用机器学习填补和评估和含衍生物的差距
Oleksandr Gurbych1,2, Petro Pavliuk1,2, Dmytro Krasnienkov1
1Blackthorn AI Ltd., London, UK.
Journal of computational chemistry
|January 13, 2025
概括
这项研究开发了准确的机器学习模型,以预测化化合物的脂友性 (logP) 和酸性/基本性 (pKa). 这些模型通过改善对具有挑战性的化学结构的预测来帮助药物发现.
科学领域:
- 药用化学 医学化学
- 计算化学计算化学
- 药物发现 药物发现 药物发现
背景情况:
- 脂性 (logP) 和酸性/基性 (pKa) 是影响药物行为的关键物理化学性质.
- 准确预测logP和pKa对于成功的早期药物发现至关重要.
- 标准预测方法与含的和化合物作斗争,限制了它们的实用性.
研究的目的:
- 开发精确的可预测模型,用于和含化合物的脂性和酸度/度.
- 为了克服这种特定化学品类的现有预测方法的局限性.
- 为有针对性的分子设计提供开源工具.
主要方法:
- 编制了一套独特的化和非化衍生物数据集,具有实验性logP和pKa值.
- 评估,训练或微调超过40个机器学习模型 (线性,基于树的,神经网络).
- 使用基层结构掩盖解释 (SME) 来验证模型发现和的作用.
主要成果:
- 开发了高精度的机器学习模型,用于预测和含化合物中的logP和pKa.
- 证实了化替代剂对脂性和酸度/度的显著影响.
- 证明了开发的预测模型的一致性和可靠性.
结论:
- 开发的模型提供了一个最佳的方法来预测具有挑战性的化化合物中的脂性和酸性/基本性.
- 开源资源 (GitHub, pip, conda, KNIME) 允许公众访问有针对性的分子设计.
- 这项工作有助于开发新的化药物候选药物.
更多相关视频
09:04Identifying Per- and Polyfluorinated Chemical Species with a Combined Targeted and Non-Targeted-Screening High-Resolution Mass Spectrometry Workflow
Published on: April 18, 2019
12.4K
09:24Application and Methodology of the Non-destructive 19F Time-domain NMR Technique to Measure the Content in Fluorine-containing Drug Products
Published on: August 22, 2017
8.3K
相关概念视频
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
39
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
39
Electrophilic Aromatic Substitution: Fluorination and Iodination of Benzene
5.8K
Bromination and chlorination of aromatic rings by electrophilic aromatic substitution reactions are easily achieved, but fluorination and iodination are difficult to achieve. Fluorine is so reactive that its reaction with benzene is difficult to control, resulting in poor yields of monofluoroaromatic products. To address this, Selectfluor reagent is used as a fluorine source in which a fluorine atom is bonded to a positively charged nitrogen.
5.8K
Hybridization of Atomic Orbitals I
46.4K
The mathematical expression known as the wave function, ψ, contains information about each orbital and the wavelike properties of electrons in an isolated atom. When atoms are bound together in a molecule, the wave functions combine to produce new mathematical descriptions that have different shapes. This process of combining the wave functions for atomic orbitals is called hybridization and is mathematically accomplished by the linear combination of atomic orbitals. The new orbitals that...
46.4K
