优点:准确预测多联体结合残留物与混合深度变压器网络,进化合和转移学习
Jian Zhang1, Sushmita Basu2, Fuhao Zhang3
1School of Computer and Information Technology, Xinyang Normal University, Xinyang 464000, China; Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324003, China.
MERIT是一种新的深度学习工具,可以直接预测多连接体结合残留物 (MLBRs). 它的性能优于现有的方法,提供了准确的预测,并减少了疾病目标识别的错误阳性.
科学领域:
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
- 分子生物学分子生物学
背景情况:
- 多联体结合残留物 (MLBRs) 是关键的氨基酸,与多种联体相互作用,在细胞功能和疾病中发挥作用.
- 目前用于MLBR识别的方法是间接的,依赖于组合特定连接体类型的预测因子.
- 需要直接预测方法来准确识别MLBR.
研究的目的:
- 概念化,设计,评估和发布MERIT (多约束余额 pRedIcTor),这是一个用于直接MLBR预测的新工具.
- 开发一个具有创新功能的深度神经网络,以提高MLBR的预测性能.
- 为 MLBR 预测提供免费访问的 Web 服务器和数据集.
主要方法:
- 开发了一种定制深度神经网络,具有多层架构,变压器模块和定制损失函数.
- 整合进化合和转移学习以提高预测准确度.
- 通过除分析评估MERIT,并将其性能与现有的联体特异性和元预测器进行比较.
主要成果:
- MERIT显示出优异的预测性能,显著优于其他方法.
- 该工具有效减少交叉预测,这是识别真正的MLBR的一个关键指标.
- 在独立的测试数据集上,MERIT 始终实现低虚假阳性率.
结论:
- MERIT代表了多连接体结合残留物直接预测的重大进步.
- 该工具提供准确可靠的MLBR识别,帮助研究细胞功能和疾病.
- MERIT 网络服务器和相关数据集是公开可用的,这有助于更广泛的科学应用.
更多相关视频
10:21Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
Published on: February 23, 2024
07:08Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
相关概念视频
Conserved Binding Sites
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...
Ligand Binding Sites
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Protein-protein Interfaces
Ligand Binding and Linkage
Improving Translational Accuracy
Cooperative Allosteric Transitions
