以集成机器学习为指导的in silico和in vitro方法揭示了针对突变IDH1的选择性小分子抑制剂
Mayank Bajaj1, Rohit Kumar2, Vishal Pandey2
1Translational Biology Laboratory, Department of Animal Biology, School of Life Sciences, University of Hyderabad Hyderabad - 500046 Telangana India roykarnati@uohyd.ac.in +91-9652921092.
RSC advances
|December 22, 2025
概括
研究人员开发了机器学习模型,以发现针对突变异位酸脱酶1 (IDH1) 的新药,这是质瘤的关键驱动因素. 确定了五种强效和选择性抑制剂,为未来的IDH1癌症疗法提供了基础.
科学领域:
- 生物化学和分子生物学
- 计算化学和化学信息学
- 瘤学和癌症治疗学 癌症治疗学
背景情况:
- 异酸脱酶1 (IDH1) 的突变,特别是R132H,在世卫组织II/III级质瘤中很普遍.
- 这些突变产生一种新型酶活性,产生2-基酸盐 (2HG),一种驱动质瘤发展的代谢物.
- 针对突变的IDH1 (MT-IDH1) 具有治疗前景,需要发现新的选择性抑制剂.
研究的目的:
- 开发和验证机器学习 (ML) 模型,用于预测化合物对MT-IDH1.1的抑制活性.
- 通过ML驱动的药物查来识别新型,强效和选择性MT-IDH1抑制剂.
- 为开发MT-IDH1驱动的恶性瘤下一代治疗方法提供基础.
主要方法:
- 基于回归的ML模型使用ChEMBL数据集训练了1631个化合物和208个RDKit分子描述符.
- 随机森林算法因其在预测pIC50值方面的卓越性能而被选中.
- 用于验证的是in silico方法 (分子对接,动力学,MM/PBSA) 和体外酶测试.
主要成果:
- 随机森林模型对MT-IDH1抑制剂活性表现出高的预测准确性和概括性.
- 脂性,素和电子因素被确定为抑制剂效力的关键决定因素.
- 确定了五种有前途的化合物,表明选择性抑制MT-IDH1 (微分子IC50),对野生类型的IDH1 (WT-IDH1) 没有显著的活性.
结论:
- 开发的ML模型有效预测MT-IDH1抑制剂活性,并促进新药候选药物的发现.
- 已识别的化合物是强效和选择性的MT-IDH1抑制剂,需要进一步调查.
- 这些发现为结构优化和开发携带MT-IDH1突变的质瘤新疗法提供了坚实的基础.
相关概念视频
01:16In-vitro Mutagenesis
To learn more about the function of a gene, researchers can observe what happens when the gene is inactivated or “knocked out,” by creating genetically engineered knockout animals. Knockout mice have been particularly useful as models for human diseases such as cancer, Parkinson’s disease, and diabetes.
02:15Experimental RNAi
RNA interference (RNAi) is a cellular mechanism that inhibits gene expression by suppressing its transcription or activating the RNA degradation process. The mechanism was discovered by Andrew Fire and Craig Mello in 1998 in plants. Today, it is observed in almost all eukaryotes, including protozoa, flies, nematodes, insects, parasites, and mammals. This precise cellular mechanism of gene silencing has been developed into a technique that provides an efficient way to identify and determine the...