I'm a Computational Enzyme Engineer passionate about developing and applying cutting-edge machine learning models for designing biotechnologically relevant enzymes. Currently, I'm leading a team focused on improving enzyme stability and activity using generative deep learning models and atomistic modeling at EnginZyme.

• Programming Languages:

  • Python
  • R

• Machine Learning / AI:

  • Classical machine learning (scikit-learn)
  • Deep learning and neural networks (PyTorch)
  • Probabilistic models (Pyro)
    • Project: Solving probabilistic problems from the "Data Analysis - A Bayesian Tutorial" textbook with Pyro.
    • Project: Solving probabilistic problems from the "Model-Based Machine Learning" textbook with Pyro.

• Bioinformatics:

  • Structure analysis (AlphaFold2, Rosetta, APBS, PyMol)
  • Sequence analysis (HHblits, CD-HIT, HMMER, BLAST, ESM2, etc.)
    • Project: CAZyme prediction in Ascomycetes yeast genomes
    • Project: Experimental exploration of the enzyme class EC 1.1.3.15

• Data Analysis & Mining:

  • Web scraping (selenium)
  • Dataset analysis and integration (pandas)

• Other:

  • Git
  • Computational pipeline development

• Protein Substrate & Activity Prediction:

  • Deep learning-based kcat prediction enables improved enzyme-constrained model reconstruction
  • A general model to predict small molecule substrates of enzymes based on machine and deep learning
  • Deep learning allows genome-scale prediction of Michaelis constants from structural features

• Enzyme Engineering & Directed Evolution:

  • Expanding functional protein sequence spaces using generative adversarial networks
  • Chiral Alcohols from Alkenes and Water: Directed Evolution of a Styrene Hydratase
  • Directed Evolution of (R)-2-Hydroxyglutarate Dehydrogenase Improves 2-Oxoadipate Reduction by 2 Orders of Magnitude
  • Modeling-Assisted Design of Thermostable Benzaldehyde Lyases from Rhodococcus erythropolis for Continuous Production of α-Hydroxy Ketones
  • Directed Evolution of Gloeobacter violaceus Rhodopsin Spectral Properties
  • Archaerhodopsin variants with enhanced voltage-sensitive fluorescence in mammalian and Caenorhabditis elegans neurons
  • Directed evolution of a far-red fluorescent rhodopsin

• Next-Generation Sequencing Data Processing:

  • Ribonucleotides incorporated by the yeast mitochondrial DNA polymerase are not repaired
  • Nucleotide pools dictate the identity and frequency of ribonucleotide incorporation in mitochondrial DNA

You will find more of my previous work at my old research groups GitHub page

• LinkedIn
• Google Scholar