Towards Predicting the Cytochrome P450 Modulation: From QSAR to Proteochemometric Modeling

Abstract

Drug metabolism determines the fate of a drug when it enters the human body and is a critical factor in defining their absorption, distribution, metabolism, excretion and toxicity (ADMET) characteristics. Among the various drug metabolizing enzymes, cytochrome P450s (CYP450) constitute an important protein family that aside from functioning in xenobiotic metabolism, is also responsible for a diverse array of other roles encompassing steroid and cholesterol biosynthesis, fatty acid metabolism, calcium homeostasis, neuroendocrine functions and growth regulation. Although CYP450 typically converts xenobiotics into safe metabolites, there are some situations whereby the metabolite is more toxic than its parent molecule. Computational modeling has been instrumental in CYP450 research by rationalizing the nature of the binding event (i.e. inhibit or induce CYP450s) or metabolic stability of query compounds of interest. A plethora of computational approaches encompassing ligand, structure and systems based approaches have been utilized to model CYP450-ligand interactions. This review provides a brief background on the CYP450 family (i.e. its roles, advantages and disadvantages as well as its modulators) and then discusses the various computational approaches that have been used to model CYP450-ligand interaction. Particular focus was given to the use of quantitative structure-activity relationship (QSAR) and more recent proteochemometric modeling studies. Finally, a perspective on the current state of the art and future trends of the field is also provided.

Unraveling the bioactivity of anticancer peptides as deduced from machine learning

“…Details on the best practices for the development of QSAR models is beyond the scope of this review and readers are directed to previous literature (Nantasenamat and Prachayasittikul, 2015[57]; Tropsha, 2010[89]; Shoombuatong et al, 2017[80][81]). Briefly, characteristics of a robust QSAR model is best summarized by the OECD principles (OECD, 2014[63]) as outlined in Table 2(Tab.…”

“…data collection, feature representation, model construction and model evaluation (Shoombuatong et al, 2012[76], 2015[78][79], 2016[77], 2017[80][81]; Win et al, 2017[102]; Pratiwi et al, 2017[70]; Nantasenamat et al, 2015)[58]. In the point of view of machine learning, the use of reliable dataset plays a crucial role to obtain an efficient and generalized model.…”

“…Overall, most research articles showed encouraging results with having satisfied accuracies of more than 90 %. Nevertheless, there is still room for development to improve the existing methods as useful and interpretable models for facilitating experimental scientists and related researchers as demonstrated by a series of recent publications (Shoombuatong et al, 2012[76], 2015[78][79], 2016[77], 2017[80][81]; Win et al, 2017[102]; Pratiwi et al, 2017[70]; Nantasenamat et al, 2015[58]) and summarized in comprehensive reviews (Nantasenamat et al, 2015[58]; Shoombuatong et al, 2017[80][81]).…”

iQSP: A Sequence-Based Tool for the Prediction and Analysis of Quorum Sensing Peptides Using Informative Physicochemical Properties

“…Rigorous 10-fold CV and independent validation test with ten independent rounds of these classifiers based on the optimal feature subset are reported in Table 6 and Figure 5. The more details of the parameter optimization of these three classifiers were described in the works [37,38,[55][56][57][58][59][60][61]. Based the independent validation test, we noticed that the Ac, MCC and auROC values of iQSP were higher than those of other classifiers by >2%, >4%, and >2%, respectively, suggesting that iQSP holds very high potential to provide an accurate and reliable result in unseen peptides when compared to the existing methods and the conventional classifiers developed in this study.…”

Statistical Profiling of One Promiscuous Protein Binding Site: Illustrated by Urokinase Catalytic Domain

“…The advantage of proteochemometric modeling is that it integrates information on both the ligand and the three-dimensional (3D) target with the interaction information simultaneously. [5,6,7,8] Thus, it can capture some information on protein-ligand interactions, such as different binding modes, different binding sites and interaction features between ligand and binding sites. Previously, we demonstrated the interest of proteochemometric protocol in analyzing double binding site and drug spaces and in establishing binding site and drug profile correspondences enlarging the notion of protein family.…”