CV
Download as PDF • View on LinkedIn
Professional Summary
Nathan C. Frey is CTO & Co-Founder at Coefficient Bio. Previously Group Leader and Principal Machine Learning Scientist at Genentech’s Prescient Design, he pioneered lab-in-the-loop autonomous antibody design systems and led the Foundation Models for Drug Discovery team. His work has been recognized with the ICLR Outstanding Paper Award (2024) and has produced 20+ peer-reviewed publications in leading journals and AI/ML conferences.
Nathan specializes in building AI-first approaches to therapeutic development, with expertise spanning foundation models for biology, autonomous design systems, therapeutic antibody engineering, and biotech AI strategy. His research focuses on practical systems that deliver ROI in drug discovery through decision automation and lab-in-the-loop optimization.
Current Positions
CTO & Co-Founder
Coefficient Bio • Sep 2025 - Present • 2 months New York, NY
Scientific Advisor
Guide Labs • Nov 2024 - Present • 1 year Building interpretable AI systems and foundation models that humans can reliably debug, trust, and understand.
Scientific Advisor
Atomscale • Jan 2023 - Present • 2 years 10 months Building intelligence infrastructure for atomic-scale engineering and materials discovery.
Experience
Prescient Design (Genentech/Roche)
Full-time • 3 years 3 months New York, NY
Group Leader and Principal Scientist
Apr 2024 - Aug 2025 • 1 year 5 months
Led Foundation Models for Drug Discovery team (Frey Lab) at Genentech’s Prescient Design. Directed research on autonomous therapeutic design, protein language models, and lab-in-the-loop optimization systems. Managed team of machine learning scientists and research engineers building discovery platforms.
Key achievements:
- Inventor and co-lead of lab-in-the-loop autonomous antibody design system
- Published ICLR Outstanding Paper Award-winning work on discrete walk-jump sampling
- Built and scaled foundation model capabilities for therapeutic development
- Established research collaborations across computational biology, antibody engineering, and platform development teams
Senior Machine Learning Scientist
Jun 2022 - Apr 2024 • 1 year 11 months Manhattan, New York
Developed foundation models and generative systems for therapeutic protein design. Led research on protein language models and active learning for antibody optimization.
Education
University of Pennsylvania
Doctor of Philosophy (Ph.D.), Materials Science • 2016 - 2021
Honors & Awards:
- National Defense Science & Engineering Graduate Fellow (2016-2021)
- S.J. Stein Dissertation Prize (2021)
- Geoffrey Belton Memorial Fellowship (2019)
- PhD Career Exploration Fellowship, Merck Quantitative Biosciences (2020)
Awards & Recognition
ICLR Outstanding Paper Award (2024)
International Conference on Learning Representations “Protein Discovery with Discrete Walk-Jump Sampling”
One of 5 Outstanding Paper Awards selected from 7,300+ submissions. Recognized for fundamental contributions to generative modeling and practical impact on protein design.
National Defense Science & Engineering Graduate Fellowship
2016 - 2021 U.S. Department of Defense
Competitive fellowship supporting PhD research in areas of critical national security interest.
S.J. Stein Dissertation Prize
University of Pennsylvania, 2021
Awarded for outstanding doctoral dissertation in materials science and engineering.
Additional Honors
- Geoffrey Belton Memorial Fellowship (2019)
- Merck PhD Career Exploration Fellowship, Quantitative Biosciences (2020)
- HHMI C3 Undergraduate Research Fellowship (2013)
- NSF Undergraduate Research Fellowship (2012)
- Phi Beta Kappa (2014)
Research Impact & Publications
Publication Metrics
- 20+ peer-reviewed publications in leading journals and conferences
- Citation metrics available on Google Scholar
- Conference publications at ICLR, NeurIPS, ICML
- Journal publications in Science Advances, Nature Machine Intelligence, ACS Nano, JACS, Chemistry of Materials
Featured Publications
See Publications page for complete list with summaries and links.
Key areas:
- AI-native drug discovery and autonomous design systems
- Foundation models for therapeutic development
- Antibody structure prediction and engineering
- Protein language models and generative modeling
- Lab-in-the-loop optimization and active learning
- Materials informatics and property prediction
Core Expertise
AI-Native Drug Discovery
Foundation models, generative modeling, autonomous design systems, active learning, lab-in-the-loop optimization, decision automation, ROI-focused ML applications in pharma.
Therapeutic Protein Engineering
Antibody design and optimization, binding affinity prediction, therapeutic antibody development.
Machine Learning & AI
Protein language models, discrete diffusion models, energy-based models, graph neural networks, neural scaling laws, transfer learning for biological systems, interpretable ML systems.
Computational Methods
High-throughput screening analysis, molecular simulation, property prediction, retrosynthetic pathway planning, computational screening protocols, experimental design automation.
Biotech Leadership & Strategy
AI team building and organizational design, AI capability assessment (build vs. buy decisions), AI drug discovery investment evaluation, research-to-production ML systems, cross-functional collaboration with biologists, chemists, and biotech operators and executives.
Patents & Intellectual Property
Multiple patent applications in therapeutic antibody design, autonomous discovery systems, and AI-enabled drug development. Details available upon request.
Professional Service
Conference Reviewing
Reviewer for ICLR, NeurIPS, ICML, Nature Biotechnology.
Keywords: AI drug discovery, foundation models biology, therapeutic antibody design, machine learning pharma, autonomous drug discovery, lab-in-the-loop, protein engineering, BioML careers, biotech AI strategy, computational biology