Figure 1. The JAK family comprises four main members: JAK1, JAK2, JAK3, and TYK2. Each kinase consists of seven homology domains (JH1-7), with JH1 being the kinase domain, JH2 the pseudokinase domain, parts of JH3 and JH4 forming the SH2 domain, and JH5, JH6, and part of JH4 making up the FERM domain. The conserved tyrosine phosphorylation sites are Y1038/Y1039 in JAK1, Y1007/Y1008 in JAK2, Y980/Y981 in JAK3, and Y1054/Y1055 in TYK2. Figure b illustrates the structure of JAKs and the sites targeted by JAK inhibitors--图1. JAK家族主要包括四个成员:JAK1、JAK2、JAK3和TYK2。每个激酶由七个同源结构域(JH1-7)组成,其中JH1是激酶结构域,JH2是伪激酶结构域,JH3和JH4的部分构成SH2结构域,而JH5、JH6和JH4的部分组成FERM结构域。保守的酪氨酸磷酸化位点分别是JAK1的Y1038/Y1039,JAK2的Y1007/Y1008,JAK3的Y980/Y981,以及TYK2的Y1054/Y1055。图b展示了JAK的结构及JAK抑制剂的靶向位点--3. CADD在JAK抑制剂筛选中的研究进展3.1. 一些临床的JAK抑制剂Figure 2. Clinical JAK inhibitors and the classification of JAK inhibitors--图2. 临床JAK抑制剂及JAK抑制剂的分类--
3.2. 结构的预测和构建Figure 3. Figure A depicts the simplified domain structure of TYK2, delineating the pseudokinase-kinase construct boundaries. Figures B and C offer distinct views of the pseudokinase and kinase complex, respectively. Figure B shows the N and C termini of the construct and the kinase inhibitor at the active site. Figure C illustrates the linker region between the pseudokinase and kinase, with simplified diagrams below for reference--图3. 图A展示了TYK2的简化结构域,标明了本研究中使用的伪激酶-激酶构建的边界。图B和图C分别展示了伪激酶和激酶复合体的两个不同视角图。图B揭示了结晶构建体的N端和C端,以及在活性位点的激酶抑制剂分子位置。图C显示了伪激酶与激酶之间的连接区域--
<xref></xref>Table 1. In the SMILES system, branches in molecules are represented by “()”, double bond cis-trans isomerism is indicated by “/” and “”, and chiral atoms in enantiomers are denoted by “[]”, with “@” representing counterclockwise and “@@” representing clockwiseTable 1. In the SMILES system, branches in molecules are represented by “()”, double bond cis-trans isomerism is indicated by “/” and “”, and chiral atoms in enantiomers are denoted by “[]”, with “@” representing counterclockwise and “@@” representing clockwise 表1. 在SMILES体系中,分子中分支用“()”表示;用“/”和“”表示双键顺反异构;对映异构中的手性原子用“[]”,@表示反时针,@@表示顺时针
中文表示
分子式
SMILES表示
苯
C6H6
C1 = CC = CC = C1
乙腈
CH3CN
CC#N
反式二溴丁烷
C4H8Br2
Br/C = C/Br或BrC = CBr
顺式二溴丁烷
C4H8Br2
Br/C = CBr或BrC = C/Br
L-丙氨酸
C3H7NO2
N [C@@H] (C) C (O) = O
D-丙氨酸
C3H7NO2
N [C@H] (C) C (O) = O
Figure 6. Generate the virtual compound by Library enumeration; the synthesis route of JAK3 inhibitor--图6. 通过文库枚举生成虚拟化合物;JAK3抑制剂的合成路线--
Figure 8. Relevance analysis on individual endpoint values and input features for the full data. a. Heat map showing the correlation among the pIC50 values of the four JAK subtype small molecular inhibitors, darker colors indicated higher relevance. b. The QED fraction distributions of the small molecules in the four tasks are plotted, the more overlapped regions the more compatible the compounds are--图8. 对整个数据的个体端点值和输入特征进行相关性分析。a. 热图显示四个JAK亚型小分子抑制剂pIC50值之间的相关性,颜色越深表示相关性越高。b. 绘制了四个任务中小分子的QED分数分布,重叠区域越多,化合物的兼容性越好--4. 总结与展望
References
Virtanen, A., Kettunen, V., Musta, K., Räkköläinen, V., Knapp, S., Haikarainen, T., et al. (2025) Molecular Basis of JAK Kinase Regulation Guiding Therapeutic Approaches: Evaluating the JAK3 Pseudokinase Domain as a Drug Target. Advances in Biological Regulation, 95, Article ID: 101072. >https://doi.org/10.1016/j.jbior.2024.101072
Lv, Y., Mi, P., Babon, J.J., Fan, G., Qi, J., Cao, L., et al. (2024) Small Molecule Drug Discovery Targeting the JAK-STAT Pathway. Pharmacological Research, 204, Article ID: 107217. >https://doi.org/10.1016/j.phrs.2024.107217
Tzeng, H., Chyuan, I. and Lai, J. (2021) Targeting the JAK-STAT Pathway in Autoimmune Diseases and Cancers: A Focus on Molecular Mechanisms and Therapeutic Potential. Biochemical Pharmacology, 193, Article ID: 114760. >https://doi.org/10.1016/j.bcp.2021.114760
Hu, X., li, J., Fu, M., Zhao, X. and Wang, W. (2021) The JAK/STAT Signaling Pathway: From Bench to Clinic. Signal Transduction and Targeted Therapy, 6, Article No. 402. >https://doi.org/10.1038/s41392-021-00791-1
Kempson, J., Ovalle, D., Guo, J., Wrobleski, S.T., Lin, S., Spergel, S.H., et al. (2017) Discovery of Highly Potent, Selective, Covalent Inhibitors of Jak3. Bioorganic&Medicinal Chemistry Letters, 27, 4622-4625. >https://doi.org/10.1016/j.bmcl.2017.09.023
Iznardo, H., Roé, E., Serra-Baldrich, E. and Puig, L. (2023) Efficacy and Safety of JAK1 Inhibitor Abrocitinib in Atopic Dermatitis. Pharmaceutics, 15, Article 385. >https://doi.org/10.3390/pharmaceutics15020385
Wrobleski, S.T., Moslin, R., Lin, S., Zhang, Y., Spergel, S., Kempson, J., et al. (2019) Highly Selective Inhibition of Tyrosine Kinase 2 (TYK2) for the Treatment of Autoimmune Diseases: Discovery of the Allosteric Inhibitor Bms-986165. Journal of Medicinal Chemistry, 62, 8973-8995. >https://doi.org/10.1021/acs.jmedchem.9b00444
Mohamed, M.F., Trueman, S., Othman, A.A., Han, J., Ju, T.R. and Marroum, P. (2019) Development of in Vitro—In Vivo Correlation for Upadacitinib Extended-Release Tablet Formulation. The AAPS Journal, 21, Article No. 108. >https://doi.org/10.1208/s12248-019-0378-y
郁倩倩, 蒋颖敏, 许磊, 等. 整合药效团及共价对接用于虚拟筛选JAK3抑制剂[J]. 化学通报(印刷版), 2021, 84(10): 1102-1107.
Lin, W. and Karin, M. (2007) A Cytokine-Mediated Link between Innate Immunity, Inflammation, and Cancer. Journal of Clinical Investigation, 117, 1175-1183. >https://doi.org/10.1172/jci31537
Sabnis, R.W. (2021) Novel Indole Compounds as TEAD Inhibitors for Treating Cancer. ACS Medicinal Chemistry Letters, 12, 1885-1886. >https://doi.org/10.1021/acsmedchemlett.1c00609
Lupardus, P.J., Ultsch, M., Wallweber, H., Bir Kohli, P., Johnson, A.R. and Eigenbrot, C. (2014) Structure of the Pseudokinase–kinase Domains from Protein Kinase TYK2 Reveals a Mechanism for Janus Kinase (JAK) Autoinhibition. Proceedings of the National Academy of Sciences, 111, 8025-8030. >https://doi.org/10.1073/pnas.1401180111
Qiu, G., Yu, L., Jia, L., Cai, Y., Chen, Y., Jin, J., et al. (2024) Identification of Novel Covalent JAK3 Inhibitors through Consensus Scoring Virtual Screening: Integration of Common Feature Pharmacophore and Covalent Docking. Molecular Diversity. >https://doi.org/10.1007/s11030-024-10918-5
Zhao, L., Liang, Q., He, Y., Liu, M., Tong, R., Jiang, Z., et al. (2022) HDAC/JAK Dual Target Inhibitors of Cancer-Related Targets: The Success of Nonclearable Linked Pharmacophore Mode. Bioorganic Chemistry, 129, Article ID: 106181. >https://doi.org/10.1016/j.bioorg.2022.106181
Bajusz, D., Ferenczy, G.G. and Keserű, G.M. (2016) Ensemble Docking-Based Virtual Screening Yields Novel Spirocyclic JAK1 Inhibitors. Journal of Molecular Graphics and Modelling, 70, 275-283. >https://doi.org/10.1016/j.jmgm.2016.10.014
Bono, A., La Monica, G., Alamia, F., Lauria, A. and Martorana, A. (2025) A Novel in Silico Approach for Identifying Multi-Target JAK/STAT Inhibitors as Anticancer Agents. Journal of Molecular Graphics and Modelling, 135, Article ID: 108913. >https://doi.org/10.1016/j.jmgm.2024.108913
Liu, J., Chen, D., Liu, H., Sha, H., Song, D., Bao, T., et al. (2018) Correction: A MicroRNA-4516 Inhibitor Sensitizes Chemo-Resistant Gastric Cancer Cells to Chemotherapy by Upregulating ING4. RSC Advances, 8, 39126-39126. >https://doi.org/10.1039/c8ra90089b
Chen, C., Yin, Y., Shi, G., Zhou, Y., Shao, S., Wei, Y., et al. (2022) A Highly Selective JAK3 Inhibitor Is Developed for Treating Rheumatoid Arthritis by Suppressing γc Cytokine-Related JAK-STAT Signal. Science Advances, 8, eabo4363. >https://doi.org/10.1126/sciadv.abo4363
Bajorath, J. (2024) Milestones in Chemoinformatics: Global View of the Field. Journal of Cheminformatics, 16, Article No. 124. >https://doi.org/10.1186/s13321-024-00922-0
Thorarensen, A., Dowty, M.E., Banker, M.E., Juba, B., Jussif, J., Lin, T., et al. (2017) Design of a Janus Kinase 3 (JAK3) Specific Inhibitor 1-((2s, 5r)-5-((7h-Pyrrolo[2, 3-d]pyrimidin-4-Yl)amino)-2-Methylpiperidin-1-Yl)prop-2-En-1-One (PF-06651600) Allowing for the Interrogation of JAK3 Signaling in Humans. Journal of Medicinal Chemistry, 60, 1971-1993. >https://doi.org/10.1021/acs.jmedchem.6b01694
Wang, Y., Sun, Y., Cao, R., Liu, D., Xie, Y., Li, L., et al. (2017) In Silico Identification of a Novel Hinge-Binding Scaffold for Kinase Inhibitor Discovery. Journal of Medicinal Chemistry, 60, 8552-8564. >https://doi.org/10.1021/acs.jmedchem.7b01075
Reymond, J. (2001) New High-Throughput Screening Assays for Biocatalysis. CHIMIA, 55, 1049-1052. >https://doi.org/10.2533/chimia.2001.1049
Lavecchia, A. (2015) Machine-learning Approaches in Drug Discovery: Methods and Applications. Drug Discovery Today, 20, 318-331. >https://doi.org/10.1016/j.drudis.2014.10.012
Carpenter, K.A., Cohen, D.S., Jarrell, J.T. and Huang, X.D. (2018) Deep Learning and Virtual Drug Screening. Future Medicinal Chemistry, 10, 2557-2567.
Gupta, R., Srivastava, D., Sahu, M., Tiwari, S., Ambasta, R.K. and Kumar, P. (2021) Artificial Intelligence to Deep Learning: Machine Intelligence Approach for Drug Discovery. Molecular Diversity, 25, 1315-1360. >https://doi.org/10.1007/s11030-021-10217-3
Arciuli, J. (2017) The Multi-Component Nature of Statistical Learning. Philosophical Transactions of the Royal Society B: Biological Sciences, 372, 20160058. >https://doi.org/10.1098/rstb.2016.0058
Belenahalli Shekarappa, S., Kandagalla, S. and Lee, J. (2023) Development of Machine Learning Models Based on Molecular Fingerprints for Selection of Small Molecule Inhibitors against JAK2 Protein. Journal of Computational Chemistry, 44, 1493-1504. >https://doi.org/10.1002/jcc.27103
He, L., Liu, J., Zhao, H., Zhang, L., Yu, R. and Kang, C. (2023) De Novo Design of Dual-Target JAK2, SMO Inhibitors Based on Deep Reinforcement Learning, Molecular Docking and Molecular Dynamics Simulations. Biochemical and Biophysical Research Communications, 638, 23-27. >https://doi.org/10.1016/j.bbrc.2022.11.017
Wang, Y., Gu, Y., Lou, C., Gong, Y., Wu, Z., Li, W., et al. (2022) A Multitask GNN-Based Interpretable Model for Discovery of Selective JAK Inhibitors. Journal of Cheminformatics, 14, Article No. 16. >https://doi.org/10.1186/s13321-022-00593-9