Optimization of Menin inhibitors based on artificial intelligence-driven molecular factory technology
-
摘要:
以深度学习为代表的新一代人工智能技术已经成为推动新药研发的重要驱动力。本文创造性地提出了一种基于人工智能技术的创新药物分子设计和优化工作流程“分子工厂”，该流程融合了自主研发的智能分子生成模型、高性能分子对接算法以及高精度亲和力预测方法，已作为核心模块被整合进一站式药物设计软件平台DrugFlow，为先导化合物发现和优化提供了一整套成熟的解决方案。利用“分子工厂”模块，针对Menin蛋白开展了抗耐药第2代抑制剂的研发。通过计算和实验的结合，快速获得多个潜力化合物，其中化合物RG-10对Menin野生型、M327I突变体和T349M突变体的IC50分别为9.681 nmol/L、233.2 nmol/L和40.09 nmol/L；与已进入Ⅱ期临床的阳性参照分子SNDX-5613相比，其对M327I和T349M突变体的抑制活性显著提升。上述研究充分展现了“分子工厂”技术在新药研发项目中的独特优势，能快速高效地针对特定蛋白结构产生高质量的活性分子，对推动新药研发具有重大价值和深远意义。
Abstract:The new generation of artificial intelligence technology, represented by deep learning, has emerged as a crucial driving force in the advancement of new drug research and development. This article creatively proposes a workflow named “Molecular Factory” for the design and optimization of drug molecules based on artificial intelligence technology. This workflow integrates intelligent molecular generation models, high-performance molecular docking algorithms, and accurate protein-ligand binding affinity prediction methods. It has been integrated as a core module into DrugFlow, a one-stop drug design software platform, providing a comprehensive set of mature solutions for the discovery and optimization of lead compounds. Utilizing the “Molecular Factory” module, we conducted the research of second-generation inhibitors against Menin that can combat drug resistance. Through the integration of computational and experimental approaches, we rapidly identified multiple promising compounds. Among them, compound RG-10 exhibited the IC50 values of 9.681 nmol/L, 233.2 nmol/L, and 40.09 nmol/L against the wild-type Menin, M327I mutant, and T349M mutant, respectively. Compared to the positive reference molecule SNDX-5613, which has entered Phase II clinical trials, RG-10 demonstrated significantly enhanced inhibitory activity against the M327I and T349M mutants. These findings fully demonstrate the unique advantages of the "Molecular Factory" technology in practical drug design and development scenarios. It can rapidly and efficiently generate high-quality active molecules targeting specific protein structures, holding significant value and profound implications for advancing new drug discovery.
-
-
![]()
Figure 4. Kernel density distributions of molecular weight, TPSA, LogP and LogS in known actives
TPSAt：Opological polar surface area；LogP：Logarithm of the n-octanol/water distribution coefficient；LogS：Logarithm of aqueous solubility value
![]()
Figure 5. Distributions of molecular weight, TPSA, LogP, LogS of the generated molecules
![]()
Figure 6. Comparison of the chemical spatial distribution using the t-distributed stochastic neighbor embedding (t-SNE) method
Table 1 Biological activities of five candidates against Menin-WT, Menin-M327I and Menin-T349M
Target Compound ID IC50/(nmol/L) Menin-WT SNDX-5613 11.86 RG-06 32.91 RG-10 9.681 D5-18-11 382.7 D5-18-9 221.7 RG-07 364.3 Menin-M327I SNDX-5613 1421 RG-06 513.8 RG-10 233.2 D5-18-11 625.3 D5-18-9 363.2 RG-07 590.7 Menin-T349M SNDX-5613 280.2 RG-06 53.8 RG-10 40.09 D5-18-11 1611 D5-18-9 326 RG-07 384.9 
下载: 导出CSV
-
[1] Yokoyama A, Cleary ML. Menin critically links MLL proteins with LEDGF on cancer-associated target genes[J]. Cancer Cell, 2008, 14(1): 36-46. doi: 10.1016/j.ccr.2008.05.003
[2] Issa GC, Aldoss I, DiPersio J, et al. The menin inhibitor revumenib in KMT2A-rearranged or NPM1-mutant leukaemia[J]. Nature, 2023, 615(7954): 920-924. doi: 10.1038/s41586-023-05812-3
[3] Perner F, Stein EM, Wenge DV, et al. MEN1 mutations mediate clinical resistance to menin inhibition[J]. Nature, 2023, 615(7954): 913-919. doi: 10.1038/s41586-023-05755-9
[4] Grisham J. Menin Inhibitors: Promising New Drug Treatment for Aggressive Leukemia | Memorial Sloan Kettering Cancer Center[EB/OL]. (2023-03-15)[2024-03-22]. https://www.mskcc.org/news/promising-new-type-drug-aggressive-leukemia.
[5] Cavasotto CN, di Filippo JI. Artificial intelligence in the early stages of drug discovery[J]. Arch Biochem Biophys, 2021, 698: 108730. doi: 10.1016/j.abb.2020.108730
[6] Gupta R, Srivastava D, Sahu M, et al. Artificial intelligence to deep learning: machine intelligence approach for drug discovery[J]. Mol Divers, 2021, 25(3): 1315-1360. doi: 10.1007/s11030-021-10217-3
[7] Zhang O, Zhang JT, Jin JY, et al. ResGen is a pocket-aware 3D molecular generation model based on parallel multiscale modelling[J]. Nat Mach Intell, 2023, 5: 1020-1030. doi: 10.1038/s42256-023-00712-7
[8] Zhang HT, Zhao HF, Zhang XJ, et al. Delete: deep lead optimization enveloped in protein pocket through unified deleting strategies and a structure-aware network[EB/OL]. arXiv, 2023: 2308.02172. http://arxiv.org/abs/2308.02172.
[9] Xiong GL, Wu ZX, Yi JC, et al. ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties[J]. Nucleic Acids Res, 2021, 49(W1): W5-W14. doi: 10.1093/nar/gkab255
[10] Jiang DJ, Lei TL, Wang Z, et al. ADMET evaluation in drug discovery. 20. Prediction of breast cancer resistance protein inhibition through machine learning[J]. J Cheminform, 2020, 12(1): 16. doi: 10.1186/s13321-020-00421-y
[11] Adasme MF, Linnemann KL, Bolz SN, et al. PLIP 2021: expanding the scope of the protein-ligand interaction profiler to DNA and RNA[J]. Nucleic Acids Res, 2021, 49(W1): W530-W534. doi: 10.1093/nar/gkab294
[12] Hain E, Camacho CJ, Koes DR. Fragment oriented molecular shapes[J]. J Mol Graph Model, 2016, 66: 143-154. doi: 10.1016/j.jmgm.2016.03.017
[13] Nicholls A, McGaughey GB, Sheridan RP, et al. Molecular shape and medicinal chemistry: a perspective[J]. J Med Chem, 2010, 53(10): 3862-3886. doi: 10.1021/jm900818s
[14] Koes DR, Camacho CJ. Shape-based virtual screening with volumetric aligned molecular shapes[J]. J Comput Chem, 2014, 35(25): 1824-1834. doi: 10.1002/jcc.23690
[15] Muhammed MT, Aki-Yalcin E. Molecular docking: principles, advances, and its applications in drug discovery[J]. Lett Drug Design Discov, 2024, 21(3): 480-495.
[16] Trott O, Olson AJ. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading[J]. J Comput Chem, 2010, 31(2): 455-461. doi: 10.1002/jcc.21334
[17] Eberhardt J, Santos-Martins D, Tillack AF, et al. AutoDock vina 1.2. 0: new docking methods, expanded force field, and python bindings[J]. J Chem Inf Model, 2021, 61(8): 3891-3898. doi: 10.1021/acs.jcim.1c00203
[18] Zhang XJ, Zhang O, Shen C, et al. Efficient and accurate large library ligand docking with KarmaDock[J]. Nat Comput Sci, 2023, 3(9): 789-804. doi: 10.1038/s43588-023-00511-5
[19] Cai H, Shen C, Jian TY, et al. CarsiDock: a deep learning paradigm for accurate protein-ligand docking and screening based on large-scale pre-training[J]. Chem Sci, 2024, 15(4): 1449-1471. doi: 10.1039/D3SC05552C
[20] Shen C, Zhang XJ, Deng YF, et al. Boosting protein-ligand binding pose prediction and virtual screening based on residue-atom distance likelihood potential and graph transformer[J]. J Med Chem, 2022, 65(15): 10691-10706. doi: 10.1021/acs.jmedchem.2c00991
计量
- 文章访问数: 172
- HTML全文浏览量: 54
- PDF下载量: 42
