D3Rings: A Fast and Accurate Method for Ring System Identification and Deep Generation of Drug-Like Cyclic Compounds

被引:1
|
作者
Ma, Minfei [1 ,2 ,3 ]
Zhang, Xinben [1 ,2 ]
Zhou, Liping [1 ,2 ,3 ]
Han, Zijian [1 ,2 ,3 ]
Shi, Yulong [1 ,2 ,3 ]
Li, Jintian [1 ,2 ,3 ]
Wu, Leyun [1 ,2 ,3 ]
Xu, Zhijian [1 ,2 ,3 ]
Zhu, Weiliang [1 ,2 ,3 ]
机构
[1] Chinese Acad Sci, Stake Key Lab Drug Res, Shanghai 201203, Peoples R China
[2] Chinese Acad Sci, Shanghai Inst Materia Med, Drug Discovery & Design Ctr, Shanghai 201203, Peoples R China
[3] Univ Chinese Acad Sci, Sch Pharm, Beijing 100049, Peoples R China
基金
中国国家自然科学基金;
关键词
CHEMICAL SPACE; LANGUAGE;
D O I
10.1021/acs.jcim.3c01657
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
Continuous exploration of the chemical space of molecules to find ligands with high affinity and specificity for specific targets is an important topic in drug discovery. A focus on cyclic compounds, particularly natural compounds with diverse scaffolds, provides important insights into novel molecular structures for drug design. However, the complexity of their ring structures has hindered the applicability of widely accepted methods and software for the systematic identification and classification of cyclic compounds. Herein, we successfully developed a new method, D3Rings, to identify acyclic, monocyclic, spiro ring, fused and bridged ring, and cage ring compounds, as well as macrocyclic compounds. By using D3Rings, we completed the statistics of cyclic compounds in three different databases, e.g., ChEMBL, DrugBank, and COCONUT. The results demonstrated the richness of ring structures in natural products, especially spiro, macrocycles, and fused and bridged rings. Based on this, three deep generative models, namely, VAE, AAE, and CharRNN, were trained and used to construct two data sets similar to DrugBank and COCONUT but 10 times larger than them. The enlarged data sets were then used to explore the molecular chemical space, focusing on complex ring structures, for novel drug discovery and development. Docking experiments with the newly generated COCONUT-like data set against three SARS-CoV-2 target proteins revealed that an expanded compound database improves molecular docking results. Cyclic structures exhibited the best docking scores among the top-ranked docking molecules. These results suggest the importance of exploring the chemical space of structurally novel cyclic compounds and continuous expansion of the library of drug-like compounds to facilitate the discovery of potent ligands with high binding affinity to specific targets. D3Rings is now freely available at http://www.d3pharma.com/D3Rings/.
引用
收藏
页码:724 / 736
页数:13
相关论文
共 11 条
  • [1] Expression of metabotropic glutamate receptors in mammalian cells as a method for identification of new chemical compounds with drug-like activity
    Barbara Chruścicka
    Grzegorz Burnat
    Piotr Brański
    Andrzej Pilc
    Pharmacological Reports, 2013, 65 (Suppl 1) : 38 - 38
  • [2] 3D-Scaffold: A Deep Learning Framework to Generate 3D Coordinates of Drug-like Molecules with Desired Scaffolds
    Joshi, Rajendra P.
    Gebauer, Niklas W. A.
    Bontha, Mridula
    Khazaieli, Mercedeh
    James, Rhema M.
    Brown, James B.
    Kumar, Neeraj
    JOURNAL OF PHYSICAL CHEMISTRY B, 2021, 125 (44): : 12166 - 12176
  • [3] GalaxySagittarius-AF: Predicting Targets for Drug-Like Compounds in the Extended Human 3D Proteome
    Kwon, Sohee
    Jung, Nuri
    Yang, Jinsol
    Seok, Chaok
    JOURNAL OF MOLECULAR BIOLOGY, 2024, 436 (17)
  • [4] NEW EFFORTS AIMED AT REPLACING ACTS: THE IDENTIFICATION OF NOVEL, DRUG-LIKE, AND FAST-ACTING ANTIMALARIAL COMPOUNDS FROM A PHENOTYPIC SCREENING
    Rueda, Lourdes
    AMERICAN JOURNAL OF TROPICAL MEDICINE AND HYGIENE, 2015, 93 (04): : 295 - 295
  • [5] NEW EFFORTS AIMED AT REPLACING ARTEMISININS FOR MALARIA TREATMENT: IDENTIFICATION OF NOVEL, DRUG-LIKE AND FAST-ACTING COMPOUNDS WITH TRANSMISSION BLOCKING POTENTIAL FROM WITH PHENOTYPIC SCREENING
    Chaparro, Maria J.
    AMERICAN JOURNAL OF TROPICAL MEDICINE AND HYGIENE, 2017, 95 (05): : 121 - 121
  • [6] A new method and system for fast and accurate 3D projections in medical imaging and iterative reconstruction
    Bajic, Ivan
    MEDICAL IMAGING 2021: PHYSICS OF MEDICAL IMAGING, 2021, 11595
  • [7] A fast experimental beam hardening correction method for accurate bone mineral measurements in 3D CT imaging system
    Koubar, Khodor
    Bekaert, Virgile
    Brasse, David
    Laquerriere, Patrice
    JOURNAL OF MICROSCOPY, 2015, 258 (03) : 241 - 252
  • [8] A fast numerical method for calculating the 3D proton dose profile in a single-ring wobbling spreading system
    Z. Riazi
    H. Afarideh
    R. Sadighi-Bonabi
    Australasian Physical & Engineering Sciences in Medicine, 2011, 34 : 317 - 325
  • [9] A fast numerical method for calculating the 3D proton dose profile in a single-ring wobbling spreading system
    Riazi, Z.
    Afarideh, H.
    Sadighi-Bonabi, R.
    AUSTRALASIAN PHYSICAL & ENGINEERING SCIENCES IN MEDICINE, 2011, 34 (03) : 317 - 325
  • [10] Virtual screening and rational drug design method using structure generation system based on 3D-QSAR and docking
    Chen, HF
    Dong, XC
    Zen, BS
    Gao, K
    Yuan, SG
    Panaye, A
    Doucet, JP
    Fan, BT
    SAR AND QSAR IN ENVIRONMENTAL RESEARCH, 2003, 14 (04) : 251 - 264