5个成员异环的C-H氨基基化:描述器,数据集大小和数据质量对机器学习模型的预测能力的影响以及基质空间超出1,3-Azoles的扩展
Stephanie Felten1, Cyndi Qixin He2, Marion H Emmert1
1Process Research and Development, MRL, Merck & Co., Inc., 126 E Lincoln Ave, Rahway, New Jersey 07065, United States.
The Journal of organic chemistry
|February 11, 2025
概括
我们开发了一种机器学习 (ML) 模型,以预测C-H氨基基化反应活性在各种5个成员的异环环中. 这种方法加速了用于药物开发的新化学反应的发现.
科学领域:
- 有机化学 有机化学
- 计算化学计算化学
- 机器学习 机器学习
背景情况:
- C-H功能化对于合成复杂分子至关重要.
- 开发有效的方法来使异环循环功能化仍然是一个挑战.
- 机器学习提供了一种强大的方法来加速化学发现.
研究的目的:
- 开发一个可预测的机器学习模型,用于C-H氨基基化5个成员的异环.
- 在欠发达的异环系统中发现新的C-H功能化反应性.
- 建立一个代的积极学习工作流程,以改进预测模型.
主要方法:
- 机器学习和实验验证的结合.
- 在6轮的代主动学习中改进预测模型.
- 利用分子描述符和指纹用于特征工程,与基于DFT的特征进行基准测试.
主要成果:
- 通过交叉验证 (CV R2 = 0.81) 和在看不见的基板上 (测试R2 = 0.95) 实现了高预测准确性.
- 最终的模型准确地预测了各种异环基架的反应性,包括N-aryl indazoles,1,2,4-triazolopyrazines,1,2,3-thiadiazoles和1,3,4-oxadiazoles.
- 确定了针对特定异环环的新型C-H功能化反应性.
结论:
- 开发的ML模型显著提高了对C-H氨基基化反应活性的预测.
- 这种工作流加速了在重要的异环基因基因中发现新型反应性的过程.
- 这种方法对合成化学家和机器学习社区在药物发现方面有价值.
相关概念视频
Five-Membered Heterocyclic Aromatic Compounds: Overview
3.7K
Heterocyclic aromatic compounds are cyclic compounds that are aromatic and have one or more heteroatoms—atoms other than carbon, in the ring. Depending upon the number of atoms present in the ring, they can be either five or six-membered. Examples of five-membered heterocyclic aromatic compounds include pyrrole, furan, thiophene, and imidazole. Pyrrole consists of one nitrogen atom having one lone pair of electrons. Furan and thiophene have one oxygen and one sulfur heteroatom,...
3.7K
Basicity of Heterocyclic Aromatic Amines
5.5K
Heterocyclic amines, where the N atom is a part of an alicyclic system, are similar in basicity to alkylamines. Interestingly, the heterocyclic amine having a nitrogen atom as part of an aromatic ring has much less basicity than its corresponding alicyclic counterpart. For this reason, as presented in Figure 1, piperidine (pKb = 2.8) is significantly more basic than pyridine (pKb = 8.8).
5.5K
Aldehydes and Ketones with HCN: Cyanohydrin Formation Overview
2.6K
Cyanohydrins are compounds that contain –CN and –OH groups on the same carbon atom. They are formed by the nucleophilic addition of the cyanide ions to the carbonyl group. Cyanide ions are highly basic and nucleophilic and can be generated from HCN under aqueous conditions. However, since HCN is a weak acid, the number of cyanide ions generated is very small. Hence, a small amount of base or KCN/NaCN is added to HCN to increase the concentration of the cyanide ions in the reaction...
2.6K
α-Alkylation of Ketones via Enolate Ions
3.0K
Ketones with α protons are deprotonated by strong bases like lithium diisopropylamide (LDA) to form enolate ions. The anion is stabilized by resonance, and its hybrid structure exhibits negative charges on the carbonyl oxygen and the α carbon. This ambident nucleophile can attack an electrophile via two possible sites: the carbonyl oxygen, known as O-attack, or the α carbon, known as C-attack. The nucleophilic attack via the carbanionic site is preferred. This is due to the...
3.0K
Nomenclature of Aryl and Heterocyclic Amines
2.3K
The simplest aromatic amine is phenylamine, which contains an –NH2 functionality directly attached to an aromatic ring. The name aniline is designated for this skeleton. As shown in Figure 1, the common names of the functionalized anilines involve prefixes ortho-, meta-, and para- to indicate the substitution position. Different functionalized aniline derivatives also have notable trivial names.
2.3K
Electrophilic Addition to Alkynes: Halogenation
8.1K
Introduction
Halogenation is another class of electrophilic addition reactions where a halogen molecule gets added across a π bond. In alkynes, the presence of two π bonds allows for the addition of two equivalents of halogens (bromine or chlorine). The addition of the first halogen molecule forms a trans-dihaloalkene as the major product and the cis isomer as the minor product. Subsequent addition of the second equivalent yields the tetrahalide.
Halogenation is another class of electrophilic addition reactions where a halogen molecule gets added across a π bond. In alkynes, the presence of two π bonds allows for the addition of two equivalents of halogens (bromine or chlorine). The addition of the first halogen molecule forms a trans-dihaloalkene as the major product and the cis isomer as the minor product. Subsequent addition of the second equivalent yields the tetrahalide.
8.1K


