John Kazan

Hello! I am a Computational Biophysicist | Data Scientist with 10 years of expertise in computational chemistry and structural biology, specializing in protein design, docking, molecular simulations, and bioinformatics. Skilled in developing computational models and implementing techniques to optimize workflows, enabling efficient data manipulation and analysis. My passion lies in leveraging machine learning techniques to advance discoveries.

Data Science Expertise:
✦ Data Manipulation: Python, R, Pandas, data.table, Dplyr
✦ Data Visualization: Matplotlib, Seaborn, Plotly, Tableau
✦ Machine Learning: scikit-learn, TensorFlow, Keras, XGBoost
✦ Feature Engineering: Featuretools, Feature-engine
✦ Model Evaluation and Validation: Cross-validation, hyperparameter tuning, SHAP
✦ Natural Language Processing (NLP): NLTK, spaCy, Gensim
✦ Big Data Technologies: Hadoop, Spark, Dask
✦ Cloud Computing Platforms: AWS, Azure, Google Cloud

Computational Chemistry Proficiency:
✦ Molecular modeling: Rosetta, Schrodinger, Modeller
✦ Quantum Mechanics: Gaussian, NWChem, Psi4
✦ Molecular Dynamics (MD) Simulations: GROMACS, AMBER, CHARMM, GROMACS, NAMD
✦ Density Functional Theory (DFT): VASP, Quantum Espresso, ORCA, ADF
✦ QM/MM Simulations: CHARMM, CP2K
✦ Molecular Docking: Rosetta, AutoDock, AutoDock Vina, Glide
✦ Cheminformatics: RDKit, ChemAxon, Open Babel
✦ Molecular Visualization: PyMOL, VMD, UCSF Chimera, Avogadro
✦ Statistical Analysis: R, SciPy

Postdoctoral Research Fellow

- Conducted extensive research in computational chemistry and computational biology, analyzing large datasets, and deriving actionable insights
- Developed and implemented advanced machine learning algorithms and predictive models to solve complex problems, resulting in reduced expense in drug discovery
- Collaborated with interdisciplinary teams of scientists to gather requirements, define project goals, and ensure successful implementation of data-driven solutions
- Presented findings and insights to clients through visualizations, reports, and presentations
- Conducted extensive data analysis and modeling for molecular dynamics simulations and structure-based drug design
- Published research findings in reputable scientific journals and presented at conferences
- Assisted in teaching and mentoring undergraduate and graduate students

PhD in Chemistry/Biophysics

- Developed a highly performant computational docking and modeling suite for protein-ligand interactions, predicting binding affinity and accurately modeling conformation changes. Enhanced drug design research and improved sampling of potential candidates.
- Built a protein database with unique dynamics information by utilizing Molecular Dynamics (MD) Simulations. Sampled equilibrium dynamics of several protein families and assessed dynamics features using Artificial Neural Networks (CNN, GNN). Enabled the design of novel proteins tailored to specific desired functions.
- Developed a dynamics-based enzyme design approach to investigate the relationship between protein sequence, structure, and function. Analyzed the dynamics of ancestral and modern enzymes to gain insights and guide the protein design process, leading to the creation of novel variants to fine-tune enzyme function.
- Developed a novel sequence and dynamics-based approach to validate the effectiveness of a drug on a protein target with limited sequence and structure information. Implemented innovative algorithms and techniques to prove the drug's efficacy, saving the life of a patient in critical condition.
- Utilized methods including MM-PBSA, FEP, and WHAM to predict computational binding free energies and associated enthalpic and entropic factors of protein-ligand interactions. Leveraged advanced computational techniques to assess the strength and stability of protein-ligand interactions accurately.
- Conducted virtual screening of thousands of ligands against SARS-CoV-2 RNA polymerase and main protease. Successfully discovered allosteric ligands that can inhibit activity, contributing to the potential development of therapeutics against COVID-19.
- Participated in Critical Assessment of Techniques for Protein Structure Prediction (CASP)