Mykola Dergai
Senior Data Scientist
Sweden
Summary
👤
Senior🎓
Top SchoolMykola Dergai is a Senior Data Scientist with 14 years of experience applying computational and experimental insights to high-dimensional biological data, now based in Sweden and currently at AstraZeneca. He combines deep domain knowledge in transcriptomics, proteomics and network analysis with robust software development skills, having built R packages, ML pipelines, SQL-backed backends and Shiny apps to operationalize omics workflows. His work spans academia and industry—from postdoctoral discoveries about paralog regulation and protein superfamily function to leading analytics for large-scale transcriptomics at Janssen and integrative target suggestions at Evotec. An active contributor to performance-sensitive open-source projects, he has hands-on experience improving GPU-accelerated simulators’ I/O and memory handling, reflecting an uncommon blend of bioinformatics and performance engineering. Colleagues rely on him for turning complex biological questions into reproducible, production-ready analysis pipelines and interpretable ML models.
14 years of coding experience
11 years of employment as a software developer
PhD Molecular Biology, PhD Molecular Biology at Taras Shevchenko National University of Kyiv
English, German, Ukrainian, Russian
Github Skills (14)
cuda10
go10
performance-optimization10
scientific-computing10
fileio9
file-access9
gpu9
fft9
file-processing9
fftw9
data-handling9
file-handling9
cprogramming-language5
c-language5
Programming languages (9)
Github contributions (5)
mumax/3
Aug 2012 - Sep 2021
GPU-accelerated micromagnetic simulator
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:1 release, 142 commits, 25 PRs in 9 years 2 months
Contributions summary:Mykola primarily contributed to the `mumax/3` repository by implementing and refining the dump tool's functionality, specifically enabling the splitting of dump files and adding gzip'ed gnuplot output for efficient data handling. They also addressed memory usage by modifying the fft tool for frame processing. Furthermore, the user introduced support for OVF2 file output, optimizing and modifying the output format to better store the time and other parameters, thus supporting the simulation data for further analysis. Code changes also focused on improving the efficiency of existing functions and related data structure.
cudagpuacceleratedscientific-computingsimulation
godsic/semargl3
May 2013 - Sep 2015
Contributions:3 commits, 2 pushes in 2 years 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.