使用对比学习进行酶功能的预测
Tianhao Yu1,2,3, Haiyang Cui1,2,3, Jianan Canal Li3,4
1Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA.
我们开发了CLEAN, 一个用于精确注释酶功能的机器学习工具. CLEAN 提高了酶量 (EC) 数量的预测,特别是在研究不足或多功能酶方面.
科学领域:
- 生物化学
- 生物信息学
- 计算生物学
背景情况:
- 酶功能注释对于计算工具来说至关重要但具有挑战性.
- 现有的方法与未经研究的蛋白质,未被描述的功能或多种酶活动作斗争.
研究的目的:
- 引入CLEAN (启用对比学习的酶注释),这是一个新的机器学习算法.
- 提高酶委员会 (EC) 数量预测的准确性,可靠性和灵敏性.
主要方法:
- 使用对比学习框架进行酶注释.
- 系统的体和体外实验来验证算法的性能.
主要成果:
- 在EC编号分配方面,CLEAN表现优于BLASTp.
- 成功注释研究不足的酶,纠正错误标记的酶,并识别杂乱的酶.
结论:
- CLEAN提供了精确预测酶功能的强大解决方案.
- 该工具预计将通过更好地了解未表征的酶来推进基因组学,合成生物学和生物催化.
更多相关视频
06:50Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
Published on: January 26, 2024
10:21Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
Published on: February 23, 2024
相关概念视频
Predicting Reaction Outcomes
Predicting Products: Substitution vs. Elimination
The following factors can influence the mechanisms competing against each other:
Predicting Products: SN1 vs. SN2
With increased substitution on the alkyl halide,...
Improving Translational Accuracy
End Point Prediction: Gran Plot
For potentiometric titration, the Gran plot is created by plotting...
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...
