Jacob Verburgt
Senior AI Applications Scientist
I support and develop GPU-accelerated research computing environments, with experience in HPC cluster operations, utilization monitoring, and distributed workloads. My interests and roles include building and supporting software for AI workloads and graphics systems, scalable software stacks, and helping researchers use advanced computing resources effectively.
Education
- Ph.D., Biological Sciences - Structural and Computational Biology & Biophysics , Purdue University (2025)
- M.S., Applied Statistics, Purdue Univeristy (2025)
- B.S., Biomolecular Engineering, Milwaukee School of Engineering (2018)
Projects
Model Quality Self-Assessment Improvement Via Deep Graph Learning
In this project, I implemented state-of-the-art graph neural network architecture to improve the self-reported confidence scores of protein structure prediction programs. This was accomplished through a combination of feature engineering, model optimization, hyperparameter tuning, and training data optimization.
High Performance Computing Resource Monitoring
This project automated the collection, analysis, and reporting of GPU performance metrics on high-performance computing clusters in an effort to identify underutilized resources and minimize computational waste.
We also built a command-line interface to allow HPC users to query and download their own GPU utilization data so they can better understand their own usage patterns.
Selected Publications
J. Verburgt, Z. Zhang, and D. Kihara, “AlphaFold model quality self-assessment improvement via deep graph learning”, Protein Sci., vol. 34, no. 9, p. e70274, 2025, doi: 10.1002/pro.70274.
R. T. DeRue and J. Verburgt, “CANARI: A Monitoring Framework for Cluster Analysis and Node Assessment for Resource Integrity,” in SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, Nov. 2024, pp. 613–620. doi: 10.1109/SCW63240.2024.00085.
M. F. Lensink, …, J. Verburgt, …, S. Wodak, “Impact of AlphaFold on structure prediction of protein complexes: The CASP15-CAPRI experiment” , Proteins: Structure, Function, and Bioinformatics, vol. 91, no. 12, pp. 1658–1683, 2023, doi: 10.1002/prot.26609.
J. Verburgt, A. Jain, and D. Kihara, “Recent Deep Learning Applications to Structure-Based Drug Design,” Methods Mol Biol, vol. 2714, pp. 215–234, 2024, doi: 10.1007/978-1-0716-3441-7_13.