Graham Holt is a computational biologist with nine years of experience bridging protein engineering and machine learning, currently building large curated molecular structure datasets and ML-ready PPI resources at Proxima. He holds a PhD from Duke where he developed distribution-based representations of protein structure and applied them to design and predict protein conformations and antibody–antigen interfaces. His work spans algorithm development in the Donald Lab to hands-on experimental protein engineering at HHMI Janelia, giving him rare fluency in both computational methods and wet-lab realities. At Proxima he led the PINDER PPI dataset collaboration with Nvidia and curated >16M labeled examples across PPIs, ligands, and molecular glue interactions, enabling production-grade ML model development. Colleagues describe him as someone who turns principled probabilistic representations into practical datasets and predictive tools for therapeutic protein design.
9 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy - PhD Computational Biology & Bioinformatics, Doctor of Philosophy - PhD Computational Biology & Bioinformatics at Duke University
Bachelor of Arts (BA) Cum Laude with Honors Biomedical Engineering, Bachelor of Arts (BA) Cum Laude with Honors Biomedical Engineering at Dartmouth College
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.