对于分子性质预测的任务特定预培训
Wenbo Zhang1, Yihui Wang2, Jin Liu3
1School of Computer Science and Technology, Xidian University, 266 Xinglong Section of Xifeng Road, Xi'an 710126, Shaanxi, China.
我们开发了TasProp,这是一个特定任务的预培训策略,以改善有限数据的分子性质预测. 这种方法增强了模型的概括性,并优于药物发现任务的现有方法.
科学领域:
- 计算化学计算化学
- 药物发现 药物发现 药物发现
- 机器学习 机器学习
背景情况:
- 深度学习模型对于分子性质预测至关重要,但由于有限的标记数据而遭受过度拟合.
- 现有的方法在缺乏标记分子数据集的场景中难以概括.
研究的目的:
- 提出TasProp,一个特定任务的预训练策略,以增强分子性质预测,特别是使用小标记数据集.
- 为了改善学习强大的分子表示,以便更好地概括.
主要方法:
- TasProp将标记和未标记的数据项目到一个统一的隐藏空间中.
- 引入了特定任务的对比损失,以使表示与预测任务保持一致.
- 提出了一种新的数据增强技术,以解决标记数据稀缺的问题.
主要成果:
- 在多个分子性质预测任务上,TasProp显著超过了最先进的方法.
- 该战略显示,在公开可用和精心策划的麻醉学数据集上,性能有所改善.
- 该方法有效地减轻了过拟合,并增强了模型的概括性.
结论:
- 在有限的标记数据下,TasProp为分子性质预测提供了有效的解决方案.
- 特定任务的预训练和数据增强提高了模型的稳定性和预测准确性.
- 有一个交互式的网络资源可用于简单的应用和模型的探索.
更多相关视频
10:29Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
Published on: May 9, 2025
09:39An Open-Source, Fully Customizable 5-Choice Serial Reaction Time Task Toolbox for Automated Behavioral Training of Rodents
Published on: January 19, 2022
相关概念视频
Predicting Molecular Geometry
Sensitivity, Specificity, and Predicted Value
Sensitivity is the...
Kinetic Molecular Theory and Gas Laws Explain Properties of Gas Molecules
pre-mRNA Processing
Once about 20-40 ribonucleotides have been joined together by RNA polymerase, a group of enzymes adds a “cap” to the 5’ end of the growing transcript. In this process, a 5’ phosphate is replaced by modified guanosine that has a methyl group attached to it (7-Methyl...
Molecular and Ionic Solids
Molecular Solids
Molecular crystalline solids, such as ice, sucrose (table sugar), and iodine, are solids that are composed of neutral molecules as their constituent units. These molecules are held together by weak intermolecular forces such as London dispersion forces, dipole-dipole interactions, or hydrogen bonds, which...
Molecular Orbital Theory II
