Property-Based Design of GPCR-Targeted Library

Balakin, Konstantin V.; Ткаченко, С. Е.; Lang, Stanley A.; Okun, Ilya; Ivashchenko, A. V.; Savchuk, Nikolay P.

doi:10.1021/ci025538y

Cited by 69 publications

(39 citation statements)

References 20 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks were used successfully for segregation of pharmaceutical compounds into categories, such as drug likeness and nondrug likeness. 26,27 Recently, we applied ANN classification methodology for property-based design of GPCR 28 and serine protease-targeted 29 libraries.…”

Section: Predictive Modeling Using a Supervised Learning Methodsmentioning

confidence: 99%

In Silico Estimation of DMSO Solubility of Organic Compounds for Bioscreening

Balakin¹,

Ivanenkov²,

Skorenko³

et al. 2004

SLAS Discovery

Self Cite

View full text Add to dashboard Cite

Solubility of organic compounds in DMSO is an important issue for commercial and academic organizations handling large compound collections or performing biological screening. In particular, solubility data are critical for the optimization of storage conditions and for the selection of compounds for bioscreening compatible with the assay protocol. Solubility is largely determined by the solvation energy and the crystal disruption energy, and these molecular phenomena should be assessed in structure-solubility correlation studies. The authors summarize our long-term experimental observations and theoretical studies of physicochemical determinants of DMSO solubility of organic substances. They compiled a comprehensive reference database of proprietary data on compound solubility (55,277 compounds with good DMSO solubility and 10,223 compounds with poor DMSO solubility), calculated specific molecular descriptors (topological, electromagnetic, charge, and lipophilicity parameters), and applied an advanced machine-learning approach for training neural networks to address the solubility. Both supervised (feed-forward, back-propagated neural networks) and unsupervised (Kohonen neural networks) learning methods were used. The resulting neural network models were validated by successfully predicting DMSO solubility of compounds in independent test selections. (Journal of Biomolecular Screening 2004:22-31)

show abstract

Section: Predictive Modeling Using a Supervised Learning Methodsmentioning

confidence: 99%

In Silico Estimation of DMSO Solubility of Organic Compounds for Bioscreening

Balakin¹,

Ivanenkov²,

Skorenko³

et al. 2004

SLAS Discovery

Self Cite

View full text Add to dashboard Cite

show abstract

“…5,15 Fragments were characterized by widely used physicochemical descriptors such as clogP, clogD (at pH = 7.4), polar surface area (PSA) (at pH = 7.4), number of rotatable bonds, number of hydrogen bond acceptors, number of hydrogen bond donors, acidic dissociation constant pK a (related to the strongest center), basic dissociation constant pK a (related to the strongest center), number of nitrogen atoms and number of oxygen atoms using ChemAxon's JChem for Excel. 16 All the descriptors were calculated for all the fragments of both the active and the reference sets, followed by the calculation of the distribution-functions for each property.…”

Section: Selection Of Relevant Physicochemical-descriptors and Scorinmentioning

confidence: 99%

A desirability function-based scoring scheme for selecting fragment-like class A aminergic GPCR ligands

Kelemen

Ferenczy

Keserü

2014

J Comput Aided Mol Des

View full text Add to dashboard Cite

A physicochemical property-based desirability scoring scheme for fragment-based drug discovery was developed for class A aminergic GPCR targeted fragment libraries.Physichochemical property distributions of known aminergic GPCR-active fragments from the ChEMBL database were examined and used for a desirability function-based score. Propertydistributions such as logD (at pH = 7.4), PSA, pK a (strongest basic center), number of nitrogen atoms, number of oxygen atoms, and the number of rotatable bonds were combined into a desirability score (FrAGS). The validation of the scoring scheme was carried out using both public and proprietary experimental screening data. The scoring scheme is suitable for the design of aminergic GPCR targeted fragment libraries and might be useful for preprocessing fragments before structure based virtual or wet screening.2 KEYWORDS G-protein coupled receptors, fragment-based drug discovery, desirability function, aminergic fragment library INTRODUCTION Fragment based drug discovery (FBDD) implies the screening of small-

show abstract

“…In particular, privileged substructures have been identified for GPCRs ligands [93]. Classification schemes to recognize molecules acting at members of specific target families like kinases, GPCRs and serine proteases have also been developed [94][95][96]. These models, which are based on 2D descriptors and neural networks, can achieve over 80% correct classifications.…”

Section: High Throughput Docking 223 Classification Methodsmentioning

confidence: 99%