Self-organizing Neural Networks for Modeling Robust 3D and 4D QSAR: Application to Dihydrofolate Reductase Inhibitors

Polański, Jarosław; Bąk, Andrzej; Gieleciak, Rafał; Magdziarz, Tomasz

doi:10.3390/91201148

Cited by 21 publications

(22 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RI 4D-QSAR models were reported in a number of references [85][86][87][88][89][90][91][92][93]. Hopfinger designed 4D-QSAR based on MDSs.…”

Section: Rd 4d-qsarmentioning

confidence: 99%

Receptor Dependent Multidimensional QSAR for Modeling Drug - Receptor Interactions

Polański

2009

CMC

Self Cite

View full text Add to dashboard Cite

Quantitative Structure Activity Relationship (QSAR) is an approach of mapping chemical structure to properties. A significant development can be observed in the last two decades in this method which originated from the Hansch analysis based on the logP data and Hammett constant towards a growing importance of the molecular descriptors derived from 3D structure including conformational dynamics and solvation scenarios. However, molecular interactions in biological systems are complex phenomena generating extremely noisy data, if simulated in silico. This decides that activity modeling and predictions are a risky business. Molecular recognition uncertainty in traditional receptor independent (RI) m-QSAR cannot be eliminated but by the inclusion of the receptor data. Modeling ligand-receptor interactions is a complex computational problem. This has limited the development of the receptor dependent (RD) m-QSAR. However, a steady increase of computational power has also improved modeling ability in chemoinformatics and novel RD QSAR methods appeared. Following the RI m-QSAR terminology this is usually classified as RD 3/6D-QSAR. However, a clear systematic m-QSAR classification can be proposed, where dimension m refers to, the static ligand representation (3D), multiple ligand representation (4D), ligand-based virtual or pseudo receptor models (5D), multiple solvation scenarios (6D) and real receptor or target-based receptor model data (7D).

show abstract

“…The RI 4D-QSAR models were reported in a number of references [85][86][87][88][89][90][91][92][93]. Hopfinger designed 4D-QSAR based on MDSs.…”

Section: Rd 4d-qsarmentioning

confidence: 99%

Receptor Dependent Multidimensional QSAR for Modeling Drug - Receptor Interactions

Polański

2009

CMC

Self Cite

View full text Add to dashboard Cite

show abstract

“…The training set of 19-nor-testosterone derivatives includes a set of compounds formed by the steroids: [1][2][3], [6][7][8][9], [11][12][13][14], [16][17][18][19][20][21][22][23][24] and 26 (n = 21, see Fig. 2 and Table 1 for more details).…”

Section: Development and Validation Of The Qsar Modelsmentioning

confidence: 99%

“…The steroid benchmark with the corresponding globulin affinity is the most extensively studied dataset of steroids [14][15][16][17][18]. Recently, we reported multi-linear regression (MLR) QSAR models for congeneric series of AAS: 17␤-hydroxy-5␣-androstane [19], 4,5␣-dihydrotestosterone [20] and testosterone [21] steroid families.…”

Section: Introductionmentioning

confidence: 99%

Anabolic and androgenic activities of 19-nor-testosterone steroids: QSAR study using quantum and physicochemical molecular descriptors

Alvarez-Ginarte

Montero‐Cabrera

Vega

et al. 2011

The Journal of Steroid Biochemistry and Molecular Biology

View full text Add to dashboard Cite

“…Some of the models include 4D-QSAR [78,80], (FEEF) RD-3D-QSAR [83], QSAR formulated with multiple regression (MLR) and genetic algorithm (GA) [84], QSAR with evolved neural networks [82,85], QSAR/optimization correlation weights of local graph invariants (OCWLGI) based on nearest neighboring codes (NNC) [86], Self-organizing maps (SOM) 4D-QSAR [81,87], QSAR/ CoMSIA [88][89]. QSAR/CoMFA [90], QSAR/All-Oriented Search (AOS)/CoMFA [90], and Most of the above models were developed based on DHFR enzymes of species (other than P. falciparum DHFR enzyme) such as E. coli, L. casei, rat liver, P. carinini and T. gondii.…”

Section: Qsar Studies Of P Falciparum Dhfr Enzyme Inhibitorsmentioning

confidence: 99%

“…This approach mainly depends on 3D-structures of ligands, and knowledge of 3D-structures of macromolecular target is not required. In the case of receptor-based 3D-QSAR analysis (also known as receptordependent 3D-QSAR analysis), the 3D-structure of the receptor is used along with corresponding ligand structure-activity data [28,29,[78][79][80][81][82].…”

Section: Qsar Studies Of P Falciparum Dhfr Enzyme Inhibitorsmentioning

confidence: 99%

Modelling and Informatics in the Analysis of P. falciparum DHFR Enzyme Inhibitors

Adane¹,

Bharatam

2008

CMC

View full text Add to dashboard Cite

Malaria is one of the most prevalent diseases of our planet which claims millions of lives annually. Plasmodium falciparum is the causative agent of majority of the mortality and morbidity associated with malaria particularly in tropical countries. Resistance of the parasite to the currently available chemotherapeutic agents poses a serious threat to human being. Inhibition of P. falciparum dihydrofolate reductase (DHFR) enzyme has been used as one of the strategies in curbing malaria. However, due to mutation in the active-site of the enzyme particularly at 16, 51, 59, 108, and 164 residues, the parasite developed resistance to most of antifolate drugs such as cycloguanil and pyrimethamine. Thus, design of new and potent antimalarial agents which are effective against both wild-type and mutant enzymes is very essential in order to minimize burden of P. falciparum malaria. Computer-aided drug design approaches are playing a crucial role in the design of potential antimalarial drug candidates. In this article, molecular modelling studies based on docking, pharmacophore mapping, QSAR, homology modelling, and quantum chemical studies are reviewed. The importance of these methods in understanding mechanism of drug resistance at a molecular level, and design of antimalarial drug candidates are discussed briefly. The examples mentioned in the review could give insights into the wide range of possibilities of using computer-aided drug design (CADD) methodologies.

show abstract

Self-organizing Neural Networks for Modeling Robust 3D and 4D QSAR: Application to Dihydrofolate Reductase Inhibitors

Abstract: Abstract:We have used SOM and grid 3D and 4D QSAR schemes for modeling the activity of a series of dihydrofolate reductase inhibitors. Careful analysis of the performance and external predictivities proves that this method can provide an efficient inhibition model.

Cited by 21 publications

References 30 publications

Receptor Dependent Multidimensional QSAR for Modeling Drug - Receptor Interactions

Receptor Dependent Multidimensional QSAR for Modeling Drug - Receptor Interactions

Anabolic and androgenic activities of 19-nor-testosterone steroids: QSAR study using quantum and physicochemical molecular descriptors

Modelling and Informatics in the Analysis of P. falciparum DHFR Enzyme Inhibitors

Contact Info

Product

Resources

About