预测MetaCyc知识库中注释的代谢物的途径参与
Erik D Huckvale1, Hunter N B Moseley2,3,4,5,6
1Markey Cancer Center, University of Kentucky, Lexington, KY, USA.
BMC bioinformatics
|January 6, 2026
概括
机器学习模型有效地使用MetaCyc数据库预测生化路径,实现与KEGG可比的性能. 这增强了生物研究中的代谢物解释.
科学领域:
- 生物化学 生物化学
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
背景情况:
- 代谢物与生化途径的关联对于解释分子数据至关重要.
- 路径注释通常稀疏,限制了数据的实用性.
- 以前的机器学习模型使用京都基因和基因组百科全书 (KEGG) 预测了路径关联.
研究的目的:
- 用MetaCyc数据库评估机器学习模型的性能,以预测使用MetaCyc数据库的代谢途径关联.
- 将基于MetaCyc的预测与KEGG的预测进行比较.
- 评估MetaCyc对通路层次解释的有用性.
主要方法:
- 经过训练和评估的多层感知子模型.
- 使用了MetaCyc数据库中的化合物条目和路径注释.
- 将性能指标 (马修斯相关系数) 与在KEGG数据上训练的模型进行比较.
主要成果:
- 在MetaCyc上训练的模型获得了0.845 (±0.0101) 的平均MCC.
- 在KEGG上训练的模型获得了0.847 (±0.0098) 的平均MCC.
- 与KEGG的仅代谢途径相比,MetaCyc在代谢途径预测性能上显示了>5.6%的改善.
结论:
- 机器学习模型在使用MetaCyc和KEGG的路径预测方面表现相似.
- MetaCyc提供了一套更全面的路径定义,用于预测.
- 这些发现支持MetaCyc有效地用于代谢途径关联预测.
相关概念视频
Introduction to Metabolism
2.6K
Metabolism encompasses all biochemical reactions in a living organism, facilitating both the breakdown and synthesis of biomolecules. These metabolic processes are categorized into catabolic and anabolic pathways, which operate in a coordinated manner to ensure energy balance and cellular function.Catabolic Pathways and Energy ReleaseCatabolic pathways involve the breakdown of complex macromolecules such as carbohydrates, lipids, and proteins into smaller structures like monosaccharides, fatty...
2.6K
Amino Acid Biosynthetic Pathways
1.1K
Amino acid biosynthesis is essential for cell growth, protein synthesis, and metabolic regulation. Cells generate essential and non-essential amino acids from metabolic intermediates to sustain vital biological functions. These intermediates originate from key metabolic pathways: glycolysis, the tricarboxylic acid (TCA) cycle, and the pentose phosphate pathway. Important precursors include α-ketoglutarate, pyruvate, oxaloacetate, phosphoenolpyruvate, and erythrose-4-phosphate, which...
1.1K
Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
Primary Active Transport
13.5K
In contrast to passive transport, active transport involves a substance being moved through membranes in a direction against its concentration or electrochemical gradient. There are two types of active transport: primary active transport and secondary active transport. Primary active transport utilizes chemical energy from ATP to drive protein pumps embedded in the cell membrane. With energy from ATP, the pumps transport ions against their electrochemical gradients—a direction they would...
13.5K


