从信号到交响乐:探索用于蛋白质功能预测的二维序列表示
Yiquan Wang1,2, Minnuo Cai1, Yuhua Dong3
1Xinjiang Key Laboratory of Biological Resources and Genetic Engineering, College of Life Science and Technology, Xinjiang University, Urumqi 830049 Xinjiang, China.
Journal of chemical information and modeling
|November 17, 2025
概括
蛋白质声化,即将氨基酸序列转换为光谱图,显示出预测蛋白质功能的前景. 这种新型的表示,特别是它的结构,在生物学序列分析中显著帮助深度学习模型.
科学领域:
- 计算生物学 计算生物学
- 生物信息学是一种生物信息学.
- 机器学习 机器学习
背景情况:
- 从初级序列预测蛋白质功能至关重要,但具有挑战性.
- 对深度学习的生物序列数据的最佳表示是一个开放的问题.
- 深度学习模型已经取得了成功,但需要有效的数据表示.
研究的目的:
- 探索蛋白质声化 (氨基酸序列到二维光谱) 作为预测蛋白质功能的新型数据表示.
- 开发和评估一个基准数据集和模型来评估 sonification 的有效性.
- 调查代表性结构与生物物理信息的贡献.
主要方法:
- 在12个类别中开发了一套18000个蛋白质序列的基准数据集.
- 实施和评估使用蛋白质声化谱图的深度学习模型.
- 对视觉,声学和生物物理信息的特征进行了废除研究.
- 与标准变压器架构 (ESM-2,ProtBERT) 和外部基准 (CARE) 进行性能比较.
- 利用由声化编码指导的扩散模型用于新型蛋白质变异生成.
主要成果:
- 作为2D谱图表示的蛋白质声化显著改善了预测性能.
- 废弃研究证实了谱图的结构转变和特征的重要性.
- 一个没有明确生物物理意义的模型达到81.08%的准确率;一个生物物理信息的模型达到84.00%.
- 在 sonification 数据上训练的聚变模型的性能与 ESM-2 和 ProtBERT 相比或更好.
- 在外部CARE酶分类基准上获得了90.44%的准确性.
- 通过声化引导的扩散模型来产生新型蛋白质变体的概念证明.
结论:
- 蛋白质声化谱图的结构表示是提高预测性能的关键因素.
- 蛋白质声化为生物序列分析和特征工程提供了一种数据高效和有效的方法.
- 这种方法显示了概括和指导新型蛋白质变体设计的潜力.
相关概念视频
Protein Families
16.6K
Protein families are groups of homologous proteins; that is, they have similarities in amino acid sequences and three-dimensional structures. Protein families usually occur because of gene duplication, where an additional copy of a gene is inserted into the genome of an organism. Mutations that change the amino acids but still allow the protein to be properly synthesized, will lead to new protein family members. If these new proteins contain similar amino acids in key...
16.6K
Protein Families
4.2K
4.2K
Conservation of Protein Domains Over Different Proteins
14.0K
Protein domains are small structurally independent units that are part of a single amino acid chain. Although these domains are often structurally independent, they may rely on synergistic effects to perform their functions as part of a larger protein. Protein domains may be conserved within the same organism, as well as across different organisms.
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
14.0K
Protein Organization
9.0K
Proteins are polymers of amino acid residues. They are versatile and responsible for different cellular functions, including DNA replication, molecular transport, catalysis, and structural support. Proteins have a hierarchical structure comprising at least three levels of organization: primary, secondary, and tertiary structure. Some large proteins have a quaternary structure where individual protein subunits are linked together.
The primary structure of a protein is its amino acid sequence....
The primary structure of a protein is its amino acid sequence....
9.0K
Protein Organization
155.6K
Overview
155.6K
Conserved Binding Sites
5.0K
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...
5.0K


