Peter Gedeck
Research Informatics Senior Scientist
Washington DC-Baltimore Area United States
Summary
🤩
Rockstar🎓
Top SchoolPeter Gedeck is a Research Informatics Senior Scientist with over a decade of experience applying cheminformatics and computational chemistry to drug discovery, spanning roles from hands-on CADD investigator to team leader and product-focused software developer. He currently builds production-quality drug discovery software at Collaborative Drug Discovery while running a data science and cheminformatics consultancy and lecturing on statistical learning. Peter combines deep domain expertise in QSAR, molecular modeling and R&D with practical engineering skills—contributing to the RDKit core and providing reproducible Python examples for O’Reilly’s Practical Statistics for Data Scientists. His career blends scientific rigor from a PhD in chemistry with a propensity for improving code quality and test coverage, making him equally effective at algorithm development and reliable software delivery. Notably, he has led global cheminformatics initiatives at Novartis and brings a track record of integrating research, pedagogy, and open-source contributions.
10 years of coding experience
PhD Chemistry, PhD Chemistry at FAU Erlangen-NürnbergUniversity College London
English, German
Github Skills (14)
scikit10
scikit-learn10
unit-testing10
rdkit10
machine-learning10
c-language10
cprogramming-language10
python10
regression-analysis10
cheminformatics10
statsmodels10
data-analysis10
anova9
k-nearest-neighbours9
Programming languages (10)
Github contributions (5)
gedeck/practical-statistics-for-data-scientists
Feb 2020 - Jan 2023
Code repository for O'Reilly book
Role in this project:
Data Scientist
Data ScientistContributions:5 reviews, 57 commits, 52 PRs in 2 years 11 months
Contributions summary:Peter contributed Python code for statistical analysis and machine learning in the Practical Statistics for Data Scientists book. They focused on implementing and demonstrating regression analysis and model selection techniques using scikit-learn and statsmodels, including the use of dummy variables, and also implemented K-Nearest Neighbors. Furthermore, there are also contributions related to resampling and p-value calculation in ANOVA. The code snippets and notebooks showcase skills related to data analysis, predictive modeling, and statistical methods.
code-repositorypythono-reillydata-science
rdkit/rdkit
Sep 2016 - Dec 2022
The official sources for the RDKit library
Role in this project:Back-end Developer & QA Engineer
Back-end Developer & QA EngineerContributions:73 reviews, 69 commits, 75 PRs in 6 years 4 months
Contributions summary:Peter primarily focused on the RDKit library's core functionality, contributing to code cleanup and improvement of unit test coverage. Their work involved removing duplicate code, improving code coverage of unit tests, and ensuring consistent code formatting. They also made changes in various directories for improving test coverage, demonstrating a focus on code quality and reliability.
cheminformaticsrdkitpythonc-plus-plussources
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.