Machine-Learning-Assisted Approach for Discovering Novel Inhibitors Targeting Bromodomain-Containing Protein 4

被引:40
作者
Xing, Jing [1 ,2 ,3 ]
Lu, Wenchao [1 ,3 ]
Liu, Rongfeng [4 ]
Wang, Yulan [1 ,3 ]
Xie, Yiqian [1 ,3 ]
Zhang, Hao [1 ,3 ]
Shi, Zhe [4 ]
Jiang, Hao [1 ,3 ]
Liu, Yu-Chih [4 ]
Chen, Kaixian [1 ]
Jiang, Hualiang [1 ]
Luo, Cheng [1 ]
Zheng, Mingyue [1 ]
机构
[1] Chinese Acad Sci, Shanghai Inst Mat Med, State Key Lab Drug Res, Drug Discovery & Design Ctr, 555 Zuchongzhi Rd, Shanghai 201203, Peoples R China
[2] Peking Univ, State Key Lab Nat & Biomimet Drugs, Xue Yuan Rd 38, Beijing 100191, Peoples R China
[3] Univ Chinese Acad Sci, Dept Pharm, 19A Yuquan Rd, Beijing 100049, Peoples R China
[4] Shanghai ChemPartner Co LTD, 5 Bldg,998 Halei Rd, Shanghai 201203, Peoples R China
基金
中国国家自然科学基金;
关键词
SCORING FUNCTIONS; BET BROMODOMAINS; DRUG DISCOVERY; DOCKING; BINDING; DESIGN; CANCER; POTENT; IDENTIFICATION; KINASE;
D O I
10.1021/acs.jcim.7b00098
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
Bromodomain-containing protein 4 (BRD4) is implicated in the pathogenesis of a number of different cancers, inflammatory diseases and heart failure. Much effort has been dedicated toward discovering novel scaffold BRD4 inhibitors (BRD4is) with different selectivity profiles and potential antiresistance properties. Structure-based drug design (SBDD) and virtual screening (VS) are the most frequently used approaches. Here, we demonstrate a novel, structure based VS approach that uses machine-learning algorithms trained on the priori structure and activity knowledge to predict the likelihood that a compound is a BRD4i based on its binding pattern with BRD4. In addition to positive experimental data, such as X-ray structures of BRD4-ligand complexes and BRD4 inhibitory potencies, negative data such as false positives (FPs) identified from our earlier ligand screening results were incorporated into our knowledge base. We used the resulting data to train a machine-learning model named BRD4LGR to predict the BRD4i-likeness of a compound. BRD4LGR achieved a 20-30% higher AUC-ROC than that of Glide using the same test set. When conducting in vitro experiments against a library of previously untested, commercially available organic compounds, the second round of VS using BRD4LGR generated 15 new BRD4is. Moreover, inverting the machine-learning model provided easy access to structure-activity relationship (SAR) interpretation for hit-to-lead optimization.
引用
收藏
页码:1677 / 1690
页数:14
相关论文
共 50 条
  • [31] A computational insight into binding modes of inhibitors XD29, XD35, and XD28 to bromodomain-containing protein 4 based on molecular dynamics simulations
    Su, Jing
    Liu, Xinguo
    Zhang, Shaolong
    Yan, Fangfang
    Zhang, Qinggang
    Chen, Jianzhong
    JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS, 2018, 36 (05) : 1212 - 1224
  • [32] Genome-Wide Screen of Human Bromodomain-Containing Proteins Identifies Cecr2 as a Novel DNA Damage Response Protein
    Lee, Seul-Ki
    Park, Eun-Jung
    Lee, Han-Sae
    Lee, Ye Seul
    Kwon, Jongbum
    MOLECULES AND CELLS, 2012, 34 (01) : 85 - 91
  • [33] Computational screening of potential bromodomain-containing protein 2 inhibitors for blocking SARS-CoV-2 infection through pharmacophore modeling, molecular docking and molecular dynamics simulation
    Xu, Shaohua
    Yuan, Huicheng
    Li, Ling
    Yang, Kai
    Zhao, Liangcun
    ARABIAN JOURNAL OF CHEMISTRY, 2024, 17 (01)
  • [34] Bromodomain-containing protein 4 activates cardiotrophin-like cytokine factor 1, an unfavorable prognostic biomarker, and promotes glioblastoma in vitro
    Shen, Shang-Hang
    Guo, Jian-Feng
    Huang, Ju
    Zhang, Qian
    Cui, Yi
    ANNALS OF TRANSLATIONAL MEDICINE, 2022, 10 (08)
  • [35] A consensual machine-learning-assisted QSAR model for effective bioactivity prediction of xanthine oxidase inhibitors using molecular fingerprints
    Wu, Yanling
    Li, Menglong
    Shen, Jinru
    Pu, Xuemei
    Guo, Yanzhi
    MOLECULAR DIVERSITY, 2024, 28 (04) : 2033 - 2048
  • [36] Discovery of Thieno[2,3-d]pyrimidine-Based Hydroxamic Acid Derivatives as Bromodomain-Containing Protein 4/Histone Deacetylase Dual Inhibitors Induce Autophagic Cell Death in Colorectal Carcinoma Cells
    Pan, Zhaoping
    Li, Xiang
    Wang, Yujia
    Jiang, Qinglin
    Jiang, Li
    Zhang, Min
    Zhang, Nan
    Wu, Fengbo
    Liu, Bo
    He, Gu
    JOURNAL OF MEDICINAL CHEMISTRY, 2020, 63 (07) : 3678 - 3700
  • [37] Epigenetic Reader Bromodomain-Containing Protein 4 in Aging-Related Vascular Pathologies and Diseases: Molecular Basis, Functional Relevance, and Clinical Potential
    Zheng, Xiaoxu
    Diktonaite, Kotryna
    Qiu, Hongyu
    BIOMOLECULES, 2023, 13 (07)
  • [38] Theoretical insight into molecular mechanisms of inhibitor bindings to bromodomain-containing protein 4 using molecular dynamics simulations and calculations of binding free energies
    Wang, Lifei
    Wang, Yan
    Sun, Haibo
    Zhao, Juan
    Wang, Qing
    CHEMICAL PHYSICS LETTERS, 2019, 736
  • [39] Machine-Learning-Assisted Material Discovery of Pyridine-Based Polymers for Efficient Removal of ReO4-
    Yuan, Ling
    Guo, Haolin
    Li, Qinyang
    Zhang, Han
    Xu, Mujian
    Zhang, Weiming
    Zhang, Yanyang
    Hua, Ming
    Lv, Lu
    Pan, Bingcai
    ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2024, 58 (34) : 15298 - 15310
  • [40] Impact of bromodomain-containing protein 4 (BRD4) and intestine-specific homeobox (ISX) expression on the prognosis of patients with hepatocellular carcinoma' for better clarity
    Chuang, Kai-Ting
    Wang, Shen-Nien
    Hsu, Shih-Hsien
    Wang, Li-Ting
    CANCER MEDICINE, 2021, 10 (16): : 5545 - 5556