Yunsie Chung
Senior Specialist II, Modeling & Informatics
South San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolYunsie Chung is a Senior Specialist in Modeling & Informatics with a decade of experience applying machine learning and cheminformatics to accelerate drug discovery from South San Francisco. At Merck she built graph neural network models that improved ADMET prediction R2 by 35% on temporal splits and deployed solubility and pharmacokinetic models used company-wide. Her PhD work at MIT combined quantum chemistry, COSMO-RS, and ML to advance liquid-phase kinetics and solvation predictions, and she led development for the RMG open-source reaction mechanism generator. She automated large-scale ADMET data curation, invented a denoising scheme that outperforms literature methods, and routinely supports screening and library-enumeration decisions. An educator and mentor, she has guided students and contractors in ML and cheminformatics projects. Beyond drug discovery, her open-source contributions to RMG highlight a rare blend of production ML, physical chemistry, and software engineering.
10 years of coding experience
8 years of employment as a software developer
Bachelor of Science - BS, Chemical Engineering, 3.9/4.0, Bachelor of Science - BS, Chemical Engineering, 3.9/4.0 at University of California, BerkeleyDoctor of Philosophy - PhD, Chemical Engineering, 4.8/5.0, Doctor of Philosophy - PhD, Chemical Engineering, 4.8/5.0 at Massachusetts Institute of Technology
English, Korean
Github Skills (6)
kinetics10
chemistry10
python10
react9
reaction9
thermodynamics9
Programming languages (4)
Github contributions (5)
ReactionMechanismGenerator/RMG-Py
Jun 2016 - Dec 2022
Python version of the amazing Reaction Mechanism Generator (RMG).
Role in this project:
Back-end Developer
Back-end DeveloperContributions:32 reviews, 108 commits, 28 PRs in 6 years 7 months
Contributions summary:Yunsie made several commits focused on enhancing the functionality of the Reaction Mechanism Generator (RMG) project. These included code changes to improve the accuracy of unit comments, adjustments to the calculation of diffusion-limited kinetics, and the addition of new attributes for solvent data and molecular structures. The user also implemented features to check for solvent presence and modified existing functions to improve the code's conciseness and robustness.
mechanismchemical-engineeringchemistrypythonreaction
yunsiechung/RMG-website
Feb 2020 - Feb 2022
A Django-powered website for Reaction Mechanism Generator (RMG)
Contributions:68 pushes, 14 branches in 2 years
mechanismreactreactiondjangormg
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.