Data Scientist

Data Science & Research Beroun, Stredocesky kraj, Czech Republic

Profile
Contacts

Summary

Experience
Merck, Sharp & Dohme (MSD) s.r.o Prague, Czech Republic
Data Scientist August 2022-Present
Revitalizing and accelerating development of image analysis pipelines to efficiently analyze terabytes of
data, enabling discovery of life-changing drugs.
Charles University Prague, Czech Republic
Junior Bioinformatician/Statistician November 2021-August 2022
Conducted statistical analyses of PhD and MSc theses using generalized additive, generalized linear,
mixed effects generalized linear, and ordinal regression models.
Spearheaded development of a user-friendly and efficient R Shiny web app to aid interactive RNA-Seq
analysis.
The University of Edinburgh Edinburgh, Scotland
Honors Year Project Supervisee (Dr. John Menzies) January 2021-May 2021
Analyzed survey data using Poisson generalized linear models.
Performed principal component analysis and Cronbachs test of internal consistency for survey
validation and reliability, respectively.
Lead Student Researcher (Prof. Mikael Bjorklunds Lab) June 2020-September 2020
Revamped an implementation of the UNet algorithm to automate cancer cell segmentation and size
determination published as a python package maintained at Contact .
Open Source Developer
Open Source Development December 2018-Present
Author of packages such as cytounet , pyautocv , pyfdc , pycite , urlfix , manymodelr , shinymde , and mde
with over 60000 downloads.
Written over 500 answers to programming questions on Stack Overflow .
Education
The University of Edinburgh Edinburgh, Scotland
BSc (Hons) Integrative Biomedical Sciences, 2021, First Class
Zhejiang University Hangzhou, China
BS Biomedical Sciences, 2021 GPA 3.78/4.0
Skills
python, R, image processing, image analysis, cell segmentation, image registration,
pandas,NumPy,matplotlib, scikit-image, scikit-learn, pytorch, scipy, deep learning, machine learning,
statistics, openCV, seaborn, CI/CD, unit testing, pytest, agile, JIRA, git, confluence, HPC, SQL, fast.ai, R
Shiny, github, bitbucket, agile-development.