MF-ProtDisMap:蛋白质实值距离预测与序列和共同进化的特征的融合
Yufei Zhang1, Suyang Zhong2, Shenghui Xu3
1College of Information Science and Engineering, Shandong Agricultural University, Tai'an, Shandong, China; State Key Laboratory of Wheat Improvement, College of Agronomy, Shandong Agricultural University, Tai'an, Shandong, China.
本研究介绍了MF-ProtDisMap,这是一种新的框架,集成了多个功能,用于准确的蛋白质距离预测. 这种方法通过结合共同进化和基于序列的特征来增强蛋白质结构建模,以获得卓越的结果.
科学领域:
- 计算生物学 计算生物学
- 结构生物信息学 结构生物信息学
- 机器学习在生物学中的应用
背景情况:
- 精确的蛋白质间残留距离估计对于蛋白质结构建模至关重要.
- 目前的方法依赖于多重序列对齐 (MSA) 衍生的共同进化特征或基于语言模型的序列特征.
- 整合不同的特征类型可能会提高预测准确性.
研究的目的:
- 开发一个整合性框架,MF-ProtDisMap (多特征蛋白质距离图),用于优异的实值蛋白质距离预测.
- 为了有效地结合来自不同来源的共同进化和序列级特征.
- 为了增强表示学习和降低计算成本.
主要方法:
- 利用MSA变压器从蛋白质多个序列对齐中提取共同进化的特征.
- 采用ESM2来捕捉远程交互和序列级特征.
- 实施了小组聚合以减少维度,并引入了Diff-former (具有三角注意力的扩散模型) 以增强表示学习.
主要成果:
- 对于实值距离预测,MF-ProtDisMap实现了2.20 Å的平均绝对误差 (MAE) 和3.40 Å的根平均平方误差 (RMSE).
- 将预测距离转换为接触预测,获得ROC为84.56%和PR为81.01%.
- 与现有的最先进的实值蛋白质距离预测方法相比,表现出卓越的性能.
结论:
- MF-ProtDisMap有效地整合了多功能信息,用于增强蛋白质距离预测.
- 开发的框架在计算蛋白质结构建模方面取得了重大进展.
- 这种方法有望提高预测蛋白质结构的准确性和效率.
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
16:02Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation
Published on: February 10, 2023
相关概念视频
Multi-species Conserved Sequences
Although the genome of each species varies greatly from each other, a few sequences are highly conserved. Such conserved...
Evolutionary Relationships through Genome Comparisons
Per-Unit Sequence Models
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
Conservation of Protein Domains Over Different Proteins
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
Distance Problem
RNA-seq
Before the discovery of RNA-seq, microarray-based methods and Sanger sequencing were used for transcriptome analysis. However, while...
