碎片级特征融合方法使用回合成碎片化算法进行分子性质预测
Qifeng Jia1, Yekang Zhang1, Yihan Wang2
1School of Information Science and Technology, Nantong University, Nantong, 226001, China.
Journal of molecular graphics & modelling
|February 26, 2025
概括
一种新的碎片级特征融合方法 (RFA-FFM) 改善了药物发现的分子性质预测. 这种人工智能方法通过整合多视角分子表示来提高准确性,加速新疗法的开发.
科学领域:
- 人工智能在药物发现中的作用
- 计算化学计算化学
- 机器学习用于分子建模
背景情况:
- 深度学习对药物发现产生重大影响,特别是在预测诸如毒性和血脑屏障 (BBB) 透性等分子性质方面.
- 自主监督学习 (SSL),特别是图形对比学习 (GCL),提供了强大的概括性,但目前的方法可能会通过数据增强来改变分子结构.
- 现有的单视角分子表示无法捕捉出分子的全部复杂性.
研究的目的:
- 开发一种新的方法,RFA-FFM,用于整合多视角分子表示,以提高预测准确度.
- 通过避免结构变化和捕获层次分子信息来解决当前GCL方法的局限性.
主要方法:
- RFA-FFM使用复合碎片化算法来生成分子碎片.
- 它采用两种逆合成方法对碎片进行对比学习,以获得详细的化学见解.
- 该方法将分子和碎片级的化学信息融合在一起,创建多视角表示.
主要成果:
- 在分子性质预测中,RFA-FFM提高了深度学习模型的性能,在四个基准标准中,ROC-AUC得分增加了0.3%-2.6%.
- 在B型肝炎病毒数据集案例研究中,RFA-FFM的表现比基线高出7% -11%.
- 与BPE和CC-Single算法相比,RFA-FFM在血脑屏障透性预测任务中显示出2%-4%的改进.
结论:
- 通过整合多视角分子表示,RFA-FFM有效地提高了分子性质预测.
- 该方法在分类基准和特定应用中表现出卓越的性能,例如BBB透性预测.
- 在应用图形对比学习以加速和更准确的药物发现方面,RFA-FFM代表了重大进展.
相关概念视频
Mass Spectrometry: Molecular Fragmentation Overview
2.8K
The ionization of a molecule into a molecular ion inside the mass spectrometer causes instability in the molecule's structure due to the loss of an electron. This eventually leads to the fragmentation or breaking of some bonds in the molecule. The fragmentation occurs predominantly at specific bonds to yield relatively stable fragments.
One type of fragmentation pattern is the cleavage of a single bond in the molecular ion. The cleavage leads to a radical and a cation. The cleavage can...
One type of fragmentation pattern is the cleavage of a single bond in the molecular ion. The cleavage leads to a radical and a cation. The cleavage can...
2.8K
Mass Spectrometry: Alkyne Fragmentation
1.4K
The fragmentation of alkynes preferentially occurs at the carbon–carbon bond between the α and β carbon of the alkyne bond to generate a 3-propynyl cation (or propargyl cation). In terminal alkynes, there is the only type of fragmentation that yields the 3-propynyl cation. The unsubstituted 3-propynyl cation exhibits a peak at a mass-to-charge ratio of 39. In internal alkynes, the 3-propynyl cation is substituted. For example, 2-pentyne fragments into methyl-substituted...
1.4K
Predicting Molecular Geometry
34.0K
VSEPR Theory for Determination of Electron Pair Geometries
34.0K
Mass Spectrometry: Carboxylic Acid, Ester, and Amide Fragmentation
1.1K
The fragmentation patterns observed for compounds such as carboxylic acids, esters, and amides in the mass spectra include ⍺-cleavage and McLafferty rearrangement. Fragmentation by ⍺-cleavage preferentially occurs at the carbon-carbon bond at the ⍺-position next to the carboxylic group to generate a neutral radical and a cation. Long chain compounds with hydrogen at their γ-carbon undergo McLafferty rearrangement to give a radical cation and a neutral alkene.
For example,...
For example,...
1.1K
Mass Spectrometry: Cycloalkene Fragmentation
979
The molecular ions of cycloalkenes undergo fragmentation via a retro-Diels–Alder reaction.
979
Mass Spectrometry: Aromatic Compound Fragmentation
1.5K
Upon ionization, aromatic compounds generate a molecular ion that is observed as a prominent peak in their mass spectra. For example, the molecular ion peak for benzene appears at a mass-to-charge ratio of 78, while toluene is observed at a mass-to-charge ratio of 92. The molecular ion benzene is highly stable and does not readily undergo further fragmentation due to the significant amount of energy required to disrupt the aromatic stability of the benzene ring. In contrast, the molecular ion...
1.5K


