In this contribution we present investigations about the use of computational intelligence for toxicity prediction of pesticides. Therefore different molecular descriptors are computed and the correlation behavior of the different descriptors in the descriptor space is studied. In a first step 164 pesticides are considered and 175 descriptors are taken into account. From this set of data prelim...

We are developing a new site descriptor for the DOCK molecular modeling program suite. Sphgen, the current site description program for the DOCK suite, describes the pockets of a macromolecule by filling a volume with intersecting spheres. DOCK then identifies possible ligand orientations in the pocket by overlapping the atoms of proposed ligands with the sphere centers. Sphgen limits use of th...

The logarithmic n-octanol/water partition coefficient (logK(ow)) is a very important property which concerns water-solubility, bioconcentration factor, toxicity and soil absorption coefficient of organic compounds. Quantitative structure-property relationship (QSPR) model for logK(ow) of 133 polychlorinated biphenyls (PCBs) is analyzed using heuristic method (HM) implemented in CODESSA. In orde...

Using the modern time-series analysis method in the time domain, based on the autoregressive moving average (ARMA) innovation model and white noise estimator, non-regular descriptor discrete-time stochastic linear systems are researched. Under assumption 1~3, an asymptotically stable reduced-order Wiener state estimator for descriptor systems is given by using projection and block matrix theori...

The Fisher's discriminant ratio has been used as a class separability criterion and implemented in a k-means clustering algorithm for performing simultaneous feature selection and data set trimming on a set of 221 HIV-1 protease inhibitors. The total number of molecular descriptors computed for each inhibitor is 43, and they are scaled to lie between 1 and 0 before being subjected to the featur...

We have previously established an in silico classification method ("CPathPred") to predict the major clearance pathways of drugs based on an empirical decision with only four physicochemical descriptors-charge, molecular weight, octanol-water distribution coefficient, and protein unbound fraction in plasma-using a rectangular method. In this study, we attempted to improve the prediction perform...

We propose a novel local nearest neighbor distance (LNND) descriptor for anomaly detection in crowded scenes. Comparing with the commonly used low-level feature descriptors in previous works, LNND descriptor has two major advantages. First, LNND descriptor efficiently incorporates spatial and temporal contextual information around the video event that is important for detecting anomalous intera...

We have previously established an in silico classification method (“CPathPred”) to predict the major clearance pathways of drugs based on an empirical decision with only four physicochemical descriptors—charge, molecular weight, octanol-water distribution coefficient, and protein unbound fraction in plasma—using a rectangular method. In this study, we attempted to improve the prediction perform...

BACKGROUND QSAR is among the most extensively used computational methodology for analogue-based design. The application of various descriptor classes like quantum chemical, molecular mechanics, conceptual density functional theory (DFT)- and docking-based descriptors for predicting anti-cancer activity is well known. Although in vitro assay for anti-cancer activity is available against many dif...