基于原子杂交的图形神经网络模型用于预测药物点
bioRxiv : the preprint server for biology
|December 31, 2025
概括
一个新的混合深度学习模型准确地预测药物半最大抑制度 (IC50) 值. 这种方法通过将图形神经网络与分子描述器相结合来增强药物发现,以改善化合物优先级.
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:
- 定量结构-活性关系 (QSAR) 模型对于药物发现至关重要,但往往难以整合本地结构模式和全球物理化学性质.
- 现有的QSAR模型在捕捉影响生物活性的分子特征的复杂相互作用方面存在局限性.
研究的目的:
- 开发一种混合深度学习框架,以提高预测半最大抑制度 (IC50) 值的准确性和可解释性.
- 通过将图形神经网络与显式分子描述器集成,解决传统QSAR模型的局限性.
主要方法:
- 开发了一种混合深度学习框架,将图形神经网络 (GNN) 与显式分子描述器结合起来.
- 该模型处理具有原子和键特性的分子图,以及可解释的物理化学性质和结构指纹.
- 在一个数据集上训练并验证了该模型,该数据集包括9个不同的生物点 (激酶,核受体,蛋白酶) 的14316种化合物.
主要成果:
- 获得了0.87的整体测试R平方 (R2),证明了高的预测准确性.
- 在各种生物标中,其表现比之前报告的方法高出6-42%.
- 展示了强大的概括与可比的培训和测试表现,表明可靠性.
结论:
- 混合框架协同地将数据驱动的学习与域名知识相结合,用于高级结构-活动建模.
- 提供更高的准确性和可解释性,在早期药物发现中促进有效的化合物优先级和优化.
- 代表了计算方法在加速药物发现管道的显著进步.
更多相关视频
05:50Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro
Published on: September 26, 2025
1.3K
08:31Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
5.4K
相关概念视频
Targets for Drug Action: Overview
9.9K
Drugs target macromolecules to modify ongoing cellular processes. Primary drug targets include receptors, ion channels, transporters, and enzymes.
Receptors are either membrane-spanning or intracellular proteins, which upon binding a ligand, get activated and transmit the signal downstream to elicit a response. Drugs bind receptors, either mimicking the action of endogenous ligands or blocking the receptor activity to bring about a modified response. Nearly 35% of approved drugs target the G...
Receptors are either membrane-spanning or intracellular proteins, which upon binding a ligand, get activated and transmit the signal downstream to elicit a response. Drugs bind receptors, either mimicking the action of endogenous ligands or blocking the receptor activity to bring about a modified response. Nearly 35% of approved drugs target the G...
9.9K
Hybridization of Atomic Orbitals I
65.1K
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...
65.1K
Molecular Models
43.3K
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.
43.3K
Drug-Receptor Bonds
4.1K
Drug-receptor bonds are formed through various chemical forces when drugs interact with target cells. Covalent bonds, strong and irreversible, are exemplified by DNA-alkylating anticancer agents that inhibit cell division. However, such irreversible drug binding lacks selectivity and can modify the DNA of the surrounding healthy cells. Covalent binding often contributes to tissue toxicity, as seen with chloroform and paracetamol metabolites binding to the liver, causing hepatotoxicity.
In...
In...
4.1K
Drug Discovery: Overview
10.9K
Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...
10.9K
Predicting Molecular Geometry
44.4K
VSEPR Theory for Determination of Electron Pair Geometries
44.4K
