Tandem 3D-QSARs approach as a valuable tool to predict binding affinity data: design of new Gly/NMDA receptor antagonists as a key study.

Quantitative structure-activity relationships (QSARs) represent a very well consolidated computational approach to correlate structural or property descriptors of chemical compounds with their chemical or biological activities. We have recently reported that autocorrelation Molecular Electrostatic Potential (autoMEP) vectors in combination to Partial Least-Square (PLS) analysis or to Response Surface Analysis (RSA) can represent an interesting alternative 3D-QSAR strategy. In the present paper, we would like to present how the applicability of in tandem linear and nonlinear 3D-QSAR methods (autoMEP/PLS&RSA) can help to predict binding affinity data of a new set of N-methyl-d-aspartate (Gly/NMDA) receptor antagonists.

Prediction of blood glucose level of type 1 diabetics using response surface methodology and data mining.

In order to improve the accuracy of predicting blood glucose levels, it is necessary to obtain details about the lifestyle and to optimize the input variables dependent on diabetics. In this study, using four subjects who are type 1 diabetics, the fasting blood glucose level (FBG), metabolic rate, food intake, and physical condition are recorded for more than 5 months as a preliminary study. Then, using data mining, an estimation model of FBG is obtained, and subsequently, the trend in fluctuations in the next morning's glucose level is predicted. The subject's physical condition is self-assessed on a scale from positive (1) to negative (5), and the values are set as the physical condition variable. By adding the physical condition variable to the input variables for the data mining, the accuracy of the FBG prediction is improved. In order to determine more appropriate input variables from the biological information reflecting on the subject's glucose metabolism, response surface methodology (RSM) is employed. As a result, using the variables exhibiting positive correlations with the FBG in the RSM, the accuracy of the FBG prediction improved. Conditions could be found such that the accuracy of the predicting trends in fluctuations in blood glucose level reached around 80%. The prediction method of the trend in fluctuations in the next morning's glucose levels might be useful to improve the quality of life of type 1 diabetics through insulin treatment, and to prevent hypoglycemia.

Consideration of physical condition in estimation of blood glucose via data mining.

Many diabetics carry a portable-type blood glucose monitor and collect their own blood to examine their blood glucose levels daily (self monitoring of blood glucose, SMBG). The use of a physical condition variable was suggested in order to estimate the blood glucose level for diabetics. Four sets of data, including FBG, food intake, metabolic rate and physical condition, were collected from four Type 1 diabetics over a five-month period. Using these data, an increasing or decreasing tendency for FBG for the next day was estimated using the data mining method. The results revealed that the estimation accuracy was improved when a physical condition variable was used. An average correspondence rate of 81 % was observed, with a maximum of 90 %. These results indicated that the data mining method could be effective in the estimation of blood glucose levels.