相关实验视频

Updated: Jun 7, 2025

JUMPn: A Streamlined Application for Protein Co-Expression Clustering and Network Analysis in Proteomics

JUMPn: A Streamlined Application for Protein Co-Expression Clustering and Network Analysis in Proteomics

Published on: October 19, 2021

AAclust:为选择冗余减少的氨基酸尺度集的k优化聚类

Stephan Breimann^1,2,3, Dmitrij Frishman¹

¹Department of Bioinformatics, School of Life Sciences, Technical University of Munich (TUM), Freising, 85354, Germany.

Bioinformatics advances

|November 15, 2024

概括

AAclust是一种选择氨基酸尺度用于蛋白质预测的新方法. 它优化了功能工程,改善了各种数据集的机器学习模型性能.

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
机器学习机器学习

背景情况:

氨基酸尺度对于基于序列的蛋白质预测至关重要.
现有的方法缺乏黄金标准尺度或简单的选择方法.

研究的目的:

为蛋白质预测开发一种优化氨基酸尺度选择的方法.
改进机器学习应用中的功能工程.

主要方法:

开发了AAclust,这是一个用于集群模型 (例如,k-means) 的包装.
AAclust通过集群和选择代表性尺度来生成冗余减少的尺度集.
优化或用户定义的集群号 (k) 用于尺度选择.

主要成果:

在24个蛋白质基准数据集上使用机器学习评估AAclust.
性能最高的尺度集因数据集而异,并且表现优于之前的研究.
模型性能显示强烈依赖于尺度设置大小.

结论:

AAclust能够系统地优化基于规模的特征工程.
该方法提高了基于序列的蛋白质预测模型的性能.

更多相关视频

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Published on: July 14, 2015

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Protein WISDOM: A Workbench for In silico De novo Design of BioMolecules

Published on: July 25, 2013

相关概念视频

Conserved Binding Sites

Conserved Binding Sites

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...