Miha Skalic
Senior Research Scientist at Boehringer Ingelheim
Biberach an der Riß, Baden-Württemberg, Germany
Summary
👤
Senior🎓
Top SchoolMiha Skalic is a Senior Research Scientist with 19 years of experience applying data science and machine learning to drug discovery and computational chemistry at Boehringer Ingelheim. With a PhD in Biomedicine and strong roots in biotechnology, he bridges deep learning for structural biology and chemoinformatics with practical pipeline and visualization engineering. A Kaggle Master and active contributor to Orange3, he combines competitive ML skills with open-source work on data import, transformation and interactive analytics. His background spans academic research, cloud-based bioinformatics platforms, and production-ready modeling, making him equally comfortable prototyping novel 3D generative models and shipping robust data tooling. Based in Germany, he is known for translating complex biological problems into reproducible computational solutions and for a rare blend of experimental intuition and software craftsmanship.
19 years of coding experience
5 years of employment as a software developer
Master of Science (MSc), Biotechnology, Master of Science (MSc), Biotechnology at University of Ljubljana, Biotechnical facultyDoctor of Philosophy (PhD), Biomedicine, Doctor of Philosophy (PhD), Biomedicine at Universitat Pompeu Fabra
Github Skills (20)
data-visualizations10
python10
data-science10
data-mining10
pandas10
machine-learning10
data-visualisation10
numpy10
data-visualization10
network-analysis9
algorithm9
algorithms9
implement9
scikit9
scikit-learn9
Programming languages (6)
Github contributions (5)
biolab/orange2
Nov 2006 - May 2014
DEPRECATED: Orange 2 (Python 2) data mining suite. NEW: https://github.com/biolab/orange3
Role in this project:
Data Scientist
Data ScientistContributions:1312 commits in 7 years 7 months
Contributions summary:Miha contributed to the modification and enhancement of a data mining suite, particularly focusing on the implementation of visualization schemes for machine learning models, specifically related to graph representations and community detection algorithms. Their work involved expanding existing modules to support feature selection criteria and implementing algorithms like label propagation for community detection, demonstrating an ability to combine statistical analysis with data visualization techniques. The user updated the code in the original project, modifying existing modules and adding features.
data-analysispythonminingorangedata-science
biolab/orange3
May 2011 - Sep 2014
🍊 :bar_chart: :bulb: Orange: Interactive data analysis
Role in this project:Data Scientist
Data ScientistContributions:8 commits, 1 comment in 3 years 4 months
Contributions summary:Miha contributed to the `Orange3` repository, an interactive data analysis and visualization tool. Their commits focused on modifying the `Orange/data/io.py` file to enhance data loading, specifically related to ARFF and Mulan formats, and adding a ModelMap Projection Rank widget. These changes suggest the user worked on data import, transformation, and visualization functionalities within the Orange3 framework, furthering its capabilities in data analysis. The user's contributions, along with widget creation, indicate a strong focus on the project's data processing capabilities.
orangepythondata-miningorange3scipy
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.