The PASS (Prediction of Activity Spectra for Substances) estimates the probable biological activity profiles for compounds under study based on their structural formulae presented in MOLfile or SDfile format. General list of predictable biological activities consists of over 4,000 terms including pharmacotherapeutic effects (e.g., antiarrhythmic), biochemical mechanisms (e.g., cyclooxygenase 1 inhibitor), toxicity (e.g., carcinogenic), metabolism (e.g., CYP3A4 inhibition), gene expression regulation (e.g., VEGF expression inhibition), transporter-related activities (e.g., P-glycoprotein substrate). PASS prediction is based on the knowledge base about structure-activity relationships for more than 1,000,000 compounds with known biological activities. Average accuracy of prediction estimated in leave-one-out cross-validation procedure for the whole PASS training set is about 96%.

PharmaExpert analyzes the relationships between biological activities, drug-drug interactions and multiple targeting of chemical compounds. PharmaExpert provides a tool for selecting compounds with a pre-defined biological activity profile including desirable pharmacotherapeutic effects and biochemical mechanisms but excluding undesirable adverse and toxic effects. PharmaExpert uses PASS predictions as input information and provides the generation of electronic reports on analysis of chemical compound libraries.

GUSAR (General Unrestricted Structure-Activity Relationships) is a tool to create models on quantitative structure-activity (structure-property) relationships. The input of the program is the in-house training set of chemical structures and quantitative data on biological activities/properties. The output is a reliable quantitative SAR/SPR (Structure Activity/Property Relationship) model. The core of GUSAR consists of a unique algorithm of self-consistent regression allows to select the best set of MNA (Multilevel Neighborhoods of Atoms), biologically-based descriptors calculated on the basis of PASS predictions and QNA (Quantitative Neighborhoods of Atoms) descriptors for a robust and reliable QSAR model. The program allows uploading of SD files for batch predictions.

In case of any question, please, contact us.