Work

Unifying sequence-structure coding for advanced protein engineering via a multimodal diffusion transformer

Year: 2025

Type: article

Abstract: This study introduces ProTokens, machine-learned “amino acids” for protein structure representation, and PT-DiT, a multimodal diffusion transformer for unified sequence–structure modeling, design, and evolution.

Source: Chemical Science

DOI: 10.1039/d5sc02055g

Authors: Xiaohan Lin, Zhenyu Chen, Yanheng Li, Zicheng Ma, Chuanliu Fan, Ziqiang Cao, Shihao Feng, Jun Zhang, Yi Qin Gao

Institutions: Peking University, Beijing National Laboratory for Molecular Sciences, Changping Laboratory, Soochow University

Language: English

Topic: Protein Structure and Dynamics

Subfield: Molecular Biology

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: diamond

Funders: National Natural Science Foundation of China, National Science and Technology Major Project, National Cancer Institute

Awards: G4243641284, G4775812314, G5292414797, G543380124, 细胞发育、分化和疾病发生过程中的染色质相分离与基因调控机制研究

OpenAlex ID: W4410409254

FWCI: 0.756

Cites: 61

Cited by: 3

Related to: 10