Jan Hapala
data scientist, bioinformatician, researcher
Heidelberg, Germany
Summary
• A data science researcher with 5+ year experience in analyzing big genomic data.
• Results-driven team player with knowledge and experience in analytics (inferential, and predictive) and object-oriented programming along with 3+ year’s international experience (Germany, Israel, Finland).
• A skilled programmer with 10+ year experience in programming, scripting and building computational pipelines.
Languages:
Czech, English, German, Spanish
Favorite Python Packages:
numpy, pandas, matplotlib, scikit-learn
Experience
Sep 2016–Sep 2018 RWTH Aachen University, Germany
Bioinformatics Data Analyst and Developer
Built pipelines (in Python, Bash & R) for processing human genomic sequencing data (RNA-seq, Bt-seq, epigenetic and gene expression microarrays). Applied machine learning algorithms (esp. Support Vector Machines, Random Forests) to complex epigenetic data from cancer patients. Implemented regression models for DNA methylation data for human and mouse age estimators.
Sep 2010–Aug 2016 Central European Institute of Technology, Czech Republic
Bioinformatics Data Mining Researcher
Developed an algorithm for fast filtration of big genomic dataset, leading to the discovery of a new motif in 11 plant species. Processed and analyzed plant genomic data, which led to the description of a new protein function. Analyzed weak sequence patterns in the human genomic data, which resulted in the unraveling of yet unknown regulatory properties in the gene promoters.
Sep 2011–Jun 2012 University of Haifa, Israel
Visiting researcher
Searching for DNA structure-related patterns in the human and animal genomic data.
May 2006–Jun 2011 Masaryk University, Czech Republic
Software Developer
Developed an application for university users profile management in .NET, used by more than 30,000 people studying or working at the university. Implemented an access control system (application) for entering buildings with chip cards.
Skills
Big Data, Data Science, Linux, Machine Learning, Mercurial, NumPy, Pandas, SQL