MycoPermeNet-v2:使用融合杂的学生自蒸改进预测菌膜透
Nelson Evbarunegbe1, Shiyun Wa1, Isha Karn1
1Manning College of Information & Computer Sciences, University of Massachusetts Amherst, 140 Governors Dr, Amherst, Massachusetts 01003, United States.
Journal of chemical information and modeling
|March 2, 2026
概括
这项研究介绍了MycoPermeNet-v2,这是一种机器学习模型,可以准确地预测药物化合物可以通过结核病细菌独特的外膜. 这一进步有助于发现新的抗生素,以挑战结核病药物发现.
科学领域:
- 计算化学是一种计算化学.
- 药物发现 药物发现
- 机器学习是机器学习.
背景情况:
- 结核病 (结核病) 药物发现面临挑战,原因是结核菌*的内在抗生素耐药性.
- 结核菌菌膜作为透性屏障,阻碍了抗生素的疗效.
- 由于有限的标记数据,现有的机器学习模型难以将预测化合物透性的概括.
研究的目的:
- 开发一个强大的机器学习模型,用于预测跨 *M.结核病* 菌膜的化合物透性.
- 用先进的机器学习技术解决抗生素发现中的数据稀缺问题.
主要方法:
- 提出了一个两阶段模型,MycoPermeNet-v2,将分子描述符与基于图形的嵌入整合起来.
- 雇员 噪音 学生自蒸 (NST) 以提高模型性能与有限的标记数据.
- 进行了对模型稳定性,组件贡献和可解释性的系统评估.
主要成果:
- 实现了显著改善的预测性能 (RMSE从0.755 ± 0.024减少到0.719 ± 0.021,调整 *p* < 0.0001).
- 证明该模型捕捉了与菌膜透性相关的化学上有意义的特征.
- 在不同的模型和物理化学性质预测任务中展示了可概括性.
结论:
- 在数据受限的情况下,MycoPermeNet-v2为预测化合物透性提供了一个强大的解决方案.
- 该模型的可解释性为*M.结核病*药物透性的关键特征提供了洞察力.
- 这种方法在加速抗生素发现方面具有很强的适用性,特别是在挑战诸如M.结核病这样的病原体方面.
更多相关视频
10:58SNARE-mediated Fusion of Single Proteoliposomes with Tethered Supported Bilayers in a Microfluidic Flow Cell Monitored by Polarized TIRF Microscopy
Published on: August 24, 2016
11.5K
10:07High-throughput Measurement of Plasma Membrane Resealing Efficiency in Mammalian Cells
Published on: January 7, 2019
8.2K
相关概念视频
01:26Membrane Fluidity
17.2K
Membrane fluidity is explained by the fluid mosaic model of the cell membrane, which describes the plasma membrane structure as a mosaic of components—including phospholipids, cholesterol, proteins, and carbohydrates—that gives the membrane a fluid character.
Mosaic nature of the membrane
The mosaic characteristic of the membrane helps the plasma membrane remain fluid. The integral proteins and lipids exist as separate but loosely-attached molecules in the membrane. The membrane is...
Mosaic nature of the membrane
The mosaic characteristic of the membrane helps the plasma membrane remain fluid. The integral proteins and lipids exist as separate but loosely-attached molecules in the membrane. The membrane is...
17.2K
01:23Membrane Fluidity
177.3K
Cell membranes are composed of phospholipids, proteins, and carbohydrates loosely attached to one another through chemical interactions. Molecules are generally able to move about in the plane of the membrane, giving the membrane its flexible nature called fluidity. Two other features of the membrane contribute to membrane fluidity: the chemical structure of the phospholipids and the presence of cholesterol in the membrane.
177.3K