"Going KiNativ": probing the Native Kinome

In this issue, Patricelli et?al. (2011) describe an in?situ chemoproteomics approach (KiNativ?) for profiling the?kinome and kinome response to specific kinase inhibitors that enables characterization of inhibitor interactions with endogenously expressed kinases in native conditions.     

Results of a new classification algorithm combining K nearest neighbors and recursive partitioning

We present results of a new computational learning algorithm combining favorable elements of two well-known techniques: K nearest neighbors and recursive partitioning. Like K nearest neighbors, the method provides an independent prediction for each test sample under consideration, while like recursive partitioning, it incorporates an automatic selection of important input variables for model construction. The new method is applied to the problem of correctly classifying a set of chemical data samples designated as being either active or inactive in a biological screen. Training is performed at varying levels of intrinsic model complexity, and classification performance is compared to that of both K nearest neighbor and recursive partitioning models trained using the identical protocol. We find that the cross-validated performance of the new method outperforms both of these standard techniques over a considerable range of user parameters. We discuss advantages and drawbacks of the new method, with particular emphasis on its parameter robustness, required training time, and performance with respect to chemical structural class.     

Neighbor effect on PPII conformation in alanine peptides

The polyproline II (PPII) conformation is dominant in short alanine oligomers. The noncooperativity of PPII structure in alanine peptides indicates that PPII in water is locally determined and that alanine neighbors are consistent with Flory's isolated pair hypothesis. However, neighbor effects from beta-branched or bulky aromatic residues tend to increase the Phi angle of the nearest neighbor as observed in coil library data. Here we demonstrate directly the neighbor effect using short alanine model peptides GGAAAGG, GGLnALnGG (Ln is norleucine), GGIAAGG, and GGIAIGG. The far-UV CD spectra, NMR 3JalphaN coupling constant, and H-D hydrogen exchange measurements reveal that Ile reduces the PPII content of the probe Ala side chain relative to Ala or norLeu. The free energy differences are consistent with predictions from electrostatic solvation free energy (ESF) calculations. The results indicate that prediction of PPII propensities or scales requires including the neighbor effect.     

Protein function prediction using neighbor relativity in protein–protein interaction network

There is a large gap between the number of discovered proteins and the number of functionally annotated ones. Due to the high cost of determining protein function by wet-lab research, function prediction has become a major task for computational biology and bioinformatics. Some researches utilize the proteins interaction information to predict function for un-annotated proteins. In this paper, we propose a novel approach called “Neighbor Relativity Coefficient” (NRC) based on interaction network topology which estimates the functional similarity between two proteins. NRC is calculated for each pair of proteins based on their graph-based features including distance, common neighbors and the number of paths between them. In order to ascribe function to an un-annotated protein, NRC estimates a weight for each neighbor to transfer its annotation to the unknown protein. Finally, the unknown protein will be annotated by the top score transferred functions. We also investigate the effect of using different coefficients for various types of functions. The proposed method has been evaluated on Saccharomyces cerevisiae and Homo sapiens interaction networks. The performance analysis demonstrates that NRC yields better results in comparison with previous protein function prediction approaches that utilize interaction network.     

Strategies for kinome profiling in cancer and potential clinical applications: chemical proteomics and array-based methods

Kinases are key enzymes involved in deregulated signal transduction associated with cancer development and progression. The advent of personalized medicine drives the development of new diagnostic tools for patient stratification and therapy selection Ginsburg and Willard (Transl Res 154:277-287, 2009). Since deregulation of kinase-mediated signal transduction is implied in tumorigenesis, the analysis of all kinases (the kinome) active in a particular tumor may yield tumor-specific information on aberrant cell signalling pathways. Tumor tissue kinase activity profiles may correlate with response to therapy and therefore may be used for future therapy selection. In this Trend paper we describe peptide array and mass spectrometry-based technologies and new developments for kinome profiling, and we present an outlook towards future implementation of therapy selection based on kinome profiling in clinical practice.     

Development of a minimal kinase ensemble receptor (MKER) for surrogate AutoShim

The target-tailored 3-D virtual screening (VS) method "Surrogate AutoShim" adds pharmacophoric shims to a 16-kinase crystal structure "Universal Kinase Ensemble Receptor" (UKER) to generate highly predictive, target-customized docking models. Predocking a corporate archive of millions of compounds into the 16-structure ensemble takes months. However, since the 16 UKER structures are always the same, docking need only be done once. The predocked results are then "shimmed" to reproduce experimental training data for any number of additional kinases far more accurately than conventional docking. Training new kinase models and predicting activity for millions of predocked compounds against dozens of kinases takes only hours. However reducing the predocking time would make the method even more advantageous. Sequential Floating Forward Search (SFFS) was employed to rationally identify a reduced subset using only 8 of the 16 structures, a "Minimal Kinase Ensemble Receptor" (MKER) that preserved the predictive accuracy for 20 kinase models. Furthermore, a performance evaluation of this subset on an extended set of 52 kinase targets and 100,000 compounds showed statistical model performance comparable to the original UKER. The MKER has halved the time for predocking large databases of internal and commercial compounds. For ad hoc virtual libraries, where predocking is not possible, 2- or 3-kinases "Approximate Kinase Ensemble Receptors" (AKER) were also identified with only a modest loss of prediction accuracy.     

Inverse screening of Simvastatin kinase targets from glioblastoma druggable kinome

The statin drug Simvastatin is a HMG-CoA reductase inhibitor that has been widely used to lower blood lipid. However, the drug is clinically observed to reposition a significant suppressing potency on glioblastoma (GBM) by unexpectedly targeting diverse kinase pathways involved in GBM tumorigensis. Here, an inverse screening strategy is described to discover potential kinase targets of Simvastatin. Various human protein kinases implicated in GBM are enriched to define a druggable kinome; the binding behavior of Simvastatin to the kinome is profiled systematically via an integrative computational approach, from which most kinases have only low or moderate binding potency to Simvastatin, while only few are identified as promising kinase hits. It is revealed that Simvastatin can potentially interact with certain known targets or key regulators of GBM such as ErbB, c-Src and FGFR signaling pathways, but exhibit low affinity to the well-established GBM target of PI3K/Akt/mTOR pathway. Further assays determine that Simvastatin can inhibit kinase hits EGFR, MET, SRC and HER2 at nanomolar level, which are comparable with those of cognate kinase inhibitors. Structural analyses reveal that the sophisticated T790 M gatekeeper mutation can considerably reduce Simvastatin sensitivity to EGFR by inducing the ligand change between different binding modes.     

Multifingerprint based similarity searches for targeted class compound selection

Molecular fingerprints are widely used for similarity-based virtual screening in drug discovery projects. In this paper we discuss the performance and the complementarity of nine two-dimensional fingerprints (Daylight, Unity, AlFi, Hologram, CATS, TRUST, Molprint 2D, ChemGPS, and ALOGP) in retrieving active molecules by similarity searching against a set of query compounds. For this purpose, we used biological data from HTS screening campaigns of four protein families (GPCRs, kinases, ion channels, and proteases). We have established threshold values for the similarity index (Tanimoto index) to be used as starting points for similarity searches. Based on the complementarities between the selections made by using different fingerprints we propose a multifingerprint approach as an efficient tool to balance the strengths and weaknesses of various fingerprints.     

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.     

A method for discovering transmembrane beta-barrel proteins in Gram-negative bacterial proteomes

Transmembrane beta-barrel (TMB) proteins play pivotal roles in many aspects of bacterial functions. This paper presents a k-nearest neighbor (K-NN) method for discriminating TMB and non-TMB proteins. We start with a method that makes predictions based on a distance computed from residue composition and gradually improve the prediction performance by including homologous sequences and searching for a set of residues and di-peptides for calculating the distance. The final method achieves an accuracy of 97.1%, with 0.876 MCC, 86.4% sensitivity and 98.8% specificity. A web server based on the proposed method is available at http://yanbioinformatics.cs.usu.edu:8080/TMBKNNsubmit.     

Heuristic-based tabu search algorithm for folding two-dimensional AB off-lattice model proteins

The protein structure prediction problem is a classical NP hard problem in bioinformatics. The lack of an effective global optimization method is the key obstacle in solving this problem. As one of the global optimization algorithms, tabu search (TS) algorithm has been successfully applied in many optimization problems. We define the new neighborhood conformation, tabu object and acceptance criteria of current conformation based on the original TS algorithm and put forward an improved TS algorithm. By integrating the heuristic initialization mechanism, the heuristic conformation updating mechanism, and the gradient method into the improved TS algorithm, a heuristic-based tabu search (HTS) algorithm is presented for predicting the two-dimensional (2D) protein folding structure in AB off-lattice model which consists of hydrophobic (A) and hydrophilic (B) monomers. The tabu search minimization leads to the basins of local minima, near which a local search mechanism is then proposed to further search for lower-energy conformations. To test the performance of the proposed algorithm, experiments are performed on four Fibonacci sequences and two real protein sequences. The experimental results show that the proposed algorithm has found the lowest-energy conformations so far for three shorter Fibonacci sequences and renewed the results for the longest one, as well as two real protein sequences, demonstrating that the HTS algorithm is quite promising in finding the ground states for AB off-lattice model proteins.     

基于近红外光谱分析技术的食品包装塑料的定性分析

该文基于近红外漫反射光谱分析技术对食品包装材料聚乙烯、聚丙烯进行定性判别试验研究,选取不同波段范围、采用不同光谱预处理方法,使用主成分分析法(Principal component analysis,PCA)结合SIMCA、贝叶斯判别、K-近邻3种模式识别方法建立定性预测模型,并根据正确识别率比较了各模型预测性能。结果表明：使用SIMCA方法、贝叶斯判别、K-近邻3种方法建立的定性校正模型均在1 050~1 550 nm波长范围内效果较好;采用矢量归一化、标准正态变量变换、中心化、滑动均值滤波、多项式平滑滤波、一阶微分6种光谱预处理方法和上述3种模式识别方法对塑料样品近红外光谱进行了数据处理,其中在1 050~1 550 nm范围内,主成分因子数为3,采用原始光谱建立的K-近邻定性校正模型较优,对样品校正集和预测集的正确识别率均为100%。可为食品包装材料聚乙烯、聚丙烯的快速鉴别研究提供参考。     

Drug Repurposing and De Novo Drug Discovery of Protein Kinase Inhibitors as New Drugs against Schistosomiasis

Schistosomiasis is a neglected tropical disease affecting more than 200 million people worldwide. Chemotherapy relies on one single drug, praziquantel, which is safe but ineffective at killing larval stages of this parasite. Furthermore, concerns have been expressed about the rise in resistance against this drug. In the absence of an antischistosomal vaccine, it is, therefore, necessary to develop new drugs against the different species of schistosomes. Protein kinases are important molecules involved in key cellular processes such as signaling, growth, and differentiation. The kinome of schistosomes has been studied and the suitability of schistosomal protein kinases as targets demonstrated by RNA interference studies. Although protein kinase inhibitors are mostly used in cancer therapy, e.g., for the treatment of chronic myeloid leukemia or melanoma, they are now being increasingly explored for the treatment of non-oncological conditions, including schistosomiasis. Here, we discuss the various approaches including screening of natural and synthetic compounds, de novo drug development, and drug repurposing in the context of the search for protein kinase inhibitors against schistosomiasis. We discuss the status quo of the development of kinase inhibitors against schistosomal serine/threonine kinases such as polo-like kinases (PLKs) and mitogen-activated protein kinases (MAP kinases), as well as protein tyrosine kinases (PTKs).     

Breaking the polar‐nonpolar division in solvation free energy prediction

Implicit solvent models divide solvation free energies into polar and nonpolar additive contributions, whereas polar and nonpolar interactions are inseparable and nonadditive. We present a feature functional theory (FFT) framework to break this ad hoc division. The essential ideas of FFT are as follows: (i) representability assumption: there exists a microscopic feature vector that can uniquely characterize and distinguish one molecule from another; (ii) feature‐function relationship assumption: the macroscopic features, including solvation free energy, of a molecule is a functional of microscopic feature vectors; and (iii) similarity assumption: molecules with similar microscopic features have similar macroscopic properties, such as solvation free energies. Based on these assumptions, solvation free energy prediction is carried out in the following protocol. First, we construct a molecular microscopic feature vector that is efficient in characterizing the solvation process using quantum mechanics and Poisson–Boltzmann theory. Microscopic feature vectors are combined with macroscopic features, that is, physical observable, to form extended feature vectors. Additionally, we partition a solvation dataset into queries according to molecular compositions. Moreover, for each target molecule, we adopt a machine learning algorithm for its nearest neighbor search, based on the selected microscopic feature vectors. Finally, from the extended feature vectors of obtained nearest neighbors, we construct a functional of solvation free energy, which is employed to predict the solvation free energy of the target molecule. The proposed FFT model has been extensively validated via a large dataset of 668 molecules. The leave‐one‐out test gives an optimal root‐mean‐square error (RMSE) of 1.05 kcal/mol. FFT predictions of SAMPL0, SAMPL1, SAMPL2, SAMPL3, and SAMPL4 challenge sets deliver the RMSEs of 0.61, 1.86, 1.64, 0.86, and 1.14 kcal/mol, respectively. Using a test set of 94 molecules and its associated training set, the present approach was carefully compared with a classic solvation model based on weighted solvent accessible surface area. © 2017 Wiley Periodicals, Inc.     

Three useful dimensions for domain applicability in QSAR models using random forest

One popular metric for estimating the accuracy of prospective quantitative structure-activity relationship (QSAR) predictions is based on the similarity of the compound being predicted to compounds in the training set from which the QSAR model was built. More recent work in the field has indicated that other parameters might be equally or more important than similarity. Here we make use of two additional parameters: the variation of prediction among random forest trees (less variation among trees indicates more accurate prediction) and the prediction itself (certain ranges of activity are intrinsically easier to predict than others). The accuracy of prediction for a QSAR model, as measured by the root-mean-square error, can be estimated by cross-validation on the training set at the time of model-building and stored as a three-dimensional array of bins. This is an obvious extension of the one-dimensional array of bins we previously proposed for similarity to the training set [Sheridan et al. J. Chem. Inf. Comput. Sci.2004, 44, 1912-1928]. We show that using these three parameters simultaneously adds much more discrimination in prediction accuracy than any single parameter. This approach can be applied to any QSAR method that produces an ensemble of models. We also show that the root-mean-square errors produced by cross-validation are predictive of root-mean-square errors of compounds tested after the model was built.