Drug–target interaction prediction by integrating multiview network data

Drug–target interaction (DTI) prediction is a challenging step in further drug repositioning, drug discovery and drug design. The advent of high-throughput technologies brings convenience to the development of DTI prediction methods. With the generation of a high number of data sets, many mathematical models and computational algorithms have been developed to identify the potential drug–target pairs. However, most existing methods are proposed based on the single view data. By integrating the drug and target data from different views, we aim to get more stable and accurate prediction results.In this paper, a multiview DTI prediction method based on clustering is proposed. We first introduce a model for single view drug–target data. The model is formulated as an optimization problem, which aims to identify the clusters in both drug similarity network and target protein similarity network, and at the same time make the clusters with more known DTIs be connected together. Then the model is extended to multiview network data by maximizing the consistency of the clusters in each view. An approximation method is proposed to solve the optimization problem. We apply the proposed algorithms to two views of data. Comparisons with some existing algorithms show that the multiview DTI prediction algorithm can produce more accurate predictions. For the considered data set, we finally predict 54 possible DTIs. From the similarity analysis of the drugs/targets, enrichment analysis of DTIs and genes in each cluster, it is shown that the predicted DTIs have a high possibility to be true.     

Prediction of drug-target interaction by integrating diverse heterogeneous information source with multiple kernel learning and clustering methods

BackgroundIdentification of potential drug-target interaction pairs is very important for pharmaceutical innovation and drug discovery. Numerous machine learning-based and network-based algorithms have been developed for predicting drug-target interactions. However, large-scale pharmacological, genomic and chemical datum emerged recently provide new opportunity for further heightening the accuracy of drug-target interactions prediction.ResultsIn this work, based on the assumption that similar drugs tend to interact with similar proteins and vice versa, we developed a novel computational method (namely MKLC-BiRW) to predict new drug-target interactions. MKLC-BiRW integrates diverse drug-related and target-related heterogeneous information source by using the multiple kernel learning and clustering methods to generate the drug and target similarity matrices, in which the low similarity elements are set to zero to build the drug and target similarity correction networks. By incorporating these drug and target similarity correction networks with known drug-target interaction bipartite graph, MKLC-BiRW constructs the heterogeneous network on which Bi-random walk algorithm is adopted to infer the potential drug-target interactions.ConclusionsCompared with other existing state-of-the-art methods, MKLC-BiRW achieves the best performance in terms of AUC and AUPR. MKLC-BiRW can effectively predict the potential drug-target interactions.     

Kernel-based data fusion improves the drug-protein interaction prediction

Proteins are involved in almost every action of every organism by interacting with other small molecules including drugs. Computationally predicting the drug-protein interactions is particularly important in speeding up the process of developing novel drugs. To borrow the information from existing drug-protein interactions, we need to define the similarity among proteins and the similarity among drugs. Usually these similarities are defined based on one single data source and many methods have been proposed. However, the availability of many genomic and chemogenomic data sources allows us to integrate these useful data sources to improve the predictions. Thus a great challenge is how to integrate these heterogeneous data sources. Here, we propose a kernel-based method to predict drug-protein interactions by integrating multiple types of data. Specially, we collect drug pharmacological and therapeutic effects, drug chemical structures, and protein genomic information to characterize the drug-target interactions, then integrate them by a kernel function within a support vector machine (SVM)-based predictor. With this data fusion technology, we establish the drug-protein interactions from a collections of data sources. Our new method is validated on four classes of drug target proteins, including enzymes, ion channels (ICs), G-protein couple receptors (GPCRs), and nuclear receptors (NRs). We find that every single data source is predictive and integration of different data sources allows the improvement of accuracy, i.e., data integration can uncover more experimentally observed drug-target interactions upon the same levels of false positive rate than single data source based methods. The functional annotation analysis indicates that our new predictions are worthy of future experimental validation. In conclusion, our new method can efficiently integrate diverse data sources, and will promote the further research in drug discovery.     

TargetNet: a web service for predicting potential drug–target interaction profiling via multi-target SAR models

Drug–target interactions (DTIs) are central to current drug discovery processes and public health fields. Analyzing the DTI profiling of the drugs helps to infer drug indications, adverse drug reactions, drug–drug interactions, and drug mode of actions. Therefore, it is of high importance to reliably and fast predict DTI profiling of the drugs on a genome-scale level. Here, we develop the TargetNet server, which can make real-time DTI predictions based only on molecular structures, following the spirit of multi-target SAR methodology. Naïve Bayes models together with various molecular fingerprints were employed to construct prediction models. Ensemble learning from these fingerprints was also provided to improve the prediction ability. When the user submits a molecule, the server will predict the activity of the user’s molecule across 623 human proteins by the established high quality SAR model, thus generating a DTI profiling that can be used as a feature vector of chemicals for wide applications. The 623 SAR models related to 623 human proteins were strictly evaluated and validated by several model validation strategies, resulting in the AUC scores of 75–100 %. We applied the generated DTI profiling to successfully predict potential targets, toxicity classification, drug–drug interactions, and drug mode of action, which sufficiently demonstrated the wide application value of the potential DTI profiling. The TargetNet webserver is designed based on the Django framework in Python, and is freely accessible at http://targetnet.scbdd.com.     

Development and application of fluorescence polarization assays in drug discovery

Fluorescence polarization technology has been used in basic research and commercial diagnostic assays for many decades, but has begun to be widely used in drug discovery only in the past six years. Originally, FP assays for drug discovery were developed for single-tube analytical instruments, but the technology was rapidly converted to high-throughput screening assays when commercial plate readers with equivalent sensitivity became available. This review will discuss fluorescence polarization assays in current use in drug discovery research as well as those in development that will likely be used in the near future. These assays include targets such as kinases, phosphatases, proteases, G-protein coupled receptors, and nuclear receptors.     

Fragment-similarity-based QSAR (FS-QSAR) algorithm for ligand biological activity predictions

Quantitative structure–activity relationship (QSAR) studies are useful computational tools often used in drug discovery research and in many scientific disciplines. In this study, a robust fragment-similarity-based QSAR (FS-QSAR) algorithm was developed to correlate structures with biological activities by integrating fragment-based drug design concept and a multiple linear regression method. Similarity between any pair of training and testing fragments was determined by calculating the difference of lowest or highest eigenvalues of the chemistry space BCUT matrices of corresponding fragments. In addition to the BCUT-similarity function, molecular fingerprint Tanimoto coefficient (Tc) similarity function was also used as an alternative for comparison. For validation studies, the FS-QSAR algorithm was applied to several case studies, including a dataset of COX2 inhibitors and a dataset of cannabinoid CB2 triaryl bis-sulfone antagonist analogues, to build predictive models achieving average coefficient of determination (r ²) of 0.62 and 0.68, respectively. The developed FS-QSAR method is proved to give more accurate predictions than the traditional and one-nearest-neighbour QSAR methods and can be a useful tool in the fragment-based drug discovery for ligand activity prediction.     

Large-scale prediction of drug–target interactions using protein sequences and drug topological structures

The identification of interactions between drugs and target proteins plays a key role in the process of genomic drug discovery. It is both consuming and costly to determine drug–target interactions by experiments alone. Therefore, there is an urgent need to develop new in silico prediction approaches capable of identifying these potential drug–target interactions in a timely manner. In this article, we aim at extending current structure–activity relationship (SAR) methodology to fulfill such requirements. In some sense, a drug–target interaction can be regarded as an event or property triggered by many influence factors from drugs and target proteins. Thus, each interaction pair can be represented theoretically by using these factors which are based on the structural and physicochemical properties simultaneously from drugs and proteins. To realize this, drug molecules are encoded with MACCS substructure fingerings representing existence of certain functional groups or fragments; and proteins are encoded with some biochemical and physicochemical properties. Four classes of drug–target interaction networks in humans involving enzymes, ion channels, G-protein-coupled receptors (GPCRs) and nuclear receptors, are independently used for establishing predictive models with support vector machines (SVMs). The SVM models gave prediction accuracy of 90.31%, 88.91%, 84.68% and 83.74% for four datasets, respectively. In conclusion, the results demonstrate the ability of our proposed method to predict the drug–target interactions, and show a general compatibility between the new scheme and current SAR methodology. They open the way to a host of new investigations on the diversity analysis and prediction of drug–target interactions.     

TargetATPsite: A template‐free method for ATP‐binding sites prediction with residue evolution image sparse representation and classifier ensemble

Understanding the interactions between proteins and ligands is critical for protein function annotations and drug discovery. We report a new sequence‐based template‐free predictor (TargetATPsite) to identify the Adenosine‐5′‐triphosphate (ATP) binding sites with machine‐learning approaches. Two steps are implemented in TargetATPsite: binding residues and pockets predictions, respectively. To predict the binding residues, a novel image sparse representation technique is proposed to encode residue evolution information treated as the input features. An ensemble classifier constructed based on support vector machines (SVM) from multiple random under‐samplings is used as the prediction model, which is effective for dealing with imbalance phenomenon between the positive and negative training samples. Compared with the existing ATP‐specific sequence‐based predictors, TargetATPsite is featured by the second step of possessing the capability of further identifying the binding pockets from the predicted binding residues through a spatial clustering algorithm. Experimental results on three benchmark datasets demonstrate the efficacy of TargetATPsite. © 2013 Wiley Periodicals, Inc.     

Improving the orbital-free density functional theory description of covalent materials

The essential challenge in orbital-free density functional theory (OF-DFT) is to construct accurate kinetic energy density functionals (KEDFs) with general applicability (i.e., transferability). During the last decade, several linear-response (LR)-based KEDFs have been proposed. Among them, the Wang-Govind-Carter (WGC) KEDF, containing a density-dependent response kernel, is one of the most accurate that still affords a linear scaling algorithm. For nearly-free-electron-like metals such as Al and its alloys, OF-DFT employing the WGC KEDF produces bulk properties in good agreement with orbital-based Kohn-Sham (KS) DFT predictions. However, when OF-DFT, using the WGC KEDF combined with a recently proposed bulk-derived local pseudopotential (BLPS), was applied to semiconducting and metallic phases of Si, problems arose with convergence of the self-consistent density and energy, leading to poor results. Here we provide evidence that the convergence problem is very likely caused by the use of a truncated Taylor series expansion of the WGC response kernel. Moreover, we show that a defect in the ansatz for the first-order reduced density matrix underlying the LR KEDFs limits the accuracy of these KEDFs. By optimizing the two free parameters involved in the WGC KEDF, the two-body Fermi wave vector mixing parameter gamma and the reference density rho* used in the Taylor expansion, OF-DFT calculations with the BLPS can achieve semiquantitative results for nine phases of bulk silicon. These new parameters are recommended whenever the WGC KEDF is used to study nonmetallic systems.     

NMR-assisted prediction of RNA secondary structure: identification of a probable pseudoknot in the coding region of an R2 retrotransposon

As the rate of functional RNA sequence discovery escalates, high-throughput techniques for reliable structural determination are becoming crucial for revealing the essential features of these RNAs in a timely fashion. Computational predictions of RNA secondary structure quickly generate reasonable models but suffer from several approximations, including overly simplified models and incomplete knowledge of significant interactions. Similar problems limit the accuracy of predictions for other self-folding polymers, including DNA and peptide nucleic acid (PNA). The work presented here demonstrates that incorporating unassigned data from simple nuclear magnetic resonance (NMR) experiments into a dynamic folding algorithm greatly reduces the potential folding space of a given RNA and therefore increases the confidence and accuracy of modeling. This procedure has been packaged into an NMR-assisted prediction of secondary structure (NAPSS) algorithm that can produce pseudoknotted as well as non-pseudoknotted secondary structures. The method reveals a probable pseudoknot in the part of the coding region of the R2 retrotransposon from Bombyx mori that orchestrates second-strand DNA cleavage during insertion into the genome.     

Reconstructing gene regulatory networks from knock-out data using Gaussian Noise Model and Pearson Correlation Coefficient

A gene regulatory network (GRN) is a large and complex network consisting of interacting elements that, over time, affect each other’s state. The dynamics of complex gene regulatory processes are difficult to understand using intuitive approaches alone. To overcome this problem, we propose an algorithm for inferring the regulatory interactions from knock-out data using a Gaussian model combines with Pearson Correlation Coefficient (PCC). There are several problems relating to GRN construction that have been outlined in this paper. We demonstrated the ability of our proposed method to (1) predict the presence of regulatory interactions between genes, (2) their directionality and (3) their states (activation or suppression). The algorithm was applied to network sizes of 10 and 50 genes from DREAM3 datasets and network sizes of 10 from DREAM4 datasets. The predicted networks were evaluated based on AUROC and AUPR. We discovered that high false positive values were generated by our GRN prediction methods because the indirect regulations have been wrongly predicted as true relationships. We achieved satisfactory results as the majority of sub-networks achieved AUROC values above 0.5.     

Engineering of Challenging G Protein-Coupled Receptors for Structure Determination and Biophysical Studies

Membrane proteins such as G protein-coupled receptors (GPCRs) exert fundamental biological functions and are involved in a multitude of physiological responses, making these receptors ideal drug targets. Drug discovery programs targeting GPCRs have been greatly facilitated by the emergence of high-resolution structures and the resulting opportunities to identify new chemical entities through structure-based drug design. To enable the determination of high-resolution structures of GPCRs, most receptors have to be engineered to overcome intrinsic hurdles such as their poor stability and low expression levels. In recent years, multiple engineering approaches have been developed to specifically address the technical difficulties of working with GPCRs, which are now beginning to make more challenging receptors accessible to detailed studies. Importantly, successfully engineered GPCRs are not only valuable in X-ray crystallography, but further enable biophysical studies with nuclear magnetic resonance spectroscopy, surface plasmon resonance, native mass spectrometry, and fluorescence anisotropy measurements, all of which are important for the detailed mechanistic understanding, which is the prerequisite for successful drug design. Here, we summarize engineering strategies based on directed evolution to reduce workload and enable biophysical experiments of particularly challenging GPCRs.     

Incurred sample reanalysis in drug discovery bioanalysis

Bioanalysis plays a key role during the drug discovery process to generate the pharmacokinetic data to facilitate unbiased evaluation of leads, optimized leads and drug candidates. Such pharmacokinetic data are used to enable key decisions in the drug discovery process. The aim of the work is to put forward a new strategy of performing the incurred sample reanalysis for select small molecule novel chemical entities at different stages of drug discovery prior to candidate selection. Three discovery programs representing hits, leads and optimized lead candidates were selected for the incurred sample reanalysis (ISR) analysis. From each discovery program, two novel chemical entities were selected for the ISR analysis. The time points considered for ISR generally varied among the programs; however, samples coinciding with drug absorption, distribution and elimination were considered in the ISR assessment. With the exception of a single ISR value that gave a high deviation (about 63%), the observed ISR values supported the discovery bioanalytical assays. While the individual bioanalytical laboratory can draw an algorithm for selecting novel chemical entities and fixing the acceptance criteria for the ISR data, it is proposed that the percentage difference between ISR vs. original concentration for 67% of the repeat samples is contained within ±30% for discovery bioanalysis.     

A MAP-based algorithm for spectroscopic semi-blind deconvolution

Spectroscopic data often suffer from common problems of bands overlapping and random noise. In this paper, we show that the issue of overlapping peaks can be considered as a maximum a posterior (MAP) problem and be solved by minimizing an object functional that includes a likelihood term and two prior terms. In the MAP framework, the likelihood probability density function (PDF) is constructed based on a spectral observation model, a robust Huber-Markov model is used as spectra prior PDF, and the kernel prior is described based on a parametric Gaussian function. Moreover, we describe an efficient optimization scheme that alternates between latent spectrum recovery and blur kernel estimation until convergence. The major novelty of the proposed algorithm is that it can estimate the kernel slit width and latent spectrum simultaneously. Comparative results with other deconvolution methods suggest that the proposed method can recover spectral structural details as well as suppress noise effectively.     

Coumarins as Tool Compounds to Aid the Discovery of Selective Function Modulators of Steroid Hormone Binding Proteins

Steroid hormones play an essential role in a wide variety of actions in the body, such as in metabolism, inflammation, initiating and maintaining sexual differentiation and reproduction, immune functions, and stress response. Androgen, aromatase, and sulfatase pathway enzymes and nuclear receptors are responsible for steroid biosynthesis and sensing steroid hormones. Changes in steroid homeostasis are associated with many endocrine diseases. Thus, the discovery and development of novel drug candidates require a detailed understanding of the small molecule structure–activity relationship with enzymes and receptors participating in steroid hormone synthesis, signaling, and metabolism. Here, we show that simple coumarin derivatives can be employed to build cost-efficiently a set of molecules that derive essential features that enable easy discovery of selective and high-affinity molecules to target proteins. In addition, these compounds are also potent tool molecules to study the metabolism of any small molecule.     

Utility-aware screening with clique-oriented prioritization

Most methods of deciding which hits from a screen to send for confirmatory testing assume that all confirmed actives are equally valuable and aim only to maximize the number of confirmed hits. In contrast, "utility-aware" methods are informed by models of screeners' preferences and can increase the rate at which the useful information is discovered. Clique-oriented prioritization (COP) extends a recently proposed economic framework and aims--by changing which hits are sent for confirmatory testing--to maximize the number of scaffolds with at least two confirmed active examples. In both retrospective and prospective experiments, COP enables accurate predictions of the number of clique discoveries in a batch of confirmatory experiments and improves the rate of clique discovery by more than 3-fold. In contrast, other similarity-based methods like ontology-based pattern identification (OPI) and local hit-rate analysis (LHR) reduce the rate of scaffold discovery by about half. The utility-aware algorithm used to implement COP is general enough to implement several other important models of screener preferences.