用大型语言模型和机器学习预测分子的血脑屏障透性
Eddie T C Huang1, Jai-Sing Yang2, Ken Y K Liao1
1NVIDIA AI Technology Center, NVIDIA Corporation, Santa Clara, USA.
Scientific reports
|July 9, 2024
概括
人工智能 (AI) 模型可以准确预测血脑屏障 (BBB) 透性,用于药物发现. 像MegaMolBART这样的新型深度学习方法加快了中枢神经系统候选药物的识别.
科学领域:
- 计算化学是一种计算化学.
- 药物发现 药物发现
- 医学中的人工智能
背景情况:
- 预测血脑屏障 (BBB) 透性对于开发针对中枢神经系统的药物至关重要.
- 传统方法耗时,可能不准确,需要先进的计算方法.
研究的目的:
- 开发和验证人工智能 (AI) 模型,包括深度学习架构,用于预测小分子BBB透性.
- 为了比较基于变压器的模型与传统指纹测试方法的性能,用于BBB透预测.
主要方法:
- 使用基于变压器的模型 (MegaMolBART) 进行简化分子输入线输入系统 (SMILES) 编码,并使用XGBoost分类器进行in silico预测.
- 采用摩根/圆形指纹与XGBoost分类器作为基线方法.
- 用3D人类BBB球形体进行体外实验验验证了in silico预测.
主要成果:
- 基于变压器的AI模型在持有测试数据集上实现了接收器运行特征曲线下的面积为0.88.
- 实验室验证证实了 in silico 预测的准确性,鉴定出具有透性和不透性的化合物表现得如预期.
- 该模型成功预测了已知的化合物,如Temozolomide (TMZ) 的透性.
结论:
- 基于变压器的AI模型,如MegaMolBART,在预测BBB透性方面表现出很高的准确性.
- 这些人工智能工具可以显著加速中枢神经系统疾病的药物发现过程.
- 开发的in silico方法提供了一个可靠的平台,用于识别可能穿越BBB的潜在候选药物.
更多相关视频
06:26Analyzing the Permeability of the Blood-Brain Barrier by Microbial Traversal through Microvascular Endothelial Cells
Published on: February 14, 2020
15.5K
07:52A Human Blood-Brain Interface Model to Study Barrier Crossings by Pathogens or Medicines and Their Interactions with the Brain
Published on: April 9, 2019
8.7K
相关概念视频
00:49The Blood-brain Barrier
47.1K
Overview
47.1K
01:25Physiological Barriers
3.5K
Physiological barriers are semi-permeable cellular structures restricting drug diffusion into intracellular compartments and tissues. There are six types of physiological barriers: blood endothelial, cell membrane, blood-brain, blood-cerebrospinal fluid (CSF), blood-placenta, and blood-testis barriers.
The blood endothelial barrier is the most porous of these. It allows all small ionized, un-ionized, and lipophilic molecules to pass through the endothelial lining into the interstitial space...
The blood endothelial barrier is the most porous of these. It allows all small ionized, un-ionized, and lipophilic molecules to pass through the endothelial lining into the interstitial space...
3.5K
01:23Factors Affecting Drug Distribution: Physiological Barriers
196
Drug distribution in the body is intricately regulated by various physiological barriers that control the passage of substances. These include the capillary endothelial barrier, the blood-brain, blood-cerebrospinal fluid, blood-placental, and blood-testis barriers.
The capillary endothelial barrier allows only smaller molecules below 600 Da (Daltons) to pass through. It also restricts drugs like heparin that are bound to blood components, limiting their movement within the bloodstream.
The...
The capillary endothelial barrier allows only smaller molecules below 600 Da (Daltons) to pass through. It also restricts drugs like heparin that are bound to blood components, limiting their movement within the bloodstream.
The...
196
00:57Physiological Pharmacokinetic Models: Blood Flow-Limited Versus Diffusion-Limited Models
77
Physiological pharmacokinetic models, often called flow-limited or perfusion models, typically assume a swift drug distribution between tissue and venous blood, creating a rapid drug equilibrium. This premise is based on the idea that drug diffusion is extremely fast, and the cell membrane presents no barrier to drug permeation. In this scenario, where no drug binding occurs, the drug concentration in the tissue equals that of the venous blood leaving the tissue. This greatly simplifies the...
77