SnapKin:一个快照深度学习组合,用于从蛋白质组学数据中对激酶基质进行预测
Di Xiao1, Michael Lin2, Chunlei Liu1
1Computational Systems Biology Group, Children's Medical Research Institute, The University of Sydney, Westmead, NSW 2145, Australia.
NAR genomics and bioinformatics
|November 13, 2023
概括
预测酶基质对于理解细胞信号来说至关重要. 这项研究介绍了SnapKin,这是一种先进的深度学习方法,可以显著提高使用蛋白质组学数据的酶基质预测准确性.
科学领域:
- 生物化学 生化学
- 计算生物学 计算生物学
- 基因组学就是基因组学.
背景情况:
- 鉴定酶基质是蛋白质组学中的一个关键挑战.
- 目前的方法受限于少量的验证基板和噪音数据.
- 机器学习为预测酶-基质相互作用提供了一个有前途的途径.
研究的目的:
- 开发先进的机器学习方法,以改善激酶基质预测.
- 为了应对小样本大小和高数据噪声在蛋白质组学数据集中的局限性.
- 引入一种新的集体深度学习模型,用于强大的酶基质识别.
主要方法:
- 利用了七个大型的蛋白组学数据集.
- 采用传统和深度学习模型.
- 实施了一种"伪积极"的学习策略,以处理小样本.
- 应用了基于数据重新采样的集体学习策略,以提高稳定性和预测性.
- 开发了SnapKin,这是一个集体深度学习模型,集成了这些策略.
主要成果:
- 证明了"伪阳性"学习策略在提高预测性能的有效性.
- 展示了集体学习对提高模型稳定性和预测准确性的实用性.
- 在酶-基质预测任务中,SnapKin始终优于现有的方法.
- 开发的模型免费提供给公众使用.
结论:
- 在计算性激酶基质预测中,SnapKin代表了显著的进步.
- 伪积极学习和整体策略的整合提高了预测的准确性和稳定性.
- 这种方法有助于更深入地了解细胞过程中的酶功能.
相关概念视频
Protein Kinases and Phosphatases
3.8K
3.8K
Amplifying Signals via Enzymatic Cascade
8.5K
When a ligand binds to a cell-surface receptor, the receptor's intracellular domain changes shape, which may either activate its enzyme function or allow its binding to other molecules. The initial signal is amplified by most signal transduction pathways. This means that a single ligand molecule can activate multiple molecules of a downstream target. Proteins that relay a signal are most commonly phosphorylated at one or more sites, activating or inactivating the protein. Kinases catalyze...
8.5K
cAMP-dependent Protein Kinase Pathways
6.4K
Cyclic Adenosine Monophosphate (cAMP) is an essential second messenger that activates protein kinase A (PKA) and regulates various biological processes. A single epinephrine molecule binds to GPCR and activates several heterotrimeric G proteins, each stimulating multiple adenylyl cyclase, amplifying the signal, and synthesizing large numbers of cAMP molecules. Small changes in cAMP concentration affect PKA activity. The binding of four cAMP molecules induces a conformational change in PKA,...
6.4K


