通过基于分子碎片的双通道转移学习来增强药物特性预测
Yue Wu1, Xinran Ni2, Zhihao Wang3
1College of Traditional Chinese Medicine, Shandong University of Traditional Chinese Medicine, Jinan, China.
BMC bioinformatics
|July 21, 2023
概括
将分子碎片集成到AI模型中可以显著改善药物发现的分子性质预测. 我们基于FRagment的双通道FREL预培训 (FREL) 模型通过利用碎片信息来提高学习效率,实现了最先进的结果.
科学领域:
- 计算化学的计算化学
- 人工智能在药物发现中的作用
背景情况:
- 准确的分子性质预测对于药物发现和医学研究至关重要.
- 由于实验数据注释的高成本,转移学习越来越多地被使用.
- 现有的预训练策略往往忽略了像分子碎片这样的特定领域的知识,限制了模型的性能.
研究的目的:
- 开发一种有效的预训练策略,包括分子碎片,以改善分子性质预测.
- 增强AI模型中分子语义空间的探索.
主要方法:
- 拟议的基于FRagment的双通道FREL预训 (FREL) 模型.
- 使用蒙面自编码器和用分子碎片进行对比学习.
- 学习了分子内部和分子间的协议,以获得可靠的表示.
主要成果:
- 与最先进的模型相比,FREL在10个公共数据集中表现出更高的性能.
- 研究了学习的分子表示和分子性质之间的关系.
- 展示了FREL有效地捕捉药物特性变化和碎片语义.
结论:
- FREL模型实现了最先进的性能,突出了分子碎片在AI模型设计中的重要性.
- 学习的分子表示具有表达性,并且与分子性质有很好的相关性.
- FREL的方法增强了对药物发现应用中的分子结构的语义理解.
相关概念视频
Drug Discovery: Overview
8.1K
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...
8.1K
Drug Distribution: Tissue Binding
2.7K
Upon entering the systemic circulation, drugs can distribute into the interstitial and intracellular fluid of various tissue cells. This distribution is facilitated by the binding of drugs to different cellular components within tissues, which may lead to drug accumulation in specific areas. Drugs bound to tissue components serve as reservoirs that release free drugs back into the system, prolonging the drug's overall action. However, this accumulation can also result in local toxicity.
For...
For...
2.7K
Tissue-Drug Binding: Localization of Drugs and its Significance
108
Body tissues, comprising approximately 40% of the body weight, are crucial in drug distribution and localization. These tissues can serve as drug storage sites, competing with plasma binding sites for drug molecules.
Drugs can bind to different tissue components, enhancing their distribution and localization. The factors influencing drug localization in tissues include the drug's lipophilicity, structural characteristics, tissue perfusion rate, and pH differences. These factors determine...
Drugs can bind to different tissue components, enhancing their distribution and localization. The factors influencing drug localization in tissues include the drug's lipophilicity, structural characteristics, tissue perfusion rate, and pH differences. These factors determine...
108
Protein-Drug Binding: Mechanism and Kinetics
616
Protein-drug binding refers to the interaction between drugs and proteins within the body. This binding process can occur intracellularly, involving drug interactions with enzymes or receptors within cells, or extracellularly, involving plasma proteins in the blood.
Various forces drive these interactions, including hydrogen bonds, hydrophobic interactions, ionic bonds, electrostatic interactions, and van der Waals forces. These bonds enable drugs to bind to specific sites on proteins,...
Various forces drive these interactions, including hydrogen bonds, hydrophobic interactions, ionic bonds, electrostatic interactions, and van der Waals forces. These bonds enable drugs to bind to specific sites on proteins,...
616
Protein-Drug Binding: Determination Methods
242
Determining protein-drug binding can be achieved through indirect and direct methods, each providing valuable insights into the interaction between proteins and drugs.
Indirect methods involve isolating the bound drug from its free form in biological samples such as blood, serum, or plasma. These techniques aim to measure the percentage of drugs bound to proteins. Equilibrium dialysis is a commonly used method where the free drug concentration at equilibrium is measured by separating the bound...
Indirect methods involve isolating the bound drug from its free form in biological samples such as blood, serum, or plasma. These techniques aim to measure the percentage of drugs bound to proteins. Equilibrium dialysis is a commonly used method where the free drug concentration at equilibrium is measured by separating the bound...
242
Drug Binding to Blood Components
174
When drugs enter systemic circulation, they interact with various components of the blood, including proteins such as human serum albumin (HSA), α1-acid glycoprotein (AAG), lipoproteins, globulins, and red blood cells (RBCs).
HSA is the most abundant plasma protein and is vital in drug binding. It contains distinct drug-binding sites, with different drugs exhibiting affinity for specific sites. There are three main drug-binding domains for HSA: sites I, II, and III. These domains are...
HSA is the most abundant plasma protein and is vital in drug binding. It contains distinct drug-binding sites, with different drugs exhibiting affinity for specific sites. There are three main drug-binding domains for HSA: sites I, II, and III. These domains are...
174


