Development of elementary modules for QSAR

• Implementation of descriptor evaluation algorithms
• Algorithm development for QSAR like artificial neural network, genetic algorithm, etc.
• Statistical modules like multiple regression analysis, principle component analysis, etc.
• Prediction of physiological activity of candidates by genetic algorithm, artificial neural network, multiple linear regression, etc.

Prediction of drug-like compounds

• Molecular descriptors for ADME/Tox prediction. (water solubility, logP, logD, pKa, polar surface area, polarizability, refractivity, No. H-bond acceptors and donors, Kier & Hall topological descriptors, solvation free energy density descriptors, etc.)
• Absorption prediction (Caco-2 cell, Madin-Darby canine kindey cell, blood-brain barrier, human intestinal absorption, skin permeability, protein binding)
• Metabolism prediction (structure lability, Cytochrom P450s induction, inhibition)
• Toxicity prediction (Rat oral LD50, mutagenicity, Chronic LOAEL)
• Drug-likeness prediction (Lipinski¡¯s rule (rule of 5), Leadlike rule, Bioavailability(Blood level)

Database system for organic chemicals

• Conceptual design of organic chemical database
• Design of viewer module (Bioinformatical support for drug-target discovery)

Chemical library design

• Molecular descriptors for Combi. Chem. and HTS library design (fast topological descriptors : Kier & Hall descriptors, information contents, E-state keys and diverse fingerprint keys, BCUT values )
• 2D, 3D fingerprint key design (2D similarity, classification of atomic types, pharmacophore definition)
• Library selection rule (considering molecular diversity, ADME/Tox, reagents cost, deconvolution)