George Varennikov
Portfolio
Inty
• Developed software using Delphi for modelling the physics of water molecules interactions. • Researched the possibility of using recurrent neural network models (LSTM) to simulate the physics of water molecules interactions. • Applied evolutionary algorithm to solve the problem of finding the minimum potential energy.
VNIIA, MIPT
• Utilized machine learning algorithms to predict various alloys properties (irradiation and corrosion resistance, strength, etc). Increased models accuracy with hyperparameter optimization and feature engineering. • Developed software using Python for automatic pre-processing, data analysis, model fitting, and prediction of alloy properties. • Developed the novel approach to the automatic search for ordered structures in multicomponent alloys.
Laboratory of Functional Genomics (RCMG)
Utilized R to search for all possible variants of detected human mutations (>20 min) that can be edited with Crispr-Cas9 systems.