Screening of selective histone deacetylase inhibitors by proteochemometric modeling

Abstract

BackgroundHistone deacetylase (HDAC) is a novel target for the treatment of cancer and it can be classified into three classes, i.e., classes I, II, and IV. The inhibitors selectively targeting individual HDAC have been proved to be the better candidate antitumor drugs. To screen selective HDAC inhibitors, several proteochemometric (PCM) models based on different combinations of three kinds of protein descriptors, two kinds of ligand descriptors and multiplication cross-terms were constructed in our study.ResultsThe results show that structure similarity descriptors are better than sequence similarity descriptors and geometry descriptors in the leftacterization of HDACs. Furthermore, the predictive ability was not improved by introducing the cross-terms in our models. Finally, a best PCM model based on protein structure similarity descriptors and 32-dimensional general descriptors was derived (R2 = 0.9897, Qtest2 = 0.7542), which shows a powerful ability to screen selective HDAC inhibitors.ConclusionsOur best model not only predict the activities of inhibitors for each HDAC isoform, but also screen and distinguish class-selective inhibitors and even more isoform-selective inhibitors, thus it provides a potential way to discover or design novel candidate antitumor drugs with reduced side effect.

Proteochemometric modeling in a Bayesian framework

“…Nonetheless, in the case of the dengue virus NS3 proteases dataset, although NP kernel produces a statistically correct modeling with RMSEP ext and $R_{0\text{italicext}}^2$ values of 0.48 and 0.91, it is slightly outperformed by the Bessel kernel, which displays respective RMSEP ext and $R_{0\text{italicext}}^2$ values of 0.44 and 0.92 (Table 2). The PUK kernel [65] exhibited strong mapping power in previous studies of HIV-1 proteases and histone deacetylases (HDAC) inhibitors, [63,64] but in the present study we could not obtain satisfactory models for none of the three datasets. The Laplacian and Bessel kernels allow a proper mapping of the three datasets with $R_{0\text{italicext}}^2$ values within the range 0.60–0.90 (see Table 2 for further details).…”

Potassium Channels: Structures, Diseases, and Modulators

“…An alternative and unbiased approach, mass spectrometry (MS)-based proteomic analysis, is also matured. Except for the advances in experiment, the developments in highperformance calculation techniques have also enhanced our knowledge into microscopic level of the working mechanism (246)(247)(248). The potential power of these methodologies in identifying the channels, as well as post-translational modifications of channel components, is already very clear (243)(244)(245).…”

Proteochemometric Modeling of the Interaction Space of Carbonic Anhydrase and its Inhibitors: An Assessment of Structure‐based and Sequence‐based Descriptors

“…A recent study has revealed that combinations of descriptors from different aspect may help increase the performance of proteochemometric modeling . PCM has been previously shown to be successful in many protein–ligand interactions studies including melanocortin receptors, G‐protein coupled receptors,, multiple mutated variants of HIV‐1 protease andreverse transcriptase, cytochrome P450,, protein kinases, dengue virus NS3 proteases, histone deacetylases, penicillin‐binding proteins, and carbonic anhydrases ,…”