Ivan Semenov

WORK HISTORY

EDUCATION

ABOUT IVAN SEMENOV

I am a highly skilled and with of industrial experience in the pharmaceutical and biotech sectors. I have worked in such companies as Insilico Medicine and BostonGene, where I contributed to developing computational workflows, analyzing biological and chemical big data, and applying AI and machine learning models to accelerate the drug discovery process. My expertise includes both structure- and ligand-based drug design, Python programming, and machine learning techniques, encompassing both classic and deep learning methods. Currently, I am pursuing a PhD in Bioinformatics at the University of British Columbia (UBC), specializing in computer-aided drug design. My research focuses on processing large-scale chemical databases, with an emphasis on clustering, drug-likeness assessment, ADMET properties prediction, and diversity analysis: Computational Chemistry • Ligand- and structure-based virtual screening • Rational drug design of small molecules • Assessment of druggability, toxicity and metabolic reactivity • Knowledge of RDKit, CDPKit, BioPandas libraries (Python) • MOE and Schrödinger software • Data extraction and processing from ChEMBL, PubChem databases • Knowledge of molecular representations (SMILES, 3D), data formats (pdb, sdf, etc.) and molecular descriptors Computer Science • Programming in Python (NumPy, Pandas, Scikit-Learn, Matplotlib, Seaborn) • Linux-based high performance computing • Distributed calculations on a cluster via SLURM • Routine use of version control (GitHub, GitLab, Bitbucket) • Experience with Docker and Docker-Compose • Knowledge of ML/AI models (PyTorch library)