His research interests focus on the application of machine learning to chemical problems. He is currently developing the RGBChem project, a method for generating chemical information representations suitable for training convolutional neural networks (CNNs). Previously, he worked on the PICle project as part of his engineering thesis, where he used classical machine learning algorithms to predict the potential energy of thirteen-atom CuNi clusters with identical symmetry.
He earned his BSc degree in Chemical Technology from Wrocław University of Science and Technology in 2023, followed by an MSc in Bioinformatics from the University of Environmental and Life Sciences in Wrocław in 2025. He is currently pursuing a PhD at Wrocław University of Science and Technology. All three theses — engineering, master’s, and doctoral — have been and are being supervised by Professor Bartek Szyja, with whom he has collaborated since 2020, when they began working together through the university’s tutoring program.
Publications
- May 12, 2025 – RGBChem: Image-Like Representation of Chemical Compounds for Property Prediction (IF = 5.7)
- Jul 18, 2024 – Challenges in Peptide Solubilization – Amyloids Case Study (IF = 7.0)
- Nov 26, 2023 – Can Machine Learning Predict the Reaction Paths in Catalytic CO2 Reduction on Small Cu/Ni Clusters? (IF = 3.9)
- Dec 9, 2022 – Application of the Pyrazolone Derivatives as Effective Modulators in the Opto-Electronic Networks (IF = 4.3)