Diagnosing breast cancer based on support vector machines

The Support Vector Machine (SVM) classification algorithm, recently developed from the machine learning community, was used to diagnose breast cancer. At the same time, the SVM was compared to several machine learning techniques currently used in this field. The classification task involves predicting the state of diseases, using data obtained from the UCI machine learning repository. SVM outperformed k-means cluster and two artificial neural networks on the whole. It can be concluded that nine samples could be mislabeled from the comparison of several machine learning techniques.     

AM1 calculations of O-H bond dissociation energies in polyoxides

Energies of homolytic cleavage of O-H bonds in 33 compounds of the general formula Ro _n H (n = 2, 3, and 4) were calculated by the AMI method. For hydrotrioxides and hydrotetroxides, the bond dissociation energies are virtually independent of the nature of the substituent R:D(RO _n -H) = 92.3±0.8 kcal mol^–1 (n = 3 and 4).     

Critical re-evaluation of the O-H bond dissociation enthalpy in phenol

The gas-phase O-H bond dissociation enthalpy, BDE, in phenol provides an essential benchmark for calibrating the O-H BDEs of other phenols, data which aids our understanding of the reactivities of phenols, such as their relevant antioxidant activities. In a recent review, the O-H BDE for phenol was presented as 90 +/- 3 kcal mol(-1) (Acc. Chem. Res. 2003, 36, 255-263). Due to the large margin of error, such a parameter cannot be used for dynamic interpretations nor can it be used as an anchor point in the development of more advanced computational models. We have reevaluated the existing experimental gas-phase data (thermolyses and ion chemistry). The large errors and variations in thermodynamic parameters associated with the gas-phase ion chemistry methods produce inconsistent results, but the thermolytic data has afforded a value of 87.0 +/- 0.5 kcal mol(-1). Next, the effect of solvent has been carefully scrutinized in four liquid-phase methods for measuring the O-H BDE in phenol: photoacoustic calorimetry, one-electron potential measurements, an electrochemical cycle, and radical equilibrium electron paramagnetic resonance (REqEPR). The enthalpic effect due to solvation, by, e.g., water, could be rigorously accounted for by means of an empirical model and the difference in hydrogen bond interactions of the solvent with phenol and the phenoxyl radical. For the REqEPR method, a second correction is required since the calibration standard, the O-H BDE in 2,4,6-tri-tert-butylphenol, had to be revised. From the gas-phase thermolysis data and three liquid-phase techniques (excluding the electrochemical cycle method), the present analysis yields a gas-phase BDE of 86.7 +/- 0.7 kcal mol(-1). The O-H BDE was also estimated by state-of-the-art computational approaches (G3, CBS-APNO, and CBS-QB3) providing a range from 86.4 to 87.7 kcal mol(-1). We therefore recommend that in the future, and until further refinement is possible, the gas-phase O-H BDE in phenol should be presented as 86.7 +/- 0.7 kcal mol(-1).     

Determination of the dissociation energy of the C-At bond in substituted astatobenzenes

The dissociation energy of C–At bond /D_C–At/ in a number of astatobenzene derivatives has been determined by pyrolytic method. The values of D_C–At for the astatoaromatic compounds investigated have been found to be independent of the substituents and their relative position in the astatoaromatic system.Dedicated to Prof. V.D. Nefedov on the occasion of his 70th birhtday     

Estimation of O-H bond dissociation energies in alcohols and acids from kinetic data

The O-H bond dissociation energies (D _O-H) in five alcohols and six acids have been determined from experimental data (rate constants of radical reactions). The ratio of the rate constants of the reactions R¹O˙+RH→R¹OH+R˙ and R ⁱ O˙+RH→R ⁱ OH+R˙ and the intersecting parabolas method are used in the estimation procedure. The D _O-H values are used to calculate the activation energies and rate constants for hydrogen abstraction from 2-methylbutane, butene-1, and cumene by alkoxyl and carboxyl radicals. The geometric parameters of the transition state are calculated for these reactions.     

DFT study of the C-Cl bond dissociation enthalpies and electronic structure of substituted chlorobenzene compounds

Quantum chemical calculations were used to estimate the bond dissociation energies (BDEs) for 13 substituted chlorobenzene compounds. These compounds were studied by employing the hybrid density functional theory methods (B3LYP, B3PW1, B3P86) with 6-31G** and 6-311G** basis sets. It was demonstrated that B3P86/6-311G** method is the best method for computing the reliable BDEs for substituted chlorobenzene compounds which contain the C-Cl bond. It was found that the C-Cl BDE depends strongly on a computational method and basis set used. Substitution effect on the C-Cl BDE of substituted chlorobenzene compounds is further discussed. It is shown that the effects of substitution on the C-Cl BDE of substituted chlorobenzene compounds are very insignificant. Frontier orbital energy gap of studied compounds was also investigated. From the data on frontier orbital energies gap, we estimated the relative thermal stability of substituted chlorobenzene compounds.     

Accurate O-H bond dissociation energy differences of hydroxylamines determined by EPR spectroscopy: computational insight into stereoelectronic effects on BDEs and EPR spectral parameters

Differences in O-H bond dissociation enthalpies (ΔBDEs) between the hydroxylamine of (15)N-labeled TEMPONE and 10 N,N-di-tert-alkyl hydroxylamines were determined by EPR. These ΔBDEs, together with the g and a(N) values of the derived nitroxide radicals, are discussed in relation to various geometric, intramolecular dipole/dipole, and steric effects and in relation to the results from DFT calculations. We find that dipole/dipole interactions are the dominant factors in dictating a(N) values and O-H BDEs in all of these structurally similar nitroxides and hydroxylamines, respectively. The importance of including the Boltzmann distribution of conformations for each nitroxide in the a(N) calculations is emphasized.     

烷烃中碳氢键离解能的估算及其应用

将烷烃中的C－H键看成氢原子H与烷基Ri相连接而成的Ri－H键，以烷基的 HOMO能级和氢原子的轨道能来关联Ri－H键的离解能BDE。研究表明，烷烃分子中 Ri－H键的离能BDE与烷基Ri的极化效应指数PEI（Ri）有良好的线性关系：BDE＝ c+dPEI(Ri)。所得方程具有良好的估算精度。烷基Ri极化效应指数PEI（Ri）在羟 基自由基与烷烃反应速度常数的定量相关中，也得到良好的应用。     

Prediction of T-cell epitopes based on least squares support vector machines and amino acid properties

T-lymphocyte (T-cell) is a very important component in human immune system. It possesses a receptor (TCR) that is specific for the foreign epitopes which are in a form of short peptides bound to the major histocompatibility complex (MHC). When T-cell receives the message about the peptides bound to MHC, it makes the immune system active and results in the disposal of the immunogen. The antigenic determinants recognized and bound by the T-cell receptor is known as T-cell epitope. The accurate prediction of T-cell epitopes is crucial for vaccine development and clinical immunology. For the first time we developed new models using least squares support vector machine (LSSVM) and amino acid properties for T-cell epitopes prediction. A dataset including 203 short peptides (167 non-epitopes and 36 epitopes) was used as the input dataset and it was randomly divided into a training set and a test set. The models based on LSSVM and amino acid properties were evaluated using leave-one-out cross-validation method and the predictive ability of the test set, and obtained the results of 0.9875 and 0.9734 under the ROC curves, respectively. This result is more satisfactory than that were reported before. Especially, the accuracy of true positive gets a marked enhancement.     

Using support vector machines for prediction of protein structural classes based on discrete wavelet transform

The prediction of secondary structure is a fundamental and important component in the analytical study of protein structure and functions. How to improve the predictive accuracy of protein structural classification by effectively incorporating the sequence‐order effects is an important and challenging problem. In this study, a new method, in which the support vector machine combines with discrete wavelet transform, is developed to predict the protein structural classes. Its performance is assessed by cross‐validation tests. The predicted results show that the proposed approach can remarkably improve the success rates, and might become a useful tool for predicting the other attributes of proteins as well. © 2008 Wiley Periodicals, Inc. J Comput Chem 2009     

取代乙烯顺反异构体键能和稳定性的密度泛函理论研究

对十甲种取代乙烯（XX’CCYY’）顺反异构体进行了DFT-B3LYP/6-31G（d)水 平的几何全优化的总能量、总键能的计算。结果表明，对无共轭大π键的二取代乙 烯，其顺式异构体的总能量比反式异构体的低，前沿轨道能隙、总键能和总π键能 均比反式异构体的大，而对有共轭大π键的体系，其情况则刚好相反。表明对于前 者其顺式异构体比反式异构体稳定，而对于后者则反式异构体比顺式异构体稳定。     

C-H bond dissociation enthalpies in norbornane. An experimental and computational study

Gas-phase C-H bond dissociation enthalpies (BDEs) in norbornane were determined by quantum chemistry calculations and the C2-H BDE was experimentally obtained for the first time by time-resolved photoacoustic calorimetry. CBS-Q and CBS-QB3 methods were used to derive the values DH degrees (C1-H) = 449 kJ mol-1, DH degrees (C7-H) = 439 kJ mol-1, and DH degrees (C2-H) = 413 kJ mol-1. The experimental result DH degrees (C2-H) = 414.6 +/- 5.4 kJ mol-1 is in excellent agreement with the theoretical value. The trend DH degrees (C1-H) > DH degrees (C7-H) > DH degrees (C2-H) is discussed.