2026-10-15T07:32:10Z https://www.scidb.cn/oai

10.57760/sciencedb.32910 2026-05-06T11:22:32Z

2026-05-06 HelixSeed: An α-Helical Seed Resource for MaSIF-Seed-Driven de novo Binder Design doi:10.57760/sciencedb.32910 en HelixSeed is a core resource library tailored specifically for molecular surface interaction fingerprinting (MaSIF)-based de novo protein binder design. This dataset comprehensively integrates nearly 400,000 α-helical fragments from multiple mammalian species, constituting an ultra-large-scale candidate seed library with exceptional biological diversity. It provides an immensely broad structural search space for protein binders design.The greatest advantage of this database lies in its out-of-the-box, pre-computed nature. The molecular surface meshes and complex physicochemical feature fingerprints for all fragments in the library have been standardized and pre-computed in advance. This resolves the long-standing bottleneck of lacking a publicly available seed library in surface-driven protein design workflows. Researchers no longer need to expend massive computational resources and extensive time on underlying data cleaning and feature extraction. These highly standardized data can be seamlessly fed directly into the core MaSIF-seed algorithm, allowing teams to bypass tedious preparatory work and proceed directly to the core stages of de novo protein binder design and drug development.Furthermore, the reliability and potential of HelixSeed have been fully validated. Through rigorous comparative testing against existing resources and experimental validation of downstream designs, the binders retrieved and generated based on this library have demonstrated extremely high interface matching, complementarity, and structural stability. This directly proves that HelixSeed holds significant practical application value and immense translational prospects in the field of drug discovery. de novo binder design; computational protein design; geometric deep learning; MaSIF; AlphaFold Protein Structure Database; Protein Data Bank Fukang Ge Linjie Zhang Jinhao Bi Yingying Zhu EMBARGO https://creativecommons.org/licenses/by-nc-nd/4.0/ dataset Science Data Bank