利用基于机器学习的QSAR模型来克服在β-乳糖酶抑制剂查中的独立共识对接限制:一项概念验证研究
Thanet Pitakbut1,2, Jennifer Munkert1,3, Wenhui Xi2
1Department of Biology, Pharmaceutical Biology, Friedrich-Alexander-Universität Erlangen-Nürnberg, Staudtstr. 5, 91058, Erlangen, Germany.
BMC chemistry
|December 20, 2024
概括
这项研究通过使用随机森林机器学习模型来增强虚拟药物选,以提高beta-lactamase抑制剂的共识对接成功率. 这种新方法克服了传统方法的局限性,提高了药物发现效率.
科学领域:
- 计算化学计算化学
- 药用化学 医学化学
- 机器学习 机器学习
背景情况:
- 共识对接是一种标准的虚拟药物选方法.
- 它的数学性质限制了与单个对接方法相比的成功率.
- 本研究使用机器学习解决了这一局限性.
研究的目的:
- 为了克服共识对接在虚拟药物查中的成功率限制.
- 开发和验证基于机器学习的定量结构-活动关系 (QSAR) 模型.
- 为了改善β-乳糖酶抑制剂的鉴定.
主要方法:
- 在体外进行了β-lactamase抑制查.
- 优化了AutoDock Vina和DOCK6的对接协议.
- 量化结构-活动关系 (QSAR) 模型使用后勤回归和随机森林进行训练.
- 共识对接结果与QSAR模型相结合.
主要成果:
- 优化DOCK6识别了高达70%的活性分子.
- 共识分析将成功率降至50%,假阳性率为16%.
- 基于森林的随机QSAR恢复了成功率至70%,同时保持了21%的错误阳性率.
结论:
- 基于森林的随机QSAR模型显著优于物流回归模型.
- 机器学习有效地克服了标准共识对接的局限性.
- 这种方法为β-乳糖酶抑制剂的发现提供了更有效的策略.
更多相关视频
08:31Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
4.9K
10:21Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
Published on: February 23, 2024
2.3K
相关概念视频
Structure-Activity Relationships and Drug Design
510
Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
510
Conserved Binding Sites
4.2K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.2K
