使用基于残留的物理化学性质景观的生成β-hairpin设计
Vardhan Satalkar1, Gemechis D Degaga2, Wei Li1
1School of Biological Sciences, Georgia Institute of Technology, Atlanta, Georgia.
Biophysical journal
|February 1, 2024
概括
这项研究引入了一种新的生成对抗网络,用于新的酸设计,创建独特的酸序列,将其折叠成特定的β-hairpin结构. 这种方法利用物理化学特性在蛋白质序列生成中超越进化约束.
科学领域:
- 计算生物学是一种计算生物学.
- 生物物理学的生物物理.
- 机器学习在药物发现中的作用
背景情况:
- 在生物和生物医学应用中,新的设计至关重要.
- 现有的方法通常依赖于序列同质性,限制新性,忽视蛋白质折叠的基本物理化学性质.
- 生成型机器学习提供了一条超越进化约束的创建独特序的途径.
研究的目的:
- 开发和评估一个定制的生成对抗网络 (GAN),用于设计新序列.
- 专门针对能够折叠成β-hairpin二次结构的的设计.
- 为生成模型奠定基础,这些模型将体设计的物理化学和结构性质纳入.
主要方法:
- 开发了一种定制的生成对抗网络 (beta-GAN),适用于序列生成.
- 含有氨基酸的物理化学性质 (例如,疏水性,残留量) 和构造特征.
- 使用来自蛋白质数据库 (PDB) 的结构特定序列数据进行培训.
- 评估了模型区分β-hairpin结构与α-helix和内在无序的能力.
主要成果:
- β-GAN在区分β-hairpin结构与其他次要结构方面达到高达96%的准确性.
- 产生了具有低序列身份的人工β-hairpin序列 (31%与PDB相比,50%与非冗余数据库相比).
- 证明了模型能够产生与现有数据库不同的新序列的能力.
结论:
- 基于物理化学和构造性质的生成模型显示出对新设计的巨大潜力.
- 这种方法可以将序列到结构的景观扩展到进化局限之外.
- 开发的β-GAN为未来设计具有特定结构和功能性质的的进步提供了基础.
更多相关视频
07:08Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
7.3K
06:50Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
Published on: January 26, 2024
1.8K
相关概念视频
01:49Conserved Binding Sites
4.2K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.2K
02:18Fischer Projections
13.2K
Learning to draw Fischer projections of molecules and understanding their relevance plays a crucial role in the visual depiction of organic molecules. A Fischer projection is a two-dimensional projection on a planar surface to simplify the three-dimensional wedge–dash representation of molecules. This is especially helpful in the case of molecules with multiple chiral centers that can be difficult to draw. Here, all the bonds of interest are represented as horizontal or vertical lines.
13.2K