS : Deep Learning‐Empowered Unconstrained‐Structural Protein Sequence Design

Zhichong Ma iD, Jiawen Yang iD

Proteins: Structure, Function, and Bioinformatics · 2025

DOI: 10.1002/prot.26847 ↗

At a glance

Journal article in Proteins: Structure, Function, and Bioinformatics, 2025. Written by Zhichong Ma and 1 co-authors. Institution: College of Publishing, University of Shanghai for Science and Technology, Shanghai, China. Major MEDLINE topics: Deep Learning, Proteins, Protein Engineering. 75 references.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Currently, the unconstrained‐structural protein sequence design models suffer from low optimization efficiency, and their generated proteins exhibit significant similarities to natural proteins and low thermal stability. To address these challenges, we propose the Deep Learning‐Empowered Unconstrained‐Structural Protein Sequence Design (DeepUSPS) model. To effectively address the inadequate thermal stability problem, we employ the innovative Inverted Dense Residual Network (IDRNet). To mitigate the designed proteins similarity issue, the Sequence‐Pairwise Features Extraction Synthetic Network (SPFESN) is constructed. Furthermore, we introduce the Warm Restart AngularGrad (WRA) optimizer to optimize the 3D Position‐Specific Scoring Matrix ( 3Dpssm ) for unconstrained‐structural protein sequence, only involving 2100 iterations (140.36 min) updates to generate idealization (IDE) protein sequences. We obtained a total of 1000 IDE protein sequences. Then we utilized in silico experiments to evaluate them, including similarity, clarity and iterations, thermal stability, spatial distribution of similarity, and predicted local‐distance difference test (pLDDT) confidence assessment. Notably, the mean lg( E ‐value) for IDE protein sequences reached −0.051, the mean TM‐score for IDE protein structures reached 0.594, the iterations only need 2100, and the mean Tm (melting point) for thermal stability reached 74.78°C. The average pLDDT value for 3D structures reached 76. Additionally, the IDE proteins' 3D structures exhibit diverse types. These in silico results conclusively demonstrate the superior performance of DeepUSPS compared with Hallucinate.

Subjects

MeSH terms (MEDLINE)

Deep LearningProteinsProtein EngineeringAmino Acid SequenceModels, MolecularProtein ConformationProtein StabilityAlgorithmsComputational BiologyDatabases, ProteinPosition-Specific Scoring MatricesComputer SimulationSequence Analysis, Protein

Author keywords

deep learninginverted dense residual network (IDRNet)protein designprotein sequencessequence‐pairwise features extraction synthetic network (SPFESN)warm restart gradient descent method‐warm restart angularGrad (WRA)

Substances

Proteins

Authors and institutions

  • College of Publishing, University of Shanghai for Science and Technology, Shanghai, China.

ORCID profiles: Zhichong Ma, Jiawen Yang

Cite

APA

Ma, Z., & Yang, J. (2025). DeepUSPS : Deep Learning‐Empowered Unconstrained‐Structural Protein Sequence Design. Proteins: Structure, Function, and Bioinformatics. https://doi.org/10.1002/prot.26847

Vancouver

Ma Z, Yang J. DeepUSPS : Deep Learning‐Empowered Unconstrained‐Structural Protein Sequence Design. Proteins: Structure, Function, and Bioinformatics. 2025. doi:10.1002/prot.26847

BibTeX
@article{Ma2025,
  author = {Ma, Zhichong and Yang, Jiawen},
  title = {DeepUSPS : Deep Learning‐Empowered Unconstrained‐Structural Protein Sequence Design},
  journal = {Proteins: Structure, Function, and Bioinformatics},
  year = {2025},
  doi = {10.1002/prot.26847}
}
Start for free →