通过机器学习预测结合的橄电解质分子的抗菌活性
Armi Tiihonen1, Sarah J Cox-Vazquez2, Qiaohao Liang1
1Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.
Journal of the American Chemical Society
|November 5, 2021
概括
开发新型抗生素对抗耐药性至关重要. 这项研究引入了一种机器学习模型,用于预测新的抗生素类别的抗菌活性,比如结合电解质,加速药物发现.
科学领域:
- 药物发现和开发
- 计算化学
- 抗菌药物耐药性
背景情况:
- 越来越多的抗生素耐药性需要开发新药,
- 目前用于药物发现的机器学习模型通常需要大量的数据集,并专注于已知的抗生素结构.
- 对于传统的结构-活性关系研究来说,非传统的抗生素类别存在挑战.
研究的目的:
- 开发一种新的抗生素类型的结合性电解质分子的抗菌活性预测模型.
- 确定用于预测抗菌有效性的关键分子描述剂.
- 展示可适应其他新抗生素领域的机器学习方法.
主要方法:
- 开发了一种机器学习模型来预测对大肠杆菌K12的最小抑制度 (MIC).
- 使用递归淘汰从5305个初始集合中选择21个相关的分子描述符.
- 采用了反映结合的三维形状的分子表示.
主要成果:
- 获得了对抗微生物活性R平方值为0.65的预测模型.
- 确定最佳分子表示,强调3D形状,对于预测准确性至关重要.
- 在没有对特定抗菌机制的先验知识的情况下证明了成功的预测.
结论:
- 一个强大的机器学习模型可以预测新型抗生素的抗菌活性,
- 对于准确的抗菌活性预测,选择分子表征至关重要.
- 这种方法提供了一个可扩展的方法来加速对抗耐药性病原体的新抗生素的发现.
更多相关视频
相关概念视频
Antimicrobial Effectiveness
412
The effectiveness of antimicrobial agents depends on various factors influencing their ability to eliminate microbial populations. Larger microbial populations require more time for complete eradication, emphasizing the importance of population size analysis when evaluating antimicrobial efficacy.Microbial resistance to antimicrobial agents varies significantly. Highly resilient microorganisms include endospores, gram-negative bacteria, and non-enveloped viruses, while prions are exceptionally...
412
Antimicrobial Proteins
9.5K
Antimicrobial proteins are important components of the immune system. They aid the body in combating pathogens by either killing them directly or hindering their replication processes. Four main types of antimicrobial substances are interferons, the complement system, iron-binding proteins, and antimicrobial proteins.
Interferons
Interferons (IFNs) are proteins produced by lymphocytes, macrophages, and fibroblasts infected with viruses. While IFNs cannot prevent viruses from entering and...
Interferons
Interferons (IFNs) are proteins produced by lymphocytes, macrophages, and fibroblasts infected with viruses. While IFNs cannot prevent viruses from entering and...
9.5K


