Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 29 min ago
Peer-reviewedCC BY-NC-NDnpj Drug Discovery.

Generative AI for controllable protein sequence design: A survey

  • Yiheng Zhu1
  • Zitai Kong2
  • Jialu Wu3,4,5,6
  • Mingze Yin2
  • Weize Liu7
  • Yuqiang Han2
  • Hongxia Xu8
  • Chang‐Yu Hsieh9,10
  • Tingjun Hou11,12
  • Jian Wu3,4,5,6
12 affiliations
  1. 1Zhongguancun Academy, Beijing, China
  2. 2Zhejiang University, College of Computer Science and Technology, Hangzhou, China
  3. 3State Key Laboratory of Transvascular Implantation Devices and TIDRI, Hangzhou, China. [email protected]
  4. 4Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence, Hangzhou, China. [email protected]
  5. 5Zhejiang University School of Medicine, The Second Affiliated Hospital and Liangzhu Laboratory, Hangzhou, China. [email protected]
  6. 6Zhejiang University, College of Pharmaceutical Sciences, Hangzhou, China
  7. 7Zhejiang University, Polytechnic Institute, Hangzhou, China
  8. 8Zhejiang University School of Medicine, The Second Affiliated Hospital and Liangzhu Laboratory, Hangzhou, China
  9. 9Zhejiang Provincial Key Laboratory for Intelligent Drug Discovery and Development, Jinhua, China. [email protected]
  10. 10Zhejiang University, College of Pharmaceutical Sciences, Hangzhou, China. [email protected]
  11. 11Zhejiang Provincial Key Laboratory for Intelligent Drug Discovery and Development, Jinhua, China. [email protected]
  12. 12Zhejiang University, College of Pharmaceutical Sciences, Hangzhou, China. [email protected]
Open at sourcePDFDOICite

Abstract

The design of novel protein sequences with targeted functionalities underpins a central theme in protein engineering, impacting diverse fields such as drug discovery and enzymatic engineering. However, navigating this vast combinatorial search space remains a severe challenge due to time and financial constraints. This scenario is rapidly evolving as the transformative advancements in AI have been propelling the protein design field into a new era. In this survey, we systematically review recent advances in generative AI for controllable protein sequence design. To set the stage, we first outline the foundational tasks in protein sequence design in terms of the constraints involved and present key generative models and optimization algorithms. We then offer in-depth reviews of each design task and discuss the in silico evaluation approaches and pertinent applications. Finally, we identify the unresolved challenges and highlight research opportunities that merit deeper exploration.

Related

  1. A Generative Neuro‐Symbolic AI for Protein Sequence Design
    Marianne Defresne, Delphine Dessaux, Samuel Buchet +10
    Advanced SciencePeer-reviewedCC BY 4.0Full text1 citedMolecular biology & gene regulationHAL
  2. EquiDesign: a versatile computational framework for de novo protein sequence design.
    Qiang Gao, Zhongyu Xu, Kai Chen +4
    Briefings in bioinformaticsPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  3. Joint protein, mRNA and DNA sequence design and optimization with nucleotide-level Potts models
    B. Banaszewski, L. J. Dornfeld, D. Chen +2
    bioRxivPreprintCC BYFull textBiophysicsbioRxiv
  4. Comparative Conformational Sampling of Apo Adenylate Kinase by Enhanced Molecular Dynamics and a Sequence-Based Generative Ensemble Model
    Qingling Zhao, Ting Cui, Ying Li
    MoleculesPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationCrossrefEurope PMC
  5. Representation learning for low-data protein fitness prediction using sequence–structure embeddings and graph neural networks
    Chanoknun Phunnasorn, Narupat Hongdilokkul, Wasakorn Laesanklang +2
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref

Cite

BibTeXRIS
BibTeX
@article{zhu2026generative,
  title = {{Generative AI for controllable protein sequence design: A survey}},
  author = {Yiheng Zhu and Zitai Kong and Jialu Wu and Mingze Yin and Weize Liu and Yuqiang Han and Hongxia Xu and Chang‐Yu Hsieh and Tingjun Hou and Jian Wu},
  journal = {npj Drug Discovery.},
  year = {2026},
  month = jul,
  doi = {10.1038/s44386-026-00054-5},
  url = {https://doi.org/10.1038/s44386-026-00054-5},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - Generative AI for controllable protein sequence design: A survey
AU  - Yiheng Zhu
AU  - Zitai Kong
AU  - Jialu Wu
AU  - Mingze Yin
AU  - Weize Liu
AU  - Yuqiang Han
AU  - Hongxia Xu
AU  - Chang‐Yu Hsieh
AU  - Tingjun Hou
AU  - Jian Wu
PY  - 2026
DA  - 2026/07/03
JO  - npj Drug Discovery.
DO  - 10.1038/s44386-026-00054-5
UR  - https://doi.org/10.1038/s44386-026-00054-5
AB  - The design of novel protein sequences with targeted functionalities underpins a central theme in protein engineering, impacting diverse fields such as drug discovery and enzymatic engineering. However, navigating this vast combinatorial search space remains a severe challenge due to time and financial constraints. This scenario is rapidly evolving as the transformative advancements in AI have been propelling the protein design field into a new era. In this survey, we systematically review recent advances in generative AI for controllable protein sequence design. To set the stage, we first outline the foundational tasks in protein sequence design in terms of the constraints involved and present key generative models and optimization algorithms. We then offer in-depth reviews of each design task and discuss the in silico evaluation approaches and pertinent applications. Finally, we identify the unresolved challenges and highlight research opportunities that merit deeper exploration.
SN  - 3005-1452
ER  -