小分子调整型发电机:对高质量数据集的传统方法和人工智能模型的评估
Zhe Wang1, Haiyang Zhong1, Jintu Zhang1
1Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China.
Journal of chemical information and modeling
|October 26, 2023
概括
人工智能模型在复制生物活性小分子构造方面没有超过传统方法. 然而,人工智能模型擅长生成低能形状,扭曲扩散在传统方法上显示出显著的优势.
科学领域:
- 计算化学计算化学
- 药物设计 药物设计
- 化学信息学 化学信息学
背景情况:
- 小分子适应器生成 (SMCG) 对于计算机辅助药物设计至关重要.
- 许多人工智能 (AI) 对SMCG的模型已经出现,但与传统方法的直接比较缺乏.
研究的目的:
- 系统地评估和比较人工智能和SMCG传统方法的性能.
- 评估这些方法在复制生物活性和低能耗形状方面的能力.
- 引入一个新的基准测试数据集和一个用户友好的SMCG.Web服务器.
主要方法:
- 策划了3354个生物活性构成的新数据集.
- 评估了四种传统方法 (ConfGenX, Conformator, OMEGA, RDKit ETKDG) 和五种人工智能模型 (ConfGF, DMCG, GeoDiff, GeoMol,扭转扩散).
- 在使用COV-R和COV-P等指标来复制生物活性和低能耗构造的评估性能.
主要成果:
- 人工智能模型在再生生物活性构造方面没有任何优势,GeoMol的表现低于传统方法.
- 扭力扩散人工智能模型在产生低能度构造方面表现出卓越的性能,显著优于ConfGenX.
- 此外,还分析了基于力场的微调对调器质量的影响.
结论:
- 人工智能模型目前无法超越生物活性形态复制的传统方法.
- 人工智能,特别是扭力扩散,在产生高质量的低能度形态方面表现有前途.
- 开发的fastSMCG网络服务器为研究小分子适应器生成的研究人员提供了宝贵的工具.
相关概念视频
02:00Molecular Models
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.
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...