1
|
Bansal Y, Minhas R, Singhal A, Arora RK, Bansal G. Benzimidazole: A Multifacted Nucelus for Anticancer Agents. CURR ORG CHEM 2021. [DOI: 10.2174/1385272825666210208141107] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
Cancer is characterized by an uncontrolled proliferation of cells, dedifferentiation,
invasiveness and metastasis. Endothelial growth factor (eGF), insulin-like growth factor
(IGF), platelet-derived growth factor (PDGF), Fibroblast growth factor (FGF), Vascular endothelial
growth factor (VEGF), checkpoint kinase 1 & 2 ( Chk1 & Chk2), aurora kinases,
topoisomerases, histone deacetylators (HDAC), poly(ADP-Ribose)polymerase (PARP), farnesyl
transferases, RAS-MAPK pathway and PI3K-Akt-mTOR pathway, are some of the
prominent mediators implicated in the proliferation of tumor cells. Huge artillery of natural
and synthetic compounds as anticancer, which act by inhibiting one or more of the enzymes
and/or pathways responsible for the progression of tumor cells, is reported in the literature.
The major limitations of anticancer agents used in clinics as well as of those under development
in literature are normal cell toxicity and other side effects due to lack of specificity.
Hence, medicinal chemists across the globe have been working for decades to develop potent and safe anticancer
agents from natural sources as well as from different classes of heterocycles. Benzimidazole is one of the most important
and explored heteronucelus because of their versatility in biological actions as well as synthetic applications
in medicinal chemistry. The structural similarity of amino derivatives of benzimidazole with purines makes it a fascinating
nucleus for the development of anticancer, antimicrobial and anti-HIV agents. This review article is an attempt
to critically analyze various reports on benzimidazole derivatives acting on different targets to act as anticancer so as
to understand the structural requirements around benzimidazole nucleus for each target and enable medicinal chemists
to promote rational development of antitumor agents.
Collapse
Affiliation(s)
- Yogita Bansal
- Department of Pharmaceutical Sciences and Drug Research, Punjabi University, Patiala - 147002, India
| | - Richa Minhas
- Department of Pharmaceutical Sciences and Drug Research, Punjabi University, Patiala - 147002, India
| | - Ankit Singhal
- Department of Pharmaceutical Sciences and Drug Research, Punjabi University, Patiala - 147002, India
| | - Radhey Krishan Arora
- Department of Pharmaceutical Sciences and Drug Research, Punjabi University, Patiala - 147002, India
| | - Gulshan Bansal
- Department of Pharmaceutical Sciences and Drug Research, Punjabi University, Patiala - 147002, India
| |
Collapse
|
2
|
Chen PY, Hsu CW, Ho TI, Ho JH. The selective synthesis of N-arylbenzene-1,2-diamines or 1-arylbenzimidazoles by irradiating 4-methoxy-4'-substituted-azobenzenes in different solvents. RSC Adv 2021; 11:6662-6666. [PMID: 35423196 PMCID: PMC8694891 DOI: 10.1039/d0ra10068d] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2020] [Accepted: 01/21/2021] [Indexed: 11/21/2022] Open
Abstract
The solvent-controllable photoreaction of 4-methoxyazobenzenes to afford 1-aryl-1H-benzimidazoles or N-arylbenzene-1,2-diamines has been studied. The irradiation of 4-methoxyazobenzenes in DMF containing 0.5 M hydrochloric acid provided N2-aryl-4-methoxybenzene-1,2-diamines as the major product, while irradiation in acetal containing 0.16 M hydrochloric acid led to 1-aryl-6-methoxy-2-methyl-1H-benzimidazoles as the major product. A possible reaction mechanism explaining the selectivity was also discussed. A solvent-controllable photoreaction involving 4-methoxyazobenzenes has been developed to synthesize 1-aryl-1H-benzimidazoles or N-arylbenzene-1,2-diamines in moderate to good yields.![]()
Collapse
Affiliation(s)
- Po-Yi Chen
- Department of Chemical Engineering, National Taiwan University of Science and Technology Taiwan
| | - Chi-Wei Hsu
- Department of Chemistry, National Taiwan University Taiwan .,EdBrother Biotechnology Ltd Taiwan
| | - Tong-Ing Ho
- Department of Chemistry, National Taiwan University Taiwan
| | - Jinn-Hsuan Ho
- Department of Chemical Engineering, National Taiwan University of Science and Technology Taiwan
| |
Collapse
|
3
|
Ivanova L, Karelson M, Dobchev DA. Identification of Natural Compounds against Neurodegenerative Diseases Using In Silico Techniques. Molecules 2018; 23:E1847. [PMID: 30044400 PMCID: PMC6222649 DOI: 10.3390/molecules23081847] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2018] [Revised: 07/14/2018] [Accepted: 07/21/2018] [Indexed: 11/16/2022] Open
Abstract
The aim of this study was to identify new potentially active compounds for three protein targets, tropomyosin receptor kinase A (TrkA), N-methyl-d-aspartate (NMDA) receptor, and leucine-rich repeat kinase 2 (LRRK2), that are related to various neurodegenerative diseases such as Alzheimer's, Parkinson's, and neuropathic pain. We used a combination of machine learning methods including artificial neural networks and advanced multilinear techniques to develop quantitative structure⁻activity relationship (QSAR) models for all target proteins. The models were applied to screen more than 13,000 natural compounds from a public database to identify active molecules. The best candidate compounds were further confirmed by docking analysis and molecular dynamics simulations using the crystal structures of the proteins. Several compounds with novel scaffolds were predicted that could be used as the basis for development of novel drug inhibitors related to each target.
Collapse
Affiliation(s)
- Larisa Ivanova
- Institute of Chemistry, University of Tartu, Ravila 14a, 50411 Tartu, Estonia.
| | - Mati Karelson
- Institute of Chemistry, University of Tartu, Ravila 14a, 50411 Tartu, Estonia.
| | - Dimitar A Dobchev
- Institute of Chemistry, University of Tartu, Ravila 14a, 50411 Tartu, Estonia.
| |
Collapse
|
4
|
García-Aranda MI, Gómez-Castro CZ, García-Báez EV, Gómez YGY, Castrejón-Flores JL, Padilla-Martínez II. Involvement of conformational isomerism in the complexity of the crystal network of 1-(4-nitrophenyl)-1H-1,3-benzimidazole derivatives driven by C-H...A (A = NO 2, N py and π) and orthogonal N py...NO 2 and ONO...Csp 2 interactions. Acta Crystallogr C Struct Chem 2018; 74:428-436. [PMID: 29620026 PMCID: PMC5885323 DOI: 10.1107/s2053229618003406] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2017] [Accepted: 02/27/2018] [Indexed: 11/22/2022] Open
Abstract
A detailed structural analysis of the benzimidazole nitroarenes 1-(4-nitrophenyl)-1H-1,3-benzimidazole, C13H9N3O2, (I), 1-(4-nitrophenyl)-2-phenyl-1H-1,3-benzimidazole, C19H13N3O2, (II), and 2-(3-methylphenyl)-1-(4-nitrophenyl)-1H-1,3-benzimidazole, C20H15N3O2, (III), has been performed. They are nonplanar structures whose crystal arrangement is governed by Csp2-H...A (A = NO2, Npy and π) hydrogen bonding. The inherent complexity of the supramolecular arrangements of compounds (I) (Z' = 2) and (II) (Z' = 4) into tapes, helices and sheets is the result of the additional participation of π-πNO2 and n-π* (n = O and Npy; π* = Csp2 and NNO2) interactions that contribute to the stabilization of the equi-energetic conformations adopted by each of the independent molecules in the asymmetric unit. In contrast, compound (III) (Z' = 1) is self-paired, probably due to the effect of the steric demand of the methyl group on the crystal packing. Theoretical ab initio calculations confirmed that the presence of the arene ring at the benzimidazole 2-position increases the rotational barrier of the nitrobenzene ring and also supports the electrostatic nature of the orthogonal ONO...Csp2 and Npy...NO2 interactions.
Collapse
Affiliation(s)
- Mónica I. García-Aranda
- Laboratorio de Química Supramolecular y Nanociencias, Unidad Profesional Interdisciplinaria de Biotecnología del Instituto Politécnico Nacional, Av. Acueducto s/n Barrio la Laguna Ticomán, 07340 Mexico City, Mexico
- Laboratorio de Farmacología, Unidad Profesional Interdisciplinaria de Biotecnología del Instituto Politécnico Nacional, Av. Acueducto s/n Barrio la Laguna Ticomán, 07340 Mexico City, Mexico
| | - Carlos Z. Gómez-Castro
- Laboratorio de Química Supramolecular y Nanociencias, Unidad Profesional Interdisciplinaria de Biotecnología del Instituto Politécnico Nacional, Av. Acueducto s/n Barrio la Laguna Ticomán, 07340 Mexico City, Mexico
| | - Efrén V. García-Báez
- Laboratorio de Química Supramolecular y Nanociencias, Unidad Profesional Interdisciplinaria de Biotecnología del Instituto Politécnico Nacional, Av. Acueducto s/n Barrio la Laguna Ticomán, 07340 Mexico City, Mexico
| | - Yolanda Gómez y Gómez
- Laboratorio de Farmacología, Unidad Profesional Interdisciplinaria de Biotecnología del Instituto Politécnico Nacional, Av. Acueducto s/n Barrio la Laguna Ticomán, 07340 Mexico City, Mexico
| | - José L. Castrejón-Flores
- Laboratorio de Biotecnología Molecular, Unidad Profesional Interdisciplinaria de Biotecnología del Instituto Politécnico Nacional, Av. Acueducto s/n Barrio la Laguna Ticomán, 07340 Mexico City, Mexico
| | - Itzia I. Padilla-Martínez
- Laboratorio de Química Supramolecular y Nanociencias, Unidad Profesional Interdisciplinaria de Biotecnología del Instituto Politécnico Nacional, Av. Acueducto s/n Barrio la Laguna Ticomán, 07340 Mexico City, Mexico
| |
Collapse
|
5
|
Galal SA, Khattab M, Andreadaki F, Chrysina ED, Praly JP, Ragab FA, El Diwani HI. Synthesis of (benzimidazol-2-yl)aniline derivatives as glycogen phosphorylase inhibitors. Bioorg Med Chem 2016; 24:5423-5430. [DOI: 10.1016/j.bmc.2016.08.069] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2016] [Revised: 08/28/2016] [Accepted: 08/31/2016] [Indexed: 11/30/2022]
|
6
|
Application of radial basis function neural network and DFT quantum mechanical calculations for the prediction of the activity of 2-biarylethylimidazole derivatives as bombesin receptor subtype-3 (BRS-3) agonists. Med Chem Res 2014. [DOI: 10.1007/s00044-014-0948-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
7
|
González-Padilla JE, Rosales-Hernández MC, Padilla-Martínez II, García-Báez EV, Rojas-Lima S, Salazar-Pereda V. π-stacking and C—X...D(X= H, NO2;D= O, π) interactions in the crystal network of both C—H...N and π-stacked dimers of 1,2-bis(4-bromophenyl)-1H-benzimidazole and 2-(4-bromophenyl)-1-(4-nitrophenyl)-1H-benzimidazole. ACTA CRYSTALLOGRAPHICA SECTION C-STRUCTURAL CHEMISTRY 2013; 70:55-9. [DOI: 10.1107/s2053229613033329] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/25/2013] [Accepted: 12/09/2013] [Indexed: 11/10/2022]
Abstract
Molecules of 1,2-bis(4-bromophenyl)-1H-benzimidazole, C19H12Br2N2, (I), and 2-(4-bromophenyl)-1-(4-nitrophenyl)-1H-benzimidazole, C19H12BrN3O2, (II), are arranged in dimeric units through C—H...N and parallel-displaced π-stacking interactions favoured by the appropriate disposition of N- and C-bonded phenyl rings with respect to the mean benzimidazole plane. The molecular packing of the dimers of (I) and (II) arises by the concurrence of a diverse set of weak intermolecular C—X...D(X= H, NO2;D= O, π) interactions.
Collapse
|
8
|
Different synthetic routes to 4-(1H-benzo[d]imidazol-2-yl)aniline. RESEARCH ON CHEMICAL INTERMEDIATES 2012. [DOI: 10.1007/s11164-012-0843-z] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
9
|
Gonzalez J, Marchand-Geneste N, Giraudel JL, Shimada T. Docking and QSAR comparative studies of polycyclic aromatic hydrocarbons and other procarcinogen interactions with cytochromes P450 1A1 and 1B1. SAR AND QSAR IN ENVIRONMENTAL RESEARCH 2012; 23:87-109. [PMID: 22150106 DOI: 10.1080/1062936x.2011.636380] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/31/2023]
Abstract
To obtain chemical clues on the process of bioactivation by cytochromes P450 1A1 and 1B1, some QSAR studies were carried out based on cellular experiments of the metabolic activation of polycyclic aromatic hydrocarbons and heterocyclic aromatic compounds by those enzymes. Firstly, the 3D structures of cytochromes 1A1 and 1B1 were built using homology modelling with a cytochrome 1A2 template. Using these structures, 32 ligands including heterocyclic aromatic compounds, polycyclic aromatic hydrocarbons and corresponding diols, were docked with LigandFit and CDOCKER algorithms. Binding mode analysis highlighted the importance of hydrophobic interactions and the hydrogen bonding network between cytochrome amino acids and docked molecules. Finally, for each enzyme, multilinear regression and artificial neural network QSAR models were developed and compared. These statistical models highlighted the importance of electronic, structural and energetic descriptors in metabolic activation process, and could be used for virtual screening of ligand databases. In the case of P450 1A1, the best model was obtained with artificial neural network analysis and gave an r (2) of 0.66 and an external prediction [Formula: see text] of 0.73. Concerning P450 1B1, artificial neural network analysis gave a much more robust model, associated with an r (2) value of 0.73 and an external prediction [Formula: see text] of 0.59.
Collapse
Affiliation(s)
- J Gonzalez
- Université Bordeaux 1, Talence Cedex, France
| | | | | | | |
Collapse
|
10
|
Prediction of the melting points of fatty acids from computed molecular descriptors: A quantitative structure–property relationship study. Chem Phys Lipids 2012; 165:1-6. [DOI: 10.1016/j.chemphyslip.2011.10.001] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2011] [Revised: 10/01/2011] [Accepted: 10/03/2011] [Indexed: 11/17/2022]
|
11
|
Simple and accurate approaches to predict the activity of benzothiadiazine derivatives as HCV inhibitors. Med Chem Res 2011. [DOI: 10.1007/s00044-011-9734-x] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
12
|
Katritzky AR, Kuanar M, Slavov S, Hall CD, Karelson M, Kahn I, Dobchev DA. Quantitative Correlation of Physical and Chemical Properties with Chemical Structure: Utility for Prediction. Chem Rev 2010; 110:5714-89. [DOI: 10.1021/cr900238d] [Citation(s) in RCA: 386] [Impact Index Per Article: 27.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Alan R. Katritzky
- Center for Heterocyclic Compounds, Department of Chemistry, University of Florida, Gainesville, Florida 32611
| | - Minati Kuanar
- Center for Heterocyclic Compounds, Department of Chemistry, University of Florida, Gainesville, Florida 32611
| | - Svetoslav Slavov
- Center for Heterocyclic Compounds, Department of Chemistry, University of Florida, Gainesville, Florida 32611
| | - C. Dennis Hall
- Center for Heterocyclic Compounds, Department of Chemistry, University of Florida, Gainesville, Florida 32611
| | - Mati Karelson
- Institute of Chemistry, Tallinn University of Technology, Akadeemia tee 15, Tallinn 19086, Estonia, and MolCode, Ltd., Soola 8, Tartu 51013, Estonia
| | - Iiris Kahn
- Institute of Chemistry, Tallinn University of Technology, Akadeemia tee 15, Tallinn 19086, Estonia, and MolCode, Ltd., Soola 8, Tartu 51013, Estonia
| | - Dimitar A. Dobchev
- Institute of Chemistry, Tallinn University of Technology, Akadeemia tee 15, Tallinn 19086, Estonia, and MolCode, Ltd., Soola 8, Tartu 51013, Estonia
| |
Collapse
|
13
|
Fatemi MH, Dorostkar F. QSAR prediction of D2 receptor antagonistic activity of 6-methoxy benzamides. Eur J Med Chem 2010; 45:4856-62. [PMID: 20728966 DOI: 10.1016/j.ejmech.2010.07.056] [Citation(s) in RCA: 11] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2010] [Revised: 07/24/2010] [Accepted: 07/29/2010] [Indexed: 10/19/2022]
Abstract
Quantitative structure-activity relationship (QSAR) method was used to predict the pIC(50) value of 58 derivatives of 6-methoxy benzamides in this work. The artificial neural network (ANN) and multiple linear regressions (MLR) were used to construct the non-linear and linear QSAR models, respectively. The standard errors in the prediction of pIC(50) for training, internal and external test sets, are; 0.280, 0.446 and 0.382 by MLR model and are; 0.175, 0.326 and 0.296 by ANN model, respectively. Also these models were further examined by cross-validation methods which produce the statistics of Q(2)=0.8340 and SPRESS=0.322 for MLR model and Q(2)=0.8055 and SPRESS=0.219 for ANN model.
Collapse
Affiliation(s)
- Mohammad H Fatemi
- Laboratory of Chemometrics, Faculty of Chemistry, University of Mazandaran, Babolsar, Iran.
| | | |
Collapse
|
14
|
Jalali‐Heravi M, Asadollahi‐Baboli M. QSAR Analysis of Platelet‐derived Growth Inhibitors Using GA‐ANN and Shuffling Crossvalidation. ACTA ACUST UNITED AC 2008. [DOI: 10.1002/qsar.200710138] [Citation(s) in RCA: 15] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
|
15
|
Torrecilla JS, Rodríguez F, Bravo JL, Rothenberg G, Seddon KR, López-Martin I. Optimising an artificial neural network for predicting the melting point of ionic liquids. Phys Chem Chem Phys 2008; 10:5826-31. [DOI: 10.1039/b806367b] [Citation(s) in RCA: 79] [Impact Index Per Article: 4.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
16
|
GonzÁlez-DÍaz H, Prado-Prado FJ. Unified QSAR and network-based computational chemistry approach to antimicrobials, part 1: Multispecies activity models for antifungals. J Comput Chem 2007; 29:656-67. [DOI: 10.1002/jcc.20826] [Citation(s) in RCA: 71] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/19/2023]
|
17
|
|
18
|
Katritzky AR, Stoyanova-Slavova IB, Dobchev DA, Karelson M. QSPR modeling of flash points: An update. J Mol Graph Model 2007; 26:529-36. [PMID: 17532242 DOI: 10.1016/j.jmgm.2007.03.006] [Citation(s) in RCA: 91] [Impact Index Per Article: 5.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2006] [Revised: 03/16/2007] [Accepted: 03/19/2007] [Indexed: 11/26/2022]
Abstract
Quantitative structure-property relationship (QSPR) models for the flash points of 758 organic compounds are developed using geometrical, topological, quantum mechanical and electronic descriptors calculated by CODESSA PRO software. Multilinear regression models link the structures to their reported flash point values. We also report a nonlinear model based on an artificial neural network. The results are discussed in the light of the main factors that influence the property under investigation and its modeling.
Collapse
Affiliation(s)
- Alan R Katritzky
- Center for Heterocyclic Compounds, Department of Chemistry, University of Florida, Gainesville, FL 32611, USA.
| | | | | | | |
Collapse
|
19
|
Katritzky AR, Kuanar M, Dobchev DA, Vanhoecke BWA, Karelson M, Parmar VS, Stevens CV, Bracke ME. QSAR modeling of anti-invasive activity of organic compounds using structural descriptors. Bioorg Med Chem 2006; 14:6933-9. [PMID: 16908166 DOI: 10.1016/j.bmc.2006.06.036] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2006] [Revised: 06/14/2006] [Accepted: 06/19/2006] [Indexed: 11/20/2022]
Abstract
The anti-invasive activity of 139 compounds was correlated by an artificial neural network approach with descriptors calculated solely from the molecular structures using CODESSA Pro. The best multilinear regression method implemented in CODESSA Pro was used for a pre-selection of descriptors. The resulting nonlinear (artificial neural network) QSAR model predicted the exact class for 66 (71%) of the training set of 93 compounds and 32 (70%) of validation set of 46 compounds. The standard deviation ratios for the both training and validation sets are less than unity, indicating a satisfactory predictive capability for classification of the nature of the anti-invasive activity data. The proposed model can be used for the prediction of the anti-invasive activity of novel classes of compounds enabling a virtual screening of large databases of anticancer drugs.
Collapse
Affiliation(s)
- Alan R Katritzky
- Center for Heterocyclic Compounds, Department of Chemistry, University of Florida, Gainesville, FL 32611, USA.
| | | | | | | | | | | | | | | |
Collapse
|
20
|
Karelson M, Dobchev DA, Kulshyn OV, Katritzky AR. Neural Networks Convergence Using Physicochemical Data. J Chem Inf Model 2006; 46:1891-7. [PMID: 16995718 DOI: 10.1021/ci0600206] [Citation(s) in RCA: 14] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Abstract
An investigation of the neural network convergence and prediction based on three optimization algorithms, namely, Levenberg-Marquardt, conjugate gradient, and delta rule, is described. Several simulated neural networks built using the above three algorithms indicated that the Levenberg-Marquardt optimizer implemented as a back-propagation neural network converged faster than the other two algorithms and provides in most of the cases better prediction. These conclusions are based on eight physicochemical data sets, each with a significant number of compounds comparable to that usually used in the QSAR/QSPR modeling. The superiority of the Levenberg-Marquardt algorithm is revealed in terms of functional dependence of the change of the neural network weights with respect to the gradient of the error propagation as well as distribution of the weight values. The prediction of the models is assessed by the error of the validation sets not used in the training process.
Collapse
Affiliation(s)
- Mati Karelson
- Department of Chemistry, University of Tartu, 2 Jakobi Street, Tartu 51014, Estonia.
| | | | | | | |
Collapse
|
21
|
Katritzky AR, Pacureanu LM, Slavov S, Dobchev DA, Karelson M. QSAR study of antiplatelet agents. Bioorg Med Chem 2006; 14:7490-500. [PMID: 16945540 DOI: 10.1016/j.bmc.2006.07.022] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2006] [Revised: 07/05/2006] [Accepted: 07/07/2006] [Indexed: 11/24/2022]
Abstract
A QSAR methodology that involves multilinear (Hansch-type) and nonlinear (ANN backpropagation) approaches was developed to correlate the antiplatelet activity of 60 benzoxazinone derivatives against factor Xa. The statistical characteristics provided by multilinear model (R2 = 0.821) indicated satisfactory stability and predictive ability, while the ANN predictive ability is somewhat superior (R2 = 0.909). The multilinear model provided insight into the main factors that modulate the inhibitory activity of the investigated compounds.
Collapse
Affiliation(s)
- Alan R Katritzky
- Center for Heterocyclic Compounds, Department of Chemistry, University of Florida, Gainesville, FL 32611, USA.
| | | | | | | | | |
Collapse
|