Stephen Kocsis' Portfolio

About Me

My name is Stephen "Christian" Kocsis and I am a Bioinformatics MS graudate student at Johns Hopkins University. I studied Biology during my undergraduate degree at the University of North Florida and since graduating I have over 3 and a half years of experience at the Mayo Clinic of Florida working in bioinformatics and statistical analyses. Upon graduation, I aspire to become a Bioinformatics Engineer and work primarily on developing tools for all aspects of Bioinformatics, Machine Learning and Aritifical Intelligence, Statistical Modeling, Simulation, and Data Science. My passions lie in next generation sequencing data, bayesian statistics, machine learning, and human disease.

I have extensive experience working with R, Python, and Linux/Unix leveraging many publically available, open-source bioinformatics software and tools. I have also worked with many machine learning and statistical frameworks within the Bayesian statistics and Python space to model and solve complex human disease and bioinformatics problems.

Feel free to reach out to me for any inquiries or collaboration at stephenkocsis14@outlook.com!

Download My Resume

Skills

R, Python, Bash shell scripting, SQL, HTML5, CSS3

Docker, Nextflow, Slurm

High Performance Computing, Cloud Computing, Linux/Unix

Git, GitHub

Jupyter Notebook, Anaconda

MySQL

RNA-seq, scRNA-seq, ChIP-seq, smRNA-seq, proteomics

WGS, WES, Statistical Analysis

Scikit-Learn, PyTorch

Data Preprocessing, Quality Control, Analysis Documentation

Projects

LFOmics (Latent Feature Omics)

LFOmics is interactive, user-friendly web tool for integrate multiomic datasets using autoencoder-based feature extraction and perform GSEApy enrichr functional enrichment analysis on top features.

NormSeq

NormSeq is a tool for performing normalization of RNA-seq read counts, written in C++ and callable from Python. It supports various normalization methods such as CPM, TPM, FPKM, RPKM, log2CPM, and Z-score normalization.

Nextflow Pipelines

Developed several bioinformatics Nextflow Pipelines for the analysis of next generation sequencing data including RNA-seq, scRNA-seq, ChIP-seq, and WGS/WES.