Computational chemistry approach to protein kinase recognition using 3D stochastic van der Waals spectral moments

Abstract

Three-dimensional (3D) protein structures now frequently lack functional annotations because of the increase in the rate at which chemical structures are solved with respect to experimental knowledge of biological activity. As a result, predicting structure-function relationships for proteins is an active research field in computational chemistry and has implications in medicinal chemistry, biochemistry and proteomics. In previous studies stochastic spectral moments were used to predict protein stability or function (González-Díaz, H. et al. Bioorg Med Chem 2005, 13, 323; Biopolymers 2005, 77, 296). Nevertheless, these moments take into consideration only electrostatic interactions and ignore other important factors such as van der Waals interactions. The present study introduces a new class of 3D structure molecular descriptors for folded proteins named the stochastic van der Waals spectral moments ((o)beta(k)). Among many possible applications, recognition of kinases was selected due to the fact that previous computational chemistry studies in this area have not been reported, despite the widespread distribution of kinases. The best linear model found was Kact = -9.44 degrees beta(0)(c) +10.94 degrees beta(5)(c) -2.40 degrees beta(0)(i) + 2.45 degrees beta(5)(m) + 0.73, where core (c), inner (i) and middle (m) refer to specific spatial protein regions. The model with a high Matthew's regression coefficient (0.79) correctly classified 206 out of 230 proteins (89.6%) including both training and predicting series. An area under the ROC curve of 0.94 differentiates our model from a random classifier. A subsequent principal components analysis of 152 heterogeneous proteins demonstrated that beta(k) codifies information different to other descriptors used in protein computational chemistry studies. Finally, the model recognizes 110 out of 125 kinases (88.0%) in a virtual screening experiment and this can be considered as an additional validation study (these proteins were not used in training or predicting series).

QSAR model for alignment‐free prediction of human breast cancer biomarkers based on electrostatic potentials of protein pseudofolding HP‐lattice networks

“…Another limitation is the dependence only of electrostatic potential ignoring other important characteristics such as van der Waals interactions. 61,[71][72][73] Both positive (HBCp) and negative (no-HBCp) data are heterogeneous. We have carried out an alignment of the different with the default parameters.…”

“…Readers are referred to previous publications that provide detailed explanations covering the use of this kind of approach in many different situations. [13][14][15][16][17]33,39,58,[61][62][63][64] The first term is the probability of node n j moving from any node n i through walks of length k and the second is the charge of the node q j [see central member of eq. (3) below]:…”

A group center overlap based approach for “3D QSAR” studies on TIBO derivatives

“…30,31 The latter focus varies from the traditional approach on developing so called explanatory QSAR models characterized by high statistical significance but only as applied to training sets of molecules with known chemical structure and biological activity. Recently, Gonzalez-Diaz et al [32][33][34][35][36][37] have performed QSAR studies using topological indices and has justified the selection of a group of arbitrary indices based on similarities and relationships between them, for evaluation of the model without using all the known descriptors and suggested their applications in QSAR for big-sized protein molecules as well. Also some of the current trends in medicinal chemistry highlight the use of network-based connectivity indices.…”

Use of Quantitative Structure–Activity Relationship (QSAR) and ADMET prediction studies as screening methods for design of benzyl urea derivatives for anti-cancer activity

“…Computational models are one of the powerful tools to design highly active molecules 20,21 that are able to predict structures and the biological activities of anti-cancer compounds. Many QSAR studies [22][23][24][25][26] were developed and published as screening methods for design of new chemical entities (NCE′s).…”