Application of support vector machines to in silico prediction of cytochrome p450 enzyme substrates and inhibitors

Synthesis of Novel Pyrido[1,2-c]pyrimidine Derivatives with 6-Fluoro-3-(4-piperidynyl)-1,2-benzisoxazole Moiety as Potential SSRI and 5-HT1A Receptor Ligands

Two series of novel 4-aryl-2H-pyrido[1,2-c]pyrimidine (6a–i) and 4-aryl-5,6,7,8-tetrahydropyrido[1,2-c]pyrimidine (7a–i) derivatives were synthesized. The chemical structures of the new compounds were confirmed by ¹H and ¹³C NMR spectroscopy and ESI-HRMS spectrometry. The affinities of all compounds for the 5-HT_1A receptor and serotonin transporter protein (SERT) were determined by in vitro radioligand binding assays. The test compounds demonstrated very high binding affinities for the 5-HT_1A receptor of all derivatives in the series (6a–i and 7a–i) and generally low binding affinities for the SERT protein, with the exception of compounds 6a and 7g. Extended affinity tests for the receptors D₂, 5-HT_2A, 5-HT₆ and 5-HT₇ were conducted with regard to selected compounds (6a, 7g, 6d and 7i). All four compounds demonstrated very high affinities for the D₂ and 5-HT_2A receptors. Compounds 6a and 7g also had high affinities for 5-HT₇, while 6d and 7i held moderate affinities for this receptor. Compounds 6a and 7g were also tested in vivo to identify their functional activity profiles with regard to the 5-HT_1A receptor, with 6a demonstrating the activity profile of a presynaptic agonist. Metabolic stability tests were also conducted for 6a and 6d.

QSAR modelling and molecular docking studies for anti-cancer compounds against melanoma cell line SK-MEL-2

A dataset of seventy-two (72) cytotoxic compounds of the National Cancer Institute (NCI) was studied by QSAR and docking approaches to gain deeper insights into ligands selectivity on SK-MEL-2 cell line. The QSAR model was built using fifty (50) molecules and the best-generated model based on multiple linear regression showed, respectively good quality of fits (R 2 (0.864),R a d j u s t e d 2 (0.845), Q2 cv (0.799) andR p r e d 2 (0.706)). The model's predictive ability was determined by a test set of twenty-two (22) compounds. Compounds 30 and 41 were selected as templates for in silico design because they had high pGI50 activity and are in the model's applicability domain. The obtained information from the model was explored to design novel molecules by introducing various modifications. Moreover, the designed compounds with better-predicted activity (pGI50) values were selected and docked on the active site of the protein (PDB-CODE: 3OG7) which is responsible for melanoma cancer to elucidate their binding mode. AN2 (-12.1kcalmol-1) and AC4 (-12.4kcalmol-1) showed a better binding score for the target when compared with (vemurafenib, -11.3kcalmol-1) the known inhibitor of the target (V600E-BRAF). These findings may be very helpful in early anti-cancer drug development.

In silico prediction of potential chemical reactions mediated by human enzymes

Background

Administered drugs are often converted into an ineffective or activated form by enzymes in our body. Conventional in silico prediction approaches focused on therapeutically important enzymes such as CYP450. However, there are more than thousands of different cellular enzymes that potentially convert administered drug into other forms.

Result

We developed an in silico model to predict which of human enzymes including metabolic enzymes as well as CYP450 family can catalyze a given chemical compound. The prediction is based on the chemical and physical similarity between known enzyme substrates and a query chemical compound. Our in silico model was developed using multiple linear regression and the model showed high performance (AUC = 0.896) despite of the large number of enzymes. When evaluated on a test dataset, it also showed significantly high performance (AUC = 0.746). Interestingly, evaluation with literature data showed that our model can be used to predict not only enzymatic reactions but also drug conversion and enzyme inhibition.

Conclusion

Our model was able to predict enzymatic reactions of a query molecule with a high accuracy. This may foster to discover new metabolic routes and to accelerate the computational development of drug candidates by enabling the prediction of the potential conversion of administered drugs into active or inactive forms.

QSAR Modeling for Acute Toxicity Prediction in Rat by Common Painkiller Drugs

Painkiller drugs or analgesics are potent pain reliever chemical agents, which are commonly used in pain therapy. Mathematical modeling by QSAR (quantitative structure activity relationship) methods are well known practices to determine predictive toxicity in biota. Now-a-days, an easy screening of chemicals, QSAR can be done by using several recommended softwares. The present study was carried out by using software namely T.E.S.T. (Toxicity estimation software tool) for rat oral LD50 (median lethal dose) predictive toxicity for common painkiller drugs. These painkiller drugs were selected as 35 compounds and tabulated on the basis characteristics of one non-narcotic viz. acetaminophen, twenty non-steroidal anti-inflammatory such as bromofenac, diclofenac, diflunsial, etodolac, fenoprofen, flurbiprofen, ibuprofen, indomethacin, ketoprofen, ketorolac, maclofenamate sodium, mefenamic acid, meloxicam, nabumetone, naproxen, oxaprozin, phenylbutazone, piroxicam, sulindac and tolmetin as well as fourteen narcotic viz. buprenorphine, butorphanol, codeine, hydrocodone, hydromorphone, levorphanol, meperidine, methadone, morphine, nalbuphine, oxycodone, pentazocine, dextropropoxyphene and tapentadol. The data were tabulated on experimental (bioassay) from ChemIDPlus and predictive toxicity of 30 compounds out of 35 compounds by using T.E.S.T. The predictive data were found by T.E.S.T. that 20 and 10 compounds were very toxic and moderately toxic respectively but not extremely, super toxic and non-toxic in rat model after acute oral exposure. It is suggested to evaluate the predicted data further with other available recommended softwares with different test models like daphnia, fish etc. to know aquatic toxicity when these compounds may discharge into waterbodies.

Novel 4-aryl-pyrido[1,2-c]pyrimidines with dual SSRI and 5-HT(1A) activity. Part 5

A series of novel 4-aryl-pyrido[1,2-c]pyrimidine derivatives containing a 1-(2-quinoline)piperazine moiety was synthesized. The chemical structure of new compounds was confirmed by FT-IR, (1)H NMR, (13)C NMR and HRMS spectra as well as elemental analysis. Affinity of the novel pyrido[1,2-c]pyrimidine derivatives for 5-HT1A, 5-HT2A receptors and serotonin transporter (SERT) was evaluated in an in vitro radioligand binding assay. Tested compounds showed moderate to high affinity for 5-HT1AR and SERT and low affinity for 5-HT2AR. Selected ligands were subjected to in vivo tests, such as induced hypothermia and the forced swimming test in mice, which determined presynaptic agonistic activity of the ligands 8d, 8e, 9d and 9e and presynaptic antagonistic activity of the ligands 8a, 8b, 9a, 9b. Additionally, metabolic stability evaluation was performed for selected ligands, proving that a para-substitution in the 4-aryl-pyrido[1,2-c]pyrimidine moiety leads to an increase in stability, whereas a substitution in the ortho-position lowers the stability.

Scaffold and cell line based approaches for QSAR studies on anticancer agents

Importance of 2D QSAR in drug discovery, lower number of descriptors containing models shows best statistical parameters, number of involved scaffolds in models affects the statistical values.

The use of machine learning and nonlinear statistical tools for ADME prediction

Absorption, distribution, metabolism and excretion (ADME)-related failure of drug candidates is a major issue for the pharmaceutical industry today. Prediction of ADME by in silico tools has now become an inevitable paradigm to reduce cost and enhance efficiency in pharmaceutical research. Recently, machine learning as well as nonlinear statistical tools has been widely applied to predict routine ADME end points. To achieve accurate and reliable predictions, it would be a prerequisite to understand the concepts, mechanisms and limitations of these tools. Here, we have devised a small synthetic nonlinear data set to help understand the mechanism of machine learning by 2D-visualisation. We applied six new machine learning methods to four different data sets. The methods include Naive Bayes classifier, classification and regression tree, random forest, Gaussian process, support vector machine and k nearest neighbour. The results demonstrated that ensemble learning and kernel machine displayed greater accuracy of prediction than classical methods irrespective of the data set size. The importance of interaction with the engineering field is also addressed. The results described here provide insights into the mechanism of machine learning, which will enable appropriate usage in the future.

Classification of cytochrome p(450) activities using machine learning methods

The cytochrome P(450) (CYP) system plays an integral part in the metabolism of drugs and other xenobiotics. Knowledge of the structural features required for interaction with any of the different isoforms of the CYP system is therefore immensely valuable in early drug discovery. In this paper, we focus on three major isoforms (CYP 1A2, CYP 2D6, and CYP 3A4) and present a data set of 335 structurally diverse drug compounds classified for their interaction (as substrate, inhibitor, or any interaction) with these isoforms. We also present machine learning models using a variety of commonly used methods (k-nearest neighbors, decision tree induction using the CHAID and CRT algorithms, random forests, artificial neural networks, and support vector machines using the radial basis function (RBF) and homogeneous polynomials as kernel functions). We discuss the physicochemical features relevant for each end point and compare it to similar studies. Many of these models perform exceptionally well, even with 10-fold cross-validation, yielding corrected classification rates of 81.7 to 91.9% for CYP 1A2, 89.2 to 92.9% for CYP 2D6, and 87.4 to 89.9% for CYP3A4. Our models help in understanding the structural requirements for CYP interactions and can serve as sensitive tools in virtual screenings and lead optimization for toxicological profiles in drug discovery.

Predicting the clinical relevance of drug interactions from pre-approval studies

Drug interactions (DIs) may result in adverse drug events that could be prevented, but in many cases the available information on potential DIs is not easily transferable to clinical practice. The majority of studies date from preclinical or premarketing phases, using animals or human-derived sources that may not accurately reflect the growing clinical complexity of high-risk populations, such as the elderly, women, children, patients with chronic disease, polytherapy and impaired organ functions. Thus, at the time of approval of a new drug the information in the summary of product characteristics refers to potential DIs, but lacks specific management recommendations and is of limited clinical utility. Therefore, we set out to review in vitro and in vivo methods to predict and quantify potential DIs, to see whether these studies could help the physician tackle daily problems of the assessment and choice of combined drug therapies, and to propose, from a clinical point of view, how premarketing studies could be improved so as to help the physician at the patient's bedside. Preclinical and premarketing study design needs to be improved to make information easily accessible and clinically transferable. Studies should also take into account appropriate sample size, duration, co-morbidity, number of coadministered drugs, within- and between-subject variability, specific at-risk populations and/or drugs with a relatively narrow therapeutic window, and clinical endpoints. After premarketing development in situations where there is potential high risk of serious adverse events, specific phase IV studies (and/or active pharmacovigilance studies) should be required to monitor and quantitatively assess their clinical impact.

Reconstructing population exposures to environmental chemicals from biomarkers: challenges and opportunities

A conceptual/computational framework for exposure reconstruction from biomarker data combined with auxiliary exposure-related data is presented, evaluated with example applications, and examined in the context of future needs and opportunities. This framework employs physiologically based toxicokinetic (PBTK) modeling in conjunction with numerical "inversion" techniques. To quantify the value of different types of exposure data "accompanying" biomarker data, a study was conducted focusing on reconstructing exposures to chlorpyrifos, from measurements of its metabolite levels in urine. The study employed biomarker data as well as supporting exposure-related information from the National Human Exposure Assessment Survey (NHEXAS), Maryland, while the MENTOR-3P system (Modeling ENvironment for TOtal Risk with Physiologically based Pharmacokinetic modeling for Populations) was used for PBTK modeling. Recently proposed, simple numerical reconstruction methods were applied in this study, in conjunction with PBTK models. Two types of reconstructions were studied using (a) just the available biomarker and supporting exposure data and (b) synthetic data developed via augmenting available observations. Reconstruction using only available data resulted in a wide range of variation in estimated exposures. Reconstruction using synthetic data facilitated evaluation of numerical inversion methods and characterization of the value of additional information, such as study-specific data that can be collected in conjunction with the biomarker data. Although the NHEXAS data set provides a significant amount of supporting exposure-related information, especially when compared to national studies such as the National Health and Nutrition Examination Survey (NHANES), this information is still not adequate for detailed reconstruction of exposures under several conditions, as demonstrated here. The analysis presented here provides a starting point for introducing improved designs for future biomonitoring studies, from the perspective of exposure reconstruction; identifies specific limitations in existing exposure reconstruction methods that can be applied to population biomarker data; and suggests potential approaches for addressing exposure reconstruction from such data.

Computational prediction of drug binding and rationalisation of selectivity towards cytochromes P450

BACKGROUND

Early in-vitro consideration of metabolism and inhibition of cytochrome P450 has proven its merits over the last 15 years. Simultaneously, many computational drug-design methods have been developed, and are being applied to study the interactions between drug candidates and cytochrome P450 enzymes (P450s).

OBJECTIVE

This review discusses the recent advances of these methods and the implications that are specific for P450s.

METHODS

Mainly focusing on the prediction of binding affinity and ligand selectivity, we outline the applicability of the different methods to answer specific questions. Special emphasis is put on the different levels of theory that are being used in recent computational descriptions of ligand-P450 interactions.

CONCLUSION

P450s offer an additional challenge for computational methods, considering the ambiguities of the catalytic cycle and the significant flexibility of the active site. Different computational methods display different limitations, which is crucial to take into account when choosing the method appropriate to each application.

Predicting human liver microsomal stability with machine learning techniques

To ensure a continuing pipeline in pharmaceutical research, lead candidates must possess appropriate metabolic stability in the drug discovery process. In vitro ADMET (absorption, distribution, metabolism, elimination, and toxicity) screening provides us with useful information regarding the metabolic stability of compounds. However, before the synthesis stage, an efficient process is required in order to deal with the vast quantity of data from large compound libraries and high-throughput screening. Here we have derived a relationship between the chemical structure and its metabolic stability for a data set of in-house compounds by means of various in silico machine learning such as random forest, support vector machine (SVM), logistic regression, and recursive partitioning. For model building, 1952 proprietary compounds comprising two classes (stable/unstable) were used with 193 descriptors calculated by Molecular Operating Environment. The results using test compounds have demonstrated that all classifiers yielded satisfactory results (accuracy > 0.8, sensitivity > 0.9, specificity > 0.6, and precision > 0.8). Above all, classification by random forest as well as SVM yielded kappa values of approximately 0.7 in an independent validation set, slightly higher than other classification tools. These results suggest that nonlinear/ensemble-based classification methods might prove useful in the area of in silico ADME modeling.