Owen Queen

Hello! I'm Owen, a computer science Ph.D. student and Knight-Hennessy Scholar at Stanford, advised by James Zou. I study how we can AI can help us solve big scientific problems.

Some of the things I'm interested in right now:

  • AI Scientists: How do we build and train better AI systems to accelerate discovery? Why haven't any "AI scientists" made impactful discoveries yet?
  • Evaluation: When, where, how does AI make mistakes in scientific reasoning? Can we characterize and define these gaps?
  • Scientific rigor in the age of automation: How do we evaluate AI-generated research? How do we prepare our scientific institutions for a future of increased automation?

I did my undergrad at the University of Tennessee, Knoxville, and I previously worked with Marinka Zitnik at Harvard Medical School as a research associate.

I've had the pleasure of working on using AI to do cool science in diverse domains, from designing new polymer materials to nominating new targets for multiple sclerorsis to predicting geographic coordinates of poplar trees just from their genomes.

Portrait of Owen Queen
Ph.D. student · Stanford University Knight-Hennessy Scholar

Updates

News

  • Dec 2025Our commentary on Agents4Science was published in Nature Biotechnology 🚀
  • Dec 2025Presented CGBench at NeurIPS!
  • Oct 2025Agents4Science 2025 was a success! Thanks to my co-organizers and our amazing participants! Stay tuned for next year 😉
  • Sep 2025Presented work on using ProCyon for finding novel targets for MS at ECTRIMS 2025 - the biggest multiple sclerosis conference in the world
  • July 2025Mentored a great group of students at the London Geometric Machine Learning summer school!

Selected work

Selected publications

All publications →

CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research

Owen Queen, Harrison Zhang, James Zou

Neural Information Processing Systems (NeurIPS) · 2025

CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research thumbnail

Exploring the use of AI authors and reviewers at Agents4Science

Federico Bianchi*, Owen Queen*, Nitya Thakkar, Eric Sun, James Zou

Nature Biotechnology · 2025

Exploring the use of AI authors and reviewers at Agents4Science thumbnail

ProCyon: A multimodal foundation model for protein phenotypes

Owen Queen, Yepeng Huang, Robert Calef, Valentina Giunchiglia, Tianlong Chen, George Dasoulas, LeAnn Tai, Gianmarco Abbadessa, Owain Howell, Michelle M. Li, Yasha Ektefaie, Ayush Noori, Ildiko Farkas, Joseph Brown, Tom Cobley, Karin Hrovatin, Tom Hartvigsen, Fabian J. Theis, Bradley L. Pentelute, James Zou, Vikram Khurana, David Owen, Richard Nicholas, Manolis Kellis, Marinka Zitnik

bioRxiv · 2025

ProCyon is an 11B-parameter model that predicts and generates protein phenotypes across molecular and therapeutic scales, enabling transfer to poorly characterized proteins.

ProCyon: A multimodal foundation model for protein phenotypes thumbnail

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

Owen Queen, Thomas Hartvigsen, Teddy Koker, Huan He, Theodoros Tsiligkaridis, Marinka Zitnik

Neural Information Processing Systems (NeurIPS) · 2023

TimeX learns interpretable surrogate masks that mirror predictor behavior through a novel consistency loss, delivering faithful explanations for time-series models.

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency thumbnail