Bo Tao Fan

Comparative study of QSAR/QSPR correlations using support vector machines, radial basis function neural networks, and multiple linear regression.

Support vector machines (SVMs) were used to develop QSAR models that correlate molecular structures to their toxicity and bioactivities. The performance and predictive ability of SVM are investigated and compared with other methods such as multiple linear regression and radial basis function neural network methods. In the present study, two different data sets were evaluated. The first one involves an application of SVM to the development of a QSAR model for the prediction of toxicities of 153 phenols, and the second investigation deals with the QSAR model between the structures and the activities of a set of 85 cyclooxygenase 2 (COX-2) inhibitors. For each application, the molecular structures were described using either the physicochemical parameters or molecular descriptors. In both studied cases, the predictive ability of the SVM model is comparable or superior to those obtained by MLR and RBFNN. The results indicate that SVM can be used as an alternative powerful modeling tool for QSAR studies.

Prediction of the Isoelectric Point of an Amino Acid Based on GA-PLS and SVMs

The support vector machine (SVM), as a novel type of a learning machine, for the first time, was used to develop a QSPR model that relates the structures of 35 amino acids to their isoelectric point. Molecular descriptors calculated from the structure alone were used to represent molecular structures. The seven descriptors selected using GA-PLS, which is a sophisticated hybrid approach that combines GA as a powerful optimization method with PLS as a robust statistical method for variable selection, were used as inputs of RBFNNs and SVM to predict the isoelectric point of an amino acid. The optimal QSPR model developed was based on support vector machines, which showed the following results: the root-mean-square error of 0.2383 and the prediction correlation coefficient R=0.9702 were obtained for the whole data set. Satisfactory results indicated that the GA-PLS approach is a very effective method for variable selection, and the support vector machine is a very promising tool for the nonlinear approximation.

Quantitative prediction of liquid chromatography retention of N-benzylideneanilines based on quantum chemical parameters and radial basis function neural network.

Based on quantum chemical parameters and a simple numerical coding, the liquid chromatography retention of bifunctionally substituted N-benzylideneaniles (NBA) has been predicted using a radial basis function neural network (RBFNN) model. The quantum chemical parameters involved in the model are dipole moment (m), energies of the highest occupied and lowest unoccupied molecular orbitals (E(homo,) E(lumo)), net charge of the most negative atom (Q(min)), sum of absolute values of the charges of all atoms in two given functional groups (Delta), total energy of the molecule (E(T)), weight of the molecule (W), and numerical coding (N). N was used to indicate the different positions of two substituents. The predictive values are consistent with the experimental results. The mean relative error of the testing set is 1.6%, and the maximum relative error is less than 5.0%. In this work the success of the whole modeling process only depends on the optimization of the spread parameter in network.

Diagnosing anorexia based on partial least squares, back propagation neural network, and support vector machines

Support vector machine (SVM), as a novel type of learning machine, for the first time, was used to develop a predictive model for early diagnosis of anorexia. It was based on the concentration of six elements (Zn, Fe, Mg, Cu, Ca, and Mn) and the age extracted from 90 cases. Compared with the results obtained from two other classifiers, partial least squares (PLS) and back-propagation neural network (BPNN), the SVM method exhibited the best whole performance. The accuracies for the test set by PLS, BPNN, and SVM methods were 52%, 65%, and 87%, respectively. Moreover, the models we proposed could also provide some insight into what factors were related to anorexia.

Spectral Code Index (SPECOIND): A General Infrared Spectral Database Search Method

A new spectral code that can be used by Relational Database Management Systems (RDBMS) as an index for infrared (IR) spectra searches in Relational Database (RDB) is presented and its suitability is evaluated. Spectral codes are constructed for all spectra in the database as the spectral indexes and three query strings are created with the same theory used for the creation of the index code for the query spectrum. Some effects of parameters used to create index strings and query strings are discussed. All spectral searches are accomplished in structured query language (SQL) approach and the utilization examples of SQL have been shown. The sequential application of this procedure can reduce the original library of about 18 000 spectra to a few spectra that can be used as references for subsequent detailed comparison. The software developed for the proposed system is particularly suitable for spectral search and structure interpretation.

MolDiA: a novel molecular diversity analysis tool. 1. Principles and architecture.

We introduce the principles and the architecture of a user-friendly software named MOLDIA (Molecular Diversity Analysis) which aims to the comparison of diverse molecular data sets through an XML structured database of predefined fragments. The MOLDIA descriptors are composed of complex fingerprint-like structures, which enclose not only structural information but also physicochemical property data. The system architecture includes the use of customizable weights on molecular descriptors and different choices of similarity/diversity measures to analyze the given data sets. Intermolecular comparisons using Ullmanns algorithm were optimized by the use of fuzzy logic, generic atoms, and a whole system of chemical graph analysis. We have found that customizing the similarity/diversity computation using structural and/or properties weights and choosing the level of fuzziness of the molecular comparison allow the user to adapt the tool to particular needs and increases the possibilities of MolDiA applications. The implementation of XML Web technologies has proven to improve and ease the extraction, processing, and analysis of chemical information.

Ring perception. Application of elimination technique to the SSSR search from a connection table

The application of an elimination technique in a new simple algorithm for ring perception is reported. This technique guarantees that each smallest ring found apart from a root node is one member of the Smallest Set of Smallest Rings (SSSR). As a consequence, the SSSR can be found without any accessory process.

Quantum chemical AM1 study of dimerization by hetero-Diels–Alder reaction of methyl 4,6-O-benzylidene-3-deoxy-3-C-methylene-α- D -hexopyranoside-2-ulose

An unusual reaction, the dimerization by hetero-Diels–Alder reaction of methyl 4,6-O-benzylidene-3-deoxy-3-C-methylene-α-D-hexapyranoside-2-ulose, has been studied by a detailed computational analysis using the AM1 method. A reaction mechanism is proposed based on the calculated results, and it is in good agreement with the experimental data. The theoretical calculations can explain the excellent regioselectivity of this dimerization and other phenomena observed during the experiments.