测量化学LLM对分子表示的稳定性:基于SMILES变异的框架
Veronika Ganeeva1, Kuzma Khrabrov2, Artur Kadurin1,3
1AIRI, 6 Presnenskaya, Moscow, Russia, 123112.
Journal of cheminformatics
|October 31, 2025
概括
这项研究引入了增强分子检索 (AMORE) 来评估化学语言模型 (LMs). AMORE揭示了当前的LM与各种化学结构表示作斗争,突出了在药物发现中提高强度的需要.
科学领域:
- 计算化学计算化学
- 化学信息学 化学信息学
- 药物发现 药物发现 药物发现
背景情况:
- 自然语言处理 (NLP) 的整合推动了药物发现.
- 在语言模型 (LMs) 中的分子表示是化学理解的关键.
研究的目的:
- 探索LM在不同表示中匹配化学结构的能力.
- 开发一个框架来评估化学LMM的稳定性.
主要方法:
- 提议的增强分子检索 (AMORE),一个零射击框架.
- 利用SMILES增强来维持基本的化学结构.
- 促进了分子的嵌入表示及其变异之间的相似性.
主要成果:
- 在分子标题 (ChEBI-20) 和MoleculeNet基准上测试化学LM (ChemLLMs).
- 证明当前的ChemLLM对不同的SMILES表示不够强大.
- 观察到SMILES字符串变化影响模型结果,与AMORE框架保持一致.
结论:
- 目前的化学LM在处理多样化的分子表示中缺乏稳定性.
- AMORE框架有效地评估了对各种化学投入的LM性能.
- 需要进一步开发以提高LM对药物发现的化学结构的理解.
相关概念视频
Molecular Models
43.4K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
43.4K
Molecular Shapes
61.2K
Molecules have characteristic shapes that are crucial for their function. The arrangement of various electron groups around the central atom dictates their molecular geometry. Electron pairs in the valence shell of a central atom will adopt an arrangement that minimizes repulsions between the electron pairs by maximizing the distance between them. The valence electrons form either bonding pairs, located primarily between bonded atoms, or lone pairs.
Two regions of electron density in a diatomic...
Two regions of electron density in a diatomic...
61.2K
Predicting Molecular Geometry
44.6K
VSEPR Theory for Determination of Electron Pair Geometries
44.6K
Chemical Shift: Internal References and Solvent Effects
1.3K
In an NMR sample, precise measurement of the absolute absorption frequencies of nuclei is difficult. A standard internal reference compound is added, and the frequency difference between the reference signal and sample signals is measured.
The internal reference compound generally used in NMR spectroscopy is tetramethylsilane (TMS). TMS is preferred because it is chemically inert, soluble in NMR solvents, and easily removable. Also, the highly shielded methyl protons in TMS yield an intense...
The internal reference compound generally used in NMR spectroscopy is tetramethylsilane (TMS). TMS is preferred because it is chemically inert, soluble in NMR solvents, and easily removable. Also, the highly shielded methyl protons in TMS yield an intense...
1.3K
Molecular Comparison of Gases, Liquids, and Solids
53.3K
Particles in a solid are tightly packed together (fixed shape) and often arranged in a regular pattern; in a liquid, they are close together with no regular arrangement (no fixed shape); in a gas, they are far apart with no regular arrangement (no fixed shape). Particles in a solid vibrate about fixed positions (cannot flow) and do not generally move in relation to one another; in a liquid, they move past each other (can flow) but remain in essentially constant contact; in a gas, they move...
53.3K
Molecular Geometry and Dipole Moments
18.0K
The VSEPR theory can be used to determine the electron pair geometries and molecular structures as follows:
18.0K


