The cross-species prediction of bacterial promoters using a support vector machine

Due to degeneracy of the observed binding sites, the in silico prediction of bacterial sigma(70)-like promoters remains a challenging problem. A large number of sigma(70)-like promoters has been biologically identified in only two species, Escherichia coli and Bacillus subtilis. In this paper we investigate the issues that arise when searching for promoters in other species using an ensemble of SVM classifiers trained on E. coli promoters. DNA sequences are represented using a tagged mismatch string kernel. The major benefit of our approach is that it does not require a prior definition of the typical -35 and -10 hexamers. This gives the SVM classifiers the freedom to discover other features relevant to the prediction of promoters. We use our approach to predict sigma(A) promoters in B. subtilis and sigma(66) promoters in Chlamydia trachomatis. We extended the analysis to identify specific regulatory features of gene sets in C. trachomatis having different expression profiles. We found a strong -35 hexamer and TGN/-10 associated with a set of early expressed genes. Our analysis highlights the advantage of using TSS-PREDICT as a starting point for predicting promoters in species where few are known.     

QSAR prediction of antagonistic activity of PCBs towards human PXR by using heuristic method and best subset modeling

Polychlorinated biphenyls(PCBs) can antagonize human pregnane X receptor(hPXR) activation.Such chemicals could pose a serious threat to the reproductive and developmental ability of humans.The quantitative structure activity relationship(QSAR) provides a promising method for the estimation of PCBs’ antagonistic activity.In this investigation,a QSAR model was developed by using heuristic method and best subset modeling(r2 = 0.873,q2LOO=0.742).The built model was validated externally by splitting the original data set into training and prediction sets.The results of the model derived are as follows:r2 = 0.907,q2LOO=0.709,r2pred=0.676,suggesting developed QSAR model had good robustness and predictive ability.The applicability domain(AD) of the model was assessed by Williams plot.The antagonistic activity(?logKi) of 108 PCBs,which are unavailable by experiment at present,was predicted within the applicability domain of the model.The critical structural features related to the activity of PCBs were identified.     

Sequence‐based prediction of protein–peptide binding sites using support vector machine

Protein–peptide interactions are essential for all cellular processes including DNA repair, replication, gene‐expression, and metabolism. As most protein – peptide interactions are uncharacterized, it is cost effective to investigate them computationally as the first step. All existing approaches for predicting protein – peptide binding sites, however, are based on protein structures despite the fact that the structures for most proteins are not yet solved. This article proposes the first machine‐learning method called SPRINT to make Sequence‐based prediction of Protein – peptide Residue‐level Interactions. SPRINT yields a robust and consistent performance for 10‐fold cross validations and independent test. The most important feature is evolution‐generated sequence profiles. For the test set (1056 binding and non‐binding residues), it yields a Matthews’ Correlation Coefficient of 0.326 with a sensitivity of 64% and a specificity of 68%. This sequence‐based technique shows comparable or more accurate than structure‐based methods for peptide‐binding site prediction. SPRINT is available as an online server at: http://sparks-lab.org/ . © 2016 Wiley Periodicals, Inc.     

Development of a sugar-binding residue prediction system from protein sequences using support vector machine

Several methods have been proposed for protein–sugar binding site prediction using machine learning algorithms. However, they are not effective to learn various properties of binding site residues caused by various interactions between proteins and sugars. In this study, we classified sugars into acidic and nonacidic sugars and showed that their binding sites have different amino acid occurrence frequencies. By using this result, we developed sugar-binding residue predictors dedicated to the two classes of sugars: an acid sugar binding predictor and a nonacidic sugar binding predictor. We also developed a combination predictor which combines the results of the two predictors. We showed that when a sugar is known to be an acidic sugar, the acidic sugar binding predictor achieves the best performance, and showed that when a sugar is known to be a nonacidic sugar or is not known to be either of the two classes, the combination predictor achieves the best performance. Our method uses only amino acid sequences for prediction. Support vector machine was used as a machine learning algorithm and the position-specific scoring matrix created by the position-specific iterative basic local alignment search tool was used as the feature vector. We evaluated the performance of the predictors using five-fold cross-validation. We have launched our system, as an open source freeware tool on the GitHub repository (https://doi.org/10.5281/zenodo.61513).     

Study of caffeine binding to human serum albumin using optical spectroscopic methods

The binding of caffeine to human serum albumin (HSA) under physiological conditions has been studied by the methods of fluorescence, UV-vis absorbance and circular dichroism (CD) spectroscopy. The mechanism of quenching of HSA fluorescence by caffeine was shown to involve a dynamic quenching procedure. The number of binding sites n and apparent binding constant K _b were measured by the fluorescence quenching method and the thermodynamic parameters ΔH, ΔG, ΔS were calculated. The results indicate that the binding is mainly enthalpy-driven, with van der Waals interactions and hydrogen bonding playing major roles in the reaction. The distance r between donor (HSA) and acceptor (caffeine) was obtained according to the Förster theory of non-radiative energy transfer. Synchronous fluorescence, CD and three-dimensional fluorescence spectroscopy showed that the microenvironment and conformation of HSA were altered during the reaction.     

Thermodynamics of porphyrin binding to human serum albumin using affinity capillary electrophoresis

Summary The interaction thermodynamics of heptacarboxylporphyrin (HCP) and protoporhyrin (PP) with human serum albumin (HSA) was studied by affinity capillary electrophoresis (ACE) over the temperature range of 25–50°C, where HCP and PP bound to HSAvia 1:1 molecular association. The binding equilibrium constants (pH 7.4, phosphate buffer) for the binding of HCP with HSA were found to decrease with an increase in temperature, whereas the binding constants of the PP/HSA system appeared to be independent of temperature changes over the range studied. The van’t Hoff relationship (25–50°C) was found to be linear for the interaction of either HCP or PP with HSA. However, the interaction thermodynamics for both of these porphyrins with HSA were found to be quite different. In particular, the interaction of HCP (a hydrophilic porphyrin) with HSA appeared to be based on an enthalpy-driven process, whereas the binding between PP (a hydrophobic porphyrin) and HSA driven by a favorable change in entropy. The ability of using ACE to evaluate the interaction thermodynamics of serum proteins (e.g., HSA) with ligands (e.g., porphyrins and related compounds) should aid in the development of new and more effective photosensitizers in the photodynamic therapy of cancer.     

LOCUSTRA: accurate prediction of local protein structure using a two-layer support vector machine approach

Constraint generation for 3d structure prediction and structure-based database searches benefit from fine-grained prediction of local structure. In this work, we present LOCUSTRA, a novel scheme for the multiclass prediction of local structure that uses two layers of support vector machines (SVM). Using a 16-letter structural alphabet from de Brevern et al. (Proteins: Struct., Funct., Bioinf. 2000, 41, 271-287), we assess its prediction ability for an independent test set of 222 proteins and compare our method to three-class secondary structure prediction and direct prediction of dihedral angles. The prediction accuracy is Q16=61.0% for the 16 classes of the structural alphabet and Q3=79.2% for a simple mapping to the three secondary classes helix, sheet, and coil. We achieve a mean phi(psi) error of 24.74 degrees (38.35 degrees) and a median RMSDA (root-mean-square deviation of the (dihedral) angles) per protein chain of 52.1 degrees. These results compare favorably with related approaches. The LOCUSTRA web server is freely available to researchers at http://www.fz-juelich.de/nic/cbb/service/service.php.     

Polyoxometalate binding to human serum albumin: a thermodynamic and spectroscopic approach

The molecular recognition of polyoxometalates by human serum albumin is studied using two different polyoxometalates (POMs) at pH 7.5. The results are compared with those obtained at pH 3.5 and 9.0. At pH 7.5, both POMs strongly interact with the protein with different binding behaviors. The Keggin shaped POM, [H(2)W(12)O(40)](6-) (H2W12), specifically binds the protein, forming a complex with a 1:1 stoichiometry with Ka = 2.9 x 10(6) M(-1). The binding constant decreased dramatically with the increase of the ionic strength, thus indicating a mostly electrostatic binding process. Isothermal titration calorimetry (ITC) experiments show that the binding is an enthalpically driven exothermic process. For the wheel shaped POM [NaP(5)W(30)O(110)](14-) (P5W30), there are up to five binding sites on the protein. Increasing the ionic strength changes the binding behavior significantly, leading to a simple exothermic process, with several binding sites. Competitive binding experiments indicate that the two POMs share one common binding site. In addition, they show the existence of another important binding site for P5W30. The two POMs exhibit different binding dependences on the pH. The combination of the experimental results with the knowledge of the surface map of the protein in its N-B conformation transition domain leads to the proposal for the probable binding site of POMs. The present work reveals a protein conformation change upon P5W30 binding, a new feature not explicitly documented in previous studies.     

High-performance liquid chromatographic determination of the binding of ceftriaxone to human serum albumin solution and albumin from diluted human serum

The binding of ceftriaxone to human serum albumin has been studied by high-performance liquid chromatography. The gel permeation method of Hummel and Dreyer was used. Ceftriaxone was tested with two sources of albumin (aqueous solution and diluted serum). After internal calibration the binding parameters were determined for each albumin, and results compared. These data are in agreement with those from classical methods for the determination of protein binding of ceftriaxone.     

基于支持向量学习机方法的人体小肠吸收药物活性的预测

为了预测分子在人体小肠中的吸收,本文计算了表征分子的电子、拓扑、几何结构、分子形状等特征的102个分子描述符,用遗传算法变量选择方法使描述符减少到47个。体系共包含了230个化合物分子,69个不能被吸收(mA-),161个可以被吸收(HIA )。对建立的SVM模型,用5重交叉验证和独立测试集进行验证,预测正确率分别达到79．1％和77．1％,结果具有较好的一致性。在模型验证中,通过聚类分析方法组合训练集和测试集,保证了模型的稳定性,提高了建模效率。     

A kinetic model and its parameter estimation for the process of binding copper to human serum albumin by a voltammetric method

Linear sweep anodic stripping voltammetry was applied to determine the concentration of free copper ions in the process of binding copper to human serum albumin (HSA) on the mercaptoethane sulfonate modified gold electrode surface. A kinetic model of two consecutive steps for the process of binding copper to HSA was first proposed on the basis of the electrochemical results and compared with a parallel kinetic response model by using residual analysis. The experimental data of the stripping peak currents with time was fitted according to the model and the kinetic parameters, binding rate constants, k₁ and k₂, were estimated to be 0.411 and 0.055 min^–1, respectively.