Predicting ADME properties in silico: methods and models

Synthesis, Biological Assessment, and Structure Activity Relationship Studies of New Flavanones Embodying Chromene Moieties

Novel flavanones that incorporate chromene motifs are synthesized via a one-step multicomponent reaction. The structures of the new chromenes are elucidated by using IR, ¹H-NMR, ¹³C-NMR, ¹H-¹H COSY, HSQC, HMBC, and elemental analysis. The new compounds are screened for their in vitro antimicrobial and cytotoxic activities. The antimicrobial properties are investigated and established against seven human pathogens, employing the agar well diffusion method and the minimum inhibitory concentrations. A majority of the assessed derivatives are found to exhibit significant antimicrobial activities against most bacterial strains, in comparison to standard reference drugs. Moreover, their cytotoxicity is appraised against four different human carcinoma cell lines: human colon carcinoma (HCT-116), human hepatocellular carcinoma (HepG-2), human breast adenocarcinoma (MCF-7), and adenocarcinoma human alveolar basal epithelial cell (A-549). All the desired compounds are subjected to in-silico studies, forecasting their drug likeness, bioactivity, and the absorption, distribution, metabolism, and excretion (ADME) properties prior to their synthetic assembly. The in-silico molecular docking evaluation of all the targeted derivatives is undertaken on gyrase B and the cyclin-dependent kinase. The in-silico predicted outcomes were endorsed by the in vitro studies.

Machine learning approaches and databases for prediction of drug-target interaction: a survey paper

The task of predicting the interactions between drugs and targets plays a key role in the process of drug discovery. There is a need to develop novel and efficient prediction approaches in order to avoid costly and laborious yet not-always-deterministic experiments to determine drug–target interactions (DTIs) by experiments alone. These approaches should be capable of identifying the potential DTIs in a timely manner. In this article, we describe the data required for the task of DTI prediction followed by a comprehensive catalog consisting of machine learning methods and databases, which have been proposed and utilized to predict DTIs. The advantages and disadvantages of each set of methods are also briefly discussed. Lastly, the challenges one may face in prediction of DTI using machine learning approaches are highlighted and we conclude by shedding some lights on important future research directions.

A Bayesian machine learning approach for drug target identification using diverse data types

Drug target identification is a crucial step in development, yet is also among the most complex. To address this, we develop BANDIT, a Bayesian machine-learning approach that integrates multiple data types to predict drug binding targets. Integrating public data, BANDIT benchmarked a ~90% accuracy on 2000+ small molecules. Applied to 14,000+ compounds without known targets, BANDIT generated ~4,000 previously unknown molecule-target predictions. From this set we validate 14 novel microtubule inhibitors, including 3 with activity on resistant cancer cells. We applied BANDIT to ONC201—an anti-cancer compound in clinical development whose target had remained elusive. We identified and validated DRD2 as ONC201’s target, and this information is now being used for precise clinical trial design. Finally, BANDIT identifies connections between different drug classes, elucidating previously unexplained clinical observations and suggesting new drug repositioning opportunities. Overall, BANDIT represents an efficient and accurate platform to accelerate drug discovery and direct clinical application.

Drug target identification is a crucial step in drug development. Here, the authors introduce a Bayesian machine learning framework that integrates multiple data types to predict the targets of small molecules, enabling identification of a new set of microtubule inhibitors and the target of the anti-cancer molecule ONC201.

Synthesis, Biological Evaluation and In Silico Computational Studies of 7-Chloro-4-(1H-1,2,3-triazol-1-yl)quinoline Derivatives: Search for New Controlling Agents against Spodoptera frugiperda (Lepidoptera: Noctuidae) Larvae

The insecticidal and antifeedant activities of five 7-chloro-4-(1H-1,2,3-triazol-1-yl)quinoline derivatives were evaluated against the maize armyworm, Spodoptera frugiperda (J.E. Smith). These hybrids were prepared through a copper-catalyzed azide alkyne cycloaddition (CuAAC, known as a click reaction) and displayed larvicidal properties with LD₅₀ values below 3 mg/g insect, and triazolyl-quinoline hybrid 6 showed an LD₅₀ of 0.65 mg/g insect, making it 2-fold less potent than methomyl, which was used as a reference insecticide (LD₅₀ = 0.34 mg/g insect). Compound 4 was the most active antifeedant derivative (CE₅₀ = 162.1 μg/mL) with a good antifeedant index (56-79%) at concentrations of 250-1000 μg/mL. Additionally, triazolyl-quinoline hybrids 4-8 exhibited weak inhibitory activity against commercial acetylcholinesterase from Electrophorus electricus (electric-eel AChE) (IC₅₀ = 27.7 μg/mL) as well as low anti-ChE activity on S. frugiperda larvae homogenate (IC₅₀ = 68.4 μg/mL). Finally, molecular docking simulations suggested that hybrid 7 binds to the catalytic active site (CAS) of this enzyme and around the rim of the enzyme cavity, acting as a mixed (competitive and noncompetitive) inhibitor like methomyl. Triazolyl-quinolines 4-6 and 8 inhibit AChE by binding over the perimeter of the enzyme cavity, functioning as noncompetitive inhibitors. The results described in this work can help to identify lead triazole structures from click chemistry for the development of insecticide and deterrent products against S. frugiperda and related insect pests.

In Vitro Methods in the Prediction of Kinetics of Drugs: Focus on Drug Metabolism

The absorption, distribution, metabolism, excretion and toxicity (ADMET) properties of a candidate drug influence its final clinical success. These properties have traditionally been evaluated by using various in vivo animal approaches, but recently, a number of in vitro and in silico methods have been introduced to determine key ADMET features. Basic events, such as absorption through the gut wall, binding to plasma proteins, active and passive transfer through the blood-brain barrier, and various metabolic parameters, can now be screened with rapid in vitro and computer modelling methods. The focus in this short review is on the basic in vitro and in silico methods that are used for studying the metabolism properties of new drug molecules.

A comprehensive review of feature based methods for drug target interaction prediction

Drug target interaction is a prominent research area in the field of drug discovery. It refers to the recognition of interactions between chemical compounds and the protein targets in the human body. Wet lab experiments to identify these interactions are expensive as well as time consuming. The computational methods of interaction prediction help limit the search space for these experiments. These computational methods can be divided into ligand based approaches, docking approaches and chemogenomic approaches. In this review, we aim to describe the various feature based chemogenomic methods for drug target interaction prediction. It provides a comprehensive overview of the various techniques, datasets, tools and metrics. The feature based methods have been categorized, explained and compared. A novel framework for drug target interaction prediction has also been proposed that aims to improve the performance of existing methods. To the best of our knowledge, this is the first comprehensive review focusing only on feature based methods of drug target interaction.

Bioinformatics Approaches to Predict Drug Responses from Genomic Sequencing

Fulfilling the promises of precision medicine will depend on our ability to create patient-specific treatment regimens. Therefore, being able to translate genomic sequencing into predicting how a patient will respond to a given drug is critical. In this chapter, we review common bioinformatics approaches that aim to use sequencing data to predict sample-specific drug susceptibility. First, we explain the importance of customized drug regimens to the future of medical care. Second, we discuss the different public databases and community efforts that can be leveraged to develop new methods for identifying new predictive biomarkers. Third, we cover the basic methods that are currently used to identify markers or signatures of drug response, without any prior knowledge of the drug's mechanism of action. We further discuss how one can integrate knowledge about drug targets, mechanisms, and predictive markers to better estimate drug response in a diverse set of samples. We begin this section with a primer on popular methods to identify targets and mechanism of action for new small molecules. This discussion also includes a set of computational methods that incorporate other drug features, which do not relate to drug-induced genetic changes or sequencing data such as drug structures, side-effects, and efficacy profiles. Those additional drug properties can aid in gaining higher accuracy for the identification of drug target and mechanism of action. We then progress to discuss using these targets in combination with disease-specific expression patterns, known pathways, and genetic interaction networks to aid drug choice. Finally, we conclude this chapter with a general overview of machine learning methods that can integrate multiple pieces of sequencing data along with prior drug or biological knowledge to drastically improve response prediction.

MDCKpred: a web-tool to calculate MDCK permeability coefficient of small molecule using membrane-interaction chemical features

Structure-based models to understand the transport of small molecules through biological membrane can be developed by enumerating intermolecular interactions of the small molecule with a biological membrane, usually a dimyristoylphosphatidylcholine (DMPC) monolayer. This ADME (absorption, distribution, metabolism, and excretion) property based on Madin-Darby Canine Kidney (MDCK) cell line demonstrates intestinal drug absorption of small molecules and correlated to human intestinal absorption which acts as a determining factor to forecast small-molecule prioritization in drug-discovery projects. We present here the development of MDCKpred web-tool which calculates MDCK permeability coefficient of small molecule based on the regression model, developed using membrane-interaction chemical features. The web-tool allows users to calculate the MDCK permeability coefficient (nm/s) instantly by providing simple descriptor inputs. The chemical-interaction features are derived from different parts of the DMPC molecule viz. head, middle, and tail regions and accounts overall intermolecular contacts of the small molecule when passively diffused through the phospholipid-rich biological membrane. The MDCKpred model is both internally (R² = .76; [Formula: see text]= .68; R_train = .87; R_test = .69) and externally (R_ext = .55) validated. Furthermore, we used natural molecules as application examples to demonstrate its utility in lead exploration and optimization projects. The MDCKpred web-tool can be accessed freely at http://www.mdckpred.in . This web-tool is designed to offer an intuitive way of prioritizing small molecules based on calculated MDCK permeabilities.

Identification of chemically diverse GABAA agonists as potential anti-epileptic agents using structure-guided virtual screening, ADMET, quantum mechanics and clinical validation through off-target analysis

Development of resistance against existing anti-epileptic drugs has alarmed the scientific innovators to find novel potential chemical starting points for the treatment of epilepsy and GABA_A inhibition is a promising drug target strategy against epilepsy. The crystal structure of a subtype-selective β3-homopentameric ligand-gated ion channel of GABA_A receptor has been used for the first time for screening the Asinex library for discovery of GABA_A agonists as potential anti-epileptic agents. Co-crystallized ligand established the involvement of part of the β7-β8 loop (Glu155 and Tyr157) and β9-β10 loop (Phe200 and Tyr205) residues as the crucial amino acids in effective binding, an essential feature, being hydrogen bond or ionic interaction with Glu155 residue. Top ranked hits were further subjected to binding energy estimation, ADMET analysis and ligand efficiency matric calculations as consecutive filters. About 19 compounds qualifying all parameters possessed interaction of one positively charged group with Glu155 with good CNS drug-like properties. Simulation studies were performed on the apo protein, its complex with co-crystallized ligand and the best hit qualifying all screening parameters. The best hit was also analyzed using Quantum mechanical studies, off-target analysis and hit modification. The off-target analysis emphasized that these agents did not have any other predicted side-effects.

Technologies for Measuring Pharmacokinetic Profiles

The creation of a pharmacokinetic (PK) curve, which follows the plasma concentration of an administered drug as a function of time, is a critical aspect of the drug development process and includes such information as the drug's bioavailability, clearance, and elimination half-life. Prior to a drug of interest gaining clearance for use in human clinical trials, research is performed during the preclinical stages to establish drug safety and dosing metrics from data obtained from the PK studies. Both in vivo animal models and in vitro platforms have limitations in predicting human reaction to a drug due to differences in species and associated simplifications, respectively. As a result, in silico experiments using computer simulation have been implemented to accurately predict PK parameters in human studies. This review assesses these three approaches (in vitro, in vivo, and in silico) when establishing PK parameters and evaluates the potential for in silico studies to be the future gold standard of PK preclinical studies.

Computer-Aided Multi-Target Management of Emergent Alzheimer's Disease

Alzheimer's disease (AD) represents an enormous global health burden in terms of human suffering and economic cost. AD management requires a shift from the prevailing paradigm targeting pathogenesis to design and develop effective drugs with adequate success in clinical trials. Therefore, it is of interest to report a review on amyloid beta (Aβ) effects and other multi-targets including cholinesterase, NFTs, tau protein and TNF associated with brain cell death to be neuro-protective from AD. It should be noted that these molecules have been generated either by target-based or phenotypic methods. Hence, the use of recent advancements in nanomedicine and other natural compounds screening tools as a feasible alternative for circumventing specific liabilities is realized. We review recent developments in the design and identification of neuro-degenerative compounds against AD generated using current advancements in computational multi-target modeling algorithms reflected by theragnosis (combination of diagnostic tests and therapy) concern.

Learning a Local-Variable Model of Aromatic and Conjugated Systems

A collection of new approaches to building and training neural networks, collectively referred to as deep learning, are attracting attention in theoretical chemistry. Several groups aim to replace computationally expensive ab initio quantum mechanics calculations with learned estimators. This raises questions about the representability of complex quantum chemical systems with neural networks. Can local-variable models efficiently approximate nonlocal quantum chemical features? Here, we find that convolutional architectures, those that only aggregate information locally, cannot efficiently represent aromaticity and conjugation in large systems. They cannot represent long-range nonlocality known to be important in quantum chemistry. This study uses aromatic and conjugated systems computed from molecule graphs, though reproducing quantum simulations is the ultimate goal. This task, by definition, is both computable and known to be important to chemistry. The failure of convolutional architectures on this focused task calls into question their use in modeling quantum mechanics. To remedy this heretofore unrecognized deficiency, we introduce a new architecture that propagates information back and forth in waves of nonlinear computation. This architecture is still a local-variable model, and it is both computationally and representationally efficient, processing molecules in sublinear time with far fewer parameters than convolutional networks. Wave-like propagation models aromatic and conjugated systems with high accuracy, and even models the impact of small structural changes on large molecules. This new architecture demonstrates that some nonlocal features of quantum chemistry can be efficiently represented in local variable models.

Linear and Kernel Model Construction Methods for Predicting Drug-Target Interactions in a Chemogenomic Framework

Identification of drug-target interactions is a crucial process in drug discovery. In this chapter, we present protocols for recent advancements in machine learning methods for predicting drug-target interactions from heterogeneous biological data in a chemogenomic framework, in which prediction is based on the chemical structure data of drug candidate compounds and translated genomic sequence data of target candidate proteins. Most existing methods are based on either linear modeling or kernel modeling. To illustrate linear modeling, we introduce sparsity-induced binary classifiers and sparse canonical correlation analysis. To illustrate kernel modeling, we introduce pairwise kernel-based support vector machines and kernel-based distance learning. Workflows for using these techniques are presented. We also discuss the characteristics of each method and suggest some directions for future research.

Sparse Modeling to Analyze Drug-Target Interaction Networks

Most drugs produce their phenotypic effects by interacting with target proteins, and understanding the molecular features that underpin drug-target interactions is crucial when designing a novel drug. In this chapter, we introduce the protocols that have driven recent advances in sparse modeling methods for analyzing drug-target interaction networks within a chemogenomic framework. In this approach, the chemical structures of candidate drug compounds are correlated with the genomic sequences of the candidate target proteins. We demonstrate the use of sparse canonical correspondence analysis and sparsity-induced binary classifiers to extract the underlying molecular features that are most strongly involved in drug-target interactions. We focus on drug chemical substructures and protein domains. Workflows for applying these methods are presented, and an application is described in detail. We consider the characteristics of each method and suggest possible directions for future research.

De Novo Design of Ligands Using Computational Methods

De novo design technique is complementary to high-throughput virtual screening and is believed to contribute in pharmaceutical development of novel drugs with desired properties at a very low cost and time-efficient manner. In this chapter, we outline the basic de novo design concepts based on computational methods with an example.

Design of Drugs by Filtering Through ADMET, Physicochemical and Ligand-Target Flexibility Properties

There is a synergistic interaction between medicinal chemistry, chemoinformatics, and bioinformatics. The last one includes analyses of sequences as well as structural analysis which employ computational techniques such as docking studies and molecular dynamics (MD) simulations. Over the last years these techniques have allowed the development of new accurate computational tools for drug design. As a result, there have been an increased number of publications where computational methods such as pharmacophore modeling, de novo drug design, evaluation of physicochemical properties, and analysis of ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties have been quite useful for eliminating the compounds with poor physicochemical or toxicological properties. Furthermore, using MD simulations and docking analysis, it is possible to estimate the binding energy of the protein-ligand complexes by using scoring functions, as well as to structurally depict the binding pose of the compounds on proteins, in order to select the best evaluated compounds for subsequent synthetizing and evaluation through biological assays. In this work, we describe some computational tools that have been used for structure-based drug design of new compounds that target histone deacetylases (HDACs), which are known to be potential targets in cancer and parasitic diseases.

Modeling Pharmacokinetics

Pharmacokinetics is the study of the fate of xenobiotics in a living organism. Physiologically based pharmacokinetic (PBPK) models provide realistic descriptions of xenobiotics' absorption, distribution, metabolism, and excretion processes. They model the body as a set of homogeneous compartments representing organs, and their parameters refer to anatomical, physiological, biochemical, and physicochemical entities. They offer a quantitative mechanistic framework to understand and simulate the time-course of the concentration of a substance in various organs and body fluids. These models are well suited for performing extrapolations inherent to toxicology and pharmacology (e.g., between species or doses) and for integrating data obtained from various sources (e.g., in vitro or in vivo experiments, structure-activity models). In this chapter, we describe the practical development and basic use of a PBPK model from model building to model simulations, through implementation with an easily accessible free software.

Prediction of Drug-Target Interaction Networks from the Integration of Protein Sequences and Drug Chemical Structures

Knowledge of drug–target interaction (DTI) plays an important role in discovering new drug candidates. Unfortunately, there are unavoidable shortcomings; including the time-consuming and expensive nature of the experimental method to predict DTI. Therefore, it motivates us to develop an effective computational method to predict DTI based on protein sequence. In the paper, we proposed a novel computational approach based on protein sequence, namely PDTPS (Predicting Drug Targets with Protein Sequence) to predict DTI. The PDTPS method combines Bi-gram probabilities (BIGP), Position Specific Scoring Matrix (PSSM), and Principal Component Analysis (PCA) with Relevance Vector Machine (RVM). In order to evaluate the prediction capacity of the PDTPS, the experiment was carried out on enzyme, ion channel, GPCR, and nuclear receptor datasets by using five-fold cross-validation tests. The proposed PDTPS method achieved average accuracy of 97.73%, 93.12%, 86.78%, and 87.78% on enzyme, ion channel, GPCR and nuclear receptor datasets, respectively. The experimental results showed that our method has good prediction performance. Furthermore, in order to further evaluate the prediction performance of the proposed PDTPS method, we compared it with the state-of-the-art support vector machine (SVM) classifier on enzyme and ion channel datasets, and other exiting methods on four datasets. The promising comparison results further demonstrate that the efficiency and robust of the proposed PDTPS method. This makes it a useful tool and suitable for predicting DTI, as well as other bioinformatics tasks.

In Silico Prediction for Intestinal Absorption and Brain Penetration of Chemical Pesticides in Humans

Intestinal absorption and brain permeation constitute key parameters of toxicokinetics for pesticides, conditioning their toxicity, including neurotoxicity. However, they remain poorly characterized in humans. The present study was therefore designed to evaluate human intestine and brain permeation for a large set of pesticides (n = 338) belonging to various chemical classes, using an in silico graphical BOILED-Egg/SwissADME online method based on lipophilicity and polarity that was initially developed for drugs. A high percentage of the pesticides (81.4%) was predicted to exhibit high intestinal absorption, with a high accuracy (96%), whereas a lower, but substantial, percentage (38.5%) displayed brain permeation. Among the pesticide classes, organochlorines (n = 30) constitute the class with the lowest percentage of intestine-permeant members (40%), whereas that of the organophosphorus compounds (n = 99) has the lowest percentage of brain-permeant chemicals (9%). The predictions of the permeations for the pesticides were additionally shown to be significantly associated with various molecular descriptors well-known to discriminate between permeant and non-permeant drugs. Overall, our in silico data suggest that human exposure to pesticides through the oral way is likely to result in an intake of these dietary contaminants for most of them and brain permeation for some of them, thus supporting the idea that they have toxic effects on human health, including neurotoxic effects.

The virtual cell based assay: Current status and future perspectives

In order to replace the use of animals in toxicity testing, there is a need to predict in vivo toxic doses from concentrations that cause toxicological effects in relevant in vitro systems. The Virtual Cell Based Assay (VCBA) estimates time-dependent concentration of a test chemical in the cell and cell culture for a given in vitro system. The concentrations in the different compartments of the cell and test system are derived from ordinary differential equations, physicochemical parameters of the test chemical and properties of the cell line. The VCBA has been developed for a range of cell lines including BALB/c 3T3 cells, HepG2, HepaRG, lung A459 cells, and cardiomyocytes. The model can be used to design and refine in vitro experiments and extrapolate in vitro effective concentrations to in vivo doses that can be applied in risk assessment. In this paper, we first discuss potential applications of the VCBA: i) design of in vitro High Throughput Screening (HTS) experiments; ii) hazard identification (based on acute systemic toxicity); and iii) risk assessment. Further extension of the VCBA is discussed in the second part, exploring potential application to i) manufactured nanomaterials, ii) additional cell lines and endpoints, and considering iii) other opportunities.

•

VCBA as an alternative approach can be applied in the domain of nanotoxicology.

•

VCBA can support better testing strategies in acute toxicity.

•

Refinement of the VCBA taking into account biological oscillators could improve toxicity prediction.

•

Extensions of the VCBA can capture effects related to additional subcellular compartments.

Synthesis, Molecular Docking Studies, and Antifungal Activity Evaluation of New Benzimidazole-Triazoles as Potential Lanosterol 14α-Demethylase Inhibitors

Due to anticandidal importance of azole compounds, a new series of benzimidazole-triazole derivatives(5a–5s)were designed and synthesized as ergosterol inhibitors. The chemical structures of the target compounds were characterized by spectroscopic methods. The final compounds were screened for antifungal activity againstCandida glabrata(ATCC 90030),Candida krusei(ATCC 6258),Candida parapsilosis(ATCC 22019), andCandida albicans(ATCC 24433). Compounds5iand5sexhibited significant inhibitory activity againstCandidastrains with MIC50values ranging from 0.78 to 1.56 μg/mL. Cytotoxicity results revealed that IC50values of compounds5iand5sagainst NIH/3T3 are significantly higher than their MIC50values. Effect of the compounds5iand5sagainst ergosterol biosynthesis was determined by LC-MS-MS analysis. Both compounds caused a significant decrease in the ergosterol level. The molecular docking studies were performed to investigate the interaction modes between the compounds and active site of lanosterol 14-α-demethylase (CYP51), which is as a target enzyme for anticandidal azoles. Theoretical ADME predictions were also calculated for final compounds.

Discovery of a potential lead compound for treating leprosy with dapsone resistance mutation in M. leprae folP1

A potential lead compound to overcome dapsone resistance in M. leprae folP1 was identified by a virtual screening strategy.

Drug-target interaction prediction from PSSM based evolutionary information

The labor-intensive and expensive experimental process of drug-target interaction prediction has motivated many researchers to focus on in silico prediction, which leads to the helpful information in supporting the experimental interaction data. Therefore, they have proposed several computational approaches for discovering new drug-target interactions. Several learning-based methods have been increasingly developed which can be categorized into two main groups: similarity-based and feature-based. In this paper, we firstly use the bi-gram features extracted from the Position Specific Scoring Matrix (PSSM) of proteins in predicting drug-target interactions. Our results demonstrate the high-confidence prediction ability of the Bigram-PSSM model in terms of several performance indicators specifically for enzymes and ion channels. Moreover, we investigate the impact of negative selection strategy on the performance of the prediction, which is not widely taken into account in the other relevant studies. This is important, as the number of non-interacting drug-target pairs are usually extremely large in comparison with the number of interacting ones in existing drug-target interaction data. An interesting observation is that different levels of performance reduction have been attained for four datasets when we change the sampling method from the random sampling to the balanced sampling.

Open Source Bayesian Models. 1. Application to ADME/Tox and Drug Discovery Datasets

On the order of hundreds of absorption, distribution, metabolism, excretion, and toxicity (ADME/Tox) models have been described in the literature in the past decade which are more often than not inaccessible to anyone but their authors. Public accessibility is also an issue with computational models for bioactivity, and the ability to share such models still remains a major challenge limiting drug discovery. We describe the creation of a reference implementation of a Bayesian model-building software module, which we have released as an open source component that is now included in the Chemistry Development Kit (CDK) project, as well as implemented in the CDD Vault and in several mobile apps. We use this implementation to build an array of Bayesian models for ADME/Tox, in vitro and in vivo bioactivity, and other physicochemical properties. We show that these models possess cross-validation receiver operator curve values comparable to those generated previously in prior publications using alternative tools. We have now described how the implementation of Bayesian models with FCFP6 descriptors generated in the CDD Vault enables the rapid production of robust machine learning models from public data or the user’s own datasets. The current study sets the stage for generating models in proprietary software (such as CDD) and exporting these models in a format that could be run in open source software using CDK components. This work also demonstrates that we can enable biocomputation across distributed private or public datasets to enhance drug discovery.

Drug-target interaction prediction via chemogenomic space: learning-based methods

INTRODUCTION

Identification of the interaction between drugs and target proteins is a crucial task in genomic drug discovery. The in silico prediction is an appropriate alternative for the laborious and costly experimental process of drug-target interaction prediction. Developing a variety of computational methods opens a new direction in analyzing and detecting new drug-target pairs.

AREAS COVERED

In this review, we will focus on chemogenomic methods which have established a learning framework for predicting drug-target interactions. Learning-based methods are classified into supervised and semi-supervised, and the supervised learning methods are studied as two separate parts including similarity-based methods and feature-based methods.

EXPERT OPINION

In spite of many improvements for pharmacology applications by learning-based methods, there are many over simplification settings in construction of predictive models that may lead to over-optimistic results on drug-target interaction prediction.

Inhibitor ranking through QM based chelation calculations for virtual screening of HIV-1 RNase H inhibition

Quantum mechanical (QM) calculations have been used to predict the binding affinity of a set of ligands towards HIV-1 RT associated RNase H (RNH). The QM based chelation calculations show improved binding affinity prediction for the inhibitors compared to using an empirical scoring function. Furthermore, full protein fragment molecular orbital (FMO) calculations were conducted and subsequently analysed for individual residue stabilization/destabilization energy contributions to the overall binding affinity in order to better understand the true and false predictions. After a successful assessment of the methods based on the use of a training set of molecules, QM based chelation calculations were used as filter in virtual screening of compounds in the ZINC database. By this, we find, compared to regular docking, QM based chelation calculations to significantly reduce the large number of false positives. Thus, the computational models tested in this study could be useful as high throughput filters for searching HIV-1 RNase H active-site molecules in the virtual screening process.

Drug-target and disease networks: polypharmacology in the post-genomic era

With the growing understanding of complex diseases, the focus of drug discovery has shifted away from the well-accepted “one target, one drug” model, to a new “multi-target, multi-drug” model, aimed at systemically modulating multiple targets. Identification of the interaction between drugs and target proteins plays an important role in genomic drug discovery, in order to discover new drugs or novel targets for existing drugs. Due to the laborious and costly experimental process of drug-target interaction prediction, in silico prediction could be an efficient way of providing useful information in supporting experimental interaction data. An important notion that has emerged in post-genomic drug discovery is that the large-scale integration of genomic, proteomic, signaling and metabolomic data can allow us to construct complex networks of the cell that would provide us with a new framework for understanding the molecular basis of physiological or pathophysiological states. An emerging paradigm of polypharmacology in the post-genomic era is that drug, target and disease spaces can be correlated to study the effect of drugs on different spaces and their interrelationships can be exploited for designing drugs or cocktails which can effectively target one or more disease states. The future goal, therefore, is to create a computational platform that integrates genome-scale metabolic pathway, protein–protein interaction networks, gene transcriptional analysis in order to build a comprehensive network for multi-target multi-drug discovery.

Computational methods for drug design and discovery: focus on China

In the past decades, China's computational drug design and discovery research has experienced fast development through various novel methodologies. Application of these methods spans a wide range, from drug target identification to hit discovery and lead optimization. In this review, we firstly provide an overview of China's status in this field and briefly analyze the possible reasons for this rapid advancement. The methodology development is then outlined. For each selected method, a short background precedes an assessment of the method with respect to the needs of drug discovery, and, in particular, work from China is highlighted. Furthermore, several successful applications of these methods are illustrated. Finally, we conclude with a discussion of current major challenges and future directions of the field.

Pharmacointeraction network models predict unknown drug-drug interactions

Drug-drug interactions (DDIs) can lead to serious and potentially lethal adverse events. In recent years, several drugs have been withdrawn from the market due to interaction-related adverse events (AEs). Current methods for detecting DDIs rely on the accumulation of sufficient clinical evidence in the post-market stage – a lengthy process that often takes years, during which time numerous patients may suffer from the adverse effects of the DDI. Detection methods are further hindered by the extremely large combinatoric space of possible drug-drug-AE combinations. There is therefore a practical need for predictive tools that can identify potential DDIs years in advance, enabling drug safety professionals to better prioritize their limited investigative resources and take appropriate regulatory action. To meet this need, we describe Predictive Pharmacointeraction Networks (PPINs) – a novel approach that predicts unknown DDIs by exploiting the network structure of all known DDIs, together with other intrinsic and taxonomic properties of drugs and AEs. We constructed an 856-drug DDI network from a 2009 snapshot of a widely-used drug safety database, and used it to develop PPIN models for predicting future DDIs. We compared the DDIs predicted based solely on these 2009 data, with newly reported DDIs that appeared in a 2012 snapshot of the same database. Using a standard multivariate approach to combine predictors, the PPIN model achieved an AUROC (area under the receiver operating characteristic curve) of 0.81 with a sensitivity of 48% given a specificity of 90%. An analysis of DDIs by severity level revealed that the model was most effective for predicting “contraindicated” DDIs (AUROC = 0.92) and less effective for “minor” DDIs (AUROC = 0.63). These results indicate that network based methods can be useful for predicting unknown drug-drug interactions.

Chemogenomic approaches to infer drug-target interaction networks

The identification of drug-target interactions from heterogeneous biological data is critical in the drug development. In this chapter, we review recently developed in silico chemogenomic approaches to infer unknown drug-target interactions from chemical information of drugs and genomic information of target proteins. We review several kernel-based statistical methods from two different viewpoints: binary classification and dimension reduction. In the results, we demonstrate the usefulness of the methods on the prediction of drug-target interactions from chemical structure data and genomic sequence data. We also discuss the characteristics of each method, and show some perspectives toward future research direction.

Discovery of estrogen receptor modulators: a review of virtual screening and SAR efforts

IMPORTANCE OF THE FIELD

Virtual screening (VS) coupled with structural biology is a significantly important approach to increase the number and enhance the success of projects in lead identification stage of drug discovery process. Recent advances and future directions in estrogen therapy have resulted in great demand for identifying the potential estrogen receptor (ER) modulators with more activity and selectivity.

AREAS COVERED IN THIS REVIEW

This review presents the current state of the art in VS and structure-activity relationship of ER modulators in recent discovery, and discusses the strengths and weaknesses of the technology.

WHAT THE READER WILL GAIN

Readers will gain an overview of the current platforms of in silico screening for discovery of ER modulators; they will learn which structural information is significantly correlated with the bioactivity of ER modulators and what novel strategies should be considered for the creation of more effective chemical structures.

TAKE HOME MESSAGE

With the goal of reducing toxicity and/or improving efficacy, challenges to the successful modeling of endocrine agents are proposed, providing new paradigms for the design of ER inhibitors.

Predicting drug-target interactions from chemical and genomic kernels using Bayesian matrix factorization

MOTIVATION

Identifying interactions between drug compounds and target proteins has a great practical importance in the drug discovery process for known diseases. Existing databases contain very few experimentally validated drug-target interactions and formulating successful computational methods for predicting interactions remains challenging.

RESULTS

In this study, we consider four different drug-target interaction networks from humans involving enzymes, ion channels, G-protein-coupled receptors and nuclear receptors. We then propose a novel Bayesian formulation that combines dimensionality reduction, matrix factorization and binary classification for predicting drug-target interaction networks using only chemical similarity between drug compounds and genomic similarity between target proteins. The novelty of our approach comes from the joint Bayesian formulation of projecting drug compounds and target proteins into a unified subspace using the similarities and estimating the interaction network in that subspace. We propose using a variational approximation in order to obtain an efficient inference scheme and give its detailed derivations. Finally, we demonstrate the performance of our proposed method in three different scenarios: (i) exploratory data analysis using low-dimensional projections, (ii) predicting interactions for the out-of-sample drug compounds and (iii) predicting unknown interactions of the given network.

AVAILABILITY

Software and Supplementary Material are available at http://users.ics.aalto.fi/gonen/kbmf2k.

CONTACT

mehmet.gonen@aalto.fi

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.