Masamoto Arakawa

Genetic algorithm-based wavelength selection method for spectral calibration

In this paper, we propose a genetic algorithm‐based wavelength selection (GAWLS) method for visible and near‐infrared (Vis/NIR) spectral calibration. The objective of GAWLS is to construct robust and predictive regression models by selecting informative wavelength regions. To demonstrate the ability of the proposed method, regression models for soil properties and sugar content of apples are constructed by using GAWLS and other variable selection methods. Copyright

Development of a New Regression Analysis Method Using Independent Component Analysis

In this paper, independent component analysis (ICA) and regression analysis are combined to extract significant components. ICA is a method that extracts mutually independent components from explanatory variables. A relationship between the independent components and an objective variable is constructed by the least-squares method. This method is named ICA-MLR (MLR = multiple linear regression). We verified the superiority of ICA-MLR over partial least squares (PLS) with simulation data and tried to apply this method to a quantitative structure-property relationship analysis of aqueous solubility. We constructed models between aqueous solubility and 173 molecular descriptors. PLS and genetic algorithm PLS models were constructed for a comparison of ICA-MLR. R2, Q2, and Rpred2 values of the PLS model are 0.836, 0.819, and 0.848, respectively. These values of the ICA-MLR model are 0.937, 0.868, and 0.894, respectively. ICA-MLR achieved higher predictive accuracy than PLS. ICA-MLR could extract effective components from explanatory variables and construct the regression model with high predictive accuracy. In addition, the information of regression coefficients bICA-MLR indicates the magnitude of contribution of each descriptor in the analysis of aqueous solubility.

Novel soft sensor method for detecting completion of transition in industrial polymer processes

Soft sensors are widely used to estimate process variables that are difficult to measure online. In polymer plants that produce various grades of polymers, the quality of products must be estimated using soft sensors in order to reduce the amount of off-grade material. However, during grade transition, the predictive accuracy deteriorates because the state in polymer reactors is unsteady, causing the values of process variables to differ from the steady-state values used to construct regression models. Therefore, we have proposed to construct models that detect the completion of transition to ensure that the polymer quality evaluated after transition conforms to the predicted one. By using these models and regression models constructed for each product grade, the polymer quality can be predicted with high accuracy, selecting a regression model appropriately. The proposed method was applied to industrial plant data and was found to exhibit higher predictive performance than traditional methods.

New molecular surface-based 3D-QSAR method using Kohonen neural network and 3-way PLS

Comparative molecular field analysis (CoMFA) has been widely used as a standard three dimensional quantitative structure-activity relationship (3D-QSAR) method. Although CoMFA is a useful technique, it does not always reflect real ligand-receptor interaction. Molecular interactions between the ligand and receptor are mainly occurred near the van der Waals surface of ligand. All grid points surrounding whole molecule in CoMFA are not important as molecular descriptors. If each molecule is represented by physico-chemical parameters on molecular surface, more precise and realistic 3D-QSAR is possible. We developed a new surface-based 3D-QSAR method using Kohonen neural network (KNN) and three-way partial least squares (3-way PLS). This method was applied to 25 dopamine 2 (D2) receptor antagonists for validation. First, the 3D coordinates of all sampling points on the van der Waals surface were projected into the 2D map by KNN. Each node in the map was coded by the associated molecular electrostatic potential (MEP) value of the original sampling point. Then, the correlation between the MEP values of all 2D maps and D2 receptor antagonist activities was analyzed by 3-way PLS. The statistics of the 3-way PLS model was excellent and the coefficients back-projected on the van der Waals surface had reasonable 3D distribution. Lastly, all data was divided into the calibration and validation sets by D-optimal designs and the activities of validation set were predicted. The external validation suggested that 3-way PLS is better than standard (2-way) PLS for prediction.

Rational choice of bioactive conformations through use of conformation analysis and 3-way partial least squares modeling

Abstract Comparative molecular field analysis (CoMFA) has become widely used in three-dimensional (3D) QSAR studies. Although CoMFA has been of general use, there are some critical problems in the proper application. A major problem of CoMFA, including most other 3D QSAR methodologies, is that the results are dependent on the chosen bioactive conformations and the corresponding alignment rules of molecules. Recently, we have proposed a novel method with a 3-way PLS formulation for solving the conformation/alignment problem in 3D QSAR studies [K. Hasegawa, M. Arakawa, K. Funatsu, Chemom. Intell. Lab. Syst., 47 (1999) 33–40]. The purpose of the present study is to demonstrate the general utility of our approach by applying to a real CoMFA data set. The data set of Protein-Tyrosine Kinase (PTK) inhibitors was used as a test sample. The possible 3D conformations of all molecules were generated by conformational analysis and they were characterized by field variables of CoMFA. To each unique conformation of the most active compound, one sample-variable sheet comprising of the most similar conformations was defined. The 3-way arrays for 3-way PLS analysis were created by collecting all sample-variable sheets. From the regression coefficient values of the 3-way PLS model, conformations largely contributing to inhibitory activity were selected and the resulting final CoMFA model could give the reasonable 3D coefficient contour maps.

Exhaustive Structure Generation for Inverse-QSPR/QSAR.

Chemical structure generation based on quantitative structure property relationship (QSPR) or quantitative structure activity relationship (QSAR) models is one of the central themes in the field of computer‐aided molecular design. The objective of structure generation is to find promising molecules, which according to statistical models, are considered to have desired properties. In this paper, a new method is proposed for the exhaustive generation of chemical structures based on inverse‐QSPR/QSAR. In this method, QSPR/QSAR models are constructed by multiple linear regression method, and then the conditional distribution of explanatory variables given the desired properties is estimated by inverse analysis of the models using the framework of a linear Gaussian model. Finally, chemical structures are exhaustively generated by a sophisticated algorithm that is based on a canonical construction path method. The usefulness of the proposed method is demonstrated using a dataset of the boiling points of acyclic hydrocarbons containing up to 12 carbon atoms. The QSPR model was constructed with 600 hydrocarbons and their boiling points. Using the proposed method, chemical structures which had boiling points of 100, 150, or 200 °C were exhaustively generated.

The Recent Trend in QSAR Modeling - Variable Selection and 3D-QSAR Methods

Quantitative structure-activity relationships (QSAR) are one of the most important methodologies for rational drug design. In QSAR, compounds are represented by chemical structure descriptors, and then statistical models are built to predict biological activities of candidate structures. In this paper, two principal topics in QSAR, variable selection and 3D-QSAR, are picked up and are reviewed in recent trend. The aim of variable selection is to construct a significant QSAR model by selecting important descriptors among from descriptor pool. Until now, many variable selection methods have been developed and proposed. On the other hand, molecular alignment is important factor of 3D-QSAR analysis because appropriate alignment is usually required to construct proper 3D-QSAR models. In addition, we review new QSAR methods using molecular surface properties, alignment independent QSAR methods, and 4D-QSAR methods.

3D-QSAR STUDY OF INSECTICIDAL NEONICOTINOID COMPOUNDS BASED ON 3-WAY PARTIAL LEAST SQUARES MODEL

Abstract A choice of an active conformer and the corresponding alignment rule is an important problem for determining the success of 3D-QSAR study. For flexible molecules, this problem is the most difficult one and construction of the method with appropriate chemometric tools has been required. Recently, Bro [J. Chemom., 10, 1996, 47–61] has proposed a trilinear PLS algorithm as the trilinear extension of standard bilinear PLS in the field of analytical chemistry. Bros 3-way PLS method seems to be suitable to the 3D-QSAR problem but only few attempts have so far been made at the subject. The object of this study is to investigate the ability of Bros 3-way PLS method for solving the conformer/alignment problem in 3D-QSAR study. The structure-activity data of insecticidal neonicotinoid compounds were used as a test example. The 3-way arrays were constructed from eight sample vectors and eight electrostatic similarity matrices derived from eight combinations of conformers and alignment rules. The correlation between the 3-way arrays and the insecticidal activity vector was investigated by Bros 3-way PLS method. The 3-way PLS model with three significant components was obtained, and from its PLS loading the best combination of conformer and alignment rule could be selected.

Systematic Generation of Chemical Structures for Rational Drug Design Based on QSAR Models

The first step in the process of drug development is to determine those lead compounds that demonstrate significant biological activity with regard to a target protein. Because this process is often costly and time consuming, there is a need to develop efficient methodologies for the generation of lead compounds for practical drug design. One promising approach for determining a potent lead compound is computational virtual screening. The biological activities of candidate structures found in virtual libraries are estimated by using quantitative structure activity relationship (QSAR) models and/or computational docking simulations. In virtual screening studies, databases of existing drugs or natural products are commonly used as a source of lead candidates. However, these databases are not sufficient for the purpose of finding lead candidates having novel scaffolds. Therefore, a method must be developed to generate novel molecular structures to indicate high activity for efficient lead discovery. In this paper, we review current trends in structure generation methods for drug design and discuss future directions. First, we present an overview of lead discovery and drug design, and then, we review structure generation methods. Here, the structure generation methods are classified on the basis of whether or not they employ QSAR models for generating structures. We conclude that the use of QSAR models for structure generation is an effective method for computational lead discovery. Finally, we discuss the problems regarding the applicability domain of QSAR models and future directions in this field.

Multi-way PLS modeling of structure-activity data by incorporating electrostatic and lipophilic potentials on molecular surface

We devised and elaborated a surface-based three-dimensional-quantitative structure-activity relationship (3D-QSAR) method, which had been proposed in the previous study. This approach can be applied to more general case where both the electrostatic and lipophilic potentials on molecular surface simultaneously change. The 3D coordinates of all sampling points on molecular surface are projected into a 2D map by Kohonen neural network (KNN). Each node in the map is coded by the associated molecular electrostatic potential (MEP) or molecular lipophilic potential (MLP) values. The electrostatic and lipophilic KNN maps are generated for each compound and the four-way array is constructed by collecting two KNN maps of all samples. The correlation between four-way array and biological activity is examined by four-way partial least-squares (PLS). For validation, the structure-activity data of estrogen receptor antagonists was investigated. The four-way PLS model gave the high statistics at calibration and validation stages. The coefficients of the four-way PLS model back-projected on molecular surface had a reasonable 3D distribution and it was nicely consistent with active site of the estrogen receptor which was recently made clear by X-ray crystallography.