📌About Us
The group of Prof. Rasulev is focused on development of artificial intelligence (AI)-based predictive models to design novel polymeric materials, nanomaterials and to predict their various properties, including toxicity, solubility, fouling release properties, elasticity, degradation rate, biodegradation, etc. The group applies computational chemistry, machine learning and cheminformatics methods for modeling, data analysis and development of predictive structure-property relationship models to find structural factors responsible for activity of investigated materials.
💻Web Site http://www.rasulev.org
Tg ML prediction
It is a free web-application for Glass Transition Temperature prediction
The glass transition temperature (Tg) is one of the most important properties of polymeric materials and indicates an approximate temperature below which a macromolecular system changes from a relatively soft, flexible and rubbery state to a hard, brittle and glass-like one1. The Tg value also determines the utilization limits of many rubbers and thermoplastic materials. Besides, the drastic changes in the mobility of the molecules in different glassy states (from the frozen to the thawed state) affect many other chemical and physical properties, such as mechanical modulus, acoustical properties, specific heat, viscosity, mechanical energy absorption, density, dielectric coefficients, viscosity and the gases and liquids difussion rate in the polymer material. The change of these mechanical properties also specifies the employment of the material and the manufacturing process.
The Tg ML predictor is a Web App that use a SVM regression model to predict the glass transition temperature.