scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Quantitative structure–activity relationship analysis and virtual screening studies for identifying HDAC2 inhibitors from known HDAC bioactive chemical libraries

TL;DR: This study illustrates the power of ML-based QSAR approaches for the screening and discovery of potent, isoform-selective HDACIs.
Abstract: Histone deacetylases (HDAC) are emerging as promising targets in cancer, neuronal diseases and immune disorders. Computational modelling approaches have been widely applied for the virtual screening and rational design of novel HDAC inhibitors. In this study, different machine learning (ML) techniques were applied for the development of models that accurately discriminate HDAC2 inhibitors form non-inhibitors. The obtained models showed encouraging results, with the global accuracy in the external set ranging from 0.83 to 0.90. Various aspects related to the comparison of modelling techniques, applicability domain and descriptor interpretations were discussed. Finally, consensus predictions of these models were used for screening HDAC2 inhibitors from four chemical libraries whose bioactivities against HDAC1, HDAC3, HDAC6 and HDAC8 have been known. According to the results of virtual screening assays, structures of some hits with pair-isoform-selective activity (between HDAC2 and other HDACs) were revealed. This study illustrates the power of ML-based QSAR approaches for the screening and discovery of potent, isoform-selective HDACIs.
Citations
More filters
Journal ArticleDOI
TL;DR: In conclusion, HDACs have shown desirable effects on breast cancer, especially when they are used in combination with other anticancer agents, and more multicenter and randomized Phase III studies are expected to be conducted pushing promising new therapies closer to the market.

41 citations

Journal ArticleDOI
TL;DR: Detailed investigation on the estimation of absorption, distribution, metabolism, excretion, and toxicity (ADMET) suggested that compounds 4g, 6c, and 6g, while showing potent HDAC2 inhibitory activity and cytotoxicity, also potentially displayed ADMET characteristics desirable to be expected as promising anticancer drug candidates.
Abstract: In our search for novel histone deacetylases inhibitors, we have designed and synthesized a series of novel hydroxamic acids and N-hydroxybenzamides incorporating quinazoline heterocycles (4a - 4i, 6a - 6i). Bioevaluation showed that these quinazoline-based hydroxamic acids and N-hydroxybenzamides were potently cytotoxic against three human cancer cell lines (SW620, colon; PC-3, prostate; NCI-H23, lung). In term of cytotoxicity, several compounds, e.g., 4g, 4c, 4g - 4i, 6c, and 6h, displayed from 5- up to 10-fold higher potency than SAHA (suberoylanilidehydroxamic acid, vorinostat). The compounds were also generally comparable to SAHA in inhibiting HDACs with IC50 values in sub-micromolar range. Some compounds, e.g., 4g, 6c, 6e, and 6h, were even more potent HDAC inhibitors compared to SAHA in HeLa extract assay. Docking studies demonstrated that the compounds tightly bound to HDAC2 at the active binding site with binding affinities higher than that of SAHA. Detailed investigation on the estimation of absorption, distribution, metabolism, excretion, and toxicity (ADMET) suggested that compounds 4g, 6c, and 6g, while showing potent HDAC2 inhibitory activity and cytotoxicity, also potentially displayed ADMET characteristics desirable to be expected as promising anticancer drug candidates.

19 citations

Journal ArticleDOI
TL;DR: Pyrrole-2,3-dicarboxylate derivatives synthesized in this study significantly inhibited the growth of HepG2 cells in a dose-dependent manner and may be proven to be novel therapeutic candidates to cure cancer.

19 citations

Journal ArticleDOI
TL;DR: This work introduces a novel approach for epigenetic quantitative structure–activity relationship (QSAR) modelling using conformal prediction and discusses the development of models for 11 sets of inhibitors of histone deacetylases, which are one of the major epigenetic target families that have been screened.
Abstract: The growing interest in epigenetic probes and drug discovery, as revealed by several epigenetic drugs in clinical use or in the lineup of the drug development pipeline, is boosting the generation of screening data. In order to maximize the use of structure-activity relationships there is a clear need to develop robust and accurate models to understand the underlying structure-activity relationship. Similarly, accurate models should be able to guide the rational screening of compound libraries. Herein we introduce a novel approach for epigenetic quantitative structure-activity relationship (QSAR) modelling using conformal prediction. As a case study, we discuss the development of models for 11 sets of inhibitors of histone deacetylases (HDACs), which are one of the major epigenetic target families that have been screened. It was found that all derived models, for every HDAC endpoint and all three significance levels, are valid with respect to predictions for the external test sets as well as the internal validation of the corresponding training sets. Furthermore, the efficiencies for the predictions are above 80% for most data sets and above 90% for four data sets at different significant levels. The findings of this work encourage prospective applications of conformal prediction for other epigenetic target data sets.

13 citations

References
More filters
Journal ArticleDOI
TL;DR: The development of small-molecule HDAC inhibitors and their use in the laboratory, in preclinical models and in the clinic are highlighted.
Abstract: Histone deacetylases (HDACs) are a class of epigenetic enzymes that remove acetyl groups from lysine residues on histones and other proteins. In this Review, the authors highlight the role of HDACs in cancer, neurological diseases and immune disorders, and discuss the development of small-molecule inhibitors. Epigenetic aberrations, which are recognized as key drivers of several human diseases, are often caused by genetic defects that result in functional deregulation of epigenetic proteins, their altered expression and/or their atypical recruitment to certain gene promoters. Importantly, epigenetic changes are reversible, and epigenetic enzymes and regulatory proteins can be targeted using small molecules. This Review discusses the role of altered expression and/or function of one class of epigenetic regulators — histone deacetylases (HDACs) — and their role in cancer, neurological diseases and immune disorders. We highlight the development of small-molecule HDAC inhibitors and their use in the laboratory, in preclinical models and in the clinic.

1,261 citations

Journal ArticleDOI
TL;DR: In vertebrates, the Rpd3/Hda1 family contains 11 members, traditionally referred to as histone deacetylases (HDAC) 1–11, which are further grouped into classes I, II and IV.
Abstract: The Rpd3/Hda1 family of protein lysine deacetylases has numerous substrates and diverse functions. Whereas class I enzymes are multiprotein histone deacetylase complexes that are crucial for chromatin modification and transcriptional regulation, some class II enzymes function as signal transducers that are regulated by nucleocytoplasmic translocation. Protein lysine deacetylases have a pivotal role in numerous biological processes and can be divided into the Rpd3/Hda1 and sirtuin families, each having members in diverse organisms including prokaryotes. In vertebrates, the Rpd3/Hda1 family contains 11 members, traditionally referred to as histone deacetylases (HDAC) 1–11, which are further grouped into classes I, II and IV. Whereas most class I HDACs are subunits of multiprotein nuclear complexes that are crucial for transcriptional repression and epigenetic landscaping, class II members regulate cytoplasmic processes or function as signal transducers that shuttle between the cytoplasm and the nucleus. Little is known about class IV HDAC11, although its evolutionary conservation implies a fundamental role in various organisms.

1,168 citations


"Quantitative structure–activity rel..." refers background in this paper

  • ...Currently, 18 HDACs have been identified in human and subdivided into four classes according to sequence homology: class I, II and IV (HDACs 1-11) are homologous to the yeast Rpd3/Hda1 family, and class III, including sirtuin proteins (Sirt 1–7), are homologous with the yeast Sir2 family [3]....

    [...]

Proceedings Article
21 Aug 2003
TL;DR: This paper proposes simple, heuristic solutions to some of the problems with Naive Bayes classifiers, addressing both systemic issues as well as problems that arise because text is not actually generated according to a multinomial model.
Abstract: Naive Bayes is often used as a baseline in text classification because it is fast and easy to implement. Its severe assumptions make such efficiency possible but also adversely affect the quality of its results. In this paper we propose simple, heuristic solutions to some of the problems with Naive Bayes classifiers, addressing both systemic issues as well as problems that arise because text is not actually generated according to a multinomial model. We find that our simple corrections result in a fast algorithm that is competitive with state-of-the-art text classification algorithms such as the Support Vector Machine.

1,050 citations


"Quantitative structure–activity rel..." refers background in this paper

  • ...Issues related to the system problems of naïve Bayes classifiers have been discussed before [62]....

    [...]

Proceedings Article
14 Aug 1997
TL;DR: The ROC convex hull method combines techniques from ROC analysis, decision analysis and computational geometry, and adapts them to the particulars of analyzing learned classifiers to present a method for the comparison of classifier performance that is robust to imprecise class distributions and misclassification costs.
Abstract: Applications of inductive learning algorithms to real-world data mining problems have shown repeatedly that using accuracy to compare classifiers is not adequate because the underlying assumptions rarely hold. We present a method for the comparison of classifier performance that is robust to imprecise class distributions and misclassification costs. The ROC convex hull method combines techniques from ROC analysis, decision analysis and computational geometry, and adapts them to the particulars of analyzing learned classifiers. The method is efficient and incremental, minimizes the management of classifier performance data, and allows for clear visual comparisons and sensitivity analyses.

821 citations

Book
17 Aug 2009
TL;DR: This essential guide to the knowledge and tools in the field includes everything from the basic concepts to modern methods, while also forming a bridge to bioinformatics.
Abstract: ChemoinformaticsChemoinformaticsTransporters as Drug CarriersMolecular Descriptors for Chemoinformatics, 2 Volume SetComputational Approaches in Cheminformatics and BioinformaticsChemokine Receptors as Drug TargetsRecent Advances in QSAR StudiesMolecular Descriptors for ChemoinformaticsA Primer on QSAR/QSPR ModelingChemoinformatics and Computational Chemical BiologyAn Introduction to ChemoinformaticsProtein Kinases as Drug TargetsAdvances in Mathematical Chemistry and Applications:Handbook of Molecular DescriptorsAspartic Acid Proteases as Therapeutic TargetsEncyclopedia of Physical Organic Chemistry, 6 Volume SetCheminformatics and its ApplicationsAdvances in QSAR ModelingChemoinformaticsVirtual ScreeningAdvanced Methods and Applications in ChemoinformaticsHandbook of ChemoinformaticsChemoinformatics and Advanced Machine Learning Perspectives: Complex Computational Methods and Collaborative TechniquesEcometabolomicsIn Silico Medicinal ChemistryKurzlehrbuch Physikalische ChemieStatistical Modelling of Molecular Descriptors in QSAR/QSPRChemical GenomicsHandbook of Bibliometric IndicatorsProdrugs and Targeted DeliveryHandbook of Computational ChemistryThe Harary Index of a GraphChemoinformaticsThe Data Analysis HandbookMedical Product Safety EvaluationPharmacokinetics and Metabolism in Drug DesignAdvances in Mathematical Chemistry and Applications:Multiscale Modeling for Process Safety ApplicationsHandbook of Chemoinformatics AlgorithmsTutorials in Chemoinformatics This essential guide to the knowledge and tools in the field includes everything from the basic concepts to modern methods, while also forming a bridge to bioinformatics. The textbook offers a very clear and didactical structure, starting from the basics and the theory, before going on to provide an overview of the methods. Learning is now even easier thanks to exercises at the end of each section or chapter. Software tools are explained in detail, so that the students not only learn the necessary theoretical background, but also how to use the different software packages available. The wide range of applications is presented in the corresponding book Applied Chemoinformatics Achievements and Future Opportunities (ISBN 9783527342013). For Master and PhD students in chemistry, biochemistry and computer science, as well as providing an excellent introduction for other newcomers to the field.Chemokines are hormone-like signaling molecules secreted by cells to signal infection and guide the immune response. Following a decade of basic chemokine research, the pharmaceutical industry has now begun to exploit this crucial signaling pathway for the development of innovative drugs against AIDS, cancer, neural and autoimmune diseases. Here is the first reference focusing on these novel drug development opportunities. Opening with a general introduction on chemokine function and chemokine receptor biology, the second part covers the known implications of these signaling molecules in human diseases, such as cancer, neural disorders, and viral infection, including AIDS. The third part systematically surveys current drug development efforts at targeting individual chemokine receptors, as well as other chemokine interaction partners, including up-to-date reports from the pharmaceutical industry.Well-recognized pioneers and investigators from diverse professional environments survey the key concepts in the field, describe cutting-edge methods, and provide exemplary pharmaceutical applications. The authors explain the theory behind the crucial concepts of molecular similarity and diversity, describe the challenging efforts to use chemoinformatics approaches to virtual and high-throughput

667 citations


"Quantitative structure–activity rel..." refers background in this paper

  • ...More information about these descriptor families can be found in Todeschini and Consonni [64]....

    [...]

  • ...This is a simple information index for unsaturated bonds, calculated as Uc = log2(1 + nDB + nTB + nAB) where nDB, nTB and nAB are the number of double, triple and aromatic bonds, respectively [64]....

    [...]