1
|
Shayanfar S, Shayanfar A. Comparison of various methods for validity evaluation of QSAR models. BMC Chem 2022; 16:63. [PMID: 35999611 PMCID: PMC9396839 DOI: 10.1186/s13065-022-00856-4] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Accepted: 08/09/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Quantitative structure-activity relationship (QSAR) modeling is one of the most important computational tools employed in drug discovery and development. The external validation of QSAR models is the main point to check the reliability of developed models for the prediction activity of not yet synthesized compounds. It was performed by different criteria in the literature. METHODS In this study, 44 reported QSAR models for biologically active compounds reported in scientific papers were collected. Various statistical parameters of external validation of a QSAR model were calculated, and the results were discussed. RESULTS The findings revealed that employing the coefficient of determination (r2) alone could not indicate the validity of a QSAR model. The established criteria for external validation have some advantages and disadvantages which should be considered in QSAR studies. CONCLUSION This study showed that these methods alone are not only enough to indicate the validity/invalidity of a QSAR model.
Collapse
Affiliation(s)
- Shadi Shayanfar
- Student Research Committee, Faculty of Pharmacy, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Ali Shayanfar
- Pharmaceutical Analysis Research Center, Tabriz University of Medical Sciences, Tabriz, Iran. .,Editorial Office of Pharmaceutical Sciences Journal, Faculty of Pharmacy, Tabriz University of Medical Sciences, Tabriz, Iran.
| |
Collapse
|
2
|
Meng L, Ou-Yang Y, Lv F, Song J, Yao J. Research on the anti-tumor activity of a novel aminopeptidase inhibitor based on 3D QSAR model. LETT DRUG DES DISCOV 2022. [DOI: 10.2174/1570180819666220210101641] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
Background:
Aminopeptidase N (APN) is a type II transmembrane zinc ion-dependent metalloprotease. It is closely related to many processes of tumor occurrence and development, such as the formation of new blood vessels and tumor metastasis. Recent studies have shown that APN is a member of the family of surface markers of liver cancer stem cells. Therefore, APN small molecule inhibitors may have multiple compound functions, exerting multiple anti-tumor effects at multiple stages of cancer occurrence and development.
Methods:
Comparative Molecular Field Analysis (CoMFA) and Comparative Molecular Similarity Indices Analysis (CoMSIA) approaches.
Results:
Both internal and external cross-validation were conducted to obtain high predictive and satisfactory CoMFA model (q2 = 0.627, r2 =0.995, SEE = 0.043) and CoMSIA model (q2 = 0.575, r2 = 0.998, SEE = 0.031). The statistical results obtained from CoMFA and CoMSIA models were full of credibility and remarkable predictive power.
Conclusion:
The results of 3D-QSAR are reliable and significant with high predictive (q2) ability, and a lower value of the standard error of estimation indicates a good correlation between predicted and observed activity. All these results revealed many useful structural insights to improve the activity of the newly designed APN small molecule inhibitors.
Collapse
Affiliation(s)
- Liqiang Meng
- Department of Pharmacy, The Fifth People\'s Hospital of Datong City, Datong Shanxi Province, People’s republic of China
| | - Yanhong Ou-Yang
- Department of Pharmacy, The Fifth People\'s Hospital of Datong City, Datong Shanxi Province, People’s republic of China
| | - Fuyin Lv
- Department of Pharmacy, The Fifth People\'s Hospital of Datong City, Datong Shanxi Province, People’s republic of China
| | - Jiarong Song
- Department of Pharmacy, The Fifth People\'s Hospital of Datong City, Datong Shanxi Province, People’s republic of China
| | - Jianxin Yao
- Department of Pharmacy, The Fifth People\'s Hospital of Datong City, Datong Shanxi Province, People’s republic of China
| |
Collapse
|
3
|
Jian-Bo T, Xing Z, Shuai B, Ding L, Tian-Hao W. Topomer CoMFA and HQSAR Study on Benzimidazole Derivative as NS5B Polymerase Inhibitor. LETT DRUG DES DISCOV 2022. [DOI: 10.2174/1570180818666210804125607] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
Background:
In recent years, the number of people infected with the hepatitis C virus
(HCV) is increasing rapidly. This has become a major threat to global health, therefore, new anti-
HCV drugs are urgently needed. HCV NS5B polymerase is an RNA-dependent RNA polymerase
(RdRp), which plays an important role in virus replication, and can effectively prevent the replication
of HCV sub-genomic RNA in daughter cells. It is considered a very promising HCV therapeutic
target for the design of anti-HCV drugs.
Methods:
In order to explore the relationship between the structure of benzimidazole derivative and
its inhibitory activity on NS5B polymerase, holographic quantitative structure-activity relationship
(HQSAR) and Topomer comparative molecular field analysis (CoMFA) were used to establish benzimidazole
QSAR model of derivative inhibitors.
Results:
The results show that for the Topomer CoMFA model, the cross-validation coefficient q2
value is 0.883, and the non-cross-validation coefficient r2 value is 0.975. The model is reasonable,
reliable, and has a good predictive ability. For the HQSAR model, the cross-validated q2 value is
0.922, and the uncross-validated r2 value is 0.971, indicating that the model data fit well and has a
high predictive ability. Through the analysis of the contour map and color code diagram, 40 new
benzimidazole inhibitor molecules were designed, and all of them have higher activity than template
molecules, and the new molecules have significant interaction sites with protein 3SKE.
Conclusion:
The 3D-QSAR model established by Topomer CoMFA and HQSAR has good prediction
results and the statistical verification is valid. The newly designed molecules and docking results
provide theoretical guidance for the synthesis of new NS5B polymerase inhibitors and for the identification
of key residues that the inhibitors bind to NS5B, which helps to better understand their inhibitory
mechanism. These findings are helpful for the development of new anti-HCV drugs.
Collapse
Affiliation(s)
- Tong Jian-Bo
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi\'an 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi\'an, 710021, China
| | - Zhang Xing
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi\'an 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi\'an, 710021, China
| | - Bian Shuai
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi\'an 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi\'an, 710021, China
| | - Luo Ding
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi\'an 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi\'an, 710021, China
| | - Wang Tian-Hao
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi\'an 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi\'an, 710021, China
| |
Collapse
|
4
|
Bitencourt-Ferreira G, Rizzotto C, de Azevedo Junior WF. Machine Learning-Based Scoring Functions, Development and Applications with SAnDReS. Curr Med Chem 2021; 28:1746-1756. [PMID: 32410551 DOI: 10.2174/0929867327666200515101820] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2019] [Revised: 04/06/2020] [Accepted: 04/07/2020] [Indexed: 11/22/2022]
Abstract
BACKGROUND Analysis of atomic coordinates of protein-ligand complexes can provide three-dimensional data to generate computational models to evaluate binding affinity and thermodynamic state functions. Application of machine learning techniques can create models to assess protein-ligand potential energy and binding affinity. These methods show superior predictive performance when compared with classical scoring functions available in docking programs. OBJECTIVE Our purpose here is to review the development and application of the program SAnDReS. We describe the creation of machine learning models to assess the binding affinity of protein-ligand complexes. METHODS SAnDReS implements machine learning methods available in the scikit-learn library. This program is available for download at https://github.com/azevedolab/sandres. SAnDReS uses crystallographic structures, binding and thermodynamic data to create targeted scoring functions. RESULTS Recent applications of the program SAnDReS to drug targets such as Coagulation factor Xa, cyclin-dependent kinases and HIV-1 protease were able to create targeted scoring functions to predict inhibition of these proteins. These targeted models outperform classical scoring functions. CONCLUSION Here, we reviewed the development of machine learning scoring functions to predict binding affinity through the application of the program SAnDReS. Our studies show the superior predictive performance of the SAnDReS-developed models when compared with classical scoring functions available in the programs such as AutoDock4, Molegro Virtual Docker and AutoDock Vina.
Collapse
Affiliation(s)
| | - Camila Rizzotto
- Pontifical Catholic University of Rio Grande do Sul - PUCRS, Porto Alegre-RS, Brazil
| | | |
Collapse
|
5
|
Investigation of Quantitative Structure Activity Relationship of Isatin-based Oxadiazole Derivatives as Thymidine Phosphorylase Inhibitors. CHINESE JOURNAL OF ANALYTICAL CHEMISTRY 2021. [DOI: 10.1016/s1872-2040(21)60095-6] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
|
6
|
Tong JB, Luo D, Feng Y, Bian S, Zhang X, Wang TH. Structural modification of 4, 5-dihydro-[1, 2, 4] triazolo [4, 3-f] pteridine derivatives as BRD4 inhibitors using 2D/3D-QSAR and molecular docking analysis. Mol Divers 2021; 25:1855-1872. [PMID: 33392965 DOI: 10.1007/s11030-020-10172-5] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2020] [Accepted: 12/11/2020] [Indexed: 11/27/2022]
Abstract
Cancer treatment continues to be one of the most serious public health issues in the world. The overexpression of BRD4 protein has led to a series of malignant tumors, hence the development of small molecule BRD4 protease inhibitors has always been a hot spot in the field of medical research. In this study, a series of 4,5-dihydro-[1, 2, 4] triazolo [4, 3-f] pteridine derivatives were used to establish 3D/2D-QSAR models and to discuss the relationship between inhibitor structure and activity. Four ideal models were established, including the comparative molecular field analysis (CoMFA: [Formula: see text] = 0.574, [Formula: see text] = 0.947) model, comparative molecular similarity index analysis (CoMSIA: [Formula: see text]= 0.622, [Formula: see text] = 0.916) model, topomer CoMFA ([Formula: see text] = 0.691, [Formula: see text]= 0.912) model and hologram quantitative structure-activity relationship (HQSAR: [Formula: see text]= 0.759, [Formula: see text] = 0.963) model. They show quite good external predictive power for the test set, with [Formula: see text] values of 0.602, 0.624, 0.671 and 0.750, respectively. In addition, the contour and color code map given by the 2D/3D-QSAR model with the results of molecular docking analyzed to chalk up modification methods for improving inhibitory activity, which was verified by designing novel compounds. The analysis results are helpful to promote the modification of the inhibitor framework and to provide a reference for the construction of new and promising BRD4 inhibitor compounds.
Collapse
Affiliation(s)
- Jian-Bo Tong
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi'an, 710021, China.
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi'an, 710021, China.
| | - Ding Luo
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi'an, 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi'an, 710021, China
| | - Yi Feng
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi'an, 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi'an, 710021, China
| | - Shuai Bian
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi'an, 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi'an, 710021, China
| | - Xing Zhang
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi'an, 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi'an, 710021, China
| | - Tian-Hao Wang
- College of Chemistry and Chemical Engineering, Shaanxi University of Science and Technology, Xi'an, 710021, China
- Shaanxi Key Laboratory of Chemical Additives for Industry, Xi'an, 710021, China
| |
Collapse
|
7
|
Tong JB, Luo D, Zhang X, Bian S. Design of novel SHP2 inhibitors using Topomer CoMFA, HQSAR analysis, and molecular docking. Struct Chem 2020. [DOI: 10.1007/s11224-020-01677-8] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
|
8
|
Abdizadeh R, Heidarian E, Hadizadeh F, Abdizadeh T. Investigation of pyrimidine analogues as xanthine oxidase inhibitors to treat of hyperuricemia and gout through combined QSAR techniques, molecular docking and molecular dynamics simulations. J Taiwan Inst Chem Eng 2020. [DOI: 10.1016/j.jtice.2020.08.028] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
9
|
In silico studies of novel scaffold of thiazolidin-4-one derivatives as anti-Toxoplasma gondii agents by 2D/3D-QSAR, molecular docking, and molecular dynamics simulations. Struct Chem 2020. [DOI: 10.1007/s11224-019-01458-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/02/2023]
|
10
|
Zhao X, Wang X, Li Y. Combined HQSAR method and molecular docking study on genotoxicity mechanism of quinolones with higher genotoxicity. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2019; 26:34830-34853. [PMID: 31655981 DOI: 10.1007/s11356-019-06482-3] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/01/2019] [Accepted: 09/09/2019] [Indexed: 06/10/2023]
Abstract
Using the hologram quantitative structure-activity relationship (HQSAR) method, a quantitative model of the structure-activity relationship between the genotoxicity of quinolones towards gram-negative bacteria and structure of quinolones is constructed. A series of novel quinolones are designed, and 4 environmentally friendly quinolone derivatives are finally selected, because of their enhanced genotoxicity towards gram-negative/positive bacteria, decreased bioconcentration and increased photodegradability and biodegradability. The mechanisms underlying the genotoxicity of quinolones and its derivatives are analysed based on amino acid residues and molecular interactions. Three hydrophilic amino acids [arginine (ARG), asparagine (ASN) and aspartic acid (ASP)] play important roles in the antibacterial effects of quinolones. The introduction of highly hydrophilic groups into the C-7 position of amifloxacin (AMI) not only improved the stability of the AMI derivative-topoisomerase IV-DNA complex but also improved the antibacterial activities of AMI derivatives.
Collapse
Affiliation(s)
- Xiaohui Zhao
- College of Environmental Science and Engineering, North China Electric Power University, Beijing, 102206, China
- MOE Key Laboratory of Resources and Environmental Systems Optimization, North China Electric Power University, Beijing, 102206, China
| | - Xiaolei Wang
- College of Environmental Science and Engineering, North China Electric Power University, Beijing, 102206, China
- MOE Key Laboratory of Resources and Environmental Systems Optimization, North China Electric Power University, Beijing, 102206, China
| | - Yu Li
- College of Environmental Science and Engineering, North China Electric Power University, Beijing, 102206, China.
- MOE Key Laboratory of Resources and Environmental Systems Optimization, North China Electric Power University, Beijing, 102206, China.
| |
Collapse
|
11
|
Abstract
Recent progress in the development of scientific libraries with machine-learning techniques paved the way for the implementation of integrated computational tools to predict ligand-binding affinity. The prediction of binding affinity uses the atomic coordinates of protein-ligand complexes. These new computational tools made application of a broad spectrum of machine-learning techniques to study protein-ligand interactions possible. The essential aspect of these machine-learning approaches is to train a new computational model by using technologies such as supervised machine-learning techniques, convolutional neural network, and random forest to mention the most commonly applied methods. In this chapter, we focus on supervised machine-learning techniques and their applications in the development of protein-targeted scoring functions for the prediction of binding affinity. We discuss the development of the program SAnDReS and its application to the creation of machine-learning models to predict inhibition of cyclin-dependent kinase and HIV-1 protease. Moreover, we describe the scoring function space, and how to use it to explain the development of targeted scoring functions.
Collapse
Affiliation(s)
- Gabriela Bitencourt-Ferreira
- Escola de Ciências da Saúde, Pontifícia Universidade Católica do Rio Grande do Sul-PUCRS, Porto Alegre, RS, Brazil
| | - Walter Filgueira de Azevedo
- Escola de Ciências da Saúde, Pontifícia Universidade Católica do Rio Grande do Sul-PUCRS, Porto Alegre, RS, Brazil.
| |
Collapse
|